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 : 3437029 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 updating current state to 1 list_input_json: [] Current got : datou_id : 4741, datou_cur_ids : ['3623725'] with mtr_portfolio_ids : ['26290977'] and first list_photo_ids : [] new path : /proc/3437029/ 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 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.7669558525085449 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 Thu Aug 28 12:01:31 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 : 10603 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 12:01:33.863472: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-08-28 12:01:33.873502: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 12:01:33.874967: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f55c0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 12:01:33.875013: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 12:01:33.877790: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 12:01:34.032438: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3c95d7b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 12:01:34.032504: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 12:01:34.033590: 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 2025-08-28 12:01:34.033952: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:01:34.036082: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:01:34.038276: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 12:01:34.038608: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 12:01:34.041357: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 12:01:34.043125: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 12:01:34.048748: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 12:01:34.050351: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 12:01:34.050457: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:01:34.051264: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 12:01:34.051280: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 12:01:34.051289: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 12:01:34.052624: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9821 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. 2025-08-28 12:01:34.323238: 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 2025-08-28 12:01:34.323344: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:01:34.323367: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:01:34.323388: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 12:01:34.323407: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 12:01:34.323426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 12:01:34.323445: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 12:01:34.323465: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 12:01:34.325072: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 12:01:34.326413: 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 2025-08-28 12:01:34.326450: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:01:34.326470: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:01:34.326489: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 12:01:34.326520: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 12:01:34.326540: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 12:01:34.326558: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 12:01:34.326577: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 12:01:34.328168: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 12:01:34.328200: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 12:01:34.328211: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 12:01:34.328221: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 12:01:34.329872: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9821 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 : [] 2025-08-28 12:01:44.923164: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:01:45.102704: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 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 : 4 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.60234 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 18 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 : 24 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: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 6 Detection mask done ! Trying to reset tf kernel 3437232 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5311 tf kernel not reseted sub process len(results) : 4 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 4 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 : 10603 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 : 0.003092527389526367 nb_pixel_total : 151368 time to create 1 rle with new method : 0.0065462589263916016 length of segment : 509 time for calcul the mask position with numpy : 0.027556180953979492 nb_pixel_total : 661029 time to create 1 rle with new method : 0.04452705383300781 length of segment : 529 time for calcul the mask position with numpy : 0.00044345855712890625 nb_pixel_total : 26065 time to create 1 rle with old method : 0.028719663619995117 length of segment : 193 time for calcul the mask position with numpy : 0.00018548965454101562 nb_pixel_total : 11076 time to create 1 rle with old method : 0.012006044387817383 length of segment : 144 time for calcul the mask position with numpy : 0.0005116462707519531 nb_pixel_total : 35905 time to create 1 rle with old method : 0.03905081748962402 length of segment : 249 time for calcul the mask position with numpy : 0.00032329559326171875 nb_pixel_total : 1852 time to create 1 rle with old method : 0.0023894309997558594 length of segment : 137 time for calcul the mask position with numpy : 0.0021445751190185547 nb_pixel_total : 157882 time to create 1 rle with new method : 0.005472898483276367 length of segment : 546 time for calcul the mask position with numpy : 0.0015523433685302734 nb_pixel_total : 60542 time to create 1 rle with old method : 0.06631898880004883 length of segment : 478 time for calcul the mask position with numpy : 0.00038552284240722656 nb_pixel_total : 21596 time to create 1 rle with old method : 0.02333664894104004 length of segment : 292 time for calcul the mask position with numpy : 0.0007352828979492188 nb_pixel_total : 38452 time to create 1 rle with old method : 0.043582916259765625 length of segment : 268 time for calcul the mask position with numpy : 0.001680612564086914 nb_pixel_total : 124332 time to create 1 rle with old method : 0.13489747047424316 length of segment : 369 time for calcul the mask position with numpy : 0.0005059242248535156 nb_pixel_total : 24554 time to create 1 rle with old method : 0.028368711471557617 length of segment : 216 time for calcul the mask position with numpy : 0.00023174285888671875 nb_pixel_total : 6430 time to create 1 rle with old method : 0.008021354675292969 length of segment : 158 time for calcul the mask position with numpy : 0.00021767616271972656 nb_pixel_total : 9099 time to create 1 rle with old method : 0.010231256484985352 length of segment : 146 time for calcul the mask position with numpy : 0.0005700588226318359 nb_pixel_total : 5311 time to create 1 rle with old method : 0.006262779235839844 length of segment : 111 time for calcul the mask position with numpy : 0.00043487548828125 nb_pixel_total : 27105 time to create 1 rle with old method : 0.030398845672607422 length of segment : 262 time for calcul the mask position with numpy : 0.0016748905181884766 nb_pixel_total : 123663 time to create 1 rle with old method : 0.13368868827819824 length of segment : 340 time for calcul the mask position with numpy : 0.0007042884826660156 nb_pixel_total : 35819 time to create 1 rle with old method : 0.0398862361907959 length of segment : 267 time for calcul the mask position with numpy : 0.00036978721618652344 nb_pixel_total : 4536 time to create 1 rle with old method : 0.005458831787109375 length of segment : 149 time for calcul the mask position with numpy : 0.0008082389831542969 nb_pixel_total : 48439 time to create 1 rle with old method : 0.05861544609069824 length of segment : 158 time for calcul the mask position with numpy : 0.008481025695800781 nb_pixel_total : 369298 time to create 1 rle with new method : 0.03863930702209473 length of segment : 653 time for calcul the mask position with numpy : 0.0008490085601806641 nb_pixel_total : 45053 time to create 1 rle with old method : 0.051996469497680664 length of segment : 178 time for calcul the mask position with numpy : 0.0022220611572265625 nb_pixel_total : 132558 time to create 1 rle with old method : 0.14057540893554688 length of segment : 503 time for calcul the mask position with numpy : 0.006558895111083984 nb_pixel_total : 141612 time to create 1 rle with old method : 0.1500539779663086 length of segment : 751 time for calcul the mask position with numpy : 0.0056304931640625 nb_pixel_total : 386800 time to create 1 rle with new method : 0.028406143188476562 length of segment : 648 time for calcul the mask position with numpy : 0.0002522468566894531 nb_pixel_total : 8675 time to create 1 rle with old method : 0.009591102600097656 length of segment : 175 time for calcul the mask position with numpy : 0.007792472839355469 nb_pixel_total : 450959 time to create 1 rle with new method : 0.03510761260986328 length of segment : 1120 time for calcul the mask position with numpy : 0.0009059906005859375 nb_pixel_total : 18143 time to create 1 rle with old method : 0.020214319229125977 length of segment : 231 time for calcul the mask position with numpy : 0.001954793930053711 nb_pixel_total : 25389 time to create 1 rle with old method : 0.02875208854675293 length of segment : 223 time for calcul the mask position with numpy : 0.0019199848175048828 nb_pixel_total : 54056 time to create 1 rle with old method : 0.05870461463928223 length of segment : 312 time for calcul the mask position with numpy : 0.0006062984466552734 nb_pixel_total : 14736 time to create 1 rle with old method : 0.016734838485717773 length of segment : 209 time for calcul the mask position with numpy : 0.0024771690368652344 nb_pixel_total : 78695 time to create 1 rle with old method : 0.08630990982055664 length of segment : 419 time for calcul the mask position with numpy : 0.001764059066772461 nb_pixel_total : 75916 time to create 1 rle with old method : 0.08127498626708984 length of segment : 447 time for calcul the mask position with numpy : 0.00026702880859375 nb_pixel_total : 12645 time to create 1 rle with old method : 0.013686180114746094 length of segment : 137 time for calcul the mask position with numpy : 0.0005779266357421875 nb_pixel_total : 12430 time to create 1 rle with old method : 0.013350486755371094 length of segment : 173 time for calcul the mask position with numpy : 0.00411224365234375 nb_pixel_total : 91330 time to create 1 rle with old method : 0.09895944595336914 length of segment : 682 time for calcul the mask position with numpy : 0.0007600784301757812 nb_pixel_total : 16316 time to create 1 rle with old method : 0.018059253692626953 length of segment : 260 time for calcul the mask position with numpy : 0.001220703125 nb_pixel_total : 27310 time to create 1 rle with old method : 0.03077983856201172 length of segment : 233 time for calcul the mask position with numpy : 0.002531290054321289 nb_pixel_total : 66047 time to create 1 rle with old method : 0.07063651084899902 length of segment : 392 time for calcul the mask position with numpy : 0.0036139488220214844 nb_pixel_total : 113061 time to create 1 rle with old method : 0.12271642684936523 length of segment : 559 time for calcul the mask position with numpy : 0.0003197193145751953 nb_pixel_total : 16637 time to create 1 rle with old method : 0.019748449325561523 length of segment : 200 time for calcul the mask position with numpy : 0.01204681396484375 nb_pixel_total : 425582 time to create 1 rle with new method : 0.04593348503112793 length of segment : 1041 time for calcul the mask position with numpy : 0.0008215904235839844 nb_pixel_total : 25399 time to create 1 rle with old method : 0.02739691734313965 length of segment : 204 time for calcul the mask position with numpy : 0.0006425380706787109 nb_pixel_total : 19690 time to create 1 rle with old method : 0.02110910415649414 length of segment : 225 time for calcul the mask position with numpy : 0.0007817745208740234 nb_pixel_total : 32496 time to create 1 rle with old method : 0.034972429275512695 length of segment : 206 time for calcul the mask position with numpy : 0.0008733272552490234 nb_pixel_total : 36079 time to create 1 rle with old method : 0.040468454360961914 length of segment : 255 time for calcul the mask position with numpy : 0.007999897003173828 nb_pixel_total : 258781 time to create 1 rle with new method : 0.02994823455810547 length of segment : 866 time for calcul the mask position with numpy : 0.004156351089477539 nb_pixel_total : 221017 time to create 1 rle with new method : 0.010951757431030273 length of segment : 