python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 8 -a ' -a 4741 -l 30 ' -s datou_current_4741 -M 0 -S 0 -U 95,95,120 import MySQLdb succeeded Import error (python version) ['/Users/moilerat/Documents/Fotonower/install/caffe/distribute/python', '/home/admin/workarea/git/Velours/python/prod', '/home/admin/workarea/install/caffe_cuda8_python3/python', '/home/admin/workarea/install/darknet', '/home/admin/workarea/git/Velours/python', '/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python', '/home/admin/mtr/.credentials', '/home/admin/workarea/install/caffe/python', '/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools', '/home/admin/workarea/git/fotonowerpip', '/home/admin/workarea/install/segment-anything', '/home/admin/workarea/git/pyfvs', '/usr/lib/python38.zip', '/usr/lib/python3.8', '/usr/lib/python3.8/lib-dynload', '/home/admin/.local/lib/python3.8/site-packages', '/usr/local/lib/python3.8/dist-packages', '/usr/lib/python3/dist-packages'] process id : 28447 load datou : 4741 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5732, 'mask_refus_amiens_050123', 16384, 25088, 'mask_refus_amiens_050123', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 1, 5, 13, 23, 59), datetime.datetime(2023, 1, 5, 13, 23, 59)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) load thcls load THCL from format json or kwargs add thcl : 3453 in CacheModelConfig load THCL from format json or kwargs add thcl : 3783 in CacheModelConfig load pdts add pdt : 5732 in CacheModelConfig add pdt : 5972 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec no input labels no input values updating current state to 1 list_input_json: {} Current got : datou_id : 4741, datou_cur_ids : ['3646764'] with mtr_portfolio_ids : ['26294096'] and first list_photo_ids : [] new path : /proc/28447/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, mask_detect, blur_detection, brightness, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : {} origin We have 1 , BFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 9 ; length of list_pids : 9 ; length of list_args : 9 time to download the photos : 2.1172657012939453 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Mon Sep 1 16:21:31 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3545 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-09-01 16:21:35.531721: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-09-01 16:21:35.560718: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-09-01 16:21:35.562922: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9f5c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-09-01 16:21:35.562955: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-09-01 16:21:35.566885: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-09-01 16:21:35.739411: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x8a5ee70 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-09-01 16:21:35.739485: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-09-01 16:21:35.740818: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-09-01 16:21:35.741811: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:21:35.746775: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:21:35.750799: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-01 16:21:35.752008: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-01 16:21:35.758757: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-01 16:21:35.760978: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-01 16:21:35.768688: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-01 16:21:35.769866: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-01 16:21:35.769955: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:21:35.770615: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-01 16:21:35.770635: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-01 16:21:35.770645: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-01 16:21:35.771657: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3093 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-09-01 16:21:36.265151: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-09-01 16:21:36.265237: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:21:36.265261: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:21:36.265281: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-01 16:21:36.265301: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-01 16:21:36.265321: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-01 16:21:36.265340: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-01 16:21:36.265360: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-01 16:21:36.266405: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-01 16:21:36.267548: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-09-01 16:21:36.267583: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:21:36.267602: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:21:36.267619: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-01 16:21:36.267649: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-01 16:21:36.267667: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-01 16:21:36.267684: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-01 16:21:36.267701: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-01 16:21:36.268753: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-01 16:21:36.268790: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-01 16:21:36.268801: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-01 16:21:36.268813: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-01 16:21:36.269893: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3093 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl3783 thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) {'thcl': {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'], 'list_hashtags_csv': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'svm_hashtag_type_desc': 5972, 'photo_desc_type': 5972, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_entrant_syctomXV_111023 NUM_CLASSES 11 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_entrant_syctomXV_111023 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-09-01 16:21:47.182232: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:21:47.497559: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-01 16:21:49.781499: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.52G (2708406272 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-09-01 16:21:50.526002: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-01 16:21:50.526080: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-01 16:21:50.532851: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-01 16:21:50.532877: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. local folder : /data/models_weight/learn_entrant_syctomXV_111023 /data/models_weight/learn_entrant_syctomXV_111023/mask_model.h5 size_local : 256052544 size in s3 : 256052544 create time local : 2023-10-26 16:36:43 create time in s3 : 2023-10-11 13:57:17 mask_model.h5 already exist and didn't need to update list_images length : 9 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.95000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 10 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.82109 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 14 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 15 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 10 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 21 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 15 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.91250 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 20 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 14 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.76250 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 4 Detection mask done ! Trying to reset tf kernel 28675 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 6858 tf kernel not reseted sub process len(results) : 9 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 9 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 10377 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl3783 Catched exception ! Connect or reconnect ! thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'] time for calcul the mask position with numpy : 0.002337217330932617 nb_pixel_total : 65069 time to create 1 rle with old method : 0.10969877243041992 length of segment : 392 time for calcul the mask position with numpy : 0.00269317626953125 nb_pixel_total : 145841 time to create 1 rle with old method : 0.16813182830810547 length of segment : 616 time for calcul the mask position with numpy : 0.0010449886322021484 nb_pixel_total : 52662 time to create 1 rle with old method : 0.061492204666137695 length of segment : 357 time for calcul the mask position with numpy : 0.020779132843017578 nb_pixel_total : 579141 time to create 1 rle with new method : 0.7312133312225342 length of segment : 1494 time for calcul the mask position with numpy : 0.0004856586456298828 nb_pixel_total : 11137 time to create 1 rle with old method : 0.013301372528076172 length of segment : 147 time for calcul the mask position with numpy : 0.0013167858123779297 nb_pixel_total : 39771 time to create 1 rle with old method : 0.047478437423706055 length of segment : 303 time for calcul the mask position with numpy : 0.0052797794342041016 nb_pixel_total : 64879 time to create 1 rle with old method : 0.07618260383605957 length of segment : 895 time for calcul the mask position with numpy : 0.00037860870361328125 nb_pixel_total : 5965 time to create 1 rle with old method : 0.007395267486572266 length of segment : 117 time for calcul the mask position with numpy : 0.005548954010009766 nb_pixel_total : 296420 time to create 1 rle with new method : 0.44104933738708496 length of segment : 1345 time for calcul the mask position with numpy : 0.0005686283111572266 nb_pixel_total : 35816 time to create 1 rle with old method : 0.04226040840148926 length of segment : 304 time for calcul the mask position with numpy : 0.0010797977447509766 nb_pixel_total : 47940 time to create 1 rle with old method : 0.05750131607055664 length of segment : 242 time for calcul the mask position with numpy : 0.0014529228210449219 nb_pixel_total : 55935 time to create 1 rle with old method : 0.0654609203338623 length of segment : 309 time for calcul the mask position with numpy : 0.0008058547973632812 nb_pixel_total : 21113 time to create 1 rle with old method : 0.025150299072265625 length of segment : 218 time for calcul the mask position with numpy : 0.0012958049774169922 nb_pixel_total : 45306 time to create 1 rle with old method : 0.05518746376037598 length of segment : 240 time for calcul the mask position with numpy : 0.0029189586639404297 nb_pixel_total : 104713 time to create 1 rle with old method : 0.12209129333496094 length of segment : 441 time for calcul the mask position with numpy : 0.0007295608520507812 nb_pixel_total : 20854 time to create 1 rle with old method : 0.025047779083251953 length of segment : 239 time for calcul the mask position with numpy : 0.006558418273925781 nb_pixel_total : 229612 time to create 1 rle with new method : 0.026921510696411133 length of segment : 617 time for calcul the mask position with numpy : 0.0022611618041992188 nb_pixel_total : 138465 time to create 1 rle with old method : 0.16369032859802246 length of segment : 373 time for calcul the mask position with numpy : 0.0020236968994140625 nb_pixel_total : 81045 time to create 1 rle with old method : 0.0974264144897461 length of segment : 451 time for calcul the mask position with numpy : 0.0005879402160644531 nb_pixel_total : 24405 time to create 1 rle with old method : 0.03013443946838379 length of segment : 119 time for calcul the mask position with numpy : 0.0003800392150878906 nb_pixel_total : 11812 time to create 1 rle with old method : 0.014436483383178711 length of segment : 76 time for calcul the mask position with numpy : 0.00044417381286621094 nb_pixel_total : 25204 time to create 1 rle with old method : 0.030428171157836914 length of segment : 167 time for calcul the mask position with numpy : 0.0003387928009033203 nb_pixel_total : 5497 time to create 1 rle with old method : 0.006746530532836914 length of segment : 118 time for calcul the mask position with numpy : 0.0005090236663818359 nb_pixel_total : 25624 time to create 1 rle with old method : 0.031135082244873047 length of segment : 127 time for calcul the mask position with numpy : 0.003506898880004883 nb_pixel_total : 119752 time to create 1 rle with old method : 0.14082860946655273 length of segment : 519 time for calcul the mask position with numpy : 0.0343477725982666 nb_pixel_total : 808510 time to create 1 rle with new method : 0.041347503662109375 length of segment : 908 time for calcul the mask position with numpy : 0.0021829605102539062 nb_pixel_total : 50568 time to create 1 rle with old method : 0.0943293571472168 length of segment : 277 time for calcul the mask position with numpy : 0.0018024444580078125 nb_pixel_total : 67332 time to create 1 rle with old method : 0.08123207092285156 length of segment : 354 time for calcul the mask position with numpy : 0.001386880874633789 nb_pixel_total : 37888 time to create 1 rle with old method : 0.04446840286254883 length of segment : 343 time for calcul the mask position with numpy : 0.0019078254699707031 nb_pixel_total : 55798 time to create 1 rle with old method : 0.06508445739746094 length of segment : 423 time for calcul the mask position with numpy : 0.0011010169982910156 nb_pixel_total : 41623 time to create 1 rle with old method : 0.0494842529296875 length of segment : 248 time for calcul the mask position with numpy : 0.0008196830749511719 nb_pixel_total : 20383 time to create 1 rle with old method : 0.024905681610107422 length of segment : 206 time for calcul the mask position with numpy : 0.0008018016815185547 nb_pixel_total : 31829 time to create 1 rle with old method : 0.038710832595825195 length of segment : 186 time for calcul the mask position with numpy : 0.003439188003540039 nb_pixel_total : 98294 time to create 1 rle with old method : 0.11577248573303223 length of segment : 782 time for calcul the mask position with numpy : 0.01695418357849121 nb_pixel_total : 395185 time to create 1 rle with new method : 0.20223188400268555 length of segment : 2000 time for calcul the mask position with numpy : 0.0006082057952880859 nb_pixel_total : 21000 time to create 1 rle with old method : 0.02636885643005371 length of segment : 170 time for calcul the mask position with numpy : 0.0020334720611572266 nb_pixel_total : 74281 time to create 1 rle with old method : 0.08809995651245117 length of segment : 338 time for calcul the mask position with numpy : 0.0019872188568115234 nb_pixel_total : 79297 time to create 1 rle with old method : 0.0941624641418457 length of segment : 296 time for calcul the mask position with numpy : 0.0008044242858886719 nb_pixel_total : 50556 time to create 1 rle with old method : 0.061151981353759766 length of segment : 350 time for calcul the mask position with numpy : 0.0068950653076171875 nb_pixel_total : 328072 time to create 1 rle with new method : 0.011974334716796875 length of segment : 532 time for calcul the mask position with numpy : 0.0020754337310791016 nb_pixel_total : 89356 time to create 1 rle with old method : 0.10400605201721191 length of segment : 560 time for calcul the mask position with numpy : 0.00020384788513183594 nb_pixel_total : 8571 time to create 1 rle with old method : 0.010302066802978516 length of segment : 169 time for calcul the mask position with numpy : 0.0011096000671386719 nb_pixel_total : 41379 time to create 1 rle with old method : 0.04947042465209961 length of segment : 133 time for calcul the mask position with numpy : 0.0009067058563232422 nb_pixel_total : 17224 time to create 1 rle with old method : 0.021008729934692383 length of segment : 268 time for calcul the mask position with numpy : 0.0003981590270996094 nb_pixel_total : 18409 time to create 1 rle with old method : 0.022922277450561523 length of segment : 190 time for calcul the mask position with numpy : 0.0002734661102294922 nb_pixel_total : 12169 time to create 1 rle with old method : 0.014902114868164062 length of segment : 123 time for calcul the mask position with numpy : 0.0004246234893798828 nb_pixel_total : 14387 time to create 1 rle with old method : 0.017461061477661133 length of segment : 119 time for calcul the mask position with numpy : 0.0009360313415527344 nb_pixel_total : 65248 time to create 1 rle with old method : 0.0786275863647461 length of segment : 358 time for calcul the mask position with numpy : 0.0004439353942871094 nb_pixel_total : 12343 time to create 1 rle with old method : 0.014979362487792969 length of segment : 131 time for calcul the mask position with numpy : 0.0025212764739990234 nb_pixel_total : 60886 time to create 1 rle with old method : 0.0724942684173584 length of segment : 352 time for calcul the mask position with numpy : 0.001071929931640625 nb_pixel_total : 38943 time to create 1 rle with old method : 0.04674696922302246 length of segment : 185 time for calcul the mask position with numpy : 0.0014507770538330078 nb_pixel_total : 44545 time to create 1 rle with old method : 0.05291271209716797 length of segment : 284 time for calcul the mask position with numpy : 0.0005931854248046875 nb_pixel_total : 17160 time to create 1 rle with old method : 0.020521163940429688 length of segment : 139 time for calcul the mask position with numpy : 0.0008034706115722656 nb_pixel_total : 29804 time to create 1 rle with old method : 0.035677433013916016 length of segment : 172 time for calcul the mask position with numpy : 0.006365537643432617 nb_pixel_total : 190584 time to create 1 rle with new method : 0.009940385818481445 length of segment : 728 time for calcul the mask position with numpy : 0.0008490085601806641 nb_pixel_total : 10197 time to create 1 rle with old method : 0.012646198272705078 length of segment : 191 time for calcul the mask position with numpy : 0.004483699798583984 nb_pixel_total : 167094 time to create 1 rle with new method : 0.00645136833190918 length of segment : 501 time for calcul the mask position with numpy : 0.0007278919219970703 nb_pixel_total : 22025 time to create 1 rle with old method : 0.026290178298950195 length of segment : 173 time for calcul the mask position with numpy : 0.0009539127349853516 nb_pixel_total : 16509 time to create 1 rle with old method : 0.020107507705688477 length of segment : 262 time for calcul the mask position with numpy : 0.0014495849609375 nb_pixel_total : 30820 time to create 1 rle with old method : 0.03899741172790527 length of segment : 242 time for calcul the mask position with numpy : 0.0011434555053710938 nb_pixel_total : 26538 time to create 1 rle with old method : 0.0315394401550293 length of segment : 246 time for calcul the mask position with numpy : 0.0011708736419677734 nb_pixel_total : 28684 time to create 1 rle with old method : 0.034607648849487305 length of segment : 299 time for calcul the mask position with numpy : 0.001001119613647461 nb_pixel_total : 35979 time to create 1 rle with old method : 0.04266619682312012 length of segment : 335 time for calcul the mask position with numpy : 0.0028557777404785156 nb_pixel_total : 109721 time to create 1 rle with old method : 0.12775731086730957 length of segment : 760 time for calcul the mask position with numpy : 0.0012211799621582031 nb_pixel_total : 32130 time to create 1 rle with old method : 0.042948007583618164 length of segment : 399 time for calcul the mask position with numpy : 0.0005865097045898438 nb_pixel_total : 12387 time to create 1 rle with old method : 0.015484809875488281 length of segment : 139 time for calcul the mask position with numpy : 0.0005936622619628906 nb_pixel_total : 11759 time to create 1 rle with old method : 0.014549732208251953 length of segment : 107 time for calcul the mask position with numpy : 0.0025908946990966797 nb_pixel_total : 113559 time to create 1 rle with old method : 0.13412904739379883 length of segment : 372 time for calcul the mask position with numpy : 0.0014514923095703125 nb_pixel_total : 80429 time to create 1 rle with old method : 0.09403181076049805 length of segment : 760 time for calcul the mask position with numpy : 0.0016105175018310547 nb_pixel_total : 14540 time to create 1 rle with old method : 0.018364667892456055 length of segment : 256 time for calcul the mask position with numpy : 0.001977682113647461 nb_pixel_total : 81153 time to create 1 rle with old method : 0.09540009498596191 length of segment : 419 time for calcul the mask position with numpy : 0.001438140869140625 nb_pixel_total : 53412 time to create 1 rle with old method : 0.06395697593688965 length of segment : 251 time for calcul the mask position with numpy : 0.00191497802734375 nb_pixel_total : 90819 time to create 1 rle with old method : 0.10831022262573242 length of segment : 506 time for calcul the mask position with numpy : 0.007344961166381836 nb_pixel_total : 293523 time to create 1 rle with new method : 0.016260623931884766 length of segment : 645 time for calcul the mask position with numpy : 0.0008981227874755859 nb_pixel_total : 30528 time to create 1 rle with old method : 0.03907585144042969 length of segment : 262 time for calcul the mask position with numpy : 0.0010442733764648438 nb_pixel_total : 36344 time to create 1 rle with old method : 0.04539656639099121 length of segment : 223 time for calcul the mask position with numpy : 0.0011403560638427734 nb_pixel_total : 32968 time to create 1 rle with old method : 0.040175437927246094 length of segment : 268 time for calcul the mask position with numpy : 0.0008921623229980469 nb_pixel_total : 24599 time to create 1 rle with old method : 0.03088235855102539 length of segment : 160 time for calcul the mask position with numpy : 0.0031518936157226562 nb_pixel_total : 142307 time to create 1 rle with old method : 0.17393231391906738 length of segment : 455 time for calcul the mask position with numpy : 0.0005948543548583984 nb_pixel_total : 31405 time to create 1 rle with old method : 0.03686857223510742 length of segment : 208 time for calcul the mask position with numpy : 0.0005826950073242188 nb_pixel_total : 18131 time to create 1 rle with old method : 0.021948814392089844 length of segment : 164 time for calcul the mask position with numpy : 0.000990152359008789 nb_pixel_total : 35567 time to create 1 rle with old method : 0.04340767860412598 length of segment : 208 time for calcul the mask position with numpy : 0.0009477138519287109 nb_pixel_total : 21636 time to create 1 rle with old method : 0.025686979293823242 length of segment : 210 time for calcul the mask position with numpy : 0.00038433074951171875 nb_pixel_total : 17806 time to create 1 rle with old method : 0.02264881134033203 length of segment : 160 time for calcul the mask position with numpy : 0.0005278587341308594 nb_pixel_total : 27188 time to create 1 rle with old method : 0.03266716003417969 length of segment : 262 time for calcul the mask position with numpy : 0.006801128387451172 nb_pixel_total : 297579 time to create 1 rle with new method : 0.009896993637084961 length of segment : 701 time for calcul the mask position with numpy : 0.0009291172027587891 nb_pixel_total : 23203 time to create 1 rle with old method : 0.02804708480834961 length of segment : 200 time for calcul the mask position with numpy : 0.0007483959197998047 nb_pixel_total : 20572 time to create 1 rle with old method : 0.024618148803710938 length of segment : 200 time for calcul the mask position with numpy : 0.0017852783203125 nb_pixel_total : 64519 time to create 1 rle with old method : 0.07671475410461426 length of segment : 359 time for calcul the mask position with numpy : 0.0007257461547851562 nb_pixel_total : 17671 time to create 1 rle with old method : 0.021094799041748047 length of segment : 180 time for calcul the mask position with numpy : 0.0012214183807373047 nb_pixel_total : 26968 time to create 1 rle with old method : 0.032291412353515625 length of segment : 326 time for calcul the mask position with numpy : 0.0031747817993164062 nb_pixel_total : 114561 time to create 1 rle with old method : 0.1331651210784912 length of segment : 539 time for calcul the mask position with numpy : 0.006586313247680664 nb_pixel_total : 232710 time to create 1 rle with new method : 0.010147333145141602 length of segment : 409 time for calcul the mask position with numpy : 0.0004470348358154297 nb_pixel_total : 4587 time to create 1 rle with old method : 0.005796670913696289 length of segment : 87 time for calcul the mask position with numpy : 0.00115203857421875 nb_pixel_total : 30357 time to create 1 rle with old method : 0.03698253631591797 length of segment : 242 time for calcul the mask position with numpy : 0.0007300376892089844 nb_pixel_total : 24622 time to create 1 rle with old method : 0.029661178588867188 length of segment : 195 time for calcul the mask position with numpy : 0.000827789306640625 nb_pixel_total : 34390 time to create 1 rle with old method : 0.04228711128234863 length of segment : 208 time for calcul the mask position with numpy : 0.0010006427764892578 nb_pixel_total : 47416 time to create 1 rle with old method : 0.05616927146911621 length of segment : 209 time for calcul the mask position with numpy : 0.0036661624908447266 nb_pixel_total : 102091 time to create 1 rle with old method : 0.11986827850341797 length of segment : 430 time for calcul the mask position with numpy : 0.002313375473022461 nb_pixel_total : 108881 time to create 1 rle with old method : 0.12764334678649902 length of segment : 411 time for calcul the mask position with numpy : 0.005883693695068359 nb_pixel_total : 210560 time to create 1 rle with new method : 0.009073972702026367 length of segment : 781 time for calcul the mask position with numpy : 0.0015819072723388672 nb_pixel_total : 81033 time to create 1 rle with old method : 0.09635353088378906 length of segment : 389 time for calcul the mask position with numpy : 0.002084493637084961 nb_pixel_total : 35544 time to create 1 rle with old method : 0.04250001907348633 length of segment : 209 time for calcul the mask position with numpy : 0.005522966384887695 nb_pixel_total : 239081 time to create 1 rle with new method : 0.012459754943847656 length of segment : 1038 length of segment : 0 time for calcul the mask position with numpy : 0.0008461475372314453 nb_pixel_total : 17838 time to create 1 rle with old method : 0.021385669708251953 length of segment : 232 time for calcul the mask position with numpy : 0.004235506057739258 nb_pixel_total : 200455 time to create 1 rle with new method : 0.006260871887207031 length of segment : 399 time for calcul the mask position with numpy : 0.0004169940948486328 nb_pixel_total : 15220 time to create 1 rle with old method : 0.01876354217529297 length of segment : 118 time for calcul the mask position with numpy : 0.0005109310150146484 nb_pixel_total : 29223 time to create 1 rle with old method : 0.03504061698913574 length of segment : 260 time for calcul the mask position with numpy : 0.009605884552001953 nb_pixel_total : 244750 time to create 1 rle with new method : 0.4633510112762451 length of segment : 1365 time for calcul the mask position with numpy : 0.0016894340515136719 nb_pixel_total : 51806 time to create 1 rle with old method : 0.06279516220092773 length of segment : 235 time for calcul the mask position with numpy : 0.0015330314636230469 nb_pixel_total : 52003 time to create 1 