701 time for calcul the mask position with numpy : 0.0007841587066650391 nb_pixel_total : 33601 time to create 1 rle with old method : 0.03831338882446289 length of segment : 220 time for calcul the mask position with numpy : 0.0006496906280517578 nb_pixel_total : 34044 time to create 1 rle with old method : 0.03744816780090332 length of segment : 383 time for calcul the mask position with numpy : 0.00420689582824707 nb_pixel_total : 307757 time to create 1 rle with new method : 0.007874250411987305 length of segment : 530 time for calcul the mask position with numpy : 0.0005843639373779297 nb_pixel_total : 31737 time to create 1 rle with old method : 0.03547954559326172 length of segment : 206 time for calcul the mask position with numpy : 0.002166748046875 nb_pixel_total : 147509 time to create 1 rle with old method : 0.16259765625 length of segment : 649 time for calcul the mask position with numpy : 0.0013544559478759766 nb_pixel_total : 38109 time to create 1 rle with old method : 0.04308485984802246 length of segment : 531 time for calcul the mask position with numpy : 0.00028777122497558594 nb_pixel_total : 7685 time to create 1 rle with old method : 0.011507034301757812 length of segment : 165 time for calcul the mask position with numpy : 0.0013654232025146484 nb_pixel_total : 32664 time to create 1 rle with old method : 0.035143136978149414 length of segment : 411 time for calcul the mask position with numpy : 0.4075944423675537 nb_pixel_total : 5668314 time to create 1 rle with new method : 0.33449411392211914 length of segment : 2103 time for calcul the mask position with numpy : 0.0004153251647949219 nb_pixel_total : 17349 time to create 1 rle with old method : 0.019266128540039062 length of segment : 139 time for calcul the mask position with numpy : 0.0257112979888916 nb_pixel_total : 1281722 time to create 1 rle with new method : 0.08870363235473633 length of segment : 2140 time for calcul the mask position with numpy : 0.014921426773071289 nb_pixel_total : 1372230 time to create 1 rle with new method : 0.06142234802246094 length of segment : 773 time for calcul the mask position with numpy : 0.005867481231689453 nb_pixel_total : 520064 time to create 1 rle with new method : 0.017597198486328125 length of segment : 609 time for calcul the mask position with numpy : 0.006915569305419922 nb_pixel_total : 553141 time to create 1 rle with new method : 0.01906871795654297 length of segment : 715 time spent for convertir_results : 9.890417575836182 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 62 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 48.05865502357483 time spend to save output : 1.57088041305542 total time spend for step 1 : 49.62953543663025 step2:mask_detect Thu Aug 28 12:02:20 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 : 10603 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 12:02:23.201955: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-08-28 12:02:23.229021: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 12:02:23.232080: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f55b4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 12:02:23.232187: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 12:02:23.236238: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 12:02:23.410118: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3dd513b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 12:02:23.410162: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 12:02:23.411533: 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 2025-08-28 12:02:23.411917: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:02:23.418653: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:02:23.421253: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 12:02:23.421727: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 12:02:23.424177: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 12:02:23.425414: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 12:02:23.430316: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 12:02:23.432052: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 12:02:23.432124: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:02:23.433055: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 12:02:23.433076: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 12:02:23.433086: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 12:02:23.434551: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9821 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. 2025-08-28 12:02:23.540193: 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 2025-08-28 12:02:23.540281: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:02:23.540305: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:02:23.540326: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 12:02:23.540368: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 12:02:23.540401: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 12:02:23.540423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 12:02:23.540444: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 12:02:23.542018: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 12:02:23.543255: 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 2025-08-28 12:02:23.543295: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 12:02:23.543318: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:02:23.543340: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 12:02:23.543362: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 12:02:23.543384: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 12:02:23.543406: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 12:02:23.543441: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 12:02:23.545030: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 12:02:23.545064: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 12:02:23.545073: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 12:02:23.545080: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 12:02:23.546387: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9821 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 : [] 2025-08-28 12:02:38.872788: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 12:02:39.046921: 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 : 4 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.60234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3120.00000 nb d'objets trouves : 64 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 : 96 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 : 80 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 : 5 Detection mask done ! Trying to reset tf kernel 3438406 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5311 tf kernel not reseted sub process len(results) : 4 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 4 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 : 10603 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 : 0.001249551773071289 nb_pixel_total : 28431 time to create 1 rle with old method : 0.03535151481628418 length of segment : 199 time for calcul the mask position with numpy : 0.022948503494262695 nb_pixel_total : 805357 time to create 1 rle with new method : 0.12009501457214355 length of segment : 564 time for calcul the mask position with numpy : 0.005917072296142578 nb_pixel_total : 334703 time to create 1 rle with new method : 0.020689010620117188 length of segment : 900 time for calcul the mask position with numpy : 0.0009458065032958984 nb_pixel_total : 43475 time to create 1 rle with old method : 0.04574894905090332 length of segment : 367 time for calcul the mask position with numpy : 0.0038819313049316406 nb_pixel_total : 243206 time to create 1 rle with new method : 0.010367155075073242 length of segment : 562 time for calcul the mask position with numpy : 0.00862431526184082 nb_pixel_total : 444438 time to create 1 rle with new method : 0.04004836082458496 length of segment : 906 time for calcul the mask position with numpy : 0.008499860763549805 nb_pixel_total : 315300 time to create 1 rle with new method : 0.025413036346435547 length of segment : 863 time for calcul the mask position with numpy : 0.004012346267700195 nb_pixel_total : 208391 time to create 1 rle with new method : 0.010571718215942383 length of segment : 542 time for calcul the mask position with numpy : 0.0014870166778564453 nb_pixel_total : 66060 time to create 1 rle with old method : 0.07603955268859863 length of segment : 376 time for calcul the mask position with numpy : 0.0008156299591064453 nb_pixel_total : 26829 time to create 1 rle with old method : 0.03370022773742676 length of segment : 254 time for calcul the mask position with numpy : 0.0005810260772705078 nb_pixel_total : 24699 time to create 1 rle with old method : 0.02953648567199707 length of segment : 208 time for calcul the mask position with numpy : 0.0002903938293457031 nb_pixel_total : 10589 time to create 1 rle with old method : 0.01351785659790039 length of segment : 96 time for calcul the mask position with numpy : 0.0035500526428222656 nb_pixel_total : 166098 time to create 1 rle with new method : 0.009799957275390625 length of segment : 542 time for calcul the mask position with numpy : 0.01067805290222168 nb_pixel_total : 401480 time to create 1 rle with new method : 0.047126054763793945 length of segment : 1054 time for calcul the mask position with numpy : 0.0003254413604736328 nb_pixel_total : 9805 time to create 1 rle with old method : 0.011858940124511719 length of segment : 114 time for calcul the mask position with numpy : 0.009430646896362305 nb_pixel_total : 123182 time to create 1 rle with old method : 0.17232799530029297 length of segment : 740 time for calcul the mask position with numpy : 0.004132747650146484 nb_pixel_total : 226779 time to create 1 rle with new method : 0.012331485748291016 length of segment : 531 time for calcul the mask position with numpy : 0.0028052330017089844 nb_pixel_total : 153676 time to create 1 rle with new method : 0.0073070526123046875 length of segment : 367 time for calcul the mask position with numpy : 0.0009722709655761719 nb_pixel_total : 43635 time to create 1 rle with old method : 0.05087113380432129 length of segment : 155 time for calcul the mask position with numpy : 0.00095367431640625 nb_pixel_total : 45293 time to create 1 rle with old method : 0.05235147476196289 length of segment : 234 time for calcul the mask position with numpy : 0.004488945007324219 nb_pixel_total : 188081 time to create 1 rle with new method : 0.011368274688720703 length of segment : 879 time for calcul the mask position with numpy : 0.0007851123809814453 nb_pixel_total : 31531 time to create 1 rle with old method : 0.03525042533874512 length of segment : 275 time for calcul the mask position with numpy : 0.0011343955993652344 nb_pixel_total : 53165 time to create 1 rle with old method : 0.06023001670837402 length of segment : 334 time for calcul the mask position with numpy : 0.0012946128845214844 nb_pixel_total : 72383 time to create 1 rle with old method : 0.08062624931335449 length of segment : 239 time for calcul the mask position with numpy : 0.0003063678741455078 nb_pixel_total : 10916 time to create 1 rle with old method : 0.012892007827758789 length of segment : 91 time for calcul the mask position with numpy : 0.002606630325317383 nb_pixel_total : 143174 time to create 1 rle with old method : 0.16316866874694824 length of segment : 407 time for calcul the mask position with numpy : 0.003659486770629883 nb_pixel_total : 179480 time to create 1 rle with new method : 0.00954580307006836 length of segment : 608 time for calcul the mask position with numpy : 0.00096893310546875 nb_pixel_total : 39827 time to create 1 rle with old method : 0.043755292892456055 length of segment : 256 time for calcul the mask position with numpy : 0.0012726783752441406 nb_pixel_total : 29682 time to create 1 rle with old method : 0.03343701362609863 length of segment : 282 time for calcul the mask position with numpy : 0.008075952529907227 nb_pixel_total : 228813 time to create 1 rle with new method : 0.02506709098815918 length of segment : 1247 time for calcul the mask position with numpy : 0.0043182373046875 nb_pixel_total : 188704 time to create 1 rle with new method : 0.011508941650390625 length of segment : 495 time for calcul the mask position with numpy : 0.003343820571899414 nb_pixel_total : 129815 time to create 1 rle with old method : 0.14638543128967285 length of segment : 435 time for calcul the mask position with numpy : 0.00034809112548828125 nb_pixel_total : 7660 time to create 1 rle with old method : 0.011382579803466797 length of segment : 98 time for calcul the mask position with numpy : 0.0006580352783203125 nb_pixel_total : 27238 time to create 1 rle with old method : 0.030406713485717773 length of segment : 207 time for calcul the mask position with numpy : 0.0024900436401367188 nb_pixel_total : 132947 time to create 1 rle with old method : 0.15658879280090332 length of segment : 434 time for calcul the mask position with numpy : 0.00115966796875 nb_pixel_total : 48527 time to create 1 rle with old method : 0.05565667152404785 length of segment : 298 time for calcul the mask position with numpy : 0.00018787384033203125 nb_pixel_total : 4387 time to create 1 rle with old method : 0.0051686763763427734 length of segment : 81 time for calcul the mask position with numpy : 0.00042939186096191406 nb_pixel_total : 18876 time to create 1 rle with old method : 0.024332761764526367 length of segment : 167 time for calcul the mask position with numpy : 0.0012607574462890625 nb_pixel_total : 69393 time to create 1 rle with old method : 0.07717132568359375 length of segment : 224 time for calcul the mask position with numpy : 0.0023229122161865234 nb_pixel_total : 118017 time to create 1 rle with old method : 0.13470053672790527 length of segment : 678 time for calcul the mask position with numpy : 0.003484010696411133 nb_pixel_total : 73794 time to create 1 rle with old method : 0.08007550239562988 length of segment : 1069 time for calcul the mask position with numpy : 0.0014081001281738281 nb_pixel_total : 54759 time to create 1 rle with old method : 0.06078290939331055 length of segment : 332 time for calcul the mask position with numpy : 0.020613670349121094 nb_pixel_total : 652834 time to create 1 rle with new method : 0.42751049995422363 length of segment : 1223 time for calcul the mask position with numpy : 0.0006601810455322266 nb_pixel_total : 31328 time to create 1 rle with old method : 0.035990238189697266 length of segment : 212 time for calcul the mask position with numpy : 0.0015721321105957031 nb_pixel_total : 85181 time to create 1 rle with old method : 0.09374570846557617 length of segment : 322 time for calcul the mask position with numpy : 0.0018472671508789062 nb_pixel_total : 82601 time to create 1 rle with old method : 0.09491515159606934 length of segment : 398 time for calcul the mask position with numpy : 0.0023546218872070312 nb_pixel_total : 71098 time to create 1 rle with old method : 0.07900595664978027 length of segment : 612 time for calcul the mask position with numpy : 0.0018575191497802734 nb_pixel_total : 87392 time to create 1 rle with old method : 0.09943461418151855 length of segment : 422 time for calcul the mask position with numpy : 0.0003285408020019531 nb_pixel_total : 13870 time to create 1 rle with old method : 0.016609907150268555 length of segment : 81 time for calcul the mask position with numpy : 0.002978801727294922 nb_pixel_total : 165547 time to create 1 rle with new method : 0.00841212272644043 length of segment : 476 time for calcul the mask position with numpy : 0.0003407001495361328 nb_pixel_total : 6976 time to create 1 rle with old method : 0.009820699691772461 length of segment : 186 time for calcul the mask position with numpy : 0.0016374588012695312 nb_pixel_total : 70993 time to create 1 rle with old method : 0.08129096031188965 length of segment : 432 time for calcul the mask position with numpy : 0.0001747608184814453 nb_pixel_total : 59 time to create 1 rle with old method : 0.0003294944763183594 length of segment : 36 time for calcul the mask position with numpy : 0.010615348815917969 nb_pixel_total : 498701 time to create 1 rle with new method : 0.051763296127319336 length of segment : 935 time for calcul the mask position with numpy : 0.004371166229248047 nb_pixel_total : 211622 time to create 1 rle with new method : 0.013299703598022461 length of segment : 502 time for calcul the mask position with numpy : 0.0010852813720703125 nb_pixel_total : 48271 time to create 1 rle with old method : 0.05441927909851074 length of segment : 269 time for calcul the mask position with numpy : 0.0012965202331542969 nb_pixel_total : 67905 time to create 1 rle with old method : 0.07544302940368652 length of segment : 226 time for calcul the mask position with numpy : 0.0011246204376220703 nb_pixel_total : 57177 time to create 1 rle with old method : 0.06271123886108398 length of segment : 447 time for calcul the mask position with numpy : 0.011445283889770508 nb_pixel_total : 531893 time to create 1 rle with new method : 0.7025439739227295 length of segment : 1484 time for calcul the mask position with numpy : 0.0009393692016601562 nb_pixel_total : 43718 time to create 1 rle with old method : 0.04933595657348633 length of segment : 284 time for calcul the mask position with numpy : 0.0020864009857177734 nb_pixel_total : 106438 time to create 1 rle with old method : 0.11941051483154297 length of segment : 342 time for calcul the mask position with numpy : 0.010962724685668945 nb_pixel_total : 406287 time to create 1 rle with new method : 0.32751035690307617 length of segment : 868 time for calcul the mask position with numpy : 0.0047740936279296875 nb_pixel_total : 136515 time to create 1 rle with old method : 0.17253947257995605 length of segment : 910 time for calcul the mask position with numpy : 0.012266397476196289 nb_pixel_total : 637479 time to create 1 rle with new method : 0.06377434730529785 length of segment : 2092 time for calcul the mask position with numpy : 0.0004410743713378906 nb_pixel_total : 17385 time to create 1 rle with old method : 0.01945781707763672 length of segment : 130 time for calcul the mask position with numpy : 0.0028848648071289062 nb_pixel_total : 123886 time to create 1 rle with old method : 0.1362760066986084 length of segment : 376 time for calcul the mask position with numpy : 0.00046563148498535156 nb_pixel_total : 16682 time to create 1 rle with old method : 0.019019603729248047 length of segment : 241 time for calcul the mask position with numpy : 0.003671407699584961 nb_pixel_total : 180225 time to create 1 rle with new method : 0.009957313537597656 length of segment : 412 time for calcul the mask position with numpy : 0.004106998443603516 nb_pixel_total : 172859 time to create 1 rle with new method : 0.011266946792602539 length of segment : 783 time for calcul the mask position with numpy : 0.0006427764892578125 nb_pixel_total : 21216 time to create 1 rle with old method : 0.025140047073364258 length of segment : 196 time for calcul the mask position with numpy : 0.012708902359008789 nb_pixel_total : 548379 time to create 1 rle with new method : 0.14821982383728027 length of segment : 1344 time for calcul the mask position with numpy : 0.0026254653930664062 nb_pixel_total : 132405 time to create 1 rle with old method : 0.15053009986877441 length of segment : 480 time for calcul the mask position with numpy : 0.0010979175567626953 nb_pixel_total : 31606 time to create 1 rle with old method : 0.03737759590148926 length of segment : 224 time for calcul the mask position with numpy : 0.0014431476593017578 nb_pixel_total : 44484 time to create 1 rle with old method : 0.06850886344909668 length of segment : 219 time for calcul the mask position with numpy : 0.0032300949096679688 nb_pixel_total : 141895 time to create 1 rle with old method : 0.15803909301757812 length of segment : 432 time for calcul the mask position with numpy : 0.0010409355163574219 nb_pixel_total : 26998 time to create 1 rle with old method : 0.030990123748779297 length of segment : 237 time for calcul the mask position with numpy : 0.0016047954559326172 nb_pixel_total : 63825 time to create 1 rle with old method : 0.07421517372131348 length of segment : 260 time for calcul the mask position with numpy : 0.004835605621337891 nb_pixel_total : 142324 time to create 1 rle with old method : 0.15748023986816406 length of segment : 529 time for calcul the mask position with numpy : 0.006354808807373047 nb_pixel_total : 301117 time to create 1 rle with new method : 0.018539905548095703 length of segment : 718 time for calcul the mask position with numpy : 0.0013365745544433594 nb_pixel_total : 49286 time to create 1 rle with old method : 0.053666114807128906 length of segment : 468 time for calcul the mask position with numpy : 0.0011510848999023438 nb_pixel_total : 41047 time to create 1 rle with old method : 0.04456686973571777 length of segment : 210 time for calcul the mask position with numpy : 0.006600141525268555 nb_pixel_total : 300784 time to create 1 rle with new method : 0.01667499542236328 length of segment : 568 time for calcul the mask position with numpy : 0.004629373550415039 nb_pixel_total : 170397 time to create 1 rle with new method : 0.013100862503051758 length of segment : 417 time for calcul the mask position with numpy : 0.0016341209411621094 nb_pixel_total : 72647 time to create 1 rle with old method : 0.09168839454650879 length of segment : 475 time for calcul the mask position with numpy : 0.000640869140625 nb_pixel_total : 29403 time to create 1 rle with old method : 0.03191804885864258 length of segment : 218 time for calcul the mask position with numpy : 0.023961782455444336 nb_pixel_total : 845624 time to create 1 rle with new method : 0.2073192596435547 length of segment : 1741 time for calcul the mask position with numpy : 0.0008544921875 nb_pixel_total : 18610 time to create 1 rle with old method : 0.021671056747436523 length of segment : 197 time for calcul the mask position with numpy : 0.002396821975708008 nb_pixel_total : 70857 time to create 1 rle with old method : 0.07965683937072754 length of segment : 479 time for calcul the mask position with numpy : 0.0004334449768066406 nb_pixel_total : 17021 time to create 1 rle with old method : 0.018596887588500977 length of segment : 147 time for calcul the mask position with numpy : 0.0017805099487304688 nb_pixel_total : 77411 time to create 1 rle with old method : 0.08707237243652344 length of segment : 436 time for calcul the mask position with numpy : 0.0012047290802001953 nb_pixel_total : 43186 time to create 1 rle with old method : 0.05003023147583008 length of segment : 435 time for calcul the mask position with numpy : 0.0014073848724365234 nb_pixel_total : 49803 time to create 1 rle with old method : 0.05581545829772949 length of segment : 324 time for calcul the mask position with numpy : 0.014020442962646484 nb_pixel_total : 569099 time to create 1 rle with new method : 0.07504868507385254 length of segment : 1031 time for calcul the mask position with numpy : 0.0010991096496582031 nb_pixel_total : 39691 time to create 1 rle with old method : 0.04297971725463867 length of segment : 174 time for calcul the mask position with numpy : 0.0005178451538085938 nb_pixel_total : 26109 time to create 1 rle with old method : 0.03931570053100586 length of segment : 119 time for calcul the mask position with numpy : 0.001789093017578125 nb_pixel_total : 62365 time to create 1 rle with old method : 0.0750734806060791 length of segment : 537 time for calcul the mask position with numpy : 0.00019431114196777344 nb_pixel_total : 6925 time to create 1 rle with old method : 0.0077495574951171875 length of segment : 60 time for calcul the mask position with numpy : 0.0006320476531982422 nb_pixel_total : 28355 time to create 1 rle with old method : 0.029881715774536133 length of segment : 237 time for calcul the mask position with numpy : 0.0011124610900878906 nb_pixel_total : 47199 time to create 1 rle with old method : 0.05105137825012207 length of segment : 244 time for calcul the mask position with numpy : 0.0012331008911132812 nb_pixel_total : 34806 time to create 1 rle with old method : 0.03894162178039551 length of segment : 219 time for calcul the mask position with numpy : 0.002345561981201172 nb_pixel_total : 101410 time to create 1 rle with old method : 0.10974311828613281 length of segment : 519 time for calcul the mask position with numpy : 0.007766008377075195 nb_pixel_total : 380181 time to create 1 rle with new method : 0.035696983337402344 length of segment : 908 time for calcul the mask position with numpy : 0.002611398696899414 nb_pixel_total : 69130 time to create 1 rle with old method : 0.07945036888122559 length of segment : 520 time for calcul the mask position with numpy : 0.00044035911560058594 nb_pixel_total : 13074 time to create 1 rle with old method : 0.014689922332763672 length of segment : 131 time for calcul the mask position with numpy : 0.0017940998077392578 nb_pixel_total : 79583 time to create 1 rle with old method : 0.08530044555664062 length of segment : 350 time for calcul the mask position with numpy : 0.0022335052490234375 nb_pixel_total : 32210 time to create 1 rle with old method : 0.03629040718078613 length of segment : 613 time for calcul the mask position with numpy : 0.0002789497375488281 nb_pixel_total : 5259 time to create 1 rle with old method : 0.0058917999267578125 length of segment : 125 time for calcul the mask position with numpy : 0.003363370895385742 nb_pixel_total : 135834 time to create 1 rle with old method : 0.14454221725463867 length of segment : 647 time for calcul the mask position with numpy : 0.0015709400177001953 nb_pixel_total : 68233 time to create 1 rle with old method : 0.076629638671875 length of segment : 374 time for calcul the mask position with numpy : 0.008543014526367188 nb_pixel_total : 270178 time to create 1 rle with new method : 0.02629876136779785 length of segment : 831 time for calcul