rle with old method : 0.06334424018859863 length of segment : 261 time for calcul the mask position with numpy : 0.0003237724304199219 nb_pixel_total : 8916 time to create 1 rle with old method : 0.010988473892211914 length of segment : 77 time for calcul the mask position with numpy : 0.0007481575012207031 nb_pixel_total : 25877 time to create 1 rle with old method : 0.031006813049316406 length of segment : 195 time for calcul the mask position with numpy : 0.00047326087951660156 nb_pixel_total : 9840 time to create 1 rle with old method : 0.012051582336425781 length of segment : 126 time for calcul the mask position with numpy : 0.0007655620574951172 nb_pixel_total : 23207 time to create 1 rle with old method : 0.027907848358154297 length of segment : 282 time for calcul the mask position with numpy : 0.001352548599243164 nb_pixel_total : 31477 time to create 1 rle with old method : 0.038185834884643555 length of segment : 285 time for calcul the mask position with numpy : 0.0007541179656982422 nb_pixel_total : 750 time to create 1 rle with old method : 0.0009794235229492188 length of segment : 50 time for calcul the mask position with numpy : 0.00060272216796875 nb_pixel_total : 3081 time to create 1 rle with old method : 0.003916501998901367 length of segment : 73 time for calcul the mask position with numpy : 0.5499186515808105 nb_pixel_total : 2248878 time to create 1 rle with new method : 0.11047625541687012 length of segment : 1423 time for calcul the mask position with numpy : 1.0001206398010254 nb_pixel_total : 8199770 time to create 1 rle with new method : 1.4539899826049805 length of segment : 3899 time for calcul the mask position with numpy : 0.0002090930938720703 nb_pixel_total : 5412 time to create 1 rle with old method : 0.006480216979980469 length of segment : 104 time for calcul the mask position with numpy : 0.17360877990722656 nb_pixel_total : 2396309 time to create 1 rle with new method : 0.10215187072753906 length of segment : 1185 time spent for convertir_results : 19.628376722335815 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 123 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 83.85534644126892 time spend to save output : 0.15831613540649414 total time spend for step 1 : 84.01366257667542 step2:mask_detect Mon Sep 1 16:22:55 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 6600 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-09-01 16:22:58.503924: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-09-01 16:22:58.528604: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-09-01 16:22:58.530585: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9f58000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-09-01 16:22:58.530636: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-09-01 16:22:58.534148: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-09-01 16:22:58.708995: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xa122750 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-09-01 16:22:58.709068: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-09-01 16:22:58.710370: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-09-01 16:22:58.710798: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:22:58.714331: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:22:58.717109: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-01 16:22:58.717537: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-01 16:22:58.719989: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-01 16:22:58.721600: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-01 16:22:58.728137: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-01 16:22:58.729868: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-01 16:22:58.729955: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:22:58.730607: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-01 16:22:58.730622: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-01 16:22:58.730631: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-01 16:22:58.732181: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6062 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-09-01 16:22:58.928762: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-09-01 16:22:58.928855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:22:58.928881: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:22:58.928905: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-01 16:22:58.928928: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-01 16:22:58.928951: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-01 16:22:58.928974: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-01 16:22:58.929002: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-01 16:22:58.930297: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-01 16:22:58.931467: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-09-01 16:22:58.931505: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-01 16:22:58.931526: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:22:58.931546: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-01 16:22:58.931565: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-01 16:22:58.931585: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-01 16:22:58.931604: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-01 16:22:58.931624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-01 16:22:58.932967: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-01 16:22:58.933000: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-01 16:22:58.933011: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-01 16:22:58.933021: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-01 16:22:58.934230: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6062 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl3453 thcls : [{'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5732 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5732, 'mask_refus_amiens_050123', 16384, 25088, 'mask_refus_amiens_050123', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 1, 5, 13, 23, 59), datetime.datetime(2023, 1, 5, 13, 23, 59)) {'thcl': {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'svm_hashtag_type_desc': 5732, 'photo_desc_type': 5732, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME mask_refus_amiens_050123 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : mask_refus_amiens_050123 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-09-01 16:23:10.272517: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-01 16:23:10.464727: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/mask_refus_amiens_050123 /data/models_weight/mask_refus_amiens_050123/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2023-01-05 13:44:07 create time in s3 : 2023-01-05 12:23:52 mask_model.h5 already exist and didn't need to update list_images length : 9 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.95000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 60 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.82109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 48 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 52 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 33 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 66 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 55 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.91250 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 44 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 63 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.76250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 3 Detection mask done ! Trying to reset tf kernel 30694 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5088 tf kernel not reseted sub process len(results) : 9 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 9 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 10156 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl3453 Catched exception ! Connect or reconnect ! thcls : [{'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5732 ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] time for calcul the mask position with numpy : 0.3131673336029053 nb_pixel_total : 496871 time to create 1 rle with new method : 0.44721150398254395 length of segment : 935 time for calcul the mask position with numpy : 0.03976941108703613 nb_pixel_total : 165621 time to create 1 rle with new method : 0.010001420974731445 length of segment : 686 time for calcul the mask position with numpy : 0.02351832389831543 nb_pixel_total : 93725 time to create 1 rle with old method : 0.10989737510681152 length of segment : 416 time for calcul the mask position with numpy : 0.18567633628845215 nb_pixel_total : 473275 time to create 1 rle with new method : 0.022205829620361328 length of segment : 1156 time for calcul the mask position with numpy : 0.24363136291503906 nb_pixel_total : 282248 time to create 1 rle with new method : 0.02147531509399414 length of segment : 944 time for calcul the mask position with numpy : 0.047868967056274414 nb_pixel_total : 156520 time to create 1 rle with new method : 0.008564949035644531 length of segment : 423 time for calcul the mask position with numpy : 0.044509172439575195 nb_pixel_total : 140139 time to create 1 rle with old method : 0.15823721885681152 length of segment : 525 time for calcul the mask position with numpy : 0.011464118957519531 nb_pixel_total : 166261 time to create 1 rle with new method : 0.0076520442962646484 length of segment : 385 time for calcul the mask position with numpy : 0.018055438995361328 nb_pixel_total : 9444 time to create 1 rle with old method : 0.015286684036254883 length of segment : 139 time for calcul the mask position with numpy : 0.042993783950805664 nb_pixel_total : 89395 time to create 1 rle with old method : 0.10375213623046875 length of segment : 363 time for calcul the mask position with numpy : 0.0028367042541503906 nb_pixel_total : 90144 time to create 1 rle with old method : 0.10025501251220703 length of segment : 420 time for calcul the mask position with numpy : 0.004933595657348633 nb_pixel_total : 121949 time to create 1 rle with old method : 0.15578389167785645 length of segment : 464 time for calcul the mask position with numpy : 0.004380702972412109 nb_pixel_total : 13794 time to create 1 rle with old method : 0.015531063079833984 length of segment : 239 time for calcul the mask position with numpy : 0.006973981857299805 nb_pixel_total : 24852 time to create 1 rle with old method : 0.03179359436035156 length of segment : 161 time for calcul the mask position with numpy : 0.007578611373901367 nb_pixel_total : 42199 time to create 1 rle with old method : 0.05610799789428711 length of segment : 306 time for calcul the mask position with numpy : 0.0006000995635986328 nb_pixel_total : 17749 time to create 1 rle with old method : 0.0204465389251709 length of segment : 177 time for calcul the mask position with numpy : 0.019355058670043945 nb_pixel_total : 32848 time to create 1 rle with old method : 0.04325056076049805 length of segment : 204 time for calcul the mask position with numpy : 0.12405896186828613 nb_pixel_total : 649494 time to create 1 rle with new method : 0.352886438369751 length of segment : 1818 time for calcul the mask position with numpy : 0.007489919662475586 nb_pixel_total : 8908 time to create 1 rle with old method : 0.01362299919128418 length of segment : 127 time for calcul the mask position with numpy : 0.003667593002319336 nb_pixel_total : 156247 time to create 1 rle with new method : 0.011464357376098633 length of segment : 569 time for calcul the mask position with numpy : 0.11570239067077637 nb_pixel_total : 441587 time to create 1 rle with new method : 0.022448062896728516 length of segment : 1135 time for calcul the mask position with numpy : 0.00628662109375 nb_pixel_total : 35283 time to create 1 rle with old method : 0.04249262809753418 length of segment : 273 time for calcul the mask position with numpy : 0.03404045104980469 nb_pixel_total : 198485 time to create 1 rle with new method : 0.012810707092285156 length of segment : 721 time for calcul the mask position with numpy : 0.0016007423400878906 nb_pixel_total : 35663 time to create 1 rle with old method : 0.04260396957397461 length of segment : 195 time for calcul the mask position with numpy : 0.002628803253173828 nb_pixel_total : 20272 time to create 1 rle with old method : 0.023581266403198242 length of segment : 181 time for calcul the mask position with numpy : 0.004104137420654297 nb_pixel_total : 5541 time to create 1 rle with old method : 0.0066373348236083984 length of segment : 253 time for calcul the mask position with numpy : 0.0017428398132324219 nb_pixel_total : 55815 time to create 1 rle with old method : 0.0633091926574707 length of segment : 265 time for calcul the mask position with numpy : 0.0042803287506103516 nb_pixel_total : 41404 time to create 1 rle with old method : 0.0499422550201416 length of segment : 289 time for calcul the mask position with numpy : 0.0016562938690185547 nb_pixel_total : 25880 time to create 1 rle with old method : 0.03320193290710449 length of segment : 509 time for calcul the mask position with numpy : 0.0034863948822021484 nb_pixel_total : 81448 time to create 1 rle with old method : 0.09941434860229492 length of segment : 448 time for calcul the mask position with numpy : 0.004269123077392578 nb_pixel_total : 226494 time to create 1 rle with new method : 0.012915372848510742 length of segment : 798 time for calcul the mask position with numpy : 0.001676321029663086 nb_pixel_total : 17569 time to create 1 rle with old method : 0.02108311653137207 length of segment : 132 time for calcul the mask position with numpy : 0.0028541088104248047 nb_pixel_total : 22744 time to create 1 rle with old method : 0.02747321128845215 length of segment : 127 time for calcul the mask position with numpy : 0.0006623268127441406 nb_pixel_total : 34588 time to create 1 rle with old method : 0.040949344635009766 length of segment : 212 time for calcul the mask position with numpy : 0.0018219947814941406 nb_pixel_total : 41752 time to create 1 rle with old method : 0.049352169036865234 length of segment : 339 time for calcul the mask position with numpy : 0.0015556812286376953 nb_pixel_total : 2758 time to create 1 rle with old method : 0.003300905227661133 length of segment : 184 time for calcul the mask position with numpy : 0.13050580024719238 nb_pixel_total : 1136833 time to create 1 rle with new method : 0.17090845108032227 length of segment : 1648 time for calcul the mask position with numpy : 0.0017304420471191406 nb_pixel_total : 29386 time to create 1 rle with old method : 0.03362441062927246 length of segment : 296 time for calcul the mask position with numpy : 0.0013508796691894531 nb_pixel_total : 52263 time to create 1 rle with old method : 0.08266067504882812 length of segment : 329 time for calcul the mask position with numpy : 0.025603532791137695 nb_pixel_total : 495770 time to create 1 rle with new method : 0.06855130195617676 length of segment : 769 time for calcul the mask position with numpy : 0.001081228256225586 nb_pixel_total : 17318 time to create 1 rle with old method : 0.020034074783325195 length of segment : 218 time for calcul the mask position with numpy : 0.0007004737854003906 nb_pixel_total : 23406 time to create 1 rle with old method : 0.026243209838867188 length of segment : 605 time for calcul the mask position with numpy : 0.003970623016357422 nb_pixel_total : 76236 time to create 1 rle with old method : 0.09067153930664062 length of segment : 337 time for calcul the mask position with numpy : 0.008514881134033203 nb_pixel_total : 288049 time to create 1 rle with new method : 0.026649951934814453 length of segment : 1180 time for calcul the mask position with numpy : 0.009053230285644531 nb_pixel_total : 21367 time to create 1 rle with old method : 0.029134750366210938 length of segment : 164 time for calcul the mask position with numpy : 0.002232074737548828 nb_pixel_total : 101313 time to create 1 rle with old method : 0.11556768417358398 length of segment : 342 time for calcul the mask position with numpy : 0.0015103816986083984 nb_pixel_total : 26587 time to create 1 rle with old method : 0.029934167861938477 length of segment : 281 time for calcul the mask position with numpy : 0.001129150390625 nb_pixel_total : 54993 time to create 1 rle with old method : 0.06384730339050293 length of segment : 212 time for calcul the mask position with numpy : 0.003736734390258789 nb_pixel_total : 141553 time to create 1 rle with old method : 0.15746855735778809 length of segment : 381 time for calcul the mask position with numpy : 0.0018429756164550781 nb_pixel_total : 98473 time to create 1 rle with old method : 0.11908316612243652 length of segment : 393 time for calcul the mask position with numpy : 0.01935601234436035 nb_pixel_total : 436408 time to create 1 rle with new method : 0.09877920150756836 length of segment : 1217 time for calcul the mask position with numpy : 0.0016410350799560547 nb_pixel_total : 78247 time to create 1 rle with old method : 0.09073162078857422 length of segment : 368 time for calcul the mask position with numpy : 0.0016057491302490234 nb_pixel_total : 77188 time to create 1 rle with old method : 0.0907735824584961 length of segment : 341 time for calcul the mask position with numpy : 0.07336091995239258 nb_pixel_total : 1093575 time to create 1 rle with new method : 0.38153886795043945 length of segment : 1357 time for calcul the mask position with numpy : 0.0008652210235595703 nb_pixel_total : 41550 time to create 1 rle with old method : 0.049701690673828125 length of segment : 174 time for calcul the mask position with numpy : 0.0012264251708984375 nb_pixel_total : 46521 time to create 1 rle with old method : 0.054654836654663086 length of segment : 339 time for calcul the mask position with numpy : 0.010108232498168945 nb_pixel_total : 546900 time to create 1 rle with new method : 0.20876526832580566 length of segment : 788 time for calcul the mask position with numpy : 0.0004711151123046875 nb_pixel_total : 19688 time to create 1 rle with old method : 0.02566242218017578 length of segment : 136 time for calcul the mask position with numpy : 0.022718191146850586 nb_pixel_total : 1001462 time to create 1 rle with new method : 0.11870241165161133 length of segment : 1506 time for calcul the mask position with numpy : 0.0003895759582519531 nb_pixel_total : 19624 time to create 1 rle with old method : 0.02393817901611328 length of segment : 132 time for calcul the mask position with numpy : 0.011204004287719727 nb_pixel_total : 320706 time to create 1 rle with new method : 0.013571500778198242 length of segment : 609 time for calcul the mask position with numpy : 0.0026619434356689453 nb_pixel_total : 28870 time to create 1 rle with old method : 0.03890419006347656 length of segment : 168 time for calcul the mask position with numpy : 0.030256032943725586 nb_pixel_total : 413720 time to create 1 rle with new method : 0.0317225456237793 length of segment : 832 time for calcul the mask position with numpy : 0.001466512680053711 nb_pixel_total : 44025 time to create 1 rle with old method : 0.05385756492614746 length of segment : 387 time for calcul the mask position with numpy : 0.005001544952392578 nb_pixel_total : 32112 time to create 1 rle with old method : 0.03960084915161133 length of segment : 188 time for calcul the mask position with numpy : 0.0005509853363037109 nb_pixel_total : 31823 time to create 1 rle with old method : 0.03652596473693848 length of segment : 328 time for calcul the mask position with numpy : 0.004136085510253906 nb_pixel_total : 61461 time to create 1 rle with old method : 0.07280516624450684 length of segment : 433 time for calcul the mask position with numpy : 0.06299090385437012 nb_pixel_total : 820599 time to create 1 rle with new method : 0.12106847763061523 length of segment : 1203 time for calcul the mask position with numpy : 0.009714365005493164 nb_pixel_total : 242326 time to create 1 rle with new method : 0.013484716415405273 length of segment : 559 time for calcul the mask position with numpy : 0.0005009174346923828 nb_pixel_total : 14832 time to create 1 rle with old method : 0.01684284210205078 length of segment : 242 time for calcul the mask position with numpy : 0.0002682209014892578 nb_pixel_total : 8346 time to create 1 rle with old method : 0.009759187698364258 length of segment : 175 time for calcul the mask position with numpy : 0.0021352767944335938 nb_pixel_total : 50116 time to create 1 rle with old method : 0.057840585708618164 length of segment : 269 time for calcul the mask position with numpy : 0.0004398822784423828 nb_pixel_total : 21734 time to create 1 rle with old method : 0.02602839469909668 length of segment : 158 time for calcul the mask position with numpy : 0.0045239925384521484 nb_pixel_total : 80784 time to create 1 rle with old method : 0.09511804580688477 length of segment : 339 time for calcul the mask position with numpy : 0.00965571403503418 nb_pixel_total : 110438 time to create 1 rle with old method : 0.1366422176361084 length of segment : 752 time for calcul the mask position with numpy : 0.00205230712890625 nb_pixel_total : 38116 time to create 1 rle with old method : 0.04306626319885254 length of segment : 194 time for calcul the mask position with numpy : 0.003654003143310547 nb_pixel_total : 73407 time to create 1 rle with old method : 0.08773922920227051 length of segment : 192 time for calcul the mask position with numpy : 0.008184432983398438 nb_pixel_total : 158293 time to create 1 rle with new method : 0.0336146354675293 length of segment : 1132 time for calcul the mask position with numpy : 0.0031585693359375 nb_pixel_total : 83239 time to create 1 rle with old method : 0.0995337963104248 length of segment : 229 time for calcul the mask position with numpy : 0.002635478973388672 nb_pixel_total : 89115 time to create 1 rle with old method : 0.1217658519744873 length of segment : 303 time for calcul the mask position with numpy : 0.000858306884765625 nb_pixel_total : 29844 time to create 1 rle with old method : 0.03553318977355957 length of segment : 245 time for calcul the mask position with numpy : 0.0108642578125 nb_pixel_total : 362158 time to create 1 rle with new method : 0.01510000228881836 length of segment : 509 time for calcul the mask position with numpy : 0.0030629634857177734 nb_pixel_total : 124073 time to create 1 rle with old method : 0.16698288917541504 length of segment : 515 time for calcul the mask position with numpy : 0.029839515686035156 nb_pixel_total : 648216 time to create 1 rle with new method : 0.20063376426696777 length of segment : 1380 time for calcul the mask position with numpy : 0.0011129379272460938 nb_pixel_total : 38941 time to create 1 rle with old method : 0.044811248779296875 length of segment : 280 time for calcul the mask position with numpy : 0.002611398696899414 nb_pixel_total : 117516 time to create 1 rle with old method : 0.13481593132019043 length of segment : 402 time for calcul the mask position with numpy : 0.006659746170043945 nb_pixel_total : 340415 time to create 1 rle with new method : 0.03776407241821289 length of segment : 756 time for calcul the mask position with numpy : 0.0012998580932617188 nb_pixel_total : 54695 time to create 1 rle with old method : 0.06392383575439453 length of segment : 273 time for calcul the mask position with numpy : 0.00043511390686035156 nb_pixel_total : 3311 time to create 1 rle with old method : 0.0040967464447021484 length of segment : 74 time for calcul the mask position with numpy : 0.011546611785888672 nb_pixel_total : 508540 time to create 1 rle with new method : 0.03616952896118164 length of segment : 762 time for calcul the mask position with numpy : 0.006841897964477539 nb_pixel_total : 302968 time to create 1 rle with new method : 0.017403125762939453 length of segment : 917 time for calcul the mask position with numpy : 0.0018916130065917969 nb_pixel_total : 110638 time to create 1 rle with old method : 0.12792301177978516 length of segment : 428 time for calcul the mask position with numpy : 0.0010330677032470703 nb_pixel_total : 14125 time to create 1 rle with old method : 0.016821861267089844 length of segment : 392 time for calcul the mask position with numpy : 0.009348630905151367 nb_pixel_total : 143629 time to create 1 rle with old method : 0.1674816608428955 length of segment : 381 time for calcul the mask position with numpy : 0.0009243488311767578 nb_pixel_total : 39746 time to create 1 rle with old method : 0.05043172836303711 length of segment : 211 time for calcul the mask position with numpy : 0.11791539192199707 nb_pixel_total : 2404095 time to create 1 rle with new method : 0.33072805404663086 length of segment : 2352 time for calcul the mask position with numpy : 0.0008990764617919922 nb_pixel_total : 33300 time to create 1 rle with old method : 0.03913378715515137 length of segment : 221 time for calcul the mask position with numpy : 0.0038220882415771484 nb_pixel_total : 111251 time to create 1 rle with old method : 0.129563570022583 length of segment : 427 time for calcul the mask position with numpy : 0.0055043697357177734 nb_pixel_total : 237865 time to create 1 rle with new method : 0.01685357093811035 length of segment : 653 time for calcul the mask position with numpy : 0.0031423568725585938 nb_pixel_total : 155952 time to create 1 rle with new method : 0.009526968002319336 length of segment : 573 time for calcul the mask position with numpy : 0.0008723735809326172 nb_pixel_total : 22823 time to create 1 rle with old method : 0.02662968635559082 length of segment : 176 time for calcul the mask position with numpy : 0.0019469261169433594 nb_pixel_total : 105627 time to create 1 rle with old method : 0.12469029426574707 length of segment : 430 time for calcul the mask position with numpy : 0.0014982223510742188 nb_pixel_total : 40521 time to create 1 rle with old method : 0.04850339889526367 length of segment : 245 time for calcul the mask position with numpy : 0.002292633056640625 nb_pixel_total : 116019 time to create 1 rle with old method : 0.13733530044555664 length of segment : 306 time for calcul the mask position with numpy : 0.0014081001281738281 nb_pixel_total : 86327 time to create 1 rle with old method : 0.10070300102233887 length of segment : 250 time for calcul the mask position with numpy : 0.0028929710388183594 nb_pixel_total : 144116 time to create 1 rle with old method : 0.17092037200927734 length of segment : 279 time for calcul the mask position with numpy : 0.0017359256744384766 nb_pixel_total : 85279 time to create 1 rle with old method : 0.10317468643188477 length of segment : 316 time for calcul the mask position with numpy : 0.002529144287109375 nb_pixel_total : 124827 time to create 1 rle with old method : 0.14759016036987305 length of segment : 547 time for calcul the mask position with numpy : 0.013341426849365234 nb_pixel_total : 299684 time to create 1 rle with new method : 0.017406702041625977 length of segment : 1388 time for calcul the mask position with numpy : 0.0039424896240234375 nb_pixel_total : 27819 time to create 1 rle with old method : 0.05878305435180664 length of segment : 241 time for calcul the mask position with numpy : 0.00017452239990234375 nb_pixel_total : 4279 time to create 1 rle with old method : 0.005262613296508789 length of segment : 162 time for calcul the mask position with numpy : 0.01449894905090332 nb_pixel_total : 343805 time to create 1 rle with new method : 0.018973827362060547 length of segment : 