the mask position with numpy : 0.0013103485107421875 nb_pixel_total : 49484 time to create 1 rle with old method : 0.05499982833862305 length of segment : 303 time for calcul the mask position with numpy : 0.0017549991607666016 nb_pixel_total : 77673 time to create 1 rle with old method : 0.08624720573425293 length of segment : 392 time for calcul the mask position with numpy : 0.0014181137084960938 nb_pixel_total : 33408 time to create 1 rle with old method : 0.038350582122802734 length of segment : 396 time for calcul the mask position with numpy : 0.0004534721374511719 nb_pixel_total : 12891 time to create 1 rle with old method : 0.0151824951171875 length of segment : 157 time for calcul the mask position with numpy : 0.011058807373046875 nb_pixel_total : 443276 time to create 1 rle with new method : 0.06354451179504395 length of segment : 770 time for calcul the mask position with numpy : 0.00041484832763671875 nb_pixel_total : 15807 time to create 1 rle with old method : 0.022496700286865234 length of segment : 120 time for calcul the mask position with numpy : 0.0005970001220703125 nb_pixel_total : 28416 time to create 1 rle with old method : 0.03233480453491211 length of segment : 209 time for calcul the mask position with numpy : 0.0011603832244873047 nb_pixel_total : 28604 time to create 1 rle with old method : 0.03217267990112305 length of segment : 351 time for calcul the mask position with numpy : 0.0006358623504638672 nb_pixel_total : 22927 time to create 1 rle with old method : 0.026535749435424805 length of segment : 167 time for calcul the mask position with numpy : 0.0016484260559082031 nb_pixel_total : 56604 time to create 1 rle with old method : 0.07027530670166016 length of segment : 423 time for calcul the mask position with numpy : 0.0024831295013427734 nb_pixel_total : 111066 time to create 1 rle with old method : 0.12098431587219238 length of segment : 386 time for calcul the mask position with numpy : 0.007653713226318359 nb_pixel_total : 321802 time to create 1 rle with new method : 0.023015260696411133 length of segment : 760 time for calcul the mask position with numpy : 0.0009222030639648438 nb_pixel_total : 34812 time to create 1 rle with old method : 0.039975643157958984 length of segment : 202 time for calcul the mask position with numpy : 0.0016164779663085938 nb_pixel_total : 51760 time to create 1 rle with old method : 0.05917954444885254 length of segment : 349 time for calcul the mask position with numpy : 0.00135040283203125 nb_pixel_total : 30889 time to create 1 rle with old method : 0.035791635513305664 length of segment : 301 time for calcul the mask position with numpy : 0.00033473968505859375 nb_pixel_total : 12338 time to create 1 rle with old method : 0.014424324035644531 length of segment : 203 time for calcul the mask position with numpy : 0.0003132820129394531 nb_pixel_total : 10854 time to create 1 rle with old method : 0.012566566467285156 length of segment : 100 time for calcul the mask position with numpy : 0.002557992935180664 nb_pixel_total : 120089 time to create 1 rle with old method : 0.1393260955810547 length of segment : 256 time for calcul the mask position with numpy : 0.0008909702301025391 nb_pixel_total : 34352 time to create 1 rle with old method : 0.03924751281738281 length of segment : 397 time for calcul the mask position with numpy : 0.0028340816497802734 nb_pixel_total : 131663 time to create 1 rle with old method : 0.15857505798339844 length of segment : 436 time for calcul the mask position with numpy : 0.003345966339111328 nb_pixel_total : 138216 time to create 1 rle with old method : 0.15018105506896973 length of segment : 599 time for calcul the mask position with numpy : 0.0005898475646972656 nb_pixel_total : 6690 time to create 1 rle with old method : 0.007575035095214844 length of segment : 240 time for calcul the mask position with numpy : 0.0021524429321289062 nb_pixel_total : 103766 time to create 1 rle with old method : 0.11617016792297363 length of segment : 455 time for calcul the mask position with numpy : 0.0004792213439941406 nb_pixel_total : 20413 time to create 1 rle with old method : 0.023359298706054688 length of segment : 201 time for calcul the mask position with numpy : 0.0005366802215576172 nb_pixel_total : 20825 time to create 1 rle with old method : 0.023653268814086914 length of segment : 172 time for calcul the mask position with numpy : 0.007230043411254883 nb_pixel_total : 357574 time to create 1 rle with new method : 0.020058631896972656 length of segment : 616 time for calcul the mask position with numpy : 0.006947755813598633 nb_pixel_total : 268004 time to create 1 rle with new method : 0.021699190139770508 length of segment : 985 time for calcul the mask position with numpy : 0.0010592937469482422 nb_pixel_total : 30626 time to create 1 rle with old method : 0.03383445739746094 length of segment : 247 time for calcul the mask position with numpy : 0.0013659000396728516 nb_pixel_total : 59797 time to create 1 rle with old method : 0.06378602981567383 length of segment : 386 time for calcul the mask position with numpy : 0.0005407333374023438 nb_pixel_total : 28587 time to create 1 rle with old method : 0.03186345100402832 length of segment : 212 time for calcul the mask position with numpy : 0.0012607574462890625 nb_pixel_total : 58613 time to create 1 rle with old method : 0.0671384334564209 length of segment : 482 time for calcul the mask position with numpy : 0.012609720230102539 nb_pixel_total : 284889 time to create 1 rle with new method : 0.04395723342895508 length of segment : 990 time for calcul the mask position with numpy : 0.0003592967987060547 nb_pixel_total : 14241 time to create 1 rle with old method : 0.01654338836669922 length of segment : 123 time for calcul the mask position with numpy : 0.0005087852478027344 nb_pixel_total : 8599 time to create 1 rle with old method : 0.010290384292602539 length of segment : 182 time for calcul the mask position with numpy : 0.0008828639984130859 nb_pixel_total : 26688 time to create 1 rle with old method : 0.02939629554748535 length of segment : 531 time for calcul the mask position with numpy : 0.0010387897491455078 nb_pixel_total : 34557 time to create 1 rle with old method : 0.039612531661987305 length of segment : 212 time for calcul the mask position with numpy : 0.0011239051818847656 nb_pixel_total : 50723 time to create 1 rle with old method : 0.05623817443847656 length of segment : 153 time for calcul the mask position with numpy : 0.0026564598083496094 nb_pixel_total : 131511 time to create 1 rle with old method : 0.14112043380737305 length of segment : 450 time for calcul the mask position with numpy : 0.0004582405090332031 nb_pixel_total : 20506 time to create 1 rle with old method : 0.022423505783081055 length of segment : 159 time for calcul the mask position with numpy : 0.007419586181640625 nb_pixel_total : 367100 time to create 1 rle with new method : 0.022188901901245117 length of segment : 681 time for calcul the mask position with numpy : 0.0036759376525878906 nb_pixel_total : 166312 time to create 1 rle with new method : 0.010917901992797852 length of segment : 522 time for calcul the mask position with numpy : 0.0010771751403808594 nb_pixel_total : 38491 time to create 1 rle with old method : 0.04320216178894043 length of segment : 214 time for calcul the mask position with numpy : 0.0012941360473632812 nb_pixel_total : 57329 time to create 1 rle with old method : 0.06487083435058594 length of segment : 357 time for calcul the mask position with numpy : 0.0010797977447509766 nb_pixel_total : 40876 time to create 1 rle with old method : 0.04926443099975586 length of segment : 148 time for calcul the mask position with numpy : 0.0005679130554199219 nb_pixel_total : 18985 time to create 1 rle with old method : 0.021900177001953125 length of segment : 175 time for calcul the mask position with numpy : 0.001550436019897461 nb_pixel_total : 30535 time to create 1 rle with old method : 0.03369712829589844 length of segment : 480 time for calcul the mask position with numpy : 0.003541707992553711 nb_pixel_total : 131171 time to create 1 rle with old method : 0.1467297077178955 length of segment : 682 time for calcul the mask position with numpy : 0.0018186569213867188 nb_pixel_total : 48527 time to create 1 rle with old method : 0.0554499626159668 length of segment : 301 time for calcul the mask position with numpy : 0.0007891654968261719 nb_pixel_total : 25703 time to create 1 rle with old method : 0.02915477752685547 length of segment : 181 time for calcul the mask position with numpy : 0.003142833709716797 nb_pixel_total : 157159 time to create 1 rle with new method : 0.009067773818969727 length of segment : 500 time for calcul the mask position with numpy : 0.004781007766723633 nb_pixel_total : 242949 time to create 1 rle with new method : 0.012420892715454102 length of segment : 806 time for calcul the mask position with numpy : 0.012354135513305664 nb_pixel_total : 538973 time to create 1 rle with new method : 0.028468847274780273 length of segment : 872 time for calcul the mask position with numpy : 0.0007574558258056641 nb_pixel_total : 34705 time to create 1 rle with old method : 0.03909873962402344 length of segment : 237 time for calcul the mask position with numpy : 0.0023040771484375 nb_pixel_total : 133246 time to create 1 rle with old method : 0.14549565315246582 length of segment : 375 time for calcul the mask position with numpy : 0.00036978721618652344 nb_pixel_total : 14953 time to create 1 rle with old method : 0.017084598541259766 length of segment : 133 time for calcul the mask position with numpy : 0.0019507408142089844 nb_pixel_total : 61741 time to create 1 rle with old method : 0.06944561004638672 length of segment : 311 time for calcul the mask position with numpy : 0.0005054473876953125 nb_pixel_total : 21733 time to create 1 rle with old method : 0.02400493621826172 length of segment : 183 time for calcul the mask position with numpy : 0.0024166107177734375 nb_pixel_total : 105324 time to create 1 rle with old method : 0.11825108528137207 length of segment : 395 time for calcul the mask position with numpy : 0.009882211685180664 nb_pixel_total : 413101 time to create 1 rle with new method : 0.025437355041503906 length of segment : 923 time for calcul the mask position with numpy : 0.002395153045654297 nb_pixel_total : 105208 time to create 1 rle with old method : 0.11428332328796387 length of segment : 556 time for calcul the mask position with numpy : 0.0033750534057617188 nb_pixel_total : 201821 time to create 1 rle with new method : 0.009684562683105469 length of segment : 869 time for calcul the mask position with numpy : 0.0028371810913085938 nb_pixel_total : 103941 time to create 1 rle with old method : 0.11452007293701172 length of segment : 434 time for calcul the mask position with numpy : 0.002650022506713867 nb_pixel_total : 89843 time to create 1 rle with old method : 0.095611572265625 length of segment : 437 time for calcul the mask position with numpy : 0.0003390312194824219 nb_pixel_total : 13467 time to create 1 rle with old method : 0.014766931533813477 length of segment : 194 time for calcul the mask position with numpy : 0.0012748241424560547 nb_pixel_total : 36126 time to create 1 rle with old method : 0.0418858528137207 length of segment : 257 time for calcul the mask position with numpy : 0.008651971817016602 nb_pixel_total : 450003 time to create 1 rle with new method : 0.02319502830505371 length of segment : 1050 time for calcul the mask position with numpy : 0.00580906867980957 nb_pixel_total : 343494 time to create 1 rle with new method : 0.013807296752929688 length of segment : 712 time for calcul the mask position with numpy : 0.000728607177734375 nb_pixel_total : 28725 time to create 1 rle with old method : 0.03194427490234375 length of segment : 288 time for calcul the mask position with numpy : 0.0018467903137207031 nb_pixel_total : 80707 time to create 1 rle with old method : 0.08749699592590332 length of segment : 324 time for calcul the mask position with numpy : 0.0008294582366943359 nb_pixel_total : 35131 time to create 1 rle with old method : 0.03900408744812012 length of segment : 213 time for calcul the mask position with numpy : 0.0014019012451171875 nb_pixel_total : 57715 time to create 1 rle with old method : 0.06178617477416992 length of segment : 307 time for calcul the mask position with numpy : 0.0019440650939941406 nb_pixel_total : 68846 time to create 1 rle with old method : 0.0782613754272461 length of segment : 264 time for calcul the mask position with numpy : 0.0033452510833740234 nb_pixel_total : 99397 time to create 1 rle with old method : 0.1370525360107422 length of segment : 491 time for calcul the mask position with numpy : 0.0012822151184082031 nb_pixel_total : 47614 time to create 1 rle with old method : 0.054818153381347656 length of segment : 275 time for calcul the mask position with numpy : 0.0011277198791503906 nb_pixel_total : 36105 time to create 1 rle with old method : 0.04092121124267578 length of segment : 203 time for calcul the mask position with numpy : 0.0013921260833740234 nb_pixel_total : 55166 time to create 1 rle with old method : 0.06100606918334961 length of segment : 379 time for calcul the mask position with numpy : 0.0017862319946289062 nb_pixel_total : 86743 time to create 1 rle with old method : 0.09613323211669922 length of segment : 276 time for calcul the mask position with numpy : 0.0035986900329589844 nb_pixel_total : 129895 time to create 1 rle with old method : 0.13926196098327637 length of segment : 606 time for calcul the mask position with numpy : 0.006804227828979492 nb_pixel_total : 284606 time to create 1 rle with new method : 0.020804643630981445 length of segment : 779 time for calcul the mask position with numpy : 0.005245685577392578 nb_pixel_total : 322543 time to create 1 rle with new method : 0.012896060943603516 length of segment : 519 time for calcul the mask position with numpy : 0.002215147018432617 nb_pixel_total : 111412 time to create 1 rle with old method : 0.11863851547241211 length of segment : 245 time for calcul the mask position with numpy : 0.009085655212402344 nb_pixel_total : 348026 time to create 1 rle with new method : 0.027835845947265625 length of segment : 671 time for calcul the mask position with numpy : 0.0008137226104736328 nb_pixel_total : 28563 time to create 1 rle with old method : 0.03309965133666992 length of segment : 229 time for calcul the mask position with numpy : 0.001033782958984375 nb_pixel_total : 47626 time to create 1 rle with old method : 0.05131244659423828 length of segment : 227 time for calcul the mask position with numpy : 0.003155231475830078 nb_pixel_total : 101767 time to create 1 rle with old method : 0.1084291934967041 length of segment : 362 time for calcul the mask position with numpy : 0.014371871948242188 nb_pixel_total : 574771 time to create 1 rle with new method : 0.18244290351867676 length of segment : 1124 time for calcul the mask position with numpy : 0.001384735107421875 nb_pixel_total : 59944 time to create 1 rle with old method : 0.06491422653198242 length of segment : 398 time for calcul the mask position with numpy : 0.0009021759033203125 nb_pixel_total : 46291 time to create 1 rle with old method : 0.04973626136779785 length of segment : 246 time for calcul the mask position with numpy : 0.0006797313690185547 nb_pixel_total : 24639 time to create 1 rle with old method : 0.02732086181640625 length of segment : 203 time for calcul the mask position with numpy : 0.0012199878692626953 nb_pixel_total : 71027 time to create 1 rle with old method : 0.07414627075195312 length of segment : 403 time for calcul the mask position with numpy : 0.0017619132995605469 nb_pixel_total : 74697 time to create 1 rle with old method : 0.08039498329162598 length of segment : 442 time for calcul the mask position with numpy : 0.008413076400756836 nb_pixel_total : 316648 time to create 1 rle with new method : 0.04575347900390625 length of segment : 1057 time for calcul the mask position with numpy : 0.0018873214721679688 nb_pixel_total : 80287 time to create 1 rle with old method : 0.08759331703186035 length of segment : 278 time for calcul the mask position with numpy : 0.00337982177734375 nb_pixel_total : 164904 time to create 1 rle with new method : 0.009560346603393555 length of segment : 719 time for calcul the mask position with numpy : 0.002641439437866211 nb_pixel_total : 118346 time to create 1 rle with old method : 0.12897777557373047 length of segment : 672 time for calcul the mask position with numpy : 0.0022907257080078125 nb_pixel_total : 117857 time to create 1 rle with old method : 0.12563586235046387 length of segment : 443 time for calcul the mask position with numpy : 0.00030875205993652344 nb_pixel_total : 12111 time to create 1 rle with old method : 0.013582944869995117 length of segment : 96 time for calcul the mask position with numpy : 0.0007424354553222656 nb_pixel_total : 33948 time to create 1 rle with old method : 0.03630852699279785 length of segment : 233 time for calcul the mask position with numpy : 0.002007007598876953 nb_pixel_total : 100181 time to create 1 rle with old method : 0.12085890769958496 length of segment : 366 time for calcul the mask position with numpy : 0.0010399818420410156 nb_pixel_total : 45889 time to create 1 rle with old method : 0.052107810974121094 length of segment : 448 time for calcul the mask position with numpy : 0.0002803802490234375 nb_pixel_total : 7725 time to create 1 rle with old method : 0.008859634399414062 length of segment : 108 time for calcul the mask position with numpy : 0.0013751983642578125 nb_pixel_total : 45131 time to create 1 rle with old method : 0.04965043067932129 length of segment : 550 time for calcul the mask position with numpy : 0.0015909671783447266 nb_pixel_total : 53414 time to create 1 rle with old method : 0.05706501007080078 length of segment : 327 time for calcul the mask position with numpy : 0.0019578933715820312 nb_pixel_total : 92651 time to create 1 rle with old method : 0.1000525951385498 length of segment : 284 time for calcul the mask position with numpy : 0.0012645721435546875 nb_pixel_total : 60620 time to create 1 rle with old method : 0.06511878967285156 length of segment : 255 time for calcul the mask position with numpy : 0.0008826255798339844 nb_pixel_total : 33900 time to create 1 rle with old method : 0.03812694549560547 length of segment : 203 time for calcul the mask position with numpy : 0.0013921260833740234 nb_pixel_total : 73562 time to create 1 rle with old method : 0.08082985877990723 length of segment : 309 time for calcul the mask position with numpy : 0.0038373470306396484 nb_pixel_total : 208342 time to create 1 rle with new method : 0.010961532592773438 length of segment : 882 time for calcul the mask position with numpy : 0.002042531967163086 nb_pixel_total : 91484 time to create 1 rle with old method : 0.10354423522949219 length of segment : 402 time for calcul the mask position with numpy : 0.0006430149078369141 nb_pixel_total : 33413 time to create 1 rle with old method : 0.03626823425292969 length of segment : 211 time for calcul the mask position with numpy : 0.000255584716796875 nb_pixel_total : 10566 time to create 1 rle with old method : 0.012020349502563477 length of segment : 127 time for calcul the mask position with numpy : 0.005049228668212891 nb_pixel_total : 175575 time to create 1 rle with new method : 0.015717267990112305 length of segment : 922 time for calcul the mask position with numpy : 0.0011975765228271484 nb_pixel_total : 55736 time to create 1 rle with old method : 0.07564544677734375 length of segment : 181 time for calcul the mask position with numpy : 0.0006434917449951172 nb_pixel_total : 21127 time to create 1 rle with old method : 0.027822017669677734 length of segment : 172 time for calcul the mask position with numpy : 0.001667022705078125 nb_pixel_total : 65048 time to create 1 rle with old method : 0.07116556167602539 length of segment : 249 time for calcul the mask position with numpy : 0.0013034343719482422 nb_pixel_total : 63154 time to create 1 rle with old method : 0.08375000953674316 length of segment : 315 time for calcul the mask position with numpy : 0.0009844303131103516 nb_pixel_total : 46515 time to create 1 rle with old method : 0.05137014389038086 length of segment : 460 time for calcul the mask position with numpy : 0.011224985122680664 nb_pixel_total : 403201 time to create 1 rle with new method : 0.05101132392883301 length of segment : 1394 time for calcul the mask position with numpy : 0.0015964508056640625 nb_pixel_total : 58544 time to create 1 rle with old method : 0.06201314926147461 length of segment : 165 time for calcul the mask position with numpy : 0.0016145706176757812 nb_pixel_total : 58625 time to create 1 rle with old method : 0.060194969177246094 length of segment : 371 time for calcul the mask position with numpy : 0.0031557083129882812 nb_pixel_total : 168100 time to create 1 rle with new method : 0.009287118911743164 length of segment : 1123 time for calcul the mask position with numpy : 0.0005786418914794922 nb_pixel_total : 23181 time to create 1 rle with old method : 0.024859905242919922 length of segment : 202 time for calcul the mask position with numpy : 0.0014314651489257812 nb_pixel_total : 58275 time to create 1 rle with old method : 0.06270909309387207 length of segment : 306 time for calcul the mask position with numpy : 0.0007658004760742188 nb_pixel_total : 25469 time to create 1 rle with old method : 0.02908039093017578 length of segment : 188 time for calcul the mask position with numpy : 0.002077817916870117 nb_pixel_total : 83471 time to create 1 rle with old method : 0.08885669708251953 length of segment : 288 time for calcul the mask position with numpy : 0.001018524169921875 nb_pixel_total : 32006 time to create 1 rle with old method : 0.03405404090881348 length of segment : 212 time for calcul the mask position with numpy : 0.001543283462524414 nb_pixel_total : 64626 time to create 1 rle with old method : 0.06908559799194336 length of segment : 241 time for calcul the mask position with numpy : 0.000997304916381836 nb_pixel_total : 42813 time to create 1 rle with old method : 0.045493364334106445 length of segment : 223 time for calcul the mask position with numpy : 0.003864288330078125 nb_pixel_total : 153563 time to create 1 rle with new method : 0.01190328598022461 length of segment : 719 time for calcul the mask position with numpy : 0.0023779869079589844 nb_pixel_total : 138433 time to create 1 rle with old method : 0.1493360996246338 length of segment : 454 time for calcul the mask position with numpy : 0.20554542541503906 nb_pixel_total : 4771892 time to create 1 rle with new method : 0.6934356689453125 length of segment : 3196 time for calcul the mask position with numpy : 0.000347137451171875 nb_pixel_total : 22676 time to create 1 rle with old method : 0.026485443115234375 length of segment : 162 time for calcul the mask position with numpy : 0.15762019157409668 nb_pixel_total : 2881772 time to create 1 rle with new method : 0.43141984939575195 length of segment : 1696 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0013048648834228516 length of segment : 44 time for calcul the mask position with numpy : 0.0003104209899902344 nb_pixel_total : 19047 time to create 1 rle with old method : 0.021054506301879883 length of segment : 207 time spent for convertir_results : 36.89065885543823 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 307 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 102.29562997817993 time spend to save output : 3.2802724838256836 total time spend for step 2 : 105.57590246200562 step3:blur_detection Thu Aug 28 12:04:06 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) 526.6879437976122 (3120, 3120) 634.390056119049 (3120, 3120) 526.3504021908315 (3120, 3120) 154.10252365459004 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 : 4 time used for this insertion : 0.018038511276245117 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.016013383865356445 save missing photos in datou_result : time spend for datou_step_exec : 1.1550214290618896 time spend to save output : 0.039014339447021484 total time spend for step 3 : 1.1940357685089111 step4:brightness Thu Aug 28 12:04:07 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 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/1756375290_3437029_1379844365_ac2d295be2bc98b78b3f3eefaeec5780.jpg treat image : temp/1756375290_3437029_1379844317_fb5f738493fd3292994218e2116fb3f2.jpg treat image : temp/1756375290_3437029_1379844257_71fb3e5d95f697a1d8d4bf6d4a466a3e.jpg treat image : temp/1756375290_3437029_1379844188_79ca3702f2c0f9186f8936992c4f3dc0.