708 time for calcul the mask position with numpy : 0.00044608116149902344 nb_pixel_total : 12681 time to create 1 rle with old method : 0.015182018280029297 length of segment : 151 time for calcul the mask position with numpy : 0.022408723831176758 nb_pixel_total : 568965 time to create 1 rle with new method : 0.05820608139038086 length of segment : 1267 time for calcul the mask position with numpy : 0.0023572444915771484 nb_pixel_total : 104432 time to create 1 rle with old method : 0.1377122402191162 length of segment : 311 time for calcul the mask position with numpy : 0.0034444332122802734 nb_pixel_total : 74419 time to create 1 rle with old method : 0.08622217178344727 length of segment : 400 time for calcul the mask position with numpy : 0.004303455352783203 nb_pixel_total : 211933 time to create 1 rle with new method : 0.010920286178588867 length of segment : 418 time for calcul the mask position with numpy : 0.0019500255584716797 nb_pixel_total : 77596 time to create 1 rle with old method : 0.08807182312011719 length of segment : 464 time for calcul the mask position with numpy : 0.0031321048736572266 nb_pixel_total : 90372 time to create 1 rle with old method : 0.10427284240722656 length of segment : 447 time for calcul the mask position with numpy : 0.010547876358032227 nb_pixel_total : 342575 time to create 1 rle with new method : 0.02927684783935547 length of segment : 934 time for calcul the mask position with numpy : 0.005475759506225586 nb_pixel_total : 29991 time to create 1 rle with old method : 0.03808903694152832 length of segment : 156 time for calcul the mask position with numpy : 0.0006582736968994141 nb_pixel_total : 24729 time to create 1 rle with old method : 0.029889822006225586 length of segment : 174 time for calcul the mask position with numpy : 0.0037338733673095703 nb_pixel_total : 36146 time to create 1 rle with old method : 0.06454348564147949 length of segment : 183 time for calcul the mask position with numpy : 0.004254341125488281 nb_pixel_total : 51650 time to create 1 rle with old method : 0.060320138931274414 length of segment : 243 time for calcul the mask position with numpy : 0.013595819473266602 nb_pixel_total : 635324 time to create 1 rle with new method : 0.028601408004760742 length of segment : 1120 time for calcul the mask position with numpy : 0.0029573440551757812 nb_pixel_total : 128291 time to create 1 rle with old method : 0.1457052230834961 length of segment : 473 time for calcul the mask position with numpy : 0.012153387069702148 nb_pixel_total : 499201 time to create 1 rle with new method : 0.025952577590942383 length of segment : 1014 time for calcul the mask position with numpy : 0.0021448135375976562 nb_pixel_total : 100198 time to create 1 rle with old method : 0.11387085914611816 length of segment : 387 time for calcul the mask position with numpy : 0.009362220764160156 nb_pixel_total : 241307 time to create 1 rle with new method : 0.01773810386657715 length of segment : 556 time for calcul the mask position with numpy : 0.008013486862182617 nb_pixel_total : 285405 time to create 1 rle with new method : 0.020317554473876953 length of segment : 681 time for calcul the mask position with numpy : 0.0033597946166992188 nb_pixel_total : 178452 time to create 1 rle with new method : 0.009953737258911133 length of segment : 507 time for calcul the mask position with numpy : 0.0009775161743164062 nb_pixel_total : 57919 time to create 1 rle with old method : 0.06734156608581543 length of segment : 275 time for calcul the mask position with numpy : 0.00139617919921875 nb_pixel_total : 39790 time to create 1 rle with old method : 0.04874134063720703 length of segment : 257 time for calcul the mask position with numpy : 0.0012023448944091797 nb_pixel_total : 57348 time to create 1 rle with old method : 0.06598782539367676 length of segment : 436 time for calcul the mask position with numpy : 0.0003554821014404297 nb_pixel_total : 13577 time to create 1 rle with old method : 0.038330078125 length of segment : 148 time for calcul the mask position with numpy : 0.01142740249633789 nb_pixel_total : 561856 time to create 1 rle with new method : 0.031717777252197266 length of segment : 1026 time for calcul the mask position with numpy : 0.00036907196044921875 nb_pixel_total : 13619 time to create 1 rle with old method : 0.01588296890258789 length of segment : 164 time for calcul the mask position with numpy : 0.0014750957489013672 nb_pixel_total : 17307 time to create 1 rle with old method : 0.020364999771118164 length of segment : 273 time for calcul the mask position with numpy : 0.03858757019042969 nb_pixel_total : 1126248 time to create 1 rle with new method : 0.24739956855773926 length of segment : 2122 time for calcul the mask position with numpy : 0.0007381439208984375 nb_pixel_total : 22272 time to create 1 rle with old method : 0.02891063690185547 length of segment : 143 time for calcul the mask position with numpy : 0.0321202278137207 nb_pixel_total : 841190 time to create 1 rle with new method : 0.20457148551940918 length of segment : 1286 time for calcul the mask position with numpy : 0.022114038467407227 nb_pixel_total : 1268637 time to create 1 rle with new method : 0.22249674797058105 length of segment : 1609 time for calcul the mask position with numpy : 0.0010013580322265625 nb_pixel_total : 58311 time to create 1 rle with old method : 0.06731295585632324 length of segment : 301 time for calcul the mask position with numpy : 0.003084897994995117 nb_pixel_total : 80126 time to create 1 rle with old method : 0.0922231674194336 length of segment : 470 time for calcul the mask position with numpy : 0.0019030570983886719 nb_pixel_total : 50406 time to create 1 rle with old method : 0.05574369430541992 length of segment : 474 time for calcul the mask position with numpy : 0.0018162727355957031 nb_pixel_total : 95662 time to create 1 rle with old method : 0.10986757278442383 length of segment : 424 time for calcul the mask position with numpy : 0.0033414363861083984 nb_pixel_total : 143142 time to create 1 rle with old method : 0.1624460220336914 length of segment : 607 time for calcul the mask position with numpy : 0.0038208961486816406 nb_pixel_total : 238264 time to create 1 rle with new method : 0.010492324829101562 length of segment : 691 time for calcul the mask position with numpy : 0.001832723617553711 nb_pixel_total : 97983 time to create 1 rle with old method : 0.1156926155090332 length of segment : 421 time for calcul the mask position with numpy : 0.0010306835174560547 nb_pixel_total : 49374 time to create 1 rle with old method : 0.05637764930725098 length of segment : 319 time for calcul the mask position with numpy : 0.007578372955322266 nb_pixel_total : 371578 time to create 1 rle with new method : 0.030935049057006836 length of segment : 912 time for calcul the mask position with numpy : 0.0003116130828857422 nb_pixel_total : 7551 time to create 1 rle with old method : 0.026311874389648438 length of segment : 146 time for calcul the mask position with numpy : 0.0024771690368652344 nb_pixel_total : 101167 time to create 1 rle with old method : 0.11718297004699707 length of segment : 449 time for calcul the mask position with numpy : 0.011893510818481445 nb_pixel_total : 591693 time to create 1 rle with new method : 0.1132204532623291 length of segment : 924 time for calcul the mask position with numpy : 0.0009644031524658203 nb_pixel_total : 41393 time to create 1 rle with old method : 0.04851484298706055 length of segment : 196 time for calcul the mask position with numpy : 0.0018875598907470703 nb_pixel_total : 113885 time to create 1 rle with old method : 0.13098359107971191 length of segment : 405 time for calcul the mask position with numpy : 0.001661539077758789 nb_pixel_total : 73638 time to create 1 rle with old method : 0.0855717658996582 length of segment : 351 time for calcul the mask position with numpy : 0.0015163421630859375 nb_pixel_total : 85384 time to create 1 rle with old method : 0.09711003303527832 length of segment : 521 time for calcul the mask position with numpy : 0.0038836002349853516 nb_pixel_total : 210154 time to create 1 rle with new method : 0.010858535766601562 length of segment : 472 time for calcul the mask position with numpy : 0.003992319107055664 nb_pixel_total : 216446 time to create 1 rle with new method : 0.010749578475952148 length of segment : 448 time for calcul the mask position with numpy : 0.0005335807800292969 nb_pixel_total : 15856 time to create 1 rle with old method : 0.018207311630249023 length of segment : 179 time for calcul the mask position with numpy : 0.005312919616699219 nb_pixel_total : 103780 time to create 1 rle with old method : 0.12413787841796875 length of segment : 278 time for calcul the mask position with numpy : 0.003866910934448242 nb_pixel_total : 113817 time to create 1 rle with old method : 0.15764665603637695 length of segment : 418 time for calcul the mask position with numpy : 0.002931833267211914 nb_pixel_total : 50824 time to create 1 rle with old method : 0.058495521545410156 length of segment : 222 time for calcul the mask position with numpy : 0.0019123554229736328 nb_pixel_total : 13416 time to create 1 rle with old method : 0.01636672019958496 length of segment : 154 time for calcul the mask position with numpy : 0.00344085693359375 nb_pixel_total : 82151 time to create 1 rle with old method : 0.09774065017700195 length of segment : 326 time for calcul the mask position with numpy : 0.0005507469177246094 nb_pixel_total : 13443 time to create 1 rle with old method : 0.015900850296020508 length of segment : 157 time for calcul the mask position with numpy : 0.017147302627563477 nb_pixel_total : 257298 time to create 1 rle with new method : 0.019415855407714844 length of segment : 660 time for calcul the mask position with numpy : 0.02399444580078125 nb_pixel_total : 383600 time to create 1 rle with new method : 0.018982410430908203 length of segment : 591 time for calcul the mask position with numpy : 0.00493168830871582 nb_pixel_total : 263474 time to create 1 rle with new method : 0.009454727172851562 length of segment : 640 time for calcul the mask position with numpy : 0.028759479522705078 nb_pixel_total : 1086963 time to create 1 rle with new method : 0.1355588436126709 length of segment : 1383 time for calcul the mask position with numpy : 0.00028252601623535156 nb_pixel_total : 10549 time to create 1 rle with old method : 0.012902021408081055 length of segment : 125 time for calcul the mask position with numpy : 0.001253366470336914 nb_pixel_total : 64533 time to create 1 rle with old method : 0.07603335380554199 length of segment : 416 time for calcul the mask position with numpy : 0.018988609313964844 nb_pixel_total : 757270 time to create 1 rle with new method : 0.11135053634643555 length of segment : 757 time for calcul the mask position with numpy : 0.005056858062744141 nb_pixel_total : 73420 time to create 1 rle with old method : 0.09344005584716797 length of segment : 425 time for calcul the mask position with numpy : 0.00030040740966796875 nb_pixel_total : 7502 time to create 1 rle with old method : 0.009318351745605469 length of segment : 93 time for calcul the mask position with numpy : 0.0011615753173828125 nb_pixel_total : 21031 time to create 1 rle with old method : 0.026530027389526367 length of segment : 178 time for calcul the mask position with numpy : 0.0009641647338867188 nb_pixel_total : 55218 time to create 1 rle with old method : 0.07514381408691406 length of segment : 167 time for calcul the mask position with numpy : 0.0010919570922851562 nb_pixel_total : 61739 time to create 1 rle with old method : 0.07200503349304199 length of segment : 449 time for calcul the mask position with numpy : 0.0009539127349853516 nb_pixel_total : 48788 time to create 1 rle with old method : 0.05660605430603027 length of segment : 310 time for calcul the mask position with numpy : 0.0433657169342041 nb_pixel_total : 1468683 time to create 1 rle with new method : 0.497495174407959 length of segment : 1125 time for calcul the mask position with numpy : 0.0004191398620605469 nb_pixel_total : 22329 time to create 1 rle with old method : 0.04914522171020508 length of segment : 155 time for calcul the mask position with numpy : 0.0009851455688476562 nb_pixel_total : 52778 time to create 1 rle with old method : 0.06336045265197754 length of segment : 216 time for calcul the mask position with numpy : 0.003919124603271484 nb_pixel_total : 258657 time to create 1 rle with new method : 0.010446310043334961 length of segment : 658 time for calcul the mask position with numpy : 0.002452373504638672 nb_pixel_total : 95046 time to create 1 rle with old method : 0.1109459400177002 length of segment : 555 time for calcul the mask position with numpy : 0.0008177757263183594 nb_pixel_total : 51789 time to create 1 rle with old method : 0.06086087226867676 length of segment : 154 time for calcul the mask position with numpy : 0.0020248889923095703 nb_pixel_total : 114400 time to create 1 rle with old method : 0.1377274990081787 length of segment : 565 time for calcul the mask position with numpy : 0.0014529228210449219 nb_pixel_total : 29048 time to create 1 rle with old method : 0.034334421157836914 length of segment : 258 time for calcul the mask position with numpy : 0.0014357566833496094 nb_pixel_total : 78124 time to create 1 rle with old method : 0.09279894828796387 length of segment : 305 time for calcul the mask position with numpy : 0.0017457008361816406 nb_pixel_total : 116752 time to create 1 rle with old method : 0.15728068351745605 length of segment : 240 time for calcul the mask position with numpy : 0.007498502731323242 nb_pixel_total : 438160 time to create 1 rle with new method : 0.014644622802734375 length of segment : 1116 time for calcul the mask position with numpy : 0.0012402534484863281 nb_pixel_total : 84736 time to create 1 rle with old method : 0.09978866577148438 length of segment : 304 time for calcul the mask position with numpy : 0.005183219909667969 nb_pixel_total : 101590 time to create 1 rle with old method : 0.11980628967285156 length of segment : 285 time for calcul the mask position with numpy : 0.008220195770263672 nb_pixel_total : 438380 time to create 1 rle with new method : 0.02225637435913086 length of segment : 1058 time for calcul the mask position with numpy : 0.0005908012390136719 nb_pixel_total : 23735 time to create 1 rle with old method : 0.02671360969543457 length of segment : 159 time for calcul the mask position with numpy : 0.0007259845733642578 nb_pixel_total : 27447 time to create 1 rle with old method : 0.03190898895263672 length of segment : 265 time for calcul the mask position with numpy : 0.004808902740478516 nb_pixel_total : 297120 time to create 1 rle with new method : 0.01313924789428711 length of segment : 1091 time for calcul the mask position with numpy : 0.002190828323364258 nb_pixel_total : 117738 time to create 1 rle with old method : 0.13344860076904297 length of segment : 432 time for calcul the mask position with numpy : 0.0005223751068115234 nb_pixel_total : 21318 time to create 1 rle with old method : 0.025304317474365234 length of segment : 241 time for calcul the mask position with numpy : 0.0070569515228271484 nb_pixel_total : 263035 time to create 1 rle with new method : 0.021528005599975586 length of segment : 724 time for calcul the mask position with numpy : 0.00063323974609375 nb_pixel_total : 19324 time to create 1 rle with old method : 0.022281408309936523 length of segment : 165 time for calcul the mask position with numpy : 0.0006947517395019531 nb_pixel_total : 32616 time to create 1 rle with old method : 0.03772091865539551 length of segment : 184 time for calcul the mask position with numpy : 0.0005602836608886719 nb_pixel_total : 25131 time to create 1 rle with old method : 0.0294039249420166 length of segment : 214 time for calcul the mask position with numpy : 0.0020847320556640625 nb_pixel_total : 113455 time to create 1 rle with old method : 0.14607954025268555 length of segment : 616 time for calcul the mask position with numpy : 0.0028781890869140625 nb_pixel_total : 147970 time to create 1 rle with old method : 0.16843128204345703 length of segment : 587 time for calcul the mask position with numpy : 0.0001647472381591797 nb_pixel_total : 4921 time to create 1 rle with old method : 0.005662441253662109 length of segment : 84 time for calcul the mask position with numpy : 0.0013091564178466797 nb_pixel_total : 41487 time to create 1 rle with old method : 0.0478215217590332 length of segment : 349 time for calcul the mask position with numpy : 0.013754844665527344 nb_pixel_total : 406943 time to create 1 rle with new method : 0.2544095516204834 length of segment : 1316 time for calcul the mask position with numpy : 0.0004818439483642578 nb_pixel_total : 23345 time to create 1 rle with old method : 0.02734541893005371 length of segment : 201 time for calcul the mask position with numpy : 0.0015211105346679688 nb_pixel_total : 58382 time to create 1 rle with old method : 0.0660400390625 length of segment : 464 time for calcul the mask position with numpy : 0.0030472278594970703 nb_pixel_total : 143794 time to create 1 rle with old method : 0.1625537872314453 length of segment : 532 time for calcul the mask position with numpy : 0.0058476924896240234 nb_pixel_total : 303295 time to create 1 rle with new method : 0.01632070541381836 length of segment : 667 time for calcul the mask position with numpy : 0.0005679130554199219 nb_pixel_total : 25830 time to create 1 rle with old method : 0.032563209533691406 length of segment : 172 time for calcul the mask position with numpy : 0.0010387897491455078 nb_pixel_total : 54782 time to create 1 rle with old method : 0.08094620704650879 length of segment : 282 time for calcul the mask position with numpy : 0.002585172653198242 nb_pixel_total : 96253 time to create 1 rle with old method : 0.11335468292236328 length of segment : 351 time for calcul the mask position with numpy : 0.012142181396484375 nb_pixel_total : 376380 time to create 1 rle with new method : 0.02336883544921875 length of segment : 1021 time for calcul the mask position with numpy : 0.0014226436614990234 nb_pixel_total : 50911 time to create 1 rle with old method : 0.06017732620239258 length of segment : 253 time for calcul the mask position with numpy : 0.0006635189056396484 nb_pixel_total : 7505 time to create 1 rle with old method : 0.009706258773803711 length of segment : 160 time for calcul the mask position with numpy : 0.0009620189666748047 nb_pixel_total : 46269 time to create 1 rle with old method : 0.056229352951049805 length of segment : 228 time for calcul the mask position with numpy : 0.0016891956329345703 nb_pixel_total : 54539 time to create 1 rle with old method : 0.08371591567993164 length of segment : 514 time for calcul the mask position with numpy : 0.0006792545318603516 nb_pixel_total : 7843 time to create 1 rle with old method : 0.010634660720825195 length of segment : 131 time for calcul the mask position with numpy : 0.0006537437438964844 nb_pixel_total : 17887 time to create 1 rle with old method : 0.021391868591308594 length of segment : 210 time for calcul the mask position with numpy : 0.0026221275329589844 nb_pixel_total : 109977 time to create 1 rle with old method : 0.129929780960083 length of segment : 469 time for calcul the mask position with numpy : 0.000484466552734375 nb_pixel_total : 17981 time to create 1 rle with old method : 0.021977663040161133 length of segment : 186 time for calcul the mask position with numpy : 0.0007753372192382812 nb_pixel_total : 33006 time to create 1 rle with old method : 0.03986978530883789 length of segment : 164 time for calcul the mask position with numpy : 0.0010769367218017578 nb_pixel_total : 43899 time to create 1 rle with old method : 0.05300712585449219 length of segment : 303 time for calcul the mask position with numpy : 0.00283050537109375 nb_pixel_total : 101569 time to create 1 rle with old method : 0.13140392303466797 length of segment : 681 time for calcul the mask position with numpy : 0.003392457962036133 nb_pixel_total : 114182 time to create 1 rle with old method : 0.13639044761657715 length of segment : 518 time for calcul the mask position with numpy : 0.029814720153808594 nb_pixel_total : 1787244 time to create 1 rle with new method : 0.16075634956359863 length of segment : 1171 time for calcul the mask position with numpy : 0.01596522331237793 nb_pixel_total : 461638 time to create 1 rle with new method : 0.06943845748901367 length of segment : 1517 time for calcul the mask position with numpy : 0.0016541481018066406 nb_pixel_total : 88873 time to create 1 rle with old method : 0.10431361198425293 length of segment : 323 time for calcul the mask position with numpy : 0.02644658088684082 nb_pixel_total : 789073 time to create 1 rle with new method : 0.4426839351654053 length of segment : 1451 time for calcul the mask position with numpy : 0.00022125244140625 nb_pixel_total : 8128 time to create 1 rle with old method : 0.010103702545166016 length of segment : 109 time for calcul the mask position with numpy : 0.0013768672943115234 nb_pixel_total : 39993 time to create 1 rle with old method : 0.050798892974853516 length of segment : 283 time for calcul the mask position with numpy : 0.002765178680419922 nb_pixel_total : 141600 time to create 1 rle with old method : 0.16883492469787598 length of segment : 369 time for calcul the mask position with numpy : 0.0013964176177978516 nb_pixel_total : 62891 time to create 1 rle with old method : 0.07419276237487793 length of segment : 323 time for calcul the mask position with numpy : 0.008536100387573242 nb_pixel_total : 196629 time to create 1 rle with new method : 0.030039072036743164 length of segment : 897 time for calcul the mask position with numpy : 0.0003337860107421875 nb_pixel_total : 13951 time to create 1 rle with old method : 0.01741790771484375 length of segment : 101 time for calcul the mask position with numpy : 0.0009386539459228516 nb_pixel_total : 44421 time to create 1 rle with old method : 0.05375361442565918 length of segment : 259 time for calcul the mask position with numpy : 0.003548860549926758 nb_pixel_total : 166445 time to create 1 rle with new method : 0.01112818717956543 length of segment : 591 time for calcul the mask position with numpy : 0.0021543502807617188 nb_pixel_total : 109161 time to create 1 rle with old method : 0.1307053565979004 length of segment : 330 time for calcul the mask position with numpy : 0.002171754837036133 nb_pixel_total : 62061 time to create 1 rle with old method : 0.07376694679260254 length of segment : 358 time for calcul the mask position with numpy : 0.0017490386962890625 nb_pixel_total : 64933 time to create 1 rle with old method : 0.07564592361450195 length of segment : 485 time for calcul the mask position with numpy : 0.0008826255798339844 nb_pixel_total : 43252 time to create 1 rle with old method : 0.053130388259887695 length of segment : 193 time for calcul the mask position with numpy : 0.0006225109100341797 nb_pixel_total : 29660 time to create 1 rle with old method : 0.0357816219329834 length of segment : 250 time for calcul the mask position with numpy : 0.0015490055084228516 nb_pixel_total : 57963 time to create 1 rle with old method : 0.06869387626647949 length of segment : 452 time for calcul the mask position with numpy : 0.0012519359588623047 nb_pixel_total : 60106 time to create 1 rle with old method : 0.07166028022766113 length of segment : 404 time for calcul the mask position with numpy : 0.0029153823852539062 nb_pixel_total : 123175 time to create 1 rle with old method : 0.14440035820007324 length of segment : 398 time for calcul the mask position with numpy : 0.0013606548309326172 nb_pixel_total : 57501 time to create 1 rle with old method : 0.07011914253234863 length of segment : 413 time for calcul the mask position with numpy : 0.0008015632629394531 nb_pixel_total : 43991 time to create 1 rle with old method : 0.053431034088134766 length of segment : 215 time for calcul the mask position with numpy : 0.001651763916015625 nb_pixel_total : 70756 time to create 1 rle with old method : 0.08287739753723145 length of segment : 304 time for calcul the mask position with numpy : 0.003964900970458984 nb_pixel_total : 136629 time to create 1 rle with old method : 0.18242692947387695 length of segment : 529 time for calcul the mask position with numpy : 0.0007855892181396484 nb_pixel_total : 32091 time to create 1 rle with old method : 0.038057565689086914 length of segment : 160 time for calcul the mask position with numpy : 0.0010614395141601562 nb_pixel_total : 51773 time to create 1 rle with old method : 0.06187272071838379 length of segment : 275 time for calcul the mask position with numpy : 0.0020287036895751953 nb_pixel_total : 122964 time to create 1 rle with old method : 0.14382576942443848 length of segment : 368 time for calcul the mask position with numpy : 0.003129720687866211 nb_pixel_total : 127432 time to create 1 rle with old method : 0.15117359161376953 length of segment : 505 time for calcul the mask position with numpy : 0.0008499622344970703 nb_pixel_total : 3528 time to create 1 rle with old method : 0.006606340408325195 length of segment : 145 time for calcul the mask position with numpy : 0.0034902095794677734 nb_pixel_total : 117827 time to create 1 rle with old method : 0.14897751808166504 length of segment : 400 time for calcul the mask position with numpy : 0.0009789466857910156 nb_pixel_total : 46395 time to create 1 rle with old method : 0.07378959655761719 length of segment : 219 time for calcul the mask position with numpy : 0.0010190010070800781 nb_pixel_total : 36976 time to create 1 rle with old method : 0.043552398681640625 length of segment : 226 time for calcul the mask position with numpy : 0.004035234451293945 nb_pixel_total : 220882 time to create 1 rle with new method : 0.010073423385620117 length of segment : 569 time for calcul the mask position with numpy : 0.002237558364868164 nb_pixel_total : 106022 time to create 1 rle with old method : 0.13013076782226562 length of segment : 420 time for calcul the mask position with numpy : 0.0032792091369628906 nb_pixel_total : 110409 time to create 1 rle with old method : 0.13675665855407715 length of segment : 300 time for calcul the mask position with numpy : 0.00403285026550293 nb_pixel_total : 213251 time to create 1 rle with new method : 0.010353565216064453 length of segment : 691 time for calcul the mask position with numpy : 0.0009791851043701172 nb_pixel_total : 44136 time to create 1 rle with old method : 0.05268430709838867 length of segment : 219 time for calcul the mask position with numpy : 0.005709409713745117 nb_pixel_total : 311796 time to create 1 rle with new method : 0.014449596405029297 length of segment : 788 time for calcul the mask position with numpy : 0.013457536697387695 nb_pixel_total : 555492 time to create 1 rle with new method : 0.06483721733093262 length of segment : 1184 time for calcul the mask position with numpy : 0.00101470947265625 nb_pixel_total : 38344 time to create 1 rle with old method : 0.04619717597961426 length of segment : 233 time for calcul the mask position with numpy : 0.003500699996948242 nb_pixel_total : 177065 time to create 1 rle with new method : 0.010556221008300781 length of segment : 462 time for calcul the mask position with numpy : 0.0014238357543945312 nb_pixel_total : 61997 time to create 1 rle with old method : 0.07364654541015625 length of segment : 282 time for calcul