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 : 4 time used for this insertion : 0.015419483184814453 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.03112506866455078 save missing photos in datou_result : time spend for datou_step_exec : 4.6484808921813965 time spend to save output : 0.051050424575805664 total time spend for step 4 : 4.699531316757202 step5:rle_unique_nms_with_priority Thu Aug 28 12:04:12 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 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 307 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 81 nb_hashtags : 12 time to prepare the origin masks : 47.053640604019165 time for calcul the mask position with numpy : 0.7781357765197754 nb_pixel_total : 2346805 time to create 1 rle with new method : 2.2983238697052 time for calcul the mask position with numpy : 0.0480496883392334 nb_pixel_total : 804857 time to create 1 rle with new method : 0.8183748722076416 time for calcul the mask position with numpy : 0.0386960506439209 nb_pixel_total : 4385 time to create 1 rle with old method : 0.0048983097076416016 time for calcul the mask position with numpy : 0.038704872131347656 nb_pixel_total : 2541 time to create 1 rle with old method : 0.002887725830078125 time for calcul the mask position with numpy : 0.03944659233093262 nb_pixel_total : 97097 time to create 1 rle with old method : 0.10264801979064941 time for calcul the mask position with numpy : 0.038591623306274414 nb_pixel_total : 151153 time to create 1 rle with new method : 1.1274242401123047 time for calcul the mask position with numpy : 0.03949856758117676 nb_pixel_total : 31457 time to create 1 rle with old method : 0.03393697738647461 time for calcul the mask position with numpy : 0.0393521785736084 nb_pixel_total : 68754 time to create 1 rle with old method : 0.07369303703308105 time for calcul the mask position with numpy : 0.040235042572021484 nb_pixel_total : 44758 time to create 1 rle with old method : 0.04975533485412598 time for calcul the mask position with numpy : 0.03861355781555176 nb_pixel_total : 10460 time to create 1 rle with old method : 0.011071205139160156 time for calcul the mask position with numpy : 0.03798937797546387 nb_pixel_total : 38349 time to create 1 rle with old method : 0.04105114936828613 time for calcul the mask position with numpy : 0.0401153564453125 nb_pixel_total : 137335 time to create 1 rle with old method : 0.14758539199829102 time for calcul the mask position with numpy : 0.040442705154418945 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007383823394775391 time for calcul the mask position with numpy : 0.040986061096191406 nb_pixel_total : 226256 time to create 1 rle with new method : 0.9288375377655029 time for calcul the mask position with numpy : 0.039505958557128906 nb_pixel_total : 197167 time to create 1 rle with new method : 0.9725852012634277 time for calcul the mask position with numpy : 0.03916645050048828 nb_pixel_total : 6938 time to create 1 rle with old method : 0.007459878921508789 time for calcul the mask position with numpy : 0.03838753700256348 nb_pixel_total : 10406 time to create 1 rle with old method : 0.011865615844726562 time for calcul the mask position with numpy : 0.03855323791503906 nb_pixel_total : 100033 time to create 1 rle with old method : 0.10652303695678711 time for calcul the mask position with numpy : 0.03856015205383301 nb_pixel_total : 43591 time to create 1 rle with old method : 0.04490947723388672 time for calcul the mask position with numpy : 0.03857111930847168 nb_pixel_total : 25944 time to create 1 rle with old method : 0.028080224990844727 time for calcul the mask position with numpy : 0.03796052932739258 nb_pixel_total : 18835 time to create 1 rle with old method : 0.019951820373535156 time for calcul the mask position with numpy : 0.03862500190734863 nb_pixel_total : 11048 time to create 1 rle with old method : 0.011795759201049805 time for calcul the mask position with numpy : 0.038452863693237305 nb_pixel_total : 21584 time to create 1 rle with old method : 0.023633241653442383 time for calcul the mask position with numpy : 0.03955411911010742 nb_pixel_total : 124099 time to create 1 rle with old method : 0.1333458423614502 time for calcul the mask position with numpy : 0.03924202919006348 nb_pixel_total : 9204 time to create 1 rle with old method : 0.010437726974487305 time for calcul the mask position with numpy : 0.037290096282958984 nb_pixel_total : 81213 time to create 1 rle with old method : 0.08575677871704102 time for calcul the mask position with numpy : 0.03783559799194336 nb_pixel_total : 4715 time to create 1 rle with old method : 0.006101846694946289 time for calcul the mask position with numpy : 0.040662288665771484 nb_pixel_total : 1870 time to create 1 rle with old method : 0.002051830291748047 time for calcul the mask position with numpy : 0.03762531280517578 nb_pixel_total : 9344 time to create 1 rle with old method : 0.010210037231445312 time for calcul the mask position with numpy : 0.040112972259521484 nb_pixel_total : 257590 time to create 1 rle with new method : 1.3851780891418457 time for calcul the mask position with numpy : 0.0402679443359375 nb_pixel_total : 165516 time to create 1 rle with new method : 0.7466259002685547 time for calcul the mask position with numpy : 0.03871273994445801 nb_pixel_total : 31455 time to create 1 rle with old method : 0.0366666316986084 time for calcul the mask position with numpy : 0.04324007034301758 nb_pixel_total : 53060 time to create 1 rle with old method : 0.06014275550842285 time for calcul the mask position with numpy : 0.03937387466430664 nb_pixel_total : 188215 time to create 1 rle with new method : 0.611032247543335 time for calcul the mask position with numpy : 0.03721022605895996 nb_pixel_total : 2707 time to create 1 rle with old method : 0.0032138824462890625 time for calcul the mask position with numpy : 0.03766822814941406 nb_pixel_total : 25382 time to create 1 rle with old method : 0.02752089500427246 time for calcul the mask position with numpy : 0.03874659538269043 nb_pixel_total : 107301 time to create 1 rle with old method : 0.11561870574951172 time for calcul the mask position with numpy : 0.03847956657409668 nb_pixel_total : 51305 time to create 1 rle with old method : 0.053733110427856445 time for calcul the mask position with numpy : 0.03843045234680176 nb_pixel_total : 42985 time to create 1 rle with old method : 0.044695377349853516 time for calcul the mask position with numpy : 0.037810325622558594 nb_pixel_total : 9061 time to create 1 rle with old method : 0.009297847747802734 time for calcul the mask position with numpy : 0.037878990173339844 nb_pixel_total : 207931 time to create 1 rle with new method : 0.6041762828826904 time for calcul the mask position with numpy : 0.04056859016418457 nb_pixel_total : 532714 time to create 1 rle with new method : 0.6818554401397705 time for calcul the mask position with numpy : 0.0386204719543457 nb_pixel_total : 28324 time to create 1 rle with old method : 0.02982020378112793 time for calcul the mask position with numpy : 0.036925554275512695 nb_pixel_total : 4368 time to create 1 rle with old method : 0.0045659542083740234 time for calcul the mask position with numpy : 0.03681302070617676 nb_pixel_total : 15012 time to create 1 rle with old method : 0.01600956916809082 time for calcul the mask position with numpy : 0.03746342658996582 nb_pixel_total : 71158 time to create 1 rle with old method : 0.07344222068786621 time for calcul the mask position with numpy : 0.0374755859375 nb_pixel_total : 48364 time to create 1 rle with old method : 0.05018901824951172 time for calcul the mask position with numpy : 0.0382838249206543 nb_pixel_total : 24590 time to create 1 rle with old method : 0.026041746139526367 time for calcul the mask position with numpy : 0.038767337799072266 nb_pixel_total : 228441 time to create 1 rle with new method : 0.5576250553131104 time for calcul the mask position with numpy : 0.03793621063232422 nb_pixel_total : 60444 time to create 1 rle with old method : 0.06242513656616211 time for calcul the mask position with numpy : 0.03892183303833008 nb_pixel_total : 39631 time to create 1 rle with old method : 0.040935516357421875 time for calcul the mask position with numpy : 0.037245750427246094 nb_pixel_total : 65903 time to create 1 rle with old method : 0.06795716285705566 time for calcul the mask position with numpy : 0.03801417350769043 nb_pixel_total : 27159 time to create 1 rle with old method : 0.02907276153564453 time for calcul the mask position with numpy : 0.039998531341552734 nb_pixel_total : 27072 time to create 1 rle with old method : 0.029188871383666992 time for calcul the mask position with numpy : 0.0396885871887207 nb_pixel_total : 334232 time to create 1 rle with new method : 0.571246862411499 time for calcul the mask position with numpy : 0.03770327568054199 nb_pixel_total : 29449 time to create 1 rle with old method : 0.03092026710510254 time for calcul the mask position with numpy : 0.037619829177856445 nb_pixel_total : 809 time to create 1 rle with old method : 0.0010256767272949219 time for calcul the mask position with numpy : 0.03817152976989746 nb_pixel_total : 110974 time to create 1 rle with old method : 0.1165168285369873 time for calcul the mask position with numpy : 0.039109230041503906 nb_pixel_total : 282884 time to create 1 rle with new method : 0.5740845203399658 time for calcul the mask position with numpy : 0.03953742980957031 nb_pixel_total : 464137 time to create 1 rle with new method : 0.6581768989562988 time for calcul the mask position with numpy : 0.037268877029418945 nb_pixel_total : 43422 time to create 1 rle with old method : 0.047139644622802734 time for calcul the mask position with numpy : 0.038717031478881836 nb_pixel_total : 10866 time to create 1 rle with old method : 0.011905431747436523 time for calcul the mask position with numpy : 0.040224552154541016 nb_pixel_total : 443092 time to create 1 rle with new method : 0.5969142913818359 time for calcul the mask position with numpy : 0.039376020431518555 nb_pixel_total : 47176 time to create 1 rle with old method : 0.05109715461730957 time for calcul the mask position with numpy : 0.03924155235290527 nb_pixel_total : 157458 time to create 1 rle with new method : 0.6044929027557373 time for calcul the mask position with numpy : 0.03868722915649414 nb_pixel_total : 122988 time to create 1 rle with old method : 0.1325526237487793 time for calcul the mask position with numpy : 0.039145469665527344 nb_pixel_total : 21789 time to create 1 rle with old method : 0.024184226989746094 time for calcul the mask position with numpy : 0.03855586051940918 nb_pixel_total : 66498 time to create 1 rle with old method : 0.07104730606079102 time for calcul the mask position with numpy : 0.038038015365600586 nb_pixel_total : 7446 time to create 1 rle with old method : 0.007977724075317383 time for calcul the mask position with numpy : 0.03793597221374512 nb_pixel_total : 3712 time to create 1 rle with old method : 0.003997802734375 time for calcul the mask position with numpy : 0.04021501541137695 nb_pixel_total : 170650 time to create 1 rle with new method : 0.8014011383056641 time for calcul the mask position with numpy : 0.03979754447937012 nb_pixel_total : 53214 time to create 1 rle with old method : 0.05631422996520996 time for calcul the mask position with numpy : 0.039086103439331055 nb_pixel_total : 153274 time to create 1 rle with new method : 0.552802562713623 time for calcul the mask position with numpy : 0.04151582717895508 nb_pixel_total : 56063 time to create 1 rle with old method : 0.06419873237609863 time for calcul the mask position with numpy : 0.04124116897583008 nb_pixel_total : 26777 time to create 1 rle with old method : 0.03578495979309082 time for calcul the mask position with numpy : 0.042368412017822266 nb_pixel_total : 671 time to create 1 rle with old method : 0.0010139942169189453 time for calcul the mask position with numpy : 0.042195796966552734 nb_pixel_total : 69066 time to create 1 rle with old method : 0.07446694374084473 time for calcul the mask position with numpy : 0.038681745529174805 nb_pixel_total : 5283 time to create 1 rle with old method : 0.005631208419799805 time for calcul the mask position with numpy : 0.03795194625854492 nb_pixel_total : 435 time to create 1 rle with old method : 0.0008351802825927734 time for calcul the mask position with numpy : 0.03845500946044922 nb_pixel_total : 71930 time to create 1 rle with old method : 0.08262157440185547 time for calcul the mask position with numpy : 0.03894448280334473 nb_pixel_total : 23231 time to create 1 rle with old method : 0.025098800659179688 time for calcul the mask position with numpy : 0.03833293914794922 nb_pixel_total : 10476 time to create 1 rle with old method : 0.011133193969726562 create new chi : 22.205373525619507 time to delete rle : 0.041062355041503906 batch 1 Loaded 82 chid ids of type : 4855 Number RLEs to save : 56592 TO DO : save crop sub photo not yet done ! save time : 484.0121331214905 nb_obj : 115 nb_hashtags : 13 time to prepare the origin masks : 59.25711965560913 time for calcul the mask position with numpy : 0.09092164039611816 nb_pixel_total : 2280150 time to create 1 rle with new method : 0.7365927696228027 time for calcul the mask position with numpy : 0.040253400802612305 nb_pixel_total : 17012 time to create 1 rle with old method : 0.018755197525024414 time for calcul the mask position with numpy : 0.03987860679626465 nb_pixel_total : 48262 time to create 1 rle with old method : 0.05232977867126465 time for calcul the mask position with numpy : 0.038988590240478516 nb_pixel_total : 40590 time to create 1 rle with old method : 0.04894375801086426 time for calcul the mask position with numpy : 0.03805136680603027 nb_pixel_total : 15362 time to create 1 rle with old method : 0.016388893127441406 time for calcul the mask position with numpy : 0.03865313529968262 nb_pixel_total : 6810 time to create 1 rle with old method : 0.007308483123779297 time for calcul the mask position with numpy : 0.03846549987792969 nb_pixel_total : 34132 time to create 1 rle with old method : 0.03645777702331543 time for calcul the mask position with numpy : 0.04081892967224121 nb_pixel_total : 63696 time to create 1 rle with old method : 0.0707237720489502 time for calcul the mask position with