the mask position with numpy : 0.003544330596923828 nb_pixel_total : 191947 time to create 1 rle with new method : 0.01011204719543457 length of segment : 849 time for calcul the mask position with numpy : 0.0004475116729736328 nb_pixel_total : 13428 time to create 1 rle with old method : 0.01589488983154297 length of segment : 175 time for calcul the mask position with numpy : 0.00039577484130859375 nb_pixel_total : 15724 time to create 1 rle with old method : 0.019065380096435547 length of segment : 165 time for calcul the mask position with numpy : 0.004237651824951172 nb_pixel_total : 202228 time to create 1 rle with new method : 0.010725736618041992 length of segment : 532 time for calcul the mask position with numpy : 0.0005633831024169922 nb_pixel_total : 25872 time to create 1 rle with old method : 0.0322725772857666 length of segment : 263 time for calcul the mask position with numpy : 0.0011324882507324219 nb_pixel_total : 55744 time to create 1 rle with old method : 0.06762528419494629 length of segment : 260 time for calcul the mask position with numpy : 0.003615856170654297 nb_pixel_total : 158754 time to create 1 rle with new method : 0.009172677993774414 length of segment : 591 time for calcul the mask position with numpy : 0.008143901824951172 nb_pixel_total : 400292 time to create 1 rle with new method : 0.017560243606567383 length of segment : 620 time for calcul the mask position with numpy : 0.0015673637390136719 nb_pixel_total : 69265 time to create 1 rle with old method : 0.08199930191040039 length of segment : 245 time for calcul the mask position with numpy : 0.016830921173095703 nb_pixel_total : 770124 time to create 1 rle with new method : 0.07752871513366699 length of segment : 858 time for calcul the mask position with numpy : 0.013401031494140625 nb_pixel_total : 567952 time to create 1 rle with new method : 0.08591461181640625 length of segment : 1136 time for calcul the mask position with numpy : 0.0014829635620117188 nb_pixel_total : 95513 time to create 1 rle with old method : 0.11357736587524414 length of segment : 362 time for calcul the mask position with numpy : 0.0020377635955810547 nb_pixel_total : 100802 time to create 1 rle with old method : 0.1425306797027588 length of segment : 358 time for calcul the mask position with numpy : 0.021518230438232422 nb_pixel_total : 920705 time to create 1 rle with new method : 0.15022802352905273 length of segment : 1221 time for calcul the mask position with numpy : 0.005536079406738281 nb_pixel_total : 168730 time to create 1 rle with new method : 0.016346454620361328 length of segment : 595 time for calcul the mask position with numpy : 0.0019414424896240234 nb_pixel_total : 105122 time to create 1 rle with old method : 0.15209698677062988 length of segment : 483 time for calcul the mask position with numpy : 0.0008630752563476562 nb_pixel_total : 36098 time to create 1 rle with old method : 0.04749178886413574 length of segment : 255 time for calcul the mask position with numpy : 0.005358457565307617 nb_pixel_total : 273281 time to create 1 rle with new method : 0.013577461242675781 length of segment : 501 time for calcul the mask position with numpy : 0.0014405250549316406 nb_pixel_total : 70066 time to create 1 rle with old method : 0.08281660079956055 length of segment : 244 time for calcul the mask position with numpy : 0.0061740875244140625 nb_pixel_total : 353338 time to create 1 rle with new method : 0.023366212844848633 length of segment : 729 time for calcul the mask position with numpy : 0.0008556842803955078 nb_pixel_total : 35277 time to create 1 rle with old method : 0.05599784851074219 length of segment : 374 time for calcul the mask position with numpy : 0.0008897781372070312 nb_pixel_total : 38170 time to create 1 rle with old method : 0.05528450012207031 length of segment : 199 time for calcul the mask position with numpy : 0.002776622772216797 nb_pixel_total : 81770 time to create 1 rle with old method : 0.1457357406616211 length of segment : 369 time for calcul the mask position with numpy : 0.026206254959106445 nb_pixel_total : 427375 time to create 1 rle with new method : 0.43697047233581543 length of segment : 1173 time for calcul the mask position with numpy : 0.003829479217529297 nb_pixel_total : 137677 time to create 1 rle with old method : 0.16382765769958496 length of segment : 803 time for calcul the mask position with numpy : 0.0009760856628417969 nb_pixel_total : 40432 time to create 1 rle with old method : 0.054367780685424805 length of segment : 236 time for calcul the mask position with numpy : 0.0019588470458984375 nb_pixel_total : 62738 time to create 1 rle with old method : 0.12578153610229492 length of segment : 528 time for calcul the mask position with numpy : 0.0006117820739746094 nb_pixel_total : 22681 time to create 1 rle with old method : 0.027849435806274414 length of segment : 244 time for calcul the mask position with numpy : 0.018207073211669922 nb_pixel_total : 763393 time to create 1 rle with new method : 0.31142234802246094 length of segment : 1339 time for calcul the mask position with numpy : 0.012163162231445312 nb_pixel_total : 424883 time to create 1 rle with new method : 0.12590336799621582 length of segment : 708 time for calcul the mask position with numpy : 0.0013089179992675781 nb_pixel_total : 54716 time to create 1 rle with old method : 0.06569766998291016 length of segment : 385 time for calcul the mask position with numpy : 0.0015108585357666016 nb_pixel_total : 78713 time to create 1 rle with old method : 0.14836573600769043 length of segment : 340 time for calcul the mask position with numpy : 0.016460180282592773 nb_pixel_total : 840521 time to create 1 rle with new method : 0.0675649642944336 length of segment : 1476 time for calcul the mask position with numpy : 0.0004956722259521484 nb_pixel_total : 21239 time to create 1 rle with old method : 0.025945425033569336 length of segment : 150 time for calcul the mask position with numpy : 0.0021047592163085938 nb_pixel_total : 116816 time to create 1 rle with old method : 0.13881349563598633 length of segment : 299 time for calcul the mask position with numpy : 0.022539138793945312 nb_pixel_total : 533904 time to create 1 rle with new method : 0.2750711441040039 length of segment : 1413 time for calcul the mask position with numpy : 0.0058040618896484375 nb_pixel_total : 248285 time to create 1 rle with new method : 0.01849985122680664 length of segment : 1219 time for calcul the mask position with numpy : 0.0031042098999023438 nb_pixel_total : 56923 time to create 1 rle with old method : 0.06738018989562988 length of segment : 199 time for calcul the mask position with numpy : 0.0011551380157470703 nb_pixel_total : 52264 time to create 1 rle with old method : 0.06308531761169434 length of segment : 251 time for calcul the mask position with numpy : 0.0010173320770263672 nb_pixel_total : 45695 time to create 1 rle with old method : 0.05518651008605957 length of segment : 294 time for calcul the mask position with numpy : 0.0040891170501708984 nb_pixel_total : 189440 time to create 1 rle with new method : 0.009445905685424805 length of segment : 541 time for calcul the mask position with numpy : 0.0014522075653076172 nb_pixel_total : 41833 time to create 1 rle with old method : 0.05193281173706055 length of segment : 312 time for calcul the mask position with numpy : 0.001264810562133789 nb_pixel_total : 48035 time to create 1 rle with old method : 0.05787396430969238 length of segment : 251 time for calcul the mask position with numpy : 0.0008366107940673828 nb_pixel_total : 25935 time to create 1 rle with old method : 0.031891822814941406 length of segment : 232 time for calcul the mask position with numpy : 0.0008234977722167969 nb_pixel_total : 34885 time to create 1 rle with old method : 0.044068098068237305 length of segment : 239 time for calcul the mask position with numpy : 0.0018215179443359375 nb_pixel_total : 90265 time to create 1 rle with old method : 0.10864424705505371 length of segment : 256 time for calcul the mask position with numpy : 0.0031070709228515625 nb_pixel_total : 176130 time to create 1 rle with new method : 0.007570028305053711 length of segment : 385 time for calcul the mask position with numpy : 0.011957168579101562 nb_pixel_total : 485844 time to create 1 rle with new method : 0.25611186027526855 length of segment : 1019 time for calcul the mask position with numpy : 0.008481979370117188 nb_pixel_total : 415570 time to create 1 rle with new method : 0.01917243003845215 length of segment : 494 time for calcul the mask position with numpy : 0.0025153160095214844 nb_pixel_total : 150185 time to create 1 rle with new method : 0.006763935089111328 length of segment : 489 time for calcul the mask position with numpy : 0.0068264007568359375 nb_pixel_total : 268352 time to create 1 rle with new method : 0.01909923553466797 length of segment : 863 time for calcul the mask position with numpy : 0.009280920028686523 nb_pixel_total : 342085 time to create 1 rle with new method : 0.02222919464111328 length of segment : 872 time for calcul the mask position with numpy : 0.0009343624114990234 nb_pixel_total : 38196 time to create 1 rle with old method : 0.044745683670043945 length of segment : 233 time for calcul the mask position with numpy : 0.008733749389648438 nb_pixel_total : 472531 time to create 1 rle with new method : 0.022938013076782227 length of segment : 1104 time for calcul the mask position with numpy : 0.0006756782531738281 nb_pixel_total : 32176 time to create 1 rle with old method : 0.038847923278808594 length of segment : 225 time for calcul the mask position with numpy : 0.0007092952728271484 nb_pixel_total : 37557 time to create 1 rle with old method : 0.04628634452819824 length of segment : 251 time for calcul the mask position with numpy : 0.0047647953033447266 nb_pixel_total : 276591 time to create 1 rle with new method : 0.012663841247558594 length of segment : 767 time for calcul the mask position with numpy : 0.0032646656036376953 nb_pixel_total : 223978 time to create 1 rle with new method : 0.008637189865112305 length of segment : 590 time for calcul the mask position with numpy : 0.0003070831298828125 nb_pixel_total : 8350 time to create 1 rle with old method : 0.02866649627685547 length of segment : 118 time for calcul the mask position with numpy : 0.002099752426147461 nb_pixel_total : 128890 time to create 1 rle with old method : 0.15473413467407227 length of segment : 432 time for calcul the mask position with numpy : 0.008555412292480469 nb_pixel_total : 397279 time to create 1 rle with new method : 0.021204233169555664 length of segment : 1015 time for calcul the mask position with numpy : 0.0011684894561767578 nb_pixel_total : 67432 time to create 1 rle with old method : 0.07801222801208496 length of segment : 343 time for calcul the mask position with numpy : 0.00030994415283203125 nb_pixel_total : 2178 time to create 1 rle with old method : 0.002911090850830078 length of segment : 62 time for calcul the mask position with numpy : 0.0003097057342529297 nb_pixel_total : 8898 time to create 1 rle with old method : 0.010784387588500977 length of segment : 101 time for calcul the mask position with numpy : 0.002730131149291992 nb_pixel_total : 143821 time to create 1 rle with old method : 0.16418933868408203 length of segment : 636 time for calcul the mask position with numpy : 0.001374959945678711 nb_pixel_total : 74538 time to create 1 rle with old method : 0.10192704200744629 length of segment : 347 time for calcul the mask position with numpy : 0.0027344226837158203 nb_pixel_total : 122069 time to create 1 rle with old method : 0.1450331211090088 length of segment : 621 time for calcul the mask position with numpy : 0.0034635066986083984 nb_pixel_total : 172701 time to create 1 rle with new method : 0.010586023330688477 length of segment : 624 time for calcul the mask position with numpy : 0.000644683837890625 nb_pixel_total : 25921 time to create 1 rle with old method : 0.03359866142272949 length of segment : 162 time for calcul the mask position with numpy : 0.0009050369262695312 nb_pixel_total : 19708 time to create 1 rle with old method : 0.0238037109375 length of segment : 223 time for calcul the mask position with numpy : 0.0011639595031738281 nb_pixel_total : 56402 time to create 1 rle with old method : 0.06820154190063477 length of segment : 229 time for calcul the mask position with numpy : 0.01056361198425293 nb_pixel_total : 409128 time to create 1 rle with new method : 0.028105735778808594 length of segment : 1592 time for calcul the mask position with numpy : 0.0010745525360107422 nb_pixel_total : 34774 time to create 1 rle with old method : 0.041646480560302734 length of segment : 334 time for calcul the mask position with numpy : 0.0009286403656005859 nb_pixel_total : 25451 time to create 1 rle with old method : 0.030880212783813477 length of segment : 236 time for calcul the mask position with numpy : 0.0013391971588134766 nb_pixel_total : 64158 time to create 1 rle with old method : 0.07295083999633789 length of segment : 327 time for calcul the mask position with numpy : 0.0020546913146972656 nb_pixel_total : 73270 time to create 1 rle with old method : 0.08706903457641602 length of segment : 459 time for calcul the mask position with numpy : 0.009391546249389648 nb_pixel_total : 226634 time to create 1 rle with new method : 0.015932798385620117 length of segment : 859 time for calcul the mask position with numpy : 0.0005731582641601562 nb_pixel_total : 22340 time to create 1 rle with old method : 0.027433156967163086 length of segment : 178 time for calcul the mask position with numpy : 0.002042531967163086 nb_pixel_total : 89033 time to create 1 rle with old method : 0.10602855682373047 length of segment : 464 time for calcul the mask position with numpy : 0.00043272972106933594 nb_pixel_total : 15012 time to create 1 rle with old method : 0.01847076416015625 length of segment : 156 time for calcul the mask position with numpy : 0.0035164356231689453 nb_pixel_total : 173968 time to create 1 rle with new method : 0.030257225036621094 length of segment : 480 time for calcul the mask position with numpy : 0.001825571060180664 nb_pixel_total : 52479 time to create 1 rle with old method : 0.0636591911315918 length of segment : 277 time for calcul the mask position with numpy : 0.006077766418457031 nb_pixel_total : 304064 time to create 1 rle with new method : 0.011853456497192383 length of segment : 694 time for calcul the mask position with numpy : 0.0004761219024658203 nb_pixel_total : 28733 time to create 1 rle with old method : 0.03388524055480957 length of segment : 210 time for calcul the mask position with numpy : 0.0008187294006347656 nb_pixel_total : 43080 time to create 1 rle with old method : 0.05084490776062012 length of segment : 214 time for calcul the mask position with numpy : 0.010968923568725586 nb_pixel_total : 575031 time to create 1 rle with new method : 0.029072999954223633 length of segment : 1568 time for calcul the mask position with numpy : 0.0008187294006347656 nb_pixel_total : 34769 time to create 1 rle with old method : 0.05804920196533203 length of segment : 273 time for calcul the mask position with numpy : 0.0012891292572021484 nb_pixel_total : 51991 time to create 1 rle with old method : 0.06039738655090332 length of segment : 215 time for calcul the mask position with numpy : 0.005725383758544922 nb_pixel_total : 255015 time to create 1 rle with new method : 0.014237403869628906 length of segment : 774 time for calcul the mask position with numpy : 0.0007348060607910156 nb_pixel_total : 25868 time to create 1 rle with old method : 0.031203269958496094 length of segment : 142 time for calcul the mask position with numpy : 0.003296375274658203 nb_pixel_total : 128056 time to create 1 rle with old method : 0.14844989776611328 length of segment : 566 time for calcul the mask position with numpy : 0.002586841583251953 nb_pixel_total : 96110 time to create 1 rle with old method : 0.11243271827697754 length of segment : 448 time for calcul the mask position with numpy : 0.0017943382263183594 nb_pixel_total : 66190 time to create 1 rle with old method : 0.07702493667602539 length of segment : 404 time for calcul the mask position with numpy : 0.001009225845336914 nb_pixel_total : 28299 time to create 1 rle with old method : 0.034183502197265625 length of segment : 144 time for calcul the mask position with numpy : 0.0009169578552246094 nb_pixel_total : 41904 time to create 1 rle with old method : 0.048766374588012695 length of segment : 150 time for calcul the mask position with numpy : 0.0023391246795654297 nb_pixel_total : 114238 time to create 1 rle with old method : 0.1581573486328125 length of segment : 440 time for calcul the mask position with numpy : 0.010751008987426758 nb_pixel_total : 425807 time to create 1 rle with new method : 0.02830362319946289 length of segment : 866 time for calcul the mask position with numpy : 0.013397693634033203 nb_pixel_total : 392711 time to create 1 rle with new method : 0.02763056755065918 length of segment : 736 time for calcul the mask position with numpy : 0.004688739776611328 nb_pixel_total : 251423 time to create 1 rle with new method : 0.012934684753417969 length of segment : 909 time for calcul the mask position with numpy : 0.00014257431030273438 nb_pixel_total : 3197 time to create 1 rle with old method : 0.0039463043212890625 length of segment : 82 time for calcul the mask position with numpy : 0.0008678436279296875 nb_pixel_total : 25797 time to create 1 rle with old method : 0.030277252197265625 length of segment : 237 time for calcul the mask position with numpy : 0.005875825881958008 nb_pixel_total : 252047 time to create 1 rle with new method : 0.017861604690551758 length of segment : 641 time for calcul the mask position with numpy : 0.001352548599243164 nb_pixel_total : 76069 time to create 1 rle with old method : 0.08746790885925293 length of segment : 242 time for calcul the mask position with numpy : 0.0034568309783935547 nb_pixel_total : 147655 time to create 1 rle with old method : 0.17357468605041504 length of segment : 462 time for calcul the mask position with numpy : 0.0008261203765869141 nb_pixel_total : 26499 time to create 1 rle with old method : 0.03163862228393555 length of segment : 303 time for calcul the mask position with numpy : 0.0018312931060791016 nb_pixel_total : 59226 time to create 1 rle with old method : 0.0911104679107666 length of segment : 445 time for calcul the mask position with numpy : 0.0011377334594726562 nb_pixel_total : 35556 time to create 1 rle with old method : 0.04308938980102539 length of segment : 241 time for calcul the mask position with numpy : 0.0003325939178466797 nb_pixel_total : 2696 time to create 1 rle with old method : 0.0033855438232421875 length of segment : 93 time for calcul the mask position with numpy : 0.0026731491088867188 nb_pixel_total : 87188 time to create 1 rle with old method : 0.10477781295776367 length of segment : 415 time for calcul the mask position with numpy : 0.00040841102600097656 nb_pixel_total : 14667 time to create 1 rle with old method : 0.0175018310546875 length of segment : 215 time for calcul the mask position with numpy : 0.0015254020690917969 nb_pixel_total : 72335 time to create 1 rle with old method : 0.08792853355407715 length of segment : 174 time for calcul the mask position with numpy : 0.0015676021575927734 nb_pixel_total : 55661 time to create 1 rle with old method : 0.06604695320129395 length of segment : 254 time for calcul the mask position with numpy : 0.011332988739013672 nb_pixel_total : 296349 time to create 1 rle with new method : 0.044577836990356445 length of segment : 672 time for calcul the mask position with numpy : 0.001802682876586914 nb_pixel_total : 83841 time to create 1 rle with old method : 0.09866571426391602 length of segment : 441 time for calcul the mask position with numpy : 0.013777971267700195 nb_pixel_total : 658275 time to create 1 rle with new method : 0.031612396240234375 length of segment : 1245 time for calcul the mask position with numpy : 0.0005476474761962891 nb_pixel_total : 22746 time to create 1 rle with old method : 0.027188777923583984 length of segment : 149 time for calcul the mask position with numpy : 0.009307622909545898 nb_pixel_total : 332353 time to create 1 rle with new method : 0.032198429107666016 length of segment : 696 time for calcul the mask position with numpy : 0.001383066177368164 nb_pixel_total : 46329 time to create 1 rle with old method : 0.05988311767578125 length of segment : 240 time for calcul the mask position with numpy : 0.0015745162963867188 nb_pixel_total : 83300 time to create 1 rle with old method : 0.09865641593933105 length of segment : 349 time for calcul the mask position with numpy : 0.0004813671112060547 nb_pixel_total : 18776 time to create 1 rle with old method : 0.022819042205810547 length of segment : 202 time for calcul the mask position with numpy : 0.0004317760467529297 nb_pixel_total : 9262 time to create 1 rle with old method : 0.011516571044921875 length of segment : 121 time for calcul the mask position with numpy : 0.00635838508605957 nb_pixel_total : 351147 time to create 1 rle with new method : 0.016273021697998047 length of segment : 498 time for calcul the mask position with numpy : 0.00561833381652832 nb_pixel_total : 343577 time to create 1 rle with new method : 0.014630317687988281 length of segment : 496 time for calcul the mask position with numpy : 0.0012259483337402344 nb_pixel_total : 39484 time to create 1 rle with old method : 0.04611468315124512 length of segment : 166 time for calcul the mask position with numpy : 0.004702091217041016 nb_pixel_total : 255100 time to create 1 rle with new method : 0.012922048568725586 length of segment : 752 time for calcul the mask position with numpy : 0.0017955303192138672 nb_pixel_total : 48057 time to create 1 rle with old method : 0.06734132766723633 length of segment : 418 time for calcul the mask position with numpy : 0.0028765201568603516 nb_pixel_total : 147528 time to create 1 rle with old method : 0.20612549781799316 length of segment : 464 time for calcul the mask position with numpy : 0.002015829086303711 nb_pixel_total : 111653 time to create 1 rle with old method : 0.1330564022064209 length of segment : 329 time for calcul the mask position with numpy : 0.0007498264312744141 nb_pixel_total : 34294 time to create 1 rle with old method : 0.0403141975402832 length of segment : 182 time for calcul the mask position with numpy : 0.0038900375366210938 nb_pixel_total : 172015 time to create 1 rle with new method : 0.01165461540222168 length of segment : 673 time for calcul the mask position with numpy : 0.001649618148803711 nb_pixel_total : 69526 time to create 1 rle with old method : 0.08336305618286133 length of segment : 235 time for calcul the mask position with numpy : 0.0010876655578613281 nb_pixel_total : 35524 time to create 1 rle with old method : 0.042412757873535156 length of segment : 355 time for calcul the mask position with numpy : 0.01214599609375 nb_pixel_total : 287300 time to create 1 rle with new method : 0.040416717529296875 length of segment : 862 time for calcul the mask position with numpy : 0.0007979869842529297 nb_pixel_total : 34711 time to create 1 rle with old method : 0.04166555404663086 length of segment : 144 time for calcul the mask position with numpy : 0.0007276535034179688 nb_pixel_total : 14874 time to create 1 rle with old method : 0.01837158203125 length of segment : 128 time for calcul the mask position with numpy : 0.0030345916748046875 nb_pixel_total : 102159 time to create 1 rle with old method : 0.12157034873962402 length of segment : 647 time for calcul the mask position with numpy : 0.001422882080078125 nb_pixel_total : 47990 time to create 1 rle with old method : 0.06150317192077637 length of segment : 260 time for calcul the mask position with numpy : 0.0006055831909179688 nb_pixel_total : 6559 time to create 1 rle with old method : 0.00802302360534668 length of segment : 172 time for calcul the mask position with numpy : 0.0022127628326416016 nb_pixel_total : 98925 time to create 1 rle with old method : 0.11727261543273926 length of segment : 336 time for calcul the mask position with numpy : 0.0005352497100830078 nb_pixel_total : 10977 time to create 1 rle with old method : 0.014126062393188477 length of segment : 128 time for calcul the mask position with numpy : 0.006602048873901367 nb_pixel_total : 302935 time to create 1 rle with new method : 0.020213603973388672 length of segment : 697 time for calcul the mask position with numpy : 0.0013477802276611328 nb_pixel_total : 53173 time to create 1 rle with old method : 0.06306099891662598 length of segment : 332 time for calcul the mask position with numpy : 0.002129793167114258 nb_pixel_total : 95323 time to create 1 rle with old method : 0.13564491271972656 length of segment : 254 time for calcul the mask position with numpy : 0.0031175613403320312 nb_pixel_total : 146131 time to create 1 rle with old method : 0.18231916427612305 length of segment : 435 time for calcul the mask position with numpy : 0.00565648078918457 nb_pixel_total : 154883 time to create 1 rle with new method : 0.008226394653320312 length of segment : 465 time for calcul the mask position with numpy : 0.003696441650390625 nb_pixel_total : 153378 time to create 1 rle with new method : 0.010010004043579102 length of segment : 667 time for calcul the mask position with numpy : 0.0031652450561523438 nb_pixel_total : 115664 time to create 1 rle with old method : 0.1356494426727295 length of segment : 537 time for calcul the mask position with numpy : 0.0014123916625976562 nb_pixel_total : 55420 time to create 1 rle with old method : 0.06547021865844727 length of segment : 178 time for calcul the mask position with numpy : 0.0006394386291503906 nb_pixel_total : 30635 time to create 1 rle with old method : 0.03659391403198242 length of segment : 201 time for calcul the mask position with numpy : 0.0007131099700927734 nb_pixel_total : 30739 time to create 1 rle with old method : 0.037103891372680664 length of segment : 200 time for calcul the mask position with numpy : 0.0005488395690917969 nb_pixel_total : 20673 time to create 1 rle with old method : 0.024832963943481445 length of segment : 191 time for calcul the mask position with numpy : 0.3327677249908447 nb_pixel_total : 7401675 time to create 1 rle with new method : 0.800849199295044 length of segment : 3870 time for calcul the mask position with numpy : 0.01876044273376465 nb_pixel_total : 1284540 time to create 1 rle with new method : 0.062380075454711914 length of segment : 530 time for calcul the mask position with numpy : 0.0072820186614990234 nb_pixel_total : 597429 time to create 1 rle with new method : 0.025343894958496094 length of segment : 344 time spent for convertir_results : 73.21087384223938 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 547 chid ids of type : 4854 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 173.36407113075256 time spend to save output : 0.26071786880493164 total time spend for step 2 : 173.6247889995575 step3:blur_detection Mon Sep 1 16:25:49 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: variance laplacian (3120, 3120) 683.6998660822908 (3120, 3120) 612.4246895947853 (3120, 3120) 705.7067960964039 (3120, 3120) 629.02646457505 (3120, 3120) 561.9831727432334 (3120, 3120) 525.5687653335234 (3120, 3120) 212.01557136614971 (3120, 3120) 894.2250352664202 (3120, 3120) 403.5308152980444 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 9 time used for this insertion : 0.01311492919921875 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 9 time used for this insertion : 0.015771865844726562 save missing photos in datou_result : time spend for datou_step_exec : 5.3957061767578125 time spend to save output : 0.033421993255615234 total time spend for step 3 : 5.429128170013428 step4:brightness Mon Sep 1 16:25:54 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1756736489_28447_1379878546_3630c742d3a2d30d9aaa4b0dd2d486d7.jpg treat image : temp/1756736489_28447_1379878482_618f134b7e714fc2dc4f8fe681f59aa2.jpg treat image : temp/1756736489_28447_1379878419_36e6217d8dc5ab1ec5855832e75a9d0f.jpg treat image : temp/1756736489_28447_1379878127_4c6a393ae070a2e1c1da3ea00643865e.jpg treat image : temp/1756736489_28447_1379878098_41b3ccb3384b0bb305abf4b9c691fdfb.jpg treat image : temp/1756736489_28447_1379878055_96bc9409b1e6baa94db51426213f1deb.jpg treat image : temp/1756736489_28447_1379878000_aa9fc1fa138f1b30501cb7fc5bf38e4f.jpg treat image : temp/1756736489_28447_1379877966_ba9a6df9ba5627642054f1fd5cfe6143.jpg treat image : temp/1756736489_28447_1379877912_e5ddf7f4ea7ac5375fc10a9e7789a2eb.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 9 time used for this insertion : 0.014258146286010742 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 9 time used for this insertion : 0.012964725494384766 save missing photos in datou_result : time spend for datou_step_exec : 12.323111534118652 time spend to save output : 0.03242039680480957 total time spend for step 4 : 12.355531930923462 step5:rle_unique_nms_with_priority Mon Sep 1 16:26:07 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 547 chid ids of type : 4854 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 70 nb_hashtags : 9 time to prepare the origin masks : 43.08068132400513 time for calcul the mask position with numpy : 0.21364259719848633 nb_pixel_total : 2123622 time to create 1 rle with new method : 1.3658947944641113 time for calcul the mask position with numpy : 0.03971409797668457 nb_pixel_total : 165495 time to create 1 rle with new method : 1.2817387580871582 time for calcul the mask position with numpy : 0.038086652755737305 nb_pixel_total : 26560 time to create 1 rle with old method : 0.02886652946472168 time for calcul the mask position with numpy : 0.0387265682220459 nb_pixel_total : 165347 time to create 1 rle with new method : 0.6999568939208984 time for calcul the mask position with numpy : 0.037283897399902344 nb_pixel_total : 28098 time to create 1 rle with old method : 0.03211832046508789 time for calcul the mask position with numpy : 0.04250955581665039 nb_pixel_total : 493705 time to create 1 rle with new method : 0.983849287033081 time for calcul the mask position with numpy : 0.03798699378967285 nb_pixel_total : 23630 time to create 1 rle with old method : 0.02594733238220215 time for calcul the mask position with numpy : 0.03912782669067383 nb_pixel_total : 267583 time to create 1 rle with new method : 0.8486199378967285 time for calcul the mask position with numpy : 0.042098283767700195 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0014226436614990234 time for calcul the mask position with numpy : 0.05014491081237793 nb_pixel_total : 75032 time to create 1 rle with old method : 0.08499813079833984 time for calcul the mask position with numpy : 0.03898215293884277 nb_pixel_total : 8851 time to create 1 rle with old method : 0.010236978530883789 time for calcul the mask position with numpy : 0.038430213928222656 nb_pixel_total : 20206 time to create 1 rle with old method : 0.022579193115234375 time for calcul the mask position with numpy : 0.039032697677612305 nb_pixel_total : 35231 time to create 1 rle with old method : 0.03956246376037598 time for calcul the mask position with numpy : 0.03894305229187012 nb_pixel_total : 41073 time to create 1 rle with old method : 0.04640007019042969 time for calcul the mask position with numpy : 0.03812003135681152 nb_pixel_total : 6597 time to create 1 rle with old method : 0.007482290267944336 time for calcul the mask position with numpy : 0.03869342803955078 nb_pixel_total : 121841 time to create 1 rle with old method : 0.13596892356872559 time for calcul the mask position with numpy : 0.04015922546386719 nb_pixel_total : 7105 time to create 1 rle with old method : 0.008362054824829102 time for calcul the mask position with numpy : 0.038857460021972656 nb_pixel_total : 35585 time to create 1 rle with old method : 0.039900779724121094 time for calcul the mask position with numpy : 0.03995394706726074 nb_pixel_total : 198367 time to create 1 rle with new method : 1.2397875785827637 time for calcul the mask position with numpy : 0.03806447982788086 nb_pixel_total : 17678 time to create 1 rle with old method : 0.01955103874206543 time for calcul the mask position with numpy : 0.03824567794799805 nb_pixel_total : 27978 time to create 1 rle with old method : 0.030635595321655273 time for calcul the mask position with numpy : 0.0412600040435791 nb_pixel_total : 473235 time to create 1 rle with new method : 0.9818971157073975 time for calcul the mask position with numpy : 0.041443586349487305 nb_pixel_total : 496362 time to create 1 rle with new method : 1.0154871940612793 time for calcul the mask position with numpy : 0.03756141662597656 nb_pixel_total : 3803 time to create 1 rle with old method : 0.004508256912231445 time for calcul the mask position with numpy : 0.03758645057678223 nb_pixel_total : 75518 time to create 1 rle with old method : 0.0808253288269043 time for calcul the mask position with numpy : 0.04822206497192383 nb_pixel_total : 41683 time to create 1 rle with old method : 0.07540297508239746 time for calcul the mask position with numpy : 0.0455629825592041 nb_pixel_total : 877 time to create 1 rle with old method : 0.0011947154998779297 time for calcul the mask position with numpy : 0.04037308692932129 nb_pixel_total : 72156 time to create 1 rle with old method : 0.08216357231140137 time for calcul the mask position with numpy : 0.03951454162597656 nb_pixel_total : 153759 time to create 1 rle with new method : 1.190199613571167 time for calcul the mask position with numpy : 0.03797578811645508 nb_pixel_total : 1726 time to create 1 rle with old method : 0.001983165740966797 time for calcul the mask position with numpy : 0.03842902183532715 nb_pixel_total : 46786 time to create 1 rle with old method : 0.05084943771362305 time for calcul the mask position with numpy : 0.037741899490356445 nb_pixel_total : 17474 time to create 1 rle with old method : 0.018892288208007812 time for calcul the mask position with numpy : 0.04057717323303223 nb_pixel_total : 283219 time to create 1 rle with new method : 1.099217176437378 time for calcul the mask position with numpy : 0.038251399993896484 nb_pixel_total : 9499 time to create 1 rle with old method : 0.010536670684814453 time for calcul the mask position with numpy : 0.03740501403808594 nb_pixel_total : 2507 time to create 1 rle with old method : 0.002813100814819336 time for calcul the mask position with numpy : 0.03763127326965332 nb_pixel_total : 5169 time to create 1 rle with old method : 0.006292581558227539 time for calcul the mask position with numpy : 0.038958072662353516 nb_pixel_total : 75998 time to create 1 rle with old method : 0.08333897590637207 time for calcul the mask position with numpy : 0.03813004493713379 nb_pixel_total : 93589 time to create 1 rle with old method : 0.10304093360900879 time for calcul the mask position with numpy : 0.037767887115478516 nb_pixel_total : 7414 time to create 1 rle with old method : 0.00868678092956543 time for calcul the mask position with numpy : 0.038535356521606445 nb_pixel_total : 65297 time to create 1 rle with old method : 0.07079172134399414 time for calcul the mask position with numpy : 0.04230499267578125 nb_pixel_total : 487113 time to create 1 rle with new method : 0.898566722869873 time for calcul the mask position with numpy : 0.03961062431335449 nb_pixel_total : 42038 time to create 1 rle with old method : 0.04948139190673828 time for calcul the mask position with numpy : 0.03984880447387695 nb_pixel_total : 89205 time to create 1 rle with old method : 0.09946990013122559 time for calcul the mask position with numpy : 0.03932023048400879 nb_pixel_total : 52479 time to create 1 rle with old method : 0.05972433090209961 time for calcul the mask position with numpy : 0.03781771659851074 nb_pixel_total : 8847 time to create 1 rle with old method : 0.009747743606567383 time for calcul the mask position with numpy : 0.0383148193359375 nb_pixel_total : 22266 time to create 1 rle with old method : 0.025387048721313477 time for calcul the mask position with numpy : 0.03786778450012207 nb_pixel_total : 20467 time to create 1 rle with old method : 0.022713422775268555 time for calcul the mask position with numpy : 0.04091501235961914 nb_pixel_total : 413351 time to create 1 rle with new method : 0.9297003746032715 time for calcul the mask position with numpy : 0.03809499740600586 nb_pixel_total : 11122 time to create 1 rle with old method : 0.01227116584777832 time for calcul the mask position with numpy : 0.03802776336669922 nb_pixel_total : 41275 time to create 1 rle with old method : 0.04580569267272949 time for calcul the mask position with numpy : 0.043489933013916016 nb_pixel_total : 579656 time to create 1 rle with new method : 1.0841865539550781 time for calcul the mask position with numpy : 0.03986620903015137 nb_pixel_total : 131194 time to create 1 rle with old method : 0.1426546573638916 time for calcul the mask position with numpy : 0.03766942024230957 nb_pixel_total : 28057 time to create 1 rle with old method : 0.030672788619995117 time for calcul the mask position with numpy : 0.03788924217224121 nb_pixel_total : 9575 time to create 1 rle with old method : 0.010529279708862305 time for calcul the mask position with numpy : 0.03779435157775879 nb_pixel_total : 13692 time to create 1 rle with old method : 0.015134096145629883 time for calcul the mask position with numpy : 0.03757190704345703 nb_pixel_total : 55554 time to create 1 rle with old method : 0.06053662300109863 time for calcul the mask position with numpy : 0.041422367095947266 nb_pixel_total : 440405 time to create 1 rle with new method : 0.8625836372375488 time for calcul the mask position with numpy : 0.039478302001953125 nb_pixel_total : 282197 time to create 1 rle with new method : 1.223137617111206 time for calcul the mask position with numpy : 0.038299560546875 nb_pixel_total : 139872 time to create 1 rle with old method : 0.1555039882659912 time for calcul the mask position with numpy : 0.0478365421295166 nb_pixel_total : 846607 time to create 1 rle with new method : 0.763120174407959 time for calcul the mask position with numpy : 0.03769540786743164 nb_pixel_total : 7456 time to create 1 rle with old method : 0.008171796798706055 time for calcul the mask position with numpy : 0.03797173500061035 nb_pixel_total : 739 time to create 1 rle with old method : 0.0009016990661621094 time for calcul the mask position with numpy : 0.03763842582702637 nb_pixel_total : 2 time to create 1 rle with old method : 4.3392181396484375e-05 time for calcul the mask position with numpy : 0.03764653205871582 nb_pixel_total : 5305 time to create 1 rle with old method : 0.0059316158294677734 time for calcul the mask position with numpy : 0.037682533264160156 nb_pixel_total : 24018 time to create 1 rle with old method : 0.02627086639404297 time for calcul the mask position with numpy : 0.03841543197631836 nb_pixel_total : 79115 time to create 1 rle with old method : 0.08709144592285156 time for calcul the mask position with numpy : 0.03794121742248535 nb_pixel_total : 32717 time to create 1 rle with old method : 0.03576922416687012 time for calcul the mask position with numpy : 0.03765368461608887 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.03755807876586914 nb_pixel_total : 9394 time to create 1 rle with old method : 0.010312557220458984 time for calcul the mask position with numpy : 0.03795957565307617 nb_pixel_total : 21203 time to create 1 rle with old method : 0.023671627044677734 time for calcul the mask position with numpy : 0.03777027130126953 nb_pixel_total : 22642 time to create 1 rle with old method : 0.02474212646484375 create new chi : 22.13515543937683 time to delete rle : 0.01692032814025879 batch 1 Loaded 71 chid ids of type : 4855 Number RLEs to save : 55724 TO DO : save crop sub photo not yet done ! save time : 2.9117870330810547 nb_obj : 60 nb_hashtags : 10 time to prepare the origin masks : 33.66368246078491 time for calcul the mask position with numpy : 0.06182742118835449 nb_pixel_total : 2459305 time to create 1 rle with new method : 1.024791955947876 time for calcul the mask position with numpy : 0.03982877731323242 nb_pixel_total : 73144 time to create 1 rle with old method : 0.08356904983520508 time for calcul the mask position with numpy : 0.03874349594116211 nb_pixel_total : 47697 time to create 1 rle with old method : 0.05393171310424805 time for calcul the mask position with numpy : 0.03883957862854004 nb_pixel_total : 44869 time to create 1 rle with old method : 0.05098581314086914 time for calcul the mask position with numpy : 0.041146039962768555 nb_pixel_total : 463032 time to create 1 rle with new method : 1.0061554908752441 time for calcul the mask position with numpy : 0.039307594299316406 nb_pixel_total : 261556 time to create 1 rle with new method : 0.9307479858398438 time for calcul the mask position with numpy : 0.03858518600463867 nb_pixel_total : 990 time to create 1 rle with old method : 0.0014657974243164062 time for calcul the mask position with numpy : 0.03899669647216797 nb_pixel_total : 73601 time to create 1 rle with old method : 0.08103418350219727 time for calcul the mask position with numpy : 0.045522451400756836 nb_pixel_total : 1832181 time to create 1 rle with new method : 0.8875448703765869 time for calcul the mask position with numpy : 0.03805804252624512 nb_pixel_total : 49978 time to create 1 rle with old method : 0.05576944351196289 time for calcul the mask position with numpy : 0.037806034088134766 nb_pixel_total : 8329 time to create 1 rle with old method : 0.009083271026611328 time for calcul the mask position with numpy : 0.03816413879394531 nb_pixel_total : 55844 time to create 1 rle with old method : 0.06258630752563477 time for calcul the mask position with numpy : 0.039340972900390625 nb_pixel_total : 53335 time to create 1 rle with old method : 0.05987238883972168 time for calcul the mask position with numpy : 0.038654327392578125 nb_pixel_total : 21676 time to create 1 rle with old method : 0.024010896682739258 time for calcul the mask position with numpy : 0.03884005546569824 nb_pixel_total : 2680 time to create 1 rle with old method : 0.0034286975860595703 time for calcul the mask position with numpy : 0.03903818130493164 nb_pixel_total : 87683 time to create 1 rle with old method : 0.09875369071960449 time for calcul the mask position with numpy : 0.03927493095397949 nb_pixel_total : 26115 time to create 1 rle with old method : 0.030143260955810547 time for calcul the mask position with numpy : 0.03964543342590332 nb_pixel_total : 104508 time to create 1 rle with old method : 0.11787724494934082 time for calcul the mask position with numpy : 0.04480099678039551 nb_pixel_total : 819410 time to create 1 rle with new method : 1.0689315795898438 time for calcul the mask position with numpy : 0.03995490074157715 nb_pixel_total : 32045 time to create 1 rle with old method : 0.036087989807128906 time for calcul the mask position with numpy : 0.039450883865356445 nb_pixel_total : 1120 time to create 1 rle with old method : 0.0014431476593017578 time for calcul the mask position with numpy : 0.04006385803222656 nb_pixel_total : 48824 time to create 1 rle with old method : 0.0566868782043457 time for calcul the mask position with numpy : 0.04083752632141113 nb_pixel_total : 128366 time to create 1 rle with old method : 0.14484882354736328 time for calcul the mask position with numpy : 0.03829383850097656 nb_pixel_total : 30696 time to create 1 rle with old method : 0.033478736877441406 time for calcul the mask position with numpy : 0.03740215301513672 nb_pixel_total : 62707 time to create 1 rle with old method : 0.06985950469970703 time for calcul the mask position with numpy : 0.03900599479675293 nb_pixel_total : 22762 time to create 1 rle with old method : 0.02609395980834961 time for calcul the mask position with numpy : 0.03775906562805176 nb_pixel_total : 54151 time to create 1 rle with old method : 0.05985093116760254 time for calcul the mask position with numpy : 0.03939628601074219 nb_pixel_total : 155817 time to create 1 rle with new method : 0.7537460327148438 time for calcul the mask position with numpy : 0.03864884376525879 nb_pixel_total : 583 time to create 1 rle with old method : 0.0007481575012207031 time for calcul the mask position with numpy : 0.0381929874420166 nb_pixel_total : 3295 time to create 1 rle with old method : 0.003765583038330078 time for calcul the mask position with numpy : 0.03844404220581055 nb_pixel_total : 11717 time to create 1 rle with old method : 0.013210773468017578 time for calcul the mask position with numpy : 0.03879094123840332 nb_pixel_total : 110467 time to create 1 rle with old method : 0.12381982803344727 time for calcul the mask position with numpy : 0.04039502143859863 nb_pixel_total : 412713 time to create 1 rle with new method : 0.759422779083252 time for calcul the mask position with numpy : 0.03919625282287598 nb_pixel_total : 21069 time to create 1 rle with old method : 0.024288415908813477 time for calcul the mask position with numpy : 0.03932833671569824 nb_pixel_total : 61244 time to create 1 rle with old method : 0.07194375991821289 time for calcul the mask position with numpy : 0.0393221378326416 nb_pixel_total : 85604 time to create 1 rle with old method : 0.09731554985046387 time for calcul the mask position with numpy : 0.039429664611816406 nb_pixel_total : 80477 time to create 1 rle with old method : 0.09218406677246094 time for calcul the mask position with numpy : 0.03951287269592285 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005660057067871094 time for calcul the mask position with numpy : 0.041727542877197266 nb_pixel_total : 615617 time to create 1 rle with new method : 1.5122504234313965 time for calcul the mask position with numpy : 0.03974175453186035 nb_pixel_total : 14108 time to create 1 rle with old method : 0.01627516746520996 time for calcul the mask position with numpy : 0.0413510799407959 nb_pixel_total : 319748 time to create 1 rle with new method : 0.8437161445617676 time for calcul the mask position with numpy : 0.0395359992980957 nb_pixel_total : 4246 time to create 1 rle with old method : 0.005141735076904297 time for calcul the mask position with numpy : 0.03989839553833008 nb_pixel_total : 22069 time to create 1 rle with old method : 0.025583744049072266 time for calcul the mask position with numpy : 0.03979301452636719 nb_pixel_total : 14716 time to create 1 rle with old method : 0.01840066909790039 time for calcul the mask position with numpy : 0.039804697036743164 nb_pixel_total : 138677 time to create 1 rle with old method : 0.15857601165771484 time for calcul the mask position with numpy : 0.04042458534240723 nb_pixel_total : 159 time to create 1 rle with old method : 0.00044155120849609375 time for calcul the mask position with numpy : 0.04026436805725098 nb_pixel_total : 99093 time to create 1 rle with old method : 0.11571168899536133 time for calcul the mask position with numpy : 0.039743900299072266 nb_pixel_total : 54538 time to create 1 rle with old method : 0.0626215934753418 time for calcul the mask position with numpy : 0.0403590202331543 nb_pixel_total : 26718 time to create 1 rle with old method : 0.031080007553100586 time for calcul the mask position with numpy : 0.041188716888427734 nb_pixel_total : 241368 time to create 1 rle with new method : 0.7083878517150879 time for calcul the mask position with numpy : 0.03848981857299805 nb_pixel_total : 31766 time to create 1 rle with old method : 0.03560304641723633 time for calcul the mask position with numpy : 0.03971529006958008 nb_pixel_total : 43978 time to create 1 rle with old method : 0.05235791206359863 time for calcul the mask position with numpy : 0.04090690612792969 nb_pixel_total : 115319 time to create 1 rle with old method : 0.13522005081176758 time for calcul the mask position with numpy : 0.04056286811828613 nb_pixel_total : 2656 time to create 1 rle with old method : 0.0037200450897216797 time for calcul the mask position with numpy : 0.04058218002319336 nb_pixel_total : 24212 time to create 1 rle with old method : 0.02843785285949707 time for calcul the mask position with numpy : 0.043189287185668945 nb_pixel_total : 82 time to create 1 rle with old method : 0.00014591217041015625 time for calcul the mask position with numpy : 0.040590524673461914 nb_pixel_total : 38189 time to create 1 rle with old method : 0.04552006721496582 time for calcul the mask position with numpy : 0.042787790298461914 nb_pixel_total : 117 time to create 1 rle with old method : 0.00014662742614746094 time for calcul the mask position with numpy : 0.03995633125305176 nb_pixel_total : 5224 time to create 1 rle with old method : 0.006684064865112305 time for calcul the mask position with numpy : 0.04063844680786133 nb_pixel_total : 83030 time to create 1 rle with old method : 0.09641432762145996 time for calcul the mask position with numpy : 0.04078841209411621 nb_pixel_total : 28822 time to create 1 rle with old method : 0.0337061882019043 create new chi : 14.719030141830444 time to delete rle : 0.0037012100219726562 batch 1 Loaded 61 chid ids of type : 4855 Number RLEs to save : 43101 TO DO : save crop sub photo not yet done ! save time : 2.2938075065612793 nb_obj : 65 nb_hashtags : 10 time to prepare the origin masks : 37.449663400650024 time for calcul the mask position with numpy : 0.5267958641052246 nb_pixel_total : 2102762 time to create 1 rle with new method : 0.7990961074829102 time for calcul the mask position with numpy : 0.03842520713806152 nb_pixel_total : 27763 time to create 1 rle with old method : 0.030765533447265625 time for calcul the mask position with numpy : 0.038506269454956055 nb_pixel_total : 1489 time to create 1 rle with old method : 0.001984119415283203 time for calcul the mask position with numpy : 0.04100847244262695 nb_pixel_total : 343286 time to create 1 rle with new method : 0.7416553497314453 time for calcul the mask position with numpy : 0.04076242446899414 nb_pixel_total : 36027 time to create 1 rle with old method : 0.04265713691711426 time for calcul the mask position with numpy : 0.04006791114807129 nb_pixel_total : 29866 time to create 1 rle with old method : 0.03522229194641113 time for calcul the mask position with numpy : 0.04522848129272461 nb_pixel_total : 50142 time to create 1 rle with old method : 0.05635690689086914 time for calcul the mask position with numpy : 0.03840160369873047 nb_pixel_total : 2641 time to create 1 rle with old method : 0.0032808780670166016 time for calcul the mask position with numpy : 0.038500308990478516 nb_pixel_total : 23 time to create 1 rle with old method : 7.081031799316406e-05 time for calcul the mask position with numpy : 0.040380001068115234 nb_pixel_total : 50563 time to create 1 rle with old method : 0.05932450294494629 time for calcul the mask position with numpy : 0.04121279716491699 nb_pixel_total : 240920 time to create 1 rle with new method : 0.6788012981414795 time for calcul the mask position with numpy : 0.038642168045043945 nb_pixel_total : 71207 time to create 1 rle with old method : 0.07831645011901855 time for calcul the mask position with numpy : 0.03869891166687012 nb_pixel_total : 283094 time to create 1 rle with new method : 0.615666389465332 time for calcul the mask position with numpy : 0.03918933868408203 nb_pixel_total : 119378 time to create 1 rle with old method : 0.1330885887145996 time for calcul the mask position with numpy : 0.038805484771728516 nb_pixel_total : 67149 time to create 1 rle with old method : 0.07492184638977051 time for calcul the mask position with numpy : 0.037902116775512695 nb_pixel_total : 2053 time to create 1 rle with old method : 0.0025794506072998047 time for calcul the mask position with numpy : 0.03821206092834473 nb_pixel_total : 42276 time to create 1 rle with old method : 0.04706072807312012 time for calcul the mask position with numpy : 0.03809475898742676 nb_pixel_total : 293944 time to create 1 rle with new method : 0.5668816566467285 time for calcul the mask position with numpy : 0.038208723068237305 nb_pixel_total : 281201 time to create 1 rle with new method : 0.6713204383850098 time for calcul the mask position with numpy : 0.038179636001586914 nb_pixel_total : 235001 time to create 1 rle with new method : 0.5573389530181885 time for calcul the mask position with numpy : 0.038590431213378906 nb_pixel_total : 1969 time to create 1 rle with old method : 0.0022902488708496094 time for calcul the mask position with numpy : 0.03835296630859375 nb_pixel_total : 19090 time to create 1 rle with old method : 0.02151203155517578 time for calcul the mask position with numpy : 0.038556575775146484 nb_pixel_total : 4276 time to create 1 rle with old method : 0.00485539436340332 time for calcul the mask position with numpy : 0.0471501350402832 nb_pixel_total : 808165 time to create 1 rle with new method : 0.7719311714172363 time for calcul the mask position with numpy : 0.040261268615722656 nb_pixel_total : 314 time to create 1 rle with old method : 0.0008087158203125 time for calcul the mask position with numpy : 0.03852438926696777 nb_pixel_total : 51293 time to create 1 rle with old method : 0.05513596534729004 time for calcul the mask position with numpy : 0.038457632064819336 nb_pixel_total : 4357 time to create 1 rle with old method : 0.004921674728393555 time for calcul the mask position with numpy : 0.03896689414978027 nb_pixel_total : 50329 time to create 1 rle with old method : 0.05453348159790039 time for calcul the mask position with numpy : 0.041960954666137695 nb_pixel_total : 707787 time to create 1 rle with new method : 0.5461976528167725 time for calcul the mask position with numpy : 0.0414423942565918 nb_pixel_total : 499993 time to create 1 rle with new method : 0.6042888164520264 time for calcul the mask position with numpy : 0.03823447227478027 nb_pixel_total : 13533 time to create 1 rle with old method : 0.015508413314819336 time for calcul the mask position with numpy : 0.03888821601867676 nb_pixel_total : 15054 time to create 1 rle with old method : 0.01677870750427246 time for calcul the mask position with numpy : 0.03742408752441406 nb_pixel_total : 94691 time to create 1 rle with old method : 0.10177230834960938 time for calcul the mask position with numpy : 0.03767800331115723 nb_pixel_total : 41596 time to create 1 rle with old method : 0.04576444625854492 time for calcul the mask position with numpy : 0.039427995681762695 nb_pixel_total : 13232 time to create 1 rle with old method : 0.015648603439331055 time for calcul the mask position with numpy : 0.03958940505981445 nb_pixel_total : 74351 time to create 1 rle with old method : 0.08269929885864258 time for calcul the mask position with numpy : 0.03901481628417969 nb_pixel_total : 299906 time to create 1 rle with new method : 0.5982563495635986 time for calcul the mask position with numpy : 0.03843045234680176 