numpy : 0.04088282585144043 nb_pixel_total : 123638 time to create 1 rle with old method : 0.13879799842834473 time for calcul the mask position with numpy : 0.042664289474487305 nb_pixel_total : 39092 time to create 1 rle with old method : 0.04516744613647461 time for calcul the mask position with numpy : 0.042151451110839844 nb_pixel_total : 2693 time to create 1 rle with old method : 0.003178834915161133 time for calcul the mask position with numpy : 0.04547119140625 nb_pixel_total : 45184 time to create 1 rle with old method : 0.04949808120727539 time for calcul the mask position with numpy : 0.040792226791381836 nb_pixel_total : 1 time to create 1 rle with old method : 4.0531158447265625e-05 time for calcul the mask position with numpy : 0.03998589515686035 nb_pixel_total : 1580 time to create 1 rle with old method : 0.0019636154174804688 time for calcul the mask position with numpy : 0.04030013084411621 nb_pixel_total : 14611 time to create 1 rle with old method : 0.016404151916503906 time for calcul the mask position with numpy : 0.0402071475982666 nb_pixel_total : 65093 time to create 1 rle with old method : 0.07172346115112305 time for calcul the mask position with numpy : 0.04099011421203613 nb_pixel_total : 2842 time to create 1 rle with old method : 0.003633260726928711 time for calcul the mask position with numpy : 0.04075336456298828 nb_pixel_total : 30957 time to create 1 rle with old method : 0.034719228744506836 time for calcul the mask position with numpy : 0.04440188407897949 nb_pixel_total : 469657 time to create 1 rle with new method : 0.7105340957641602 time for calcul the mask position with numpy : 0.041107177734375 nb_pixel_total : 18462 time to create 1 rle with old method : 0.020749330520629883 time for calcul the mask position with numpy : 0.04256296157836914 nb_pixel_total : 137801 time to create 1 rle with old method : 0.14932727813720703 time for calcul the mask position with numpy : 0.03973579406738281 nb_pixel_total : 17174 time to create 1 rle with old method : 0.01875925064086914 time for calcul the mask position with numpy : 0.044054269790649414 nb_pixel_total : 230458 time to create 1 rle with new method : 0.6113195419311523 time for calcul the mask position with numpy : 0.04027271270751953 nb_pixel_total : 8182 time to create 1 rle with old method : 0.00898289680480957 time for calcul the mask position with numpy : 0.03985285758972168 nb_pixel_total : 33229 time to create 1 rle with old method : 0.0345454216003418 time for calcul the mask position with numpy : 0.039650917053222656 nb_pixel_total : 44303 time to create 1 rle with old method : 0.04693031311035156 time for calcul the mask position with numpy : 0.04049873352050781 nb_pixel_total : 44877 time to create 1 rle with old method : 0.04763054847717285 time for calcul the mask position with numpy : 0.03900575637817383 nb_pixel_total : 25354 time to create 1 rle with old method : 0.026418209075927734 time for calcul the mask position with numpy : 0.038818359375 nb_pixel_total : 11914 time to create 1 rle with old method : 0.01255345344543457 time for calcul the mask position with numpy : 0.04174518585205078 nb_pixel_total : 170035 time to create 1 rle with new method : 0.5097031593322754 time for calcul the mask position with numpy : 0.039072275161743164 nb_pixel_total : 29326 time to create 1 rle with old method : 0.03101372718811035 time for calcul the mask position with numpy : 0.03942298889160156 nb_pixel_total : 101098 time to create 1 rle with old method : 0.10526561737060547 time for calcul the mask position with numpy : 0.038450002670288086 nb_pixel_total : 1355 time to create 1 rle with old method : 0.0017757415771484375 time for calcul the mask position with numpy : 0.038765668869018555 nb_pixel_total : 13265 time to create 1 rle with old method : 0.014059066772460938 time for calcul the mask position with numpy : 0.038469791412353516 nb_pixel_total : 12776 time to create 1 rle with old method : 0.013491630554199219 time for calcul the mask position with numpy : 0.03846406936645508 nb_pixel_total : 18918 time to create 1 rle with old method : 0.01989150047302246 time for calcul the mask position with numpy : 0.03960776329040527 nb_pixel_total : 21183 time to create 1 rle with old method : 0.022311925888061523 time for calcul the mask position with numpy : 0.03895163536071777 nb_pixel_total : 76725 time to create 1 rle with old method : 0.08029484748840332 time for calcul the mask position with numpy : 0.03926897048950195 nb_pixel_total : 52882 time to create 1 rle with old method : 0.05573320388793945 time for calcul the mask position with numpy : 0.0385286808013916 nb_pixel_total : 2950 time to create 1 rle with old method : 0.0034399032592773438 time for calcul the mask position with numpy : 0.03837299346923828 nb_pixel_total : 22876 time to create 1 rle with old method : 0.02425551414489746 time for calcul the mask position with numpy : 0.03866100311279297 nb_pixel_total : 1644 time to create 1 rle with old method : 0.0017864704132080078 time for calcul the mask position with numpy : 0.039140939712524414 nb_pixel_total : 20533 time to create 1 rle with old method : 0.022513151168823242 time for calcul the mask position with numpy : 0.040044307708740234 nb_pixel_total : 141862 time to create 1 rle with old method : 0.15217185020446777 time for calcul the mask position with numpy : 0.041179656982421875 nb_pixel_total : 300922 time to create 1 rle with new method : 0.8853514194488525 time for calcul the mask position with numpy : 0.041441917419433594 nb_pixel_total : 6012 time to create 1 rle with old method : 0.007268428802490234 time for calcul the mask position with numpy : 0.04159426689147949 nb_pixel_total : 21720 time to create 1 rle with old method : 0.024763107299804688 time for calcul the mask position with numpy : 0.041574954986572266 nb_pixel_total : 48224 time to create 1 rle with old method : 0.05361747741699219 time for calcul the mask position with numpy : 0.04101967811584473 nb_pixel_total : 141 time to create 1 rle with old method : 0.00038242340087890625 time for calcul the mask position with numpy : 0.04297685623168945 nb_pixel_total : 141692 time to create 1 rle with old method : 0.20319366455078125 time for calcul the mask position with numpy : 0.0410466194152832 nb_pixel_total : 6509 time to create 1 rle with old method : 0.007448434829711914 time for calcul the mask position with numpy : 0.041457176208496094 nb_pixel_total : 34645 time to create 1 rle with old method : 0.038739681243896484 time for calcul the mask position with numpy : 0.04223465919494629 nb_pixel_total : 58900 time to create 1 rle with old method : 0.06577897071838379 time for calcul the mask position with numpy : 0.04441404342651367 nb_pixel_total : 247315 time to create 1 rle with new method : 0.5186054706573486 time for calcul the mask position with numpy : 0.039351463317871094 nb_pixel_total : 49327 time to create 1 rle with old method : 0.05601215362548828 time for calcul the mask position with numpy : 0.03988933563232422 nb_pixel_total : 39455 time to create 1 rle with old method : 0.0432286262512207 time for calcul the mask position with numpy : 0.040277719497680664 nb_pixel_total : 77270 time to create 1 rle with old method : 0.08487629890441895 time for calcul the mask position with numpy : 0.040560245513916016 nb_pixel_total : 17309 time to create 1 rle with old method : 0.018724441528320312 time for calcul the mask position with numpy : 0.04077863693237305 nb_pixel_total : 49330 time to create 1 rle with old method : 0.053882598876953125 time for calcul the mask position with numpy : 0.04153561592102051 nb_pixel_total : 268265 time to create 1 rle with new method : 0.6728060245513916 time for calcul the mask position with numpy : 0.042621612548828125 nb_pixel_total : 367257 time to create 1 rle with new method : 0.5954527854919434 time for calcul the mask position with numpy : 0.03922891616821289 nb_pixel_total : 67227 time to create 1 rle with old method : 0.07106447219848633 time for calcul the mask position with numpy : 0.038765668869018555 nb_pixel_total : 274 time to create 1 rle with old method : 0.00045680999755859375 time for calcul the mask position with numpy : 0.038645267486572266 nb_pixel_total : 2432 time to create 1 rle with old method : 0.003229379653930664 time for calcul the mask position with numpy : 0.038846731185913086 nb_pixel_total : 33237 time to create 1 rle with old method : 0.035299062728881836 time for calcul the mask position with numpy : 0.038643598556518555 nb_pixel_total : 12812 time to create 1 rle with old method : 0.014140844345092773 time for calcul the mask position with numpy : 0.038964271545410156 nb_pixel_total : 5774 time to create 1 rle with old method : 0.006726980209350586 time for calcul the mask position with numpy : 0.03895068168640137 nb_pixel_total : 4225 time to create 1 rle with old method : 0.005455732345581055 time for calcul the mask position with numpy : 0.03925728797912598 nb_pixel_total : 16590 time to create 1 rle with old method : 0.01815962791442871 time for calcul the mask position with numpy : 0.040289878845214844 nb_pixel_total : 1085 time to create 1 rle with old method : 0.0012989044189453125 time for calcul the mask position with numpy : 0.040532827377319336 nb_pixel_total : 15777 time to create 1 rle with old method : 0.017733335494995117 time for calcul the mask position with numpy : 0.04066324234008789 nb_pixel_total : 30707 time to create 1 rle with old method : 0.034407854080200195 time for calcul the mask position with numpy : 0.04074907302856445 nb_pixel_total : 944 time to create 1 rle with old method : 0.001332998275756836 time for calcul the mask position with numpy : 0.041129112243652344 nb_pixel_total : 70622 time to create 1 rle with old method : 0.07872676849365234 time for calcul the mask position with numpy : 0.04100203514099121 nb_pixel_total : 28348 time to create 1 rle with old method : 0.03354978561401367 time for calcul the mask position with numpy : 0.04540205001831055 nb_pixel_total : 32049 time to create 1 rle with old method : 0.03586935997009277 time for calcul the mask position with numpy : 0.04109835624694824 nb_pixel_total : 62404 time to create 1 rle with old method : 0.06859230995178223 time for calcul the mask position with numpy : 0.04096722602844238 nb_pixel_total : 54964 time to create 1 rle with old method : 0.06131386756896973 time for calcul the mask position with numpy : 0.04097437858581543 nb_pixel_total : 36751 time to create 1 rle with old method : 0.040962934494018555 time for calcul the mask position with numpy : 0.04103994369506836 nb_pixel_total : 24163 time to create 1 rle with old method : 0.027118921279907227 time for calcul the mask position with numpy : 0.041821956634521484 nb_pixel_total : 110951 time to create 1 rle with old method : 0.12206602096557617 time for calcul the mask position with numpy : 0.04114580154418945 nb_pixel_total : 28332 time to create 1 rle with old method : 0.03252267837524414 time for calcul the mask position with numpy : 0.04084491729736328 nb_pixel_total : 31536 time to create 1 rle with old method : 0.03510594367980957 time for calcul the mask position with numpy : 0.04225277900695801 nb_pixel_total : 179852 time to create 1 rle with new method : 0.6747245788574219 time for calcul the mask position with numpy : 0.0393826961517334 nb_pixel_total : 8545 time to create 1 rle with old method : 0.009380340576171875 time for calcul the mask position with numpy : 0.0393831729888916 nb_pixel_total : 72397 time to create 1 rle with old method : 0.07969307899475098 time for calcul the mask position with numpy : 0.03880620002746582 nb_pixel_total : 172774 time to create 1 rle with new method : 0.5263857841491699 time for calcul the mask position with numpy : 0.040225982666015625 nb_pixel_total : 223211 time to create 1 rle with new method : 0.5654175281524658 time for calcul the mask position with numpy : 0.03984975814819336 nb_pixel_total : 29153 time to create 1 rle with old method : 0.030853271484375 time for calcul the mask position with numpy : 0.03898024559020996 nb_pixel_total : 8770 time to create 1 rle with old method : 0.00971531867980957 time for calcul the mask position with numpy : 0.051167964935302734 nb_pixel_total : 740134 time to create 1 rle with new method : 0.5694386959075928 time for calcul the mask position with numpy : 0.03799295425415039 nb_pixel_total : 8461 time to create 1 rle with old method : 0.008925914764404297 time for calcul the mask position with numpy : 0.037773847579956055 nb_pixel_total : 577 time to create 1 rle with old method : 0.0007836818695068359 time for calcul the mask position with numpy : 0.04010319709777832 nb_pixel_total : 319677 time to create 1 rle with new method : 0.5205442905426025 time for calcul the mask position with numpy : 0.038622140884399414 nb_pixel_total : 3432 time to create 1 rle with old method : 0.004296779632568359 time for calcul the mask position with numpy : 0.0385892391204834 nb_pixel_total : 18127 time to create 1 rle with old method : 0.019463777542114258 