nb_pixel_total : 17274 time to create 1 rle with old method : 0.020077943801879883 time for calcul the mask position with numpy : 0.03877854347229004 nb_pixel_total : 78261 time to create 1 rle with old method : 0.08861804008483887 time for calcul the mask position with numpy : 0.038823604583740234 nb_pixel_total : 14841 time to create 1 rle with old method : 0.01669788360595703 time for calcul the mask position with numpy : 0.038581132888793945 nb_pixel_total : 37806 time to create 1 rle with old method : 0.04194784164428711 time for calcul the mask position with numpy : 0.04647564888000488 nb_pixel_total : 567009 time to create 1 rle with new method : 0.6895933151245117 time for calcul the mask position with numpy : 0.03903913497924805 nb_pixel_total : 90103 time to create 1 rle with old method : 0.09947371482849121 time for calcul the mask position with numpy : 0.038614511489868164 nb_pixel_total : 41 time to create 1 rle with old method : 0.0002586841583251953 time for calcul the mask position with numpy : 0.039386749267578125 nb_pixel_total : 113639 time to create 1 rle with old method : 0.12854933738708496 time for calcul the mask position with numpy : 0.038984060287475586 nb_pixel_total : 77514 time to create 1 rle with old method : 0.08916735649108887 time for calcul the mask position with numpy : 0.0390470027923584 nb_pixel_total : 17185 time to create 1 rle with old method : 0.019960403442382812 time for calcul the mask position with numpy : 0.03827524185180664 nb_pixel_total : 22133 time to create 1 rle with old method : 0.025353193283081055 time for calcul the mask position with numpy : 0.04129838943481445 nb_pixel_total : 632458 time to create 1 rle with new method : 0.775684118270874 time for calcul the mask position with numpy : 0.04041147232055664 nb_pixel_total : 127889 time to create 1 rle with old method : 0.14104747772216797 time for calcul the mask position with numpy : 0.03845405578613281 nb_pixel_total : 10403 time to create 1 rle with old method : 0.01233363151550293 time for calcul the mask position with numpy : 0.04004549980163574 nb_pixel_total : 8 time to create 1 rle with old method : 0.00013399124145507812 time for calcul the mask position with numpy : 0.037842512130737305 nb_pixel_total : 104112 time to create 1 rle with old method : 0.1139068603515625 time for calcul the mask position with numpy : 0.03811383247375488 nb_pixel_total : 307961 time to create 1 rle with new method : 0.6385529041290283 time for calcul the mask position with numpy : 0.03763580322265625 nb_pixel_total : 6795 time to create 1 rle with old method : 0.0079345703125 time for calcul the mask position with numpy : 0.03930234909057617 nb_pixel_total : 39528 time to create 1 rle with old method : 0.046175479888916016 time for calcul the mask position with numpy : 0.044440507888793945 nb_pixel_total : 4331 time to create 1 rle with old method : 0.00721287727355957 time for calcul the mask position with numpy : 0.04524087905883789 nb_pixel_total : 175565 time to create 1 rle with new method : 0.7373483180999756 time for calcul the mask position with numpy : 0.03891730308532715 nb_pixel_total : 9388 time to create 1 rle with old method : 0.011348485946655273 time for calcul the mask position with numpy : 0.03917360305786133 nb_pixel_total : 24861 time to create 1 rle with old method : 0.027875185012817383 time for calcul the mask position with numpy : 0.03868722915649414 nb_pixel_total : 172 time to create 1 rle with old method : 0.0003714561462402344 time for calcul the mask position with numpy : 0.038938283920288086 nb_pixel_total : 37287 time to create 1 rle with old method : 0.044029951095581055 time for calcul the mask position with numpy : 0.04058957099914551 nb_pixel_total : 12600 time to create 1 rle with old method : 0.015360355377197266 time for calcul the mask position with numpy : 0.03922247886657715 nb_pixel_total : 210941 time to create 1 rle with new method : 0.7084596157073975 time for calcul the mask position with numpy : 0.04153251647949219 nb_pixel_total : 2 time to create 1 rle with old method : 3.0279159545898438e-05 time for calcul the mask position with numpy : 0.04041123390197754 nb_pixel_total : 13572 time to create 1 rle with old method : 0.015910625457763672 create new chi : 16.261526584625244 time to delete rle : 0.004149675369262695 batch 1 Loaded 66 chid ids of type : 4855 Number RLEs to save : 48010 TO DO : save crop sub photo not yet done ! save time : 2.5481534004211426 nb_obj : 41 nb_hashtags : 7 time to prepare the origin masks : 20.965023279190063 time for calcul the mask position with numpy : 0.3045227527618408 nb_pixel_total : 4165568 time to create 1 rle with new method : 0.9051847457885742 time for calcul the mask position with numpy : 0.04037141799926758 nb_pixel_total : 47987 time to create 1 rle with old method : 0.05626845359802246 time for calcul the mask position with numpy : 0.04030585289001465 nb_pixel_total : 1627 time to create 1 rle with old method : 0.0020308494567871094 time for calcul the mask position with numpy : 0.040201663970947266 nb_pixel_total : 7825 time to create 1 rle with old method : 0.00943756103515625 time for calcul the mask position with numpy : 0.04041767120361328 nb_pixel_total : 51617 time to create 1 rle with old method : 0.06042146682739258 time for calcul the mask position with numpy : 0.04180097579956055 nb_pixel_total : 10521 time to create 1 rle with old method : 0.012344598770141602 time for calcul the mask position with numpy : 0.03935503959655762 nb_pixel_total : 13383 time to create 1 rle with old method : 0.01688838005065918 time for calcul the mask position with numpy : 0.04218435287475586 nb_pixel_total : 41153 time to create 1 rle with old method : 0.04731488227844238 time for calcul the mask position with numpy : 0.03914618492126465 nb_pixel_total : 56595 time to create 1 rle with old method : 0.06435918807983398 time for calcul the mask position with numpy : 0.04490542411804199 nb_pixel_total : 1087108 time to create 1 rle with new method : 0.9541828632354736 time for calcul the mask position with numpy : 0.04273080825805664 nb_pixel_total : 426431 time to create 1 rle with new method : 0.671506404876709 time for calcul the mask position with numpy : 0.03998923301696777 nb_pixel_total : 326946 time to create 1 rle with new method : 0.5627036094665527 time for calcul the mask position with numpy : 0.03924298286437988 nb_pixel_total : 82010 time to create 1 rle with old method : 0.09229803085327148 time for calcul the mask position with numpy : 0.03960919380187988 nb_pixel_total : 7447 time to create 1 rle with old method : 0.008561372756958008 time for calcul the mask position with numpy : 0.039723873138427734 nb_pixel_total : 100168 time to create 1 rle with old method : 0.11383295059204102 time for calcul the mask position with numpy : 0.03972792625427246 nb_pixel_total : 103553 time to create 1 rle with old method : 0.11793637275695801 time for calcul the mask position with numpy : 0.038532257080078125 nb_pixel_total : 13377 time to create 1 rle with old method : 0.015236854553222656 time for calcul the mask position with numpy : 0.03899383544921875 nb_pixel_total : 20981 time to create 1 rle with old method : 0.023325681686401367 time for calcul the mask position with numpy : 0.04015612602233887 nb_pixel_total : 382489 time to create 1 rle with new method : 0.5585994720458984 time for calcul the mask position with numpy : 0.04033827781677246 nb_pixel_total : 12312 time to create 1 rle with old method : 0.014603853225708008 time for calcul the mask position with numpy : 0.0400242805480957 nb_pixel_total : 14322 time to create 1 rle with old method : 0.01674652099609375 time for calcul the mask position with numpy : 0.03914380073547363 nb_pixel_total : 5513 time to create 1 rle with old method : 0.0065784454345703125 time for calcul the mask position with numpy : 0.0398097038269043 nb_pixel_total : 28940 time to create 1 rle with old method : 0.03359651565551758 time for calcul the mask position with numpy : 0.04010319709777832 nb_pixel_total : 6965 time to create 1 rle with old method : 0.008350849151611328 time for calcul the mask position with numpy : 0.04035043716430664 nb_pixel_total : 77925 time to create 1 rle with old method : 0.09057807922363281 time for calcul the mask position with numpy : 0.040474891662597656 nb_pixel_total : 255175 time to create 1 rle with new method : 0.6315226554870605 time for calcul the mask position with numpy : 0.051271915435791016 nb_pixel_total : 1447134 time to create 1 rle with new method : 0.6373159885406494 time for calcul the mask position with numpy : 0.0394289493560791 nb_pixel_total : 63771 time to create 1 rle with old method : 0.07287931442260742 time for calcul the mask position with numpy : 0.03895688056945801 nb_pixel_total : 192423 time to create 1 rle with new method : 0.544001579284668 time for calcul the mask position with numpy : 0.03939008712768555 nb_pixel_total : 2322 time to create 1 rle with old method : 0.0027704238891601562 time for calcul the mask position with numpy : 0.042009830474853516 nb_pixel_total : 73362 time to create 1 rle with old method : 0.08041715621948242 time for calcul the mask position with numpy : 0.038303375244140625 nb_pixel_total : 12830 time to create 1 rle with old method : 0.014488697052001953 time for calcul the mask position with numpy : 0.03864908218383789 nb_pixel_total : 29380 time to create 1 rle with old method : 0.032485246658325195 time for calcul the mask position with numpy : 0.03856801986694336 nb_pixel_total : 89074 time to create 1 rle with old method : 0.10015368461608887 time for calcul the mask position with numpy : 0.038407325744628906 nb_pixel_total : 10010 time to create 1 rle with old method : 0.012309789657592773 time for calcul the mask position with numpy : 0.03883504867553711 nb_pixel_total : 2277 time to create 1 rle with old method : 0.0028510093688964844 time for calcul the mask position with numpy : 0.03902912139892578 nb_pixel_total : 8395 time to create 1 rle with old method : 0.009806394577026367 time for calcul the mask position with numpy : 0.03895163536071777 nb_pixel_total : 211971 time to create 1 rle with new method : 0.6931812763214111 time for calcul the mask position with numpy : 0.0384526252746582 nb_pixel_total : 15813 time to create 1 rle with old method : 0.01799917221069336 time for calcul the mask position with numpy : 0.03954362869262695 nb_pixel_total : 113561 time to create 1 rle with old method : 0.1282787322998047 time for calcul the mask position with numpy : 0.03981447219848633 nb_pixel_total : 50679 time to create 1 rle with old method : 0.05728602409362793 time for calcul the mask position with numpy : 0.039956092834472656 nb_pixel_total : 63460 time to create 1 rle with old method : 0.07113170623779297 create new chi : 9.819714784622192 time to delete rle : 0.0023984909057617188 batch 1 Loaded 42 chid ids of type : 4855 Number RLEs to save : 28612 TO DO : save crop sub photo not yet done ! save time : 1.6215240955352783 nb_obj : 83 nb_hashtags : 11 time to prepare the origin masks : 42.10303497314453 time for calcul the mask position with numpy : 0.20886659622192383 nb_pixel_total : 3298714 time to create 1 rle with new method : 0.7592310905456543 time for calcul the mask position with numpy : 0.04308366775512695 nb_pixel_total : 38830 time to create 1 rle with old method : 0.04757237434387207 time for calcul the mask position with numpy : 0.0391697883605957 nb_pixel_total : 2598 time to create 1 rle with old method : 0.0032279491424560547 time for calcul the mask position with numpy : 0.03925967216491699 nb_pixel_total : 2493 time to create 1 rle with old method : 0.0030460357666015625 time for calcul the mask position with numpy : 0.20568108558654785 nb_pixel_total : 1466639 time to create 1 rle with new method : 0.6347682476043701 time for calcul the mask position with numpy : 0.0396273136138916 nb_pixel_total : 364978 time to create 1 rle with new method : 0.6362316608428955 time for calcul the mask position with numpy : 0.03881239891052246 nb_pixel_total : 32322 time to create 1 rle with old method : 0.03694558143615723 time for calcul the mask position with numpy : 0.038308143615722656 nb_pixel_total : 3435 time to create 1 rle with old method : 0.004190206527709961 time for calcul the mask position with numpy : 0.03872537612915039 nb_pixel_total : 25024 time to create 1 rle with old method : 0.027976036071777344 time for calcul the mask position with numpy : 0.038094520568847656 nb_pixel_total : 3922 time to create 1 rle with old method : 0.00473785400390625 time for calcul the mask position with numpy : 0.03909420967102051 nb_pixel_total : 27414 time to create 1 rle with old method : 0.030774354934692383 time for calcul the mask position with numpy : 0.038750410079956055 nb_pixel_total : 21308 time to create 1 rle with old method : 0.024266958236694336 time for calcul the mask position with numpy : 0.03969573974609375 nb_pixel_total : 29589 time to create 1 rle with old method : 0.033904314041137695 time for calcul the mask position with numpy : 0.03914809226989746 nb_pixel_total : 139787 time to create 1 rle with old method : 0.15768003463745117 time for calcul the mask position with numpy : 0.039237260818481445 nb_pixel_total : 44455 time to create 1 rle with old method : 0.050969839096069336 time for calcul the mask position with numpy : 0.03979682922363281 nb_pixel_total : 22000 time to create 1 rle with old method : 0.02485966682434082 time for calcul the mask position with numpy : 0.03847455978393555 nb_pixel_total : 29632 time to create 1 rle with old method : 0.03339362144470215 time for calcul the mask position with numpy : 0.03907942771911621 nb_pixel_total : 3523 time to create 1 rle with old method : 0.00416874885559082 time for calcul the mask position with numpy : 0.03814864158630371 nb_pixel_total : 80 time to create 1 rle with old method : 0.0003237724304199219 time for calcul the mask position with numpy : 0.0380251407623291 nb_pixel_total : 4911 time to create 1 rle with old method : 0.005654811859130859 time for calcul the mask position with numpy : 0.039945363998413086 nb_pixel_total : 262406 time to create 1 rle with new method : 0.688338041305542 time for calcul the mask position with numpy : 0.04086709022521973 nb_pixel_total : 406009 time to create 1 rle with new method : 0.671130895614624 time for calcul the mask position with numpy : 0.03887200355529785 nb_pixel_total : 43154 time to create 1 rle with old method : 0.06970095634460449 time for calcul the mask position with numpy : 0.042479753494262695 nb_pixel_total : 87210 time to create 1 rle with old method : 0.0997161865234375 time for calcul the mask position with numpy : 0.03893899917602539 nb_pixel_total : 16025 time to create 1 rle with old method : 0.017949581146240234 time for calcul the mask position with numpy : 0.03995013236999512 nb_pixel_total : 436686 time to create 1 rle with new method : 0.6005344390869141 time for calcul the mask position with numpy : 0.038521528244018555 nb_pixel_total : 62740 time to create 1 rle with old method : 0.06944632530212402 time for calcul the mask position with numpy : 0.037880659103393555 nb_pixel_total : 9495 time to create 1 rle with old method : 0.010914087295532227 time for calcul the mask position with numpy : 0.03874516487121582 nb_pixel_total : 2393 time to create 1 rle with old method : 0.003000974655151367 time for calcul the mask position with numpy : 0.03919482231140137 nb_pixel_total : 43926 time to create 1 rle with old method : 0.04972052574157715 time for calcul the mask position with numpy : 0.038224220275878906 nb_pixel_total : 173460 time to create 1 rle with new method : 0.6239697933197021 time for calcul the mask position with numpy : 0.03829646110534668 nb_pixel_total : 27500 time to create 1 rle with old method : 0.03019237518310547 time for calcul the mask position with numpy : 0.03882193565368652 nb_pixel_total : 20177 time to create 1 rle with old method : 0.02275562286376953 time for calcul the mask position with numpy : 0.038398027420043945 nb_pixel_total : 1163 time to create 1 rle with old method : 0.0015058517456054688 time for calcul the mask position with numpy : 0.037929534912109375 nb_pixel_total : 225 time to create 1 rle with old method : 0.00027751922607421875 time for calcul the mask position with numpy : 0.03879666328430176 nb_pixel_total : 30724 time to create 1 rle with old method : 0.03521275520324707 time for calcul the mask position with numpy : 0.039489030838012695 nb_pixel_total : 66026 time to create 1 rle with old method : 0.07308769226074219 time for calcul the mask position with numpy : 0.03809094429016113 nb_pixel_total : 112695 time to create 1 rle with old method : 0.12323951721191406 time for calcul the mask position with numpy : 0.037682533264160156 nb_pixel_total : 83693 time to create 1 rle with old method : 0.09383726119995117 time for calcul the mask position with numpy : 0.03792285919189453 nb_pixel_total : 44130 time to create 1 rle with old method : 0.05048680305480957 time for calcul the mask position with numpy : 0.039034128189086914 nb_pixel_total : 36110 time to create 1 rle with old method : 0.039988040924072266 time for calcul the mask position with numpy : 0.03759646415710449 nb_pixel_total : 5057 time to create 1 rle with old method : 0.005663871765136719 time for calcul the mask position with numpy : 0.03754830360412598 nb_pixel_total : 7940 time to create 1 rle with old method : 0.009058952331542969 time for calcul the mask position with numpy : 0.03827714920043945 nb_pixel_total : 147724 time to create 1 rle with old method : 0.1643846035003662 time for calcul the mask position with numpy : 0.037926673889160156 nb_pixel_total : 1842 time to create 1 rle with old method : 0.002332925796508789 time for calcul the mask position with numpy : 0.03912353515625 nb_pixel_total : 50830 time to create 1 rle with old method : 0.06360530853271484 time for calcul the mask position with numpy : 0.04401969909667969 nb_pixel_total : 15473 time to create 1 rle with old method : 0.019612550735473633 time for calcul the mask position with numpy : 0.04547452926635742 nb_pixel_total : 17361 time to create 1 rle with old method : 0.030950546264648438 time for calcul the mask position with numpy : 0.05048537254333496 nb_pixel_total : 318560 time to create 1 rle with new method : 1.8111286163330078 time for calcul the mask position with numpy : 0.04053497314453125 nb_pixel_total : 38387 time to create 1 rle with old method : 0.044060468673706055 time for calcul the mask position with numpy : 0.03977608680725098 nb_pixel_total : 13858 time to create 1 rle with old method : 0.016042232513427734 time for calcul the mask position with numpy : 0.04064369201660156 nb_pixel_total : 301614 time to create 1 rle with new method : 0.6855878829956055 time for calcul the mask position with numpy : 0.04099917411804199 nb_pixel_total : 22857 time to create 1 rle with old method : 0.02660346031188965 time for calcul the mask position with numpy : 0.0397028923034668 nb_pixel_total : 58310 time to create 1 rle with old method : 0.06749916076660156 time for calcul the mask position with numpy : 0.03918051719665527 nb_pixel_total : 23702 time to create 1 rle with old method : 0.026803970336914062 time for calcul the mask position with numpy : 0.03981781005859375 nb_pixel_total : 1253 time to create 1 rle with old method : 0.0017032623291015625 time for calcul the mask position with numpy : 0.03951430320739746 nb_pixel_total : 98 time to create 1 rle with old method : 0.00016021728515625 time for calcul the mask position with numpy : 0.0408625602722168 nb_pixel_total : 296543 time to create 1 rle with new method : 0.686314582824707 time for calcul the mask position with numpy : 0.040480613708496094 nb_pixel_total : 3497 time to create 1 rle with old method : 0.004284858703613281 time for calcul the mask position with numpy : 0.0413355827331543 nb_pixel_total : 101350 time to create 1 rle with old method : 0.12268352508544922 time for calcul the mask position with numpy : 0.04139971733093262 nb_pixel_total : 451 time to create 1 rle with old method : 0.0005543231964111328 time for calcul the mask position with numpy : 0.042127132415771484 nb_pixel_total : 46117 time to create 1 rle with old method : 0.06952285766601562 time for calcul the mask position with numpy : 0.04060220718383789 nb_pixel_total : 12318 time to create 1 rle with old method : 0.014536142349243164 time for calcul the mask position with numpy : 0.04264044761657715 nb_pixel_total : 60774 time to create 1 rle with old method : 0.0770561695098877 time for calcul the mask position with numpy : 0.041062355041503906 nb_pixel_total : 143687 time to create 1 rle with old method : 0.16680693626403809 time for calcul the mask position with numpy : 0.04014873504638672 nb_pixel_total : 4155 time to create 1 rle with old method : 0.00525975227355957 time for calcul the mask position with numpy : 0.040723562240600586 nb_pixel_total : 43822 time to create 1 rle with old method : 0.05524134635925293 time for calcul the mask position with numpy : 0.041113853454589844 nb_pixel_total : 10121 time to create 1 rle with old method : 0.01222681999206543 time for calcul the mask position with numpy : 0.0418701171875 nb_pixel_total : 3352 time to create 1 rle with old method : 0.004131793975830078 time for calcul the mask position with numpy : 0.040450334548950195 nb_pixel_total : 7449 time to create 1 rle with old method : 0.009095430374145508 time for calcul the mask position with numpy : 0.04098844528198242 nb_pixel_total : 195 time to create 1 rle with old method : 0.0005204677581787109 time for calcul the mask position with numpy : 0.04119729995727539 nb_pixel_total : 63897 time to create 1 rle with old method : 0.07514309883117676 time for calcul the mask position with numpy : 0.040813446044921875 nb_pixel_total : 117620 time to create 1 rle with old method : 0.15697884559631348 time for calcul the mask position with numpy : 0.04543447494506836 nb_pixel_total : 712 time to create 1 rle with old method : 0.0012564659118652344 time for calcul the mask position with numpy : 0.043447017669677734 nb_pixel_total : 28180 time to create 1 rle with old method : 0.03309988975524902 time for calcul the mask position with numpy : 0.04086923599243164 nb_pixel_total : 49059 time to create 1 rle with old method : 0.058417558670043945 time for calcul the mask position with numpy : 0.04163932800292969 nb_pixel_total : 109008 time to create 1 rle with old method : 0.12785840034484863 time for calcul the mask position with numpy : 0.04058957099914551 nb_pixel_total : 41300 time to create 1 rle with old method : 0.050116777420043945 time for calcul the mask position with numpy : 0.04288029670715332 nb_pixel_total : 46 time to create 1 rle with old method : 0.00013756752014160156 time for calcul the mask position with numpy : 0.04360342025756836 nb_pixel_total : 1735 time to create 1 rle with old method : 0.002430438995361328 time for calcul the mask position with numpy : 0.04060983657836914 nb_pixel_total : 17087 time to create 1 rle with old method : 0.020142793655395508 time for calcul the mask position with numpy : 0.04495525360107422 nb_pixel_total : 703 time to create 1 rle with old method : 0.0011262893676757812 time for calcul the mask position with numpy : 0.03984713554382324 nb_pixel_total : 17886 time to create 1 rle with old method : 0.02104806900024414 time for calcul the mask position with numpy : 0.03969073295593262 nb_pixel_total : 869 time to create 1 rle with old method : 0.001148223876953125 create new chi : 14.688902139663696 time to delete rle : 0.003991842269897461 batch 1 Loaded 84 chid ids of type : 4855 Number RLEs to save : 49001 TO DO : save crop sub photo not yet done ! save time : 2.50769305229187 nb_obj : 64 nb_hashtags : 9 time to prepare the origin masks : 38.76088762283325 time for calcul the mask position with numpy : 0.09661293029785156 nb_pixel_total : 2325712 time to create 1 rle with new method : 1.0731921195983887 time for calcul the mask position with numpy : 0.03874826431274414 nb_pixel_total : 30493 time to create 1 rle with old method : 0.03379464149475098 time for calcul the mask position with numpy : 0.04136490821838379 nb_pixel_total : 54422 time to create 1 rle with old method : 0.08580613136291504 time for calcul the mask position with numpy : 0.044503211975097656 nb_pixel_total : 468 time to create 1 rle with old method : 0.0007526874542236328 time for calcul the mask position with numpy : 0.043426513671875 nb_pixel_total : 165330 time to create 1 rle with new method : 0.8219623565673828 time for calcul the mask position with numpy : 0.04032707214355469 nb_pixel_total : 69642 time to create 1 rle with old method : 0.07752704620361328 time for calcul the mask position with numpy : 0.04432940483093262 nb_pixel_total : 421985 time to create 1 rle with new method : 0.8830325603485107 time for calcul the mask position with numpy : 0.043051719665527344 nb_pixel_total : 137411 time to create 1 rle with old method : 0.15401387214660645 time for calcul the mask position with numpy : 0.04671049118041992 nb_pixel_total : 311698 time to create 1 rle with new method : 1.4544835090637207 time for calcul the mask position with numpy : 0.05107545852661133 nb_pixel_total : 301349 time to create 1 rle with new method : 1.539025068283081 time for calcul the mask position with numpy : 0.04519343376159668 nb_pixel_total : 52840 time to create 1 rle with old method : 0.0672607421875 time for calcul the mask position with numpy : 0.04718279838562012 nb_pixel_total : 53197 time to create 1 rle with old method : 0.06444215774536133 time for calcul the mask position with numpy : 0.047202348709106445 nb_pixel_total : 35264 time to create 1 rle with old method : 0.04066324234008789 time for calcul the mask position with numpy : 0.04706883430480957 nb_pixel_total : 278580 time to create 1 rle with new method : 1.0998306274414062 time for calcul the mask position with numpy : 0.039807796478271484 nb_pixel_total : 26771 time to create 1 rle with old method : 0.029126644134521484 time for calcul the mask position with numpy : 0.04041457176208496 nb_pixel_total : 41774 time to create 1 rle with old method : 0.04732346534729004 time for calcul the mask position with numpy : 0.04359769821166992 nb_pixel_total : 113003 time to create 1 rle with old method : 0.13364481925964355 time for calcul the mask position with numpy : 0.0427553653717041 nb_pixel_total : 45661 time to create 1 rle with old method : 0.053815603256225586 time for calcul the mask position with numpy : 0.04268789291381836 nb_pixel_total : 69068 time to create 1 rle with old method : 0.08126187324523926 time for calcul the mask position with numpy : 0.04221749305725098 nb_pixel_total : 38141 time to create 1 rle with old method : 0.04641413688659668 time for calcul the mask position with numpy : 0.044287919998168945 nb_pixel_total : 176503 time to create 1 rle with new method : 0.9767987728118896 time for calcul the mask position with numpy : 0.049018144607543945 nb_pixel_total : 237362 time to create 1 rle with new method : 0.9963593482971191 time for calcul the mask position with numpy : 0.04636883735656738 nb_pixel_total : 293324 time to create 1 rle with new method : 0.8358259201049805 time for calcul the mask position with numpy : 0.04508495330810547 nb_pixel_total : 15672 time to create 1 rle with old method : 0.01844930648803711 time for calcul the mask position with numpy : 0.04397916793823242 nb_pixel_total : 81557 time to create 1 rle with old method : 0.09615683555603027 time for calcul the mask position with numpy : 0.04332780838012695 nb_pixel_total : 17522 time to create 1 rle with old method : 0.02100205421447754 time for calcul the mask position with numpy : 0.0644524097442627 nb_pixel_total : 715061 time to create 1 rle with new method : 1.517202377319336 time for calcul the mask position with numpy : 0.04895138740539551 nb_pixel_total : 412855 time to create 1 rle with new method : 1.7599999904632568 time for calcul the mask position with numpy : 0.04260659217834473 nb_pixel_total : 36053 time to create 1 rle with old method : 0.24434804916381836 time for calcul the mask position with numpy : 0.042044878005981445 nb_pixel_total : 82290 time to create 1 rle with old method : 0.09628629684448242 time for calcul the mask position with numpy : 0.041443824768066406 nb_pixel_total : 37271 time to create 1 rle with old method : 0.042490482330322266 time for calcul the mask position with numpy : 0.04203677177429199 nb_pixel_total : 272664 time to create 1 rle with new method : 1.1835393905639648 time for calcul the mask position with numpy : 0.0425872802734375 nb_pixel_total : 43962 time to create 1 rle with old method : 0.054299354553222656 time for calcul the mask position with numpy : 0.042035579681396484 nb_pixel_total : 90630 time to create 1 rle with old method : 0.11686992645263672 time for calcul the mask position with numpy : 0.045325517654418945 nb_pixel_total : 19702 time to create 1 rle with old method : 0.022872447967529297 time for calcul the mask position with numpy : 0.04327726364135742 nb_pixel_total : 158841 time to create 1 rle with new method : 2.0220227241516113 time for calcul the mask position with numpy : 0.04107856750488281 nb_pixel_total : 10553 time to create 1 rle with old method : 0.012476921081542969 time for calcul the mask position with numpy : 0.04141545295715332 nb_pixel_total : 10146 time to create 1 rle with old method : 0.013385534286499023 time for calcul the mask position with numpy : 0.04415750503540039 nb_pixel_total : 13432 time to create 1 rle with old method : 0.015973806381225586 time for calcul the mask position with numpy : 0.04064583778381348 nb_pixel_total : 308 time to create 1 rle with old method : 0.00046563148498535156 time for calcul the mask position with numpy : 0.045618534088134766 nb_pixel_total : 220473 time to create 1 rle with new method : 0.6150705814361572 time for calcul the mask position with numpy : 0.03970050811767578 nb_pixel_total : 105937 time to create 1 rle with old method : 0.11552047729492188 time for calcul the mask position with numpy : 0.04155421257019043 nb_pixel_total : 115741 time to create 1 rle with old method : 0.13052964210510254 time for calcul the mask position with numpy : 0.042432546615600586 nb_pixel_total : 239377 time to create 1 rle with new method : 0.7801544666290283 time for calcul the mask position with numpy : 0.048131465911865234 nb_pixel_total : 535287 time to create 1 rle with new method : 0.971519947052002 time for calcul the mask position with numpy : 0.042940616607666016 nb_pixel_total : 201963 time to create 1 rle with new method : 0.968743085861206 time for calcul the mask position with numpy : 0.03926706314086914 nb_pixel_total : 36855 time to create 1 rle with old method : 0.040346622467041016 time for calcul the mask position with numpy : 0.03870272636413574 nb_pixel_total : 22810 time to create 1 rle with old method : 0.024994850158691406 time for calcul the mask position with numpy : 0.039186954498291016 nb_pixel_total : 26028 time to create 1 rle with old method : 0.029145479202270508 time for calcul the mask position with numpy : 0.03853154182434082 nb_pixel_total : 5632 time to create 1 rle with old method : 0.006520748138427734 time for calcul the mask position with numpy : 0.040320634841918945 nb_pixel_total : 212952 time to create 1 rle with new method : 0.8338704109191895 time for calcul the mask position with numpy : 0.03849220275878906 nb_pixel_total : 14218 time to create 1 rle with old method : 0.016474008560180664 time for calcul the mask position with numpy : 0.04281878471374512 nb_pixel_total : 399452 time to create 1 rle with new method : 0.4280886650085449 time for calcul the mask position with numpy : 0.03940844535827637 nb_pixel_total : 4583 time to create 1 rle with old method : 0.005244731903076172 time for calcul the mask position with numpy : 0.040453195571899414 nb_pixel_total : 18033 time to create 1 rle with old method : 0.02071237564086914 time for calcul the mask position with numpy : 0.03975510597229004 nb_pixel_total : 61715 time to create 1 rle with old method : 0.06864261627197266 time for calcul the mask position with numpy : 0.040491342544555664 nb_pixel_total : 15 time to create 1 rle with old method : 0.00013637542724609375 time for calcul the mask position with numpy : 0.04317474365234375 nb_pixel_total : 110173 time to create 1 rle with old method : 0.13019394874572754 time for calcul the mask position with numpy : 0.04122209548950195 nb_pixel_total : 27175 time to create 1 rle with old method : 0.03235888481140137 time for calcul the mask position with numpy : 0.04130816459655762 nb_pixel_total : 36196 time to create 1 rle with old method : 0.04273819923400879 time for calcul the mask position with numpy : 0.04113888740539551 nb_pixel_total : 13413 time to create 1 rle with old method : 0.015733718872070312 time for calcul the mask position with numpy : 0.04711627960205078 nb_pixel_total : 620 time to create 1 rle with old method : 0.0009143352508544922 time for calcul the mask position with numpy : 0.04381513595581055 nb_pixel_total : 24372 time to create 1 rle with old method : 0.032418251037597656 time for calcul the mask position with numpy : 0.046088218688964844 nb_pixel_total : 196 time to create 1 rle with old method : 0.0007333755493164062 time for calcul the mask position with numpy : 0.04416942596435547 nb_pixel_total : 2667 time to create 1 rle with old method : 0.0032591819763183594 create new chi : 26.943230628967285 time to delete rle : 0.006258726119995117 batch 1 Loaded 65 chid ids of type : 4855 Number RLEs to save : 47770 TO DO : save crop sub photo not yet done ! save time : 2.5206949710845947 nb_obj : 62 nb_hashtags : 9 time to prepare the origin masks : 32.23822808265686 time for calcul the mask position with numpy : 1.3602142333984375 nb_pixel_total : 4440569 time to create 1 rle with new method : 1.0311203002929688 time for calcul the mask position with numpy : 0.03874778747558594 nb_pixel_total : 175234 time to create 1 rle with new method : 0.6818318367004395 time for calcul the mask position with numpy : 0.04105091094970703 nb_pixel_total : 471382 time to create 1 rle with new method : 0.6512181758880615 time for calcul the mask position with numpy : 0.0431208610534668 nb_pixel_total : 340744 time to create 1 rle with new method : 0.991401195526123 time for calcul the mask position with numpy : 0.04010748863220215 nb_pixel_total : 214350 time to create 1 rle with new method : 0.5834236145019531 time for calcul the mask position with numpy : 0.03996706008911133 nb_pixel_total : 75977 time to create 1 rle with old method : 0.08603477478027344 time for calcul the mask position with numpy : 0.03882026672363281 nb_pixel_total : 25782 time to create 1 rle with old method : 0.028715848922729492 time for calcul the mask position with numpy : 0.039595842361450195 nb_pixel_total : 125003 time to create 1 rle with old method : 0.1392202377319336 time for calcul the mask position with numpy : 0.0385279655456543 nb_pixel_total : 8164 time to create 1 rle with old method : 0.009855031967163086 time for calcul the mask position with numpy : 0.040589332580566406 nb_pixel_total : 268859 time to create 1 rle with new method : 0.5789494514465332 time for calcul the mask position with numpy : 0.04068565368652344 nb_pixel_total : 89520 time to create 1 rle with old method : 0.10297203063964844 time for calcul the mask position with numpy : 0.045830488204956055 nb_pixel_total : 17630 time to create 1 rle with old method : 0.021239519119262695 time for calcul the mask position with numpy : 0.043313026428222656 nb_pixel_total : 62652 time to create 1 rle with old method : 0.07804536819458008 time for calcul the mask position with numpy : 0.04061579704284668 nb_pixel_total : 6369 time to create 1 rle with old method : 0.009476661682128906 time for calcul the mask position with numpy : 0.04385089874267578 nb_pixel_total : 119322 time to create 1 rle with old method : 0.14429831504821777 time for calcul the mask position with numpy : 0.04053449630737305 nb_pixel_total : 14873 time to create 1 rle with old method : 0.017367124557495117 time for calcul the mask position with numpy : 0.040329933166503906 nb_pixel_total : 31812 time to create 1 rle with old method : 0.380399227142334 time for calcul the mask position with numpy : 0.041643619537353516 nb_pixel_total : 297079 time to create 1 rle with new method : 0.707965612411499 time for calcul the mask position with numpy : 0.04108071327209473 nb_pixel_total : 172520 time to create 1 rle with new method : 0.706712007522583 time for calcul the mask position with numpy : 0.04056739807128906 nb_pixel_total : 51538 time to create 1 rle with old method : 0.05994057655334473 time for calcul the mask position with numpy : 0.04088234901428223 nb_pixel_total : 128130 time to create 1 rle with old method : 0.15386366844177246 time for calcul the mask position with numpy : 0.041312217712402344 nb_pixel_total : 8317 time to create 1 rle with old method : 0.009912729263305664 time for calcul the mask position with numpy : 0.040578603744506836 nb_pixel_total : 89913 time to create 1 rle with old method : 0.10067486763000488 time for calcul the mask position with numpy : 0.04007124900817871 nb_pixel_total : 122060 time to create 1 rle with old method : 0.14447546005249023 time for calcul the mask position with numpy : 0.044799089431762695 nb_pixel_total : 1 time to create 1 rle with old method : 2.4318695068359375e-05 time for calcul the mask position with numpy : 0.045446157455444336 nb_pixel_total : 30306 time to create 1 rle with old method : 0.057456254959106445 time for calcul the mask position with numpy : 0.04670143127441406 nb_pixel_total : 42650 time to create 1 rle with old method : 0.13379645347595215 time for calcul the mask position with numpy : 0.04122352600097656 nb_pixel_total : 3158 time to create 1 rle with old method : 0.004067182540893555 time for calcul the mask position with numpy : 0.04103231430053711 nb_pixel_total : 34639 time to create 1 rle with old method : 0.040677785873413086 time for calcul the mask position with numpy : 0.04523038864135742 nb_pixel_total : 5877 time to create 1 rle with old method : 0.0070421695709228516 time for calcul the mask position with numpy : 0.04318809509277344 nb_pixel_total : 341684 time to create 1 rle with new method : 1.2119488716125488 time for calcul the mask position with numpy : 0.039916038513183594 nb_pixel_total : 2409 time to create 1 rle with old method : 0.0029914379119873047 time for calcul the mask position with numpy : 0.039552927017211914 nb_pixel_total : 44502 time to create 1 rle with old method : 0.05192899703979492 time for calcul the mask position with numpy : 0.04070281982421875 nb_pixel_total : 38054 time to create 1 rle with old method : 0.04387617111206055 time for calcul the mask position with numpy : 0.04049849510192871 nb_pixel_total : 64046 time to create 1 rle with old method : 0.08466172218322754 time for calcul the mask position with numpy : 0.040177106857299805 nb_pixel_total : 4544 time to create 1 rle with old method : 0.0052835941314697266 time for calcul the mask position with numpy : 0.04135894775390625 nb_pixel_total : 207705 time to create 1 rle with new method : 0.971951961517334 time for calcul the mask position with numpy : 0.04170846939086914 nb_pixel_total : 20521 time to create 1 rle with old method : 0.023900508880615234 time for calcul the mask position with numpy : 0.04043769836425781 nb_pixel_total : 13883 time to create 1 rle with old method : 0.01625967025756836 time for calcul the mask position with numpy : 0.04035139083862305 nb_pixel_total : 2487 time to create 1 rle with old method : 0.0030214786529541016 time for calcul the mask position with numpy : 0.04061436653137207 nb_pixel_total : 64472 time to create 1 rle with old method : 0.07516360282897949 time for calcul the mask position with numpy : 0.04333782196044922 nb_pixel_total : 485573 time to create 1 rle with new method : 0.7690567970275879 time for calcul the mask position with numpy : 0.0399479866027832 nb_pixel_total : 11212 time to create 1 rle with old method : 0.01438283920288086 time for calcul the mask position with numpy : 0.04231381416320801 nb_pixel_total : 36 time to create 1 rle with old method : 6.127357482910156e-05 time for calcul the mask position with numpy : 0.040071725845336914 nb_pixel_total : 25290 time to create 1 rle with old method : 0.02933645248413086 time for calcul the mask position with numpy : 0.04168295860290527 nb_pixel_total : 23093 time to create 1 rle with old method : 0.027922630310058594 time for calcul the mask position with numpy : 0.04004383087158203 nb_pixel_total : 22290 time to create 1 rle with old method : 0.025609254837036133 time for calcul the mask position with numpy : 0.039602041244506836 nb_pixel_total : 73230 time to create 1 rle with old method : 0.08418846130371094 time for calcul the mask position with numpy : 0.03998112678527832 nb_pixel_total : 2126 time to create 1 rle with old method : 0.0026221275329589844 time for calcul the mask position with numpy : 0.040418148040771484 nb_pixel_total : 201767 time to create 1 rle with new method : 0.6243324279785156 time for calcul the mask position with numpy : 0.0404052734375 nb_pixel_total : 7683 time to create 1 rle with old method : 0.00946044921875 time for calcul the mask position with numpy : 0.04044771194458008 nb_pixel_total : 47492 time to create 1 rle with old method : 0.05754232406616211 time for calcul the mask position with numpy : 0.04388689994812012 nb_pixel_total : 414638 time to create 1 rle with new method : 0.7101342678070068 time for calcul the mask position with numpy : 0.04046177864074707 nb_pixel_total : 5280 time to create 1 rle with old method : 0.006474494934082031 time for calcul the mask position with numpy : 0.04053807258605957 nb_pixel_total : 37452 time to create 1 rle with old method : 0.04382157325744629 time for calcul the mask position with numpy : 0.04056215286254883 nb_pixel_total : 14017 time to create 1 rle with old method : 0.016720294952392578 time for calcul the mask position with numpy : 0.04024338722229004 nb_pixel_total : 15819 time to create 1 rle with old method : 0.018613815307617188 time for calcul the mask position with numpy : 0.04039168357849121 nb_pixel_total : 4317 time to create 1 rle with old method : 0.005229473114013672 time for calcul the mask position with numpy : 0.04050588607788086 nb_pixel_total : 23542 time to create 1 rle with old method : 0.027419090270996094 time for calcul the mask position with numpy : 0.04036593437194824 nb_pixel_total : 756 time to create 1 rle with old method : 0.0010063648223876953 time for calcul the mask position with numpy : 0.040596723556518555 nb_pixel_total : 34738 time to create 1 rle with old method : 0.04042863845825195 time for calcul the mask position with numpy : 0.04028511047363281 nb_pixel_total : 2014 time to create 1 rle with old method : 0.002718687057495117 time for calcul the mask position with numpy : 0.04033374786376953 nb_pixel_total : 3298 time to create 1 rle with old method : 0.004187583923339844 create new chi : 17.042240381240845 time to delete rle : 0.0038144588470458984 batch 1 Loaded 63 chid ids of type : 4855 Number RLEs to save : 41706 TO DO : save crop sub photo not yet done ! save time : 2.1502671241760254 nb_obj : 73 nb_hashtags : 9 time to prepare the origin masks : 40.55606460571289 time for calcul the mask position with numpy : 0.2779264450073242 nb_pixel_total : 3192772 time to create 1 rle with new method : 1.1570501327514648 time for calcul the mask position with numpy : 0.0407257080078125 nb_pixel_total : 69354 time to create 1 rle with old method : 0.08096766471862793 time for calcul the mask position with numpy : 0.04070448875427246 nb_pixel_total : 8869 time to create 1 rle with old method : 0.010857105255126953 time for calcul the mask position with numpy : 0.04235029220581055 nb_pixel_total : 199964 time to create 1 rle with new method : 0.7118039131164551 time for calcul the mask position with numpy : 0.04042696952819824 nb_pixel_total : 15156 time to create 1 rle with old method : 0.01783919334411621 time for calcul the mask position with numpy : 0.04270339012145996 nb_pixel_total : 293279 time to create 1 rle with new method : 0.8848936557769775 time for calcul the mask position with numpy : 0.04043078422546387 nb_pixel_total : 6291 time to create 1 rle with old method : 0.007702350616455078 time for calcul the mask position with numpy : 0.04056549072265625 nb_pixel_total : 29244 time to create 1 rle with old method : 0.0340728759765625 time for calcul the mask position with numpy : 0.040441274642944336 nb_pixel_total : 25654 time to create 1 rle with old method : 0.03014349937438965 time for calcul the mask position with numpy : 0.04106497764587402 nb_pixel_total : 116709 time to create 1 rle with old method : 0.13776302337646484 time for calcul the mask position with numpy : 0.04652714729309082 nb_pixel_total : 26438 time to create 1 rle with old method : 0.0408937931060791 time for calcul the mask position with numpy : 0.04094886779785156 nb_pixel_total : 86983 time to create 1 rle with old method : 0.10108828544616699 time for calcul the mask position with numpy : 0.04036402702331543 nb_pixel_total : 5365 time to create 1 rle with old method : 0.0064449310302734375 time for calcul the mask position with numpy : 0.0404815673828125 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003294944763183594 time for calcul the mask position with numpy : 0.04814767837524414 nb_pixel_total : 22670 time to create 1 rle with old method : 0.026324033737182617 time for calcul the mask position with numpy : 0.040346622467041016 nb_pixel_total : 51398 time to create 1 rle with old method : 0.059954166412353516 time for calcul the mask position with numpy : 0.040389299392700195 nb_pixel_total : 82034 time to create 1 rle with old method : 0.0948183536529541 time for calcul the mask position with numpy : 0.04026031494140625 nb_pixel_total : 52967 time to create 1 rle with old method : 0.061801910400390625 time for calcul the mask position with numpy : 0.040230751037597656 nb_pixel_total : 10796 time to create 1 rle with old method : 0.012974262237548828 time for calcul the mask position with numpy : 0.040128469467163086 nb_pixel_total : 14645 time to create 1 rle with old method : 0.017061233520507812 time for calcul the mask position with numpy : 0.04032421112060547 nb_pixel_total : 23090 time to create 1 rle with old method : 0.02719902992248535 time for calcul the mask position with numpy : 0.04155445098876953 nb_pixel_total : 300879 time to create 1 rle with new method : 0.8252513408660889 time for calcul the mask position with numpy : 0.04090595245361328 nb_pixel_total : 114462 time to create 1 rle with old method : 0.13144803047180176 time for calcul the mask position with numpy : 0.04128575325012207 nb_pixel_total : 111336 time to create 1 rle with old method : 0.13098669052124023 time for calcul the mask position with numpy : 0.04094386100769043 nb_pixel_total : 48016 time to create 1 rle with old method : 0.05552816390991211 time for calcul the mask position with numpy : 0.04033827781677246 nb_pixel_total : 31395 time to create 1 rle with old method : 0.03675484657287598 time for calcul the mask position with numpy : 0.040756940841674805 nb_pixel_total : 171895 time to create 1 rle with new method : 0.9402587413787842 time for calcul the mask position with numpy : 0.041004180908203125 nb_pixel_total : 197497 time to create 1 rle with new method : 0.8598580360412598 time for calcul the mask position with numpy : 0.04483532905578613 nb_pixel_total : 95913 time to create 1 rle with old method : 0.11229419708251953 time for calcul the mask position with numpy : 0.04015707969665527 nb_pixel_total : 2690 time to create 1 rle with old method : 0.0031609535217285156 time for calcul the mask position with numpy : 0.042328596115112305 nb_pixel_total : 22196 time to create 1 rle with old method : 0.026314258575439453 time for calcul the mask position with numpy : 0.04026937484741211 nb_pixel_total : 25774 time to create 1 rle with old method : 0.030214786529541016 time for calcul the mask position with numpy : 0.040189266204833984 nb_pixel_total : 102168 time to create 1 rle with old method : 0.12132883071899414 time for calcul the mask position with numpy : 0.04166913032531738 nb_pixel_total : 445490 time to create 1 rle with new method : 0.9934170246124268 time for calcul the mask position with numpy : 0.042977333068847656 nb_pixel_total : 75937 time to create 1 rle with old method : 0.10341978073120117 time for calcul the mask position with numpy : 0.04401707649230957 nb_pixel_total : 18637 time to create 1 rle with old method : 0.0235440731048584 time for calcul the mask position with numpy : 0.0416262149810791 nb_pixel_total : 33616 time to create 1 rle with old method : 0.03993058204650879 time for calcul the mask position with numpy : 0.04214310646057129 nb_pixel_total : 20632 time to create 1 rle with old method : 0.02784276008605957 time for calcul the mask position with numpy : 0.04507565498352051 nb_pixel_total : 114467 time to create 1 rle with old method : 0.13499784469604492 time for calcul the mask position with numpy : 0.04235696792602539 nb_pixel_total : 127794 time to create 1 rle with old method : 0.15225768089294434 time for calcul the mask position with numpy : 0.04360508918762207 nb_pixel_total : 249451 time to create 1 rle with new method : 1.1446526050567627 time for calcul the mask position with numpy : 0.04343891143798828 nb_pixel_total : 244659 time to create 1 rle with new method : 1.355046272277832 time for calcul the mask position with numpy : 0.041818857192993164 nb_pixel_total : 154561 time to create 1 rle with new method : 0.7580370903015137 time for calcul the mask position with numpy : 0.0424954891204834 nb_pixel_total : 83126 time to create 1 rle with old method : 0.10039496421813965 time for calcul the mask position with numpy : 0.04195451736450195 nb_pixel_total : 55570 time to create 1 rle with old method : 0.06744050979614258 time for calcul the mask position with numpy : 0.04095005989074707 nb_pixel_total : 59206 time to create 1 rle with old method : 0.07237505912780762 time for calcul the mask position with numpy : 0.04077768325805664 nb_pixel_total : 25737 time to create 1 rle with old method : 0.030896902084350586 time for calcul the mask position with numpy : 0.0476231575012207 nb_pixel_total : 421573 time to create 1 rle with new method : 0.8191187381744385 time for calcul the mask position with numpy : 0.04072093963623047 nb_pixel_total : 66044 time to create 1 rle with old method : 0.0769045352935791 time for calcul the mask position with numpy : 0.040703773498535156 nb_pixel_total : 39409 time to create 1 rle with old method : 0.04620027542114258 time for calcul the mask position with numpy : 0.04037189483642578 nb_pixel_total : 124 time to create 1 rle with old method : 0.0002608299255371094 time for calcul the mask position with numpy : 0.04067635536193848 nb_pixel_total : 42945 time to create 1 rle with old method : 0.050069570541381836 time for calcul the mask position with numpy : 0.04029035568237305 nb_pixel_total : 9177 time to create 1 rle with old method : 0.010818004608154297 time for calcul the mask position with numpy : 0.040509939193725586 nb_pixel_total : 9119 time to create 1 rle with old method : 0.011229991912841797 time for calcul the mask position with numpy : 0.040694475173950195 nb_pixel_total : 83603 time to create 1 rle with old method : 0.10472941398620605 time for calcul the mask position with numpy : 0.04025912284851074 nb_pixel_total : 257 time to create 1 rle with old method : 0.00032138824462890625 time for calcul the mask position with numpy : 0.04014754295349121 nb_pixel_total : 17815 time to create 1 rle with old method : 0.020838022232055664 time for calcul the mask position with numpy : 0.04073333740234375 nb_pixel_total : 14562 time to create 1 rle with old method : 0.017481327056884766 time for calcul the mask position with numpy : 0.041619300842285156 nb_pixel_total : 178463 time to create 1 rle with new method : 1.1263782978057861 time for calcul the mask position with numpy : 0.04317951202392578 nb_pixel_total : 388627 time to create 1 rle with new method : 0.7285280227661133 time for calcul the mask position with numpy : 0.044352054595947266 nb_pixel_total : 338824 time to create 1 rle with new method : 0.6994473934173584 time for calcul the mask position with numpy : 0.04200387001037598 nb_pixel_total : 707 time to create 1 rle with old method : 0.0015218257904052734 time for calcul the mask position with numpy : 0.04052305221557617 nb_pixel_total : 28875 time to create 1 rle with old method : 0.033522844314575195 time for calcul the mask position with numpy : 0.04388165473937988 nb_pixel_total : 254241 time to create 1 rle with new method : 0.7700369358062744 time for calcul the mask position with numpy : 0.04114723205566406 nb_pixel_total : 114045 time to create 1 rle with old method : 0.1321425437927246 time for calcul the mask position with numpy : 0.04031682014465332 nb_pixel_total : 2575 time to create 1 rle with old method : 0.003030061721801758 time for calcul the mask position with numpy : 0.04146552085876465 nb_pixel_total : 6524 time to create 1 rle with old method : 0.010680198669433594 time for calcul the mask position with numpy : 0.04617428779602051 nb_pixel_total : 95070 time to create 1 rle with old method : 0.11453509330749512 time for calcul the mask position with numpy : 0.04041790962219238 nb_pixel_total : 3265 time to create 1 rle with old method : 0.0041043758392333984 time for calcul the mask position with numpy : 0.04639101028442383 nb_pixel_total : 168446 time to create 1 rle with new method : 0.6663787364959717 time for calcul the mask position with numpy : 0.04065203666687012 nb_pixel_total : 41735 time to create 1 rle with old method : 0.0498654842376709 time for calcul the mask position with numpy : 0.04231858253479004 nb_pixel_total : 55101 time to create 1 rle with old method : 0.06612753868103027 time for calcul the mask position with numpy : 0.040812015533447266 nb_pixel_total : 58173 time to create 1 rle with old method : 0.06991314888000488 time for calcul the mask position with numpy : 0.03974127769470215 nb_pixel_total : 28068 time to create 1 rle with old method : 0.03232765197753906 create new chi : 21.316499710083008 time to delete rle : 0.005846977233886719 batch 1 Loaded 74 chid ids of type : 4855 Number RLEs to save : 50151 TO DO : save crop sub photo not yet done ! save time : 3.9661991596221924 nb_obj : 6 nb_hashtags : 1 time to prepare the origin masks : 7.804553747177124 time for calcul the mask position with numpy : 0.060416460037231445 nb_pixel_total : 589853 time to create 1 rle with new method : 0.8779609203338623 time for calcul the mask position with numpy : 0.049060821533203125 nb_pixel_total : 236223 time to create 1 rle with new method : 0.9812383651733398 time for calcul the mask position with numpy : 0.029341936111450195 nb_pixel_total : 5390 time to create 1 rle with old method : 0.006379842758178711 time for calcul the mask position with numpy : 0.02983689308166504 nb_pixel_total : 94338 time to create 1 rle with old method : 0.11047935485839844 time for calcul the mask position with numpy : 0.03445625305175781 nb_pixel_total : 478151 time to create 1 rle with new method : 0.8897099494934082 time for calcul the mask position with numpy : 0.0480194091796875 nb_pixel_total : 70439 time to create 1 rle with old method : 0.08156204223632812 time for calcul the mask position with numpy : 0.5472571849822998 nb_pixel_total : 8260006 time to create 1 rle with new method : 0.9913744926452637 create new chi : 4.882891416549683 time to delete rle : 0.002054929733276367 batch 1 Loaded 7 chid ids of type : 4855 Number RLEs to save : 14364 TO DO : save crop sub photo not yet done ! save time : 0.7768909931182861 map_output_result : {1379878546: (0.49548873552156675, 'Should be the crop_list due to order', 0.35503017117540836), 1379878482: (0.49548873552156675, 'Should be the crop_list due to order', 0.7783479303508569), 1379878419: (0.49548873552156675, 'Should be the crop_list due to order', 0.5967862888913128), 1379878127: (0.49548873552156675, 'Should be the crop_list due to order', 0.4388413695389633), 1379878098: (0.49548873552156675, 'Should be the crop_list due to order', 0.7451191091754058), 1379878055: (0.49548873552156675, 'Should be the crop_list due to order', 0.6323841156711963), 1379878000: (0.49548873552156675, 'Should be the crop_list due to order', 0.49676260857388443), 1379877966: (0.49548873552156675, 'Should be the crop_list due to order', 0.4161270263170722), 1379877912: (0.49548873552156675, 'Should be the crop_list due to order', 0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1379878546, 1379878482, 1379878419, 1379878127, 1379878098, 1379878055, 1379878000, 1379877966, 1379877912] Looping around the photos to save general results len do output : 9 /1379878546.Didn't retrieve data . /1379878482.Didn't retrieve data . /1379878419.Didn't retrieve data . /1379878127.Didn't retrieve data . /1379878098.Didn't retrieve data . /1379878055.Didn't retrieve data . /1379878000.Didn't retrieve data . /1379877966.Didn't retrieve data . /1379877912.Didn't retrieve data . before output type Used above Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878546', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878482', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878419', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878127', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878098', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878055', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878000', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877966', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877912', None, None, None, None, None, '3646764') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 27 time used for this insertion : 0.019594430923461914 save_final save missing photos in datou_result : time spend for datou_step_exec : 467.47562050819397 time spend to save output : 0.020053863525390625 total time spend for step 5 : 467.49567437171936 step6:crop_condition Mon Sep 1 16:33:54 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4855 Loading chi in step crop for list_pids : 9 ! batch 1 Loaded 533 chid ids of type : 4855 begin to crop the class : papier param for this class : {'min_score': 0.1} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 74 About to insert : list_path_to_insert length 74 new photo from crops ! About to upload 74 photos upload in portfolio : 3015255 init cache_photo without model_param we have 74 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737295_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 74 photos in the portfolio 3015255 time of upload the photos Elapsed time : 20.99558448791504 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.1} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 65 About to insert : list_path_to_insert length 65 new photo from crops ! About to upload 65 photos upload in portfolio : 3015255 init cache_photo without model_param we have 65 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737345_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 65 photos in the portfolio 3015255 time of upload the photos Elapsed time : 17.190533876419067 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.1} filtre for class : metal hashtag_id of this class : 492628673 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 8 About to insert : list_path_to_insert length 8 new photo from crops ! About to upload 8 photos upload in portfolio : 3015255 init cache_photo without model_param we have 8 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737366_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 8 photos in the portfolio 3015255 time of upload the photos Elapsed time : 2.015878438949585 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.1} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 16 About to insert : list_path_to_insert length 16 new photo from crops ! About to upload 16 photos upload in portfolio : 3015255 init cache_photo without model_param we have 16 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737375_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 16 photos in the portfolio 3015255 time of upload the photos Elapsed time : 5.533473968505859 we have finished the crop for the class : pet_clair begin to crop the class : pehd param for this class : {'min_score': 0.1} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 3015255 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737384_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 4 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.171604871749878 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.1} filtre for class : pet_fonce hashtag_id of this class : 2107755900 Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 3015255 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737389_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 3 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.0765905380249023 we have finished the crop for the class : pet_fonce begin to crop the class : sac param for this class : {'min_score': 0.1} filtre for class : sac hashtag_id of this class : 492618350 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 40 About to insert : list_path_to_insert length 40 new photo from crops ! About to upload 40 photos upload in portfolio : 3015255 init cache_photo without model_param we have 40 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737410_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 40 photos in the portfolio 3015255 time of upload the photos Elapsed time : 9.750540256500244 we have finished the crop for the class : sac begin to crop the class : textiles param for this class : {'min_score': 0.1} filtre for class : textiles hashtag_id of this class : 494789423 Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! About to upload 5 photos upload in portfolio : 3015255 init cache_photo without model_param we have 5 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737422_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 5 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.4595777988433838 we have finished the crop for the class : textiles begin to crop the class : verre param for this class : {'min_score': 0.1} filtre for class : verre hashtag_id of this class : 492631919 map_result returned by crop_photo_return_map_crop : length : 0 About to insert : list_path_to_insert length 0 new photo from crops ! About to upload 0 photos WARNING : list_path_to_insert is empty, cannot upload ! we have finished the crop for the class : verre begin to crop the class : organique param for this class : {'min_score': 0.1} filtre for class : organique hashtag_id of this class : 530726390 begin to crop the class : dasri param for this class : {'min_score': 0.1} filtre for class : dasri hashtag_id of this class : 1608424396 begin to crop the class : masque param for this class : {'min_score': 0.1} filtre for class : masque hashtag_id of this class : 492626781 begin to crop the class : encombrant param for this class : {'min_score': 0.1} filtre for class : encombrant hashtag_id of this class : 605975549 begin to crop the class : autre param for this class : {'min_score': 0.1} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 88 About to insert : list_path_to_insert length 88 new photo from crops ! About to upload 88 photos upload in portfolio : 3015255 init cache_photo without model_param we have 88 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737520_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 88 photos in the portfolio 3015255 time of upload the photos Elapsed time : 23.922878742218018 we have finished the crop for the class : autre begin to crop the class : autre_emballage param for this class : {'min_score': 0.1} filtre for class : autre_emballage hashtag_id of this class : 2107760328 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3015255 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737547_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 3015255 time of upload the photos Elapsed time : 0.6098177433013916 we have finished the crop for the class : autre_emballage begin to crop the class : autre_non_emballage param for this class : {'min_score': 0.1} filtre for class : autre_non_emballage hashtag_id of this class : 2107760329 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 20 About to insert : list_path_to_insert length 20 new photo from crops ! About to upload 20 photos upload in portfolio : 3015255 init cache_photo without model_param we have 20 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737557_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 20 photos in the portfolio 3015255 time of upload the photos Elapsed time : 5.62457799911499 we have finished the crop for the class : autre_non_emballage begin to crop the class : environnement param for this class : {'min_score': 0.1} filtre for class : environnement hashtag_id of this class : 493012381 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 63 About to insert : list_path_to_insert length 63 new photo from crops ! About to upload 63 photos upload in portfolio : 3015255 init cache_photo without model_param we have 63 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756737677_28447 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 63 photos in the portfolio 3015255 time of upload the photos Elapsed time : 17.67026925086975 we have finished the crop for the class : environnement delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1379878546, 1379878482, 1379878419, 1379878127, 1379878098, 1379878055, 1379878000, 1379877966, 1379877912] Looping around the photos to save general results len do output : 387 /1380658560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380658854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659219Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659232Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659239Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659240Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659242Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380659531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1380660386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878546', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878482', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878419', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878127', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878098', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878055', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878000', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877966', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877912', None, None, None, None, None, '3646764') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1170 time used for this insertion : 0.09736466407775879 save_final save missing photos in datou_result : time spend for datou_step_exec : 464.10632705688477 time spend to save output : 0.11307930946350098 total time spend for step 6 : 464.21940636634827 step7:ventilate_hashtags_in_portfolio Mon Sep 1 16:41:39 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure beginning of datou step ventilate_hashtags_in_portfolio : To implement ! Iterating over portfolio : 26294096 get user id for portfolio 26294096 SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26294096 AND mptpi.`type`=4855 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26294096 AND mptpi.`type`=4855 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26294096 AND mptpi.`type`=4856 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26294096 AND mptpi.`type`=4856 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do lien utilise dans velours : https://marlene.fotonower.com/velours/26404611,26404612,26404613,26404614,26404615,26404620,26404622,26404623,26404624,26404625,26404626,26404627,26404629,26404630,26404632,26404633,26404634,26404635,26404636,26404637?tags=papier,carton,metal,pet_clair,pehd,ela,textiles,verre,organique,dasri,masque,encombrant,autre_non_emballage,environnement,autre,flux_dev,mal_croppe,flou,film_dev_souple,sac_om_plein&datou_id_consolidate=4742&port_consolidate=26294096 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1379878546, 1379878482, 1379878419, 1379878127, 1379878098, 1379878055, 1379878000, 1379877966, 1379877912] Looping around the photos to save general results len do output : 1 /26294096. before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878546', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878482', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878419', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878127', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878098', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878055', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878000', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877966', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877912', None, None, None, None, None, '3646764') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 10 time used for this insertion : 0.02195572853088379 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.5862998962402344 time spend to save output : 0.02223968505859375 total time spend for step 7 : 2.608539581298828 step8:final Mon Sep 1 16:41:41 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {1379878546: ('0.5637195716511032',), 1379878482: ('0.5637195716511032',), 1379878419: ('0.5637195716511032',), 1379878127: ('0.5637195716511032',), 1379878098: ('0.5637195716511032',), 1379878055: ('0.5637195716511032',), 1379878000: ('0.5637195716511032',), 1379877966: ('0.5637195716511032',), 1379877912: ('0.5637195716511032',)} new output for save of step final : {1379878546: ('0.5637195716511032',), 1379878482: ('0.5637195716511032',), 1379878419: ('0.5637195716511032',), 1379878127: ('0.5637195716511032',), 1379878098: ('0.5637195716511032',), 1379878055: ('0.5637195716511032',), 1379878000: ('0.5637195716511032',), 1379877966: ('0.5637195716511032',), 1379877912: ('0.5637195716511032',)} [1379878546, 1379878482, 1379878419, 1379878127, 1379878098, 1379878055, 1379878000, 1379877966, 1379877912] Looping around the photos to save general results len do output : 9 /1379878546.Didn't retrieve data . /1379878482.Didn't retrieve data . /1379878419.Didn't retrieve data . /1379878127.Didn't retrieve data . /1379878098.Didn't retrieve data . /1379878055.Didn't retrieve data . /1379878000.Didn't retrieve data . /1379877966.Didn't retrieve data . /1379877912.Didn't retrieve data . before output type Used above Used above Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878546', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878482', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878419', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878127', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878098', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878055', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878000', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877966', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877912', None, None, None, None, None, '3646764') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 27 time used for this insertion : 0.014615297317504883 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12645602226257324 time spend to save output : 0.015276670455932617 total time spend for step 8 : 0.14173269271850586 step9:velours_tree Mon Sep 1 16:41:41 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 0.44002342224121094 time spend to save output : 4.5299530029296875e-05 total time spend for step 9 : 0.44006872177124023 step10:send_mail_cod Mon Sep 1 16:41:42 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 complete output_args for input 2 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 3 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure dans la step send mail cod work_area: /home/admin/workarea/git/Velours/python in order to get the selector url, please entre the license of selector results_Auto_P26294096_01-09-2025_16_41_42.pdf 26404585 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264045851756737702 26404586 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264045861756737703 26404587 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264045871756737705 26404588 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264045881756737706 26404589 change filename to text .change filename to text .change filename to text .change filename to text .imagette264045891756737707 26404590 change filename to text .change filename to text .change filename to text .imagette264045901756737707 26404591 imagette264045911756737708 26404592 imagette264045921756737708 26404593 imagette264045931756737708 26404594 imagette264045941756737708 26404595 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264045951756737708 26404596 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264045961756737709 26404597 imagette264045971756737709 26404598 imagette264045981756737709 26404599 imagette264045991756737709 26404600 imagette264046001756737709 26404601 imagette264046011756737709 26404602 change filename to text .imagette264046021756737709 26404603 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264046031756737709 26404605 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette264046051756737711 26404606 imagette264046061756737713 26404607 imagette264046071756737713 26404608 imagette264046081756737713 26404609 imagette264046091756737713 26404610 imagette264046101756737713 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=26294096 and hashtag_type = 4855 and pcr.hashtag_id = h.hashtag_id; velour_link : https://marlene.fotonower.com/velours/26404611,26404612,26404613,26404614,26404615,26404620,26404622,26404623,26404624,26404625,26404626,26404627,26404629,26404630,26404632,26404633,26404634,26404635,26404636,26404637?tags=papier,carton,metal,pet_clair,pehd,ela,textiles,verre,organique,dasri,masque,encombrant,autre_non_emballage,environnement,autre,flux_dev,mal_croppe,flou,film_dev_souple,sac_om_plein&datou_id_consolidate=4742&port_consolidate=26294096 your option no_mail is active, we will not send the real mail to your client args[1379878546] : ((1379878546, 683.6998660822908, 492688767), (1379878546, -0.1391342396569396, 496442774), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379878482] : ((1379878482, 612.4246895947853, 492688767), (1379878482, -0.35707739142406314, 496442774), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379878419] : ((1379878419, 705.7067960964039, 492688767), (1379878419, -0.22093025146924944, 496442774), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379878127] : ((1379878127, 629.02646457505, 492688767), (1379878127, -0.22622095035483294, 496442774), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379878098] : ((1379878098, 561.9831727432334, 492688767), (1379878098, -0.17082922681524815, 496442774), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379878055] : ((1379878055, 525.5687653335234, 492688767), (1379878055, -0.4839999270052731, 501862349), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379878000] : ((1379878000, 212.01557136614971, 492688767), (1379878000, -0.4728954242036546, 496442774), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379877966] : ((1379877966, 894.2250352664202, 2107751945), (1379877966, -0.4348427730523465, 496442774), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379877912] : ((1379877912, 403.5308152980444, 492688767), (1379877912, -0.7723323617522398, 501862349), '0.5637195716511032') We are sending mail with results at report@fotonower.com,cod@fotonower.com refus_total : 0.5637195716511032 2022-04-13 10:29:59 0 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26294096_01-09-2025_16_41_42.pdf results_Auto_P26294096_01-09-2025_16_41_42.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26294096_01-09-2025_16_41_42.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4741','26294096','results_Auto_P26294096_01-09-2025_16_41_42.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26294096_01-09-2025_16_41_42.pdf','pdf','','2.1','0.5637195716511032') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1379878546, 1379878482, 1379878419, 1379878127, 1379878098, 1379878055, 1379878000, 1379877966, 1379877912] Looping around the photos to save general results len do output : 0 before output type Used above Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878546', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878482', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878419', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878127', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878098', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878055', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878000', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877966', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877912', None, None, None, None, None, '3646764') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 9 time used for this insertion : 0.022397279739379883 save_final save missing photos in datou_result : time spend for datou_step_exec : 14.852851390838623 time spend to save output : 0.02269768714904785 total time spend for step 10 : 14.875549077987671 step11:split_time_score Mon Sep 1 16:41:57 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 1 VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 861, 'mtr_user_id': 31, 'name': 'Rungis_class_dechets_1212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Rungis_Aluminium,Rungis_Carton,Rungis_Papier,Rungis_Plastique_clair,Rungis_Plastique_dur,Rungis_Plastique_fonce,Rungis_Tapis_vide,Rungis_Tetrapak', 'svm_portfolios_learning': '1160730,571842,571844,571839,571933,571840,571841,572307', 'photo_hashtag_type': 999, 'photo_desc_type': 3963, 'type_classification': 'caffe', 'hashtag_id_list': '2107751280,2107750907,2107750908,2107750909,2107750910,2107750911,2107750912,2107750913'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('15', 4), ('16', 4), ('17', 1)) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 28082025 26294096 Nombre de photos uploadées : 9 / 23040 (0%) 28082025 26294096 Nombre de photos taguées (types de déchets): 0 / 9 (0%) 28082025 26294096 Nombre de photos taguées (volume) : 0 / 9 (0%) elapsed_time : load_data_split_time_score 2.6226043701171875e-06 elapsed_time : order_list_meta_photo_and_scores 1.5020370483398438e-05 ????????? elapsed_time : fill_and_build_computed_from_old_data 0.0003459453582763672 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.20657658576965332 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.2808311243033833 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26292108_28-08-2025_13_56_43.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26292108 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26292108 AND mptpi.`type`=4855 To do Qualite : 0.45326993737877697 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26292109_01-09-2025_15_46_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26292109 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26292109 AND mptpi.`type`=4855 To do Qualite : 0.3235829256287251 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26292110_28-08-2025_13_18_58.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26292110 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26292110 AND mptpi.`type`=4855 To do Qualite : 0.5794230840386216 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26292111_28-08-2025_13_42_12.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26292111 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26292111 AND mptpi.`type`=4855 To do Qualite : 0.548860349869327 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26292112_28-08-2025_13_04_35.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26292112 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26292112 AND mptpi.`type`=4855 To do Qualite : 0.5637195716511032 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26294096_01-09-2025_16_41_42.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26294096 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26294096 AND mptpi.`type`=4855 To do Qualite : 0.2938870389409992 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26307203_28-08-2025_23_09_34.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26307203 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26307203 AND mptpi.`type`=4855 To do Qualite : 0.39387006977059996 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26307204_28-08-2025_22_48_52.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26307204 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=26307204 AND mptpi.`type`=4855 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'28082025': {'nb_upload': 9, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1379878546, 1379878482, 1379878419, 1379878127, 1379878098, 1379878055, 1379878000, 1379877966, 1379877912] Looping around the photos to save general results len do output : 1 /26294096Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878546', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878482', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878419', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878127', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878098', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878055', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379878000', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877966', None, None, None, None, None, '3646764') ('4741', None, None, None, None, None, None, None, '3646764') ('4741', '26294096', '1379877912', None, None, None, None, None, '3646764') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 10 time used for this insertion : 0.019583702087402344 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.8795173168182373 time spend to save output : 0.01977086067199707 total time spend for step 11 : 0.8992881774902344 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 9 set_done_treatment 803.90user 333.50system 20:33.86elapsed 92%CPU (0avgtext+0avgdata 7598896maxresident)k 3916832inputs+766024outputs (99788major+56036161minor)pagefaults 0swaps