time for calcul the mask position with numpy : 0.03878211975097656 nb_pixel_total : 1749 time to create 1 rle with old method : 0.0020232200622558594 time for calcul the mask position with numpy : 0.038968801498413086 nb_pixel_total : 49719 time to create 1 rle with old method : 0.05361819267272949 time for calcul the mask position with numpy : 0.039302825927734375 nb_pixel_total : 43281 time to create 1 rle with old method : 0.0461728572845459 time for calcul the mask position with numpy : 0.038993120193481445 nb_pixel_total : 1693 time to create 1 rle with old method : 0.002040386199951172 time for calcul the mask position with numpy : 0.03861427307128906 nb_pixel_total : 7462 time to create 1 rle with old method : 0.00862264633178711 time for calcul the mask position with numpy : 0.03946495056152344 nb_pixel_total : 1504 time to create 1 rle with old method : 0.0019385814666748047 time for calcul the mask position with numpy : 0.03860616683959961 nb_pixel_total : 4614 time to create 1 rle with old method : 0.00505518913269043 time for calcul the mask position with numpy : 0.040695905685424805 nb_pixel_total : 129578 time to create 1 rle with old method : 0.13683295249938965 time for calcul the mask position with numpy : 0.03976774215698242 nb_pixel_total : 52945 time to create 1 rle with old method : 0.05843830108642578 time for calcul the mask position with numpy : 0.040021657943725586 nb_pixel_total : 4507 time to create 1 rle with old method : 0.005118846893310547 time for calcul the mask position with numpy : 0.04139971733093262 nb_pixel_total : 140843 time to create 1 rle with old method : 0.15395355224609375 time for calcul the mask position with numpy : 0.04358196258544922 nb_pixel_total : 299282 time to create 1 rle with new method : 0.593421459197998 time for calcul the mask position with numpy : 0.043762922286987305 nb_pixel_total : 2490 time to create 1 rle with old method : 0.003005504608154297 time for calcul the mask position with numpy : 0.04377937316894531 nb_pixel_total : 132331 time to create 1 rle with old method : 0.14780950546264648 time for calcul the mask position with numpy : 0.03920722007751465 nb_pixel_total : 8434 time to create 1 rle with old method : 0.009261131286621094 time for calcul the mask position with numpy : 0.04069638252258301 nb_pixel_total : 26892 time to create 1 rle with old method : 0.029553651809692383 time for calcul the mask position with numpy : 0.04064226150512695 nb_pixel_total : 40902 time to create 1 rle with old method : 0.045284271240234375 time for calcul the mask position with numpy : 0.039490461349487305 nb_pixel_total : 5154 time to create 1 rle with old method : 0.005986213684082031 time for calcul the mask position with numpy : 0.040850162506103516 nb_pixel_total : 15794 time to create 1 rle with old method : 0.017563343048095703 time for calcul the mask position with numpy : 0.03990030288696289 nb_pixel_total : 14075 time to create 1 rle with old method : 0.015304803848266602 create new chi : 17.873159885406494 time to delete rle : 0.010888814926147461 batch 1 Loaded 116 chid ids of type : 4855 Number RLEs to save : 67208 TO DO : save crop sub photo not yet done ! save time : 75.1508674621582 nb_obj : 90 nb_hashtags : 10 time to prepare the origin masks : 50.46965765953064 time for calcul the mask position with numpy : 0.4388411045074463 nb_pixel_total : 2693526 time to create 1 rle with new method : 1.07535982131958 time for calcul the mask position with numpy : 0.03938746452331543 nb_pixel_total : 55487 time to create 1 rle with old method : 0.05801677703857422 time for calcul the mask position with numpy : 0.04257655143737793 nb_pixel_total : 5596 time to create 1 rle with old method : 0.006707429885864258 time for calcul the mask position with numpy : 0.03980302810668945 nb_pixel_total : 24199 time to create 1 rle with old method : 0.02639603614807129 time for calcul the mask position with numpy : 0.03991889953613281 nb_pixel_total : 25481 time to create 1 rle with old method : 0.027678966522216797 time for calcul the mask position with numpy : 0.038522958755493164 nb_pixel_total : 64788 time to create 1 rle with old method : 0.06676626205444336 time for calcul the mask position with numpy : 0.03827786445617676 nb_pixel_total : 992 time to create 1 rle with old method : 0.0014574527740478516 time for calcul the mask position with numpy : 0.04375505447387695 nb_pixel_total : 467357 time to create 1 rle with new method : 0.8137061595916748 time for calcul the mask position with numpy : 0.037973642349243164 nb_pixel_total : 24656 time to create 1 rle with old method : 0.025654077529907227 time for calcul the mask position with numpy : 0.0386505126953125 nb_pixel_total : 35098 time to create 1 rle with old method : 0.03710579872131348 time for calcul the mask position with numpy : 0.0392613410949707 nb_pixel_total : 80482 time to create 1 rle with old method : 0.08442282676696777 time for calcul the mask position with numpy : 0.04247093200683594 nb_pixel_total : 242633 time to create 1 rle with new method : 2.256580352783203 time for calcul the mask position with numpy : 0.03886747360229492 nb_pixel_total : 61813 time to create 1 rle with old method : 0.06493759155273438 time for calcul the mask position with numpy : 0.03993105888366699 nb_pixel_total : 76472 time to create 1 rle with old method : 0.08094596862792969 time for calcul the mask position with numpy : 0.039034128189086914 nb_pixel_total : 44902 time to create 1 rle with old method : 0.049887895584106445 time for calcul the mask position with numpy : 0.04120206832885742 nb_pixel_total : 19654 time to create 1 rle with old method : 0.02103447914123535 time for calcul the mask position with numpy : 0.038547515869140625 nb_pixel_total : 1501 time to create 1 rle with old method : 0.0017201900482177734 time for calcul the mask position with numpy : 0.03893303871154785 nb_pixel_total : 46147 time to create 1 rle with old method : 0.04927396774291992 time for calcul the mask position with numpy : 0.04296302795410156 nb_pixel_total : 33788 time to create 1 rle with old method : 0.036644697189331055 time for calcul the mask position with numpy : 0.04025435447692871 nb_pixel_total : 47495 time to create 1 rle with old method : 0.05279850959777832 time for calcul the mask position with numpy : 0.04270195960998535 nb_pixel_total : 53288 time to create 1 rle with old method : 0.06447267532348633 time for calcul the mask position with numpy : 0.039615631103515625 nb_pixel_total : 54844 time to create 1 rle with old method : 0.07627391815185547 time for calcul the mask position with numpy : 0.04048013687133789 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005652904510498047 time for calcul the mask position with numpy : 0.04386639595031738 nb_pixel_total : 25342 time to create 1 rle with old method : 0.028501272201538086 time for calcul the mask position with numpy : 0.04098176956176758 nb_pixel_total : 2017 time to create 1 rle with old method : 0.0023131370544433594 time for calcul the mask position with numpy : 0.04040694236755371 nb_pixel_total : 7682 time to create 1 rle with old method : 0.00867915153503418 time for calcul the mask position with numpy : 0.040749549865722656 nb_pixel_total : 80476 time to create 1 rle with old method : 0.09017539024353027 time for calcul the mask position with numpy : 0.040706634521484375 nb_pixel_total : 2506 time to create 1 rle with old method : 0.003267526626586914 time for calcul the mask position with numpy : 0.04105353355407715 nb_pixel_total : 35778 time to create 1 rle with old method : 0.039829254150390625 time for calcul the mask position with numpy : 0.04272150993347168 nb_pixel_total : 412764 time to create 1 rle with new method : 1.9920899868011475 time for calcul the mask position with numpy : 0.03833174705505371 nb_pixel_total : 68678 time to create 1 rle with old method : 0.07147550582885742 time for calcul the mask position with numpy : 0.0408015251159668 nb_pixel_total : 110908 time to create 1 rle with old method : 0.11722493171691895 time for calcul the mask position with numpy : 0.03917670249938965 nb_pixel_total : 105141 time to create 1 rle with old method : 0.10942935943603516 time for calcul the mask position with numpy : 0.038831472396850586 nb_pixel_total : 12067 time to create 1 rle with old method : 0.012856006622314453 time for calcul the mask position with numpy : 0.0389552116394043 nb_pixel_total : 72765 time to create 1 rle with old method : 0.0777280330657959 time for calcul the mask position with numpy : 0.03938889503479004 nb_pixel_total : 1693 time to create 1 rle with old method : 0.0019500255584716797 time for calcul the mask position with numpy : 0.04080486297607422 nb_pixel_total : 117748 time to create 1 rle with old method : 0.12776899337768555 time for calcul the mask position with numpy : 0.03969979286193848 nb_pixel_total : 101476 time to create 1 rle with old method : 0.10878825187683105 time for calcul the mask position with numpy : 0.04227781295776367 nb_pixel_total : 343075 time to create 1 rle with new method : 1.0976386070251465 time for calcul the mask position with numpy : 0.041443824768066406 nb_pixel_total : 45876 time to create 1 rle with old method : 0.07623934745788574 time for calcul the mask position with numpy : 0.04259610176086426 nb_pixel_total : 70887 time to create 1 rle with old method : 0.07712650299072266 time for calcul the mask position with numpy : 0.03983640670776367 nb_pixel_total : 10407 time to create 1 rle with old method : 0.011443853378295898 time for calcul the mask position with numpy : 0.04009652137756348 nb_pixel_total : 1549 time to create 1 rle with old method : 0.0018324851989746094 time for calcul the mask position with numpy : 0.04383492469787598 nb_pixel_total : 447050 time to create 1 rle with new method : 1.2624826431274414 time for calcul the mask position with numpy : 0.040529489517211914 nb_pixel_total : 14875 time to create 1 rle with old method : 0.01679086685180664 time for calcul the mask position with numpy : 0.040891408920288086 nb_pixel_total : 57392 time to create 1 rle with old method : 0.0665283203125 time for calcul the mask position with numpy : 0.04107403755187988 nb_pixel_total : 73579 time to create 1 rle with old method : 0.08057117462158203 time for calcul the mask position with numpy : 0.03912782669067383 nb_pixel_total : 42683 time to create 1 rle with old method : 0.05108046531677246 time for calcul the mask position with numpy : 0.040117502212524414 nb_pixel_total : 103426 time to create 1 rle with old method : 0.12104630470275879 time for calcul the mask position with numpy : 0.03917050361633301 nb_pixel_total : 185 time to create 1 rle with old method : 0.0003612041473388672 time for calcul the mask position with numpy : 0.03983807563781738 nb_pixel_total : 99467 time to create 1 rle with old method : 0.10857081413269043 time for calcul the mask position with numpy : 0.04093027114868164 nb_pixel_total : 10768 time to create 1 rle with old method : 0.012686491012573242 time for calcul the mask position with numpy : 0.04092526435852051 nb_pixel_total : 47347 time to create 1 rle with old method : 0.054083824157714844 time for calcul the mask position with numpy : 0.04042387008666992 nb_pixel_total : 23108 time to create 1 rle with old method : 0.025554656982421875 time for calcul the mask position with numpy : 0.040558576583862305 nb_pixel_total : 21685 time to create 1 rle with old method : 0.02410721778869629 time for calcul the mask position with numpy : 0.04054713249206543 nb_pixel_total : 21053 time to create 1 rle with old method : 0.02349543571472168 time for calcul the mask position with numpy : 0.040907859802246094 nb_pixel_total : 76324 time to create 1 rle with old method : 0.08534550666809082 time for calcul the mask position with numpy : 0.04000735282897949 nb_pixel_total : 220919 time to create 1 rle with new method : 0.8505089282989502 time for calcul the mask position with numpy : 0.040184974670410156 nb_pixel_total : 35827 time to create 1 rle with old method : 0.03992414474487305 time for calcul the mask position with numpy : 0.039922475814819336 nb_pixel_total : 58589 time to create 1 rle with old method : 0.06306600570678711 time for calcul the mask position with numpy : 0.03962898254394531 nb_pixel_total : 2391 time to create 1 rle with old method : 0.0029609203338623047 time for calcul the mask position with numpy : 0.03847455978393555 nb_pixel_total : 71082 time to create 1 rle with old method : 0.07645082473754883 time for calcul the mask position with numpy : 0.03865385055541992 nb_pixel_total : 61615 time to create 1 rle with old method : 0.06616425514221191 time for calcul the mask position with numpy : 0.03811073303222656 nb_pixel_total : 37282 time to create 1 rle with old method : 0.038939476013183594 time for calcul the mask position with numpy : 0.03844165802001953 nb_pixel_total : 7692 time to create 1 rle with old method : 0.008507966995239258 time for calcul the mask position with numpy : 0.03855586051940918 nb_pixel_total : 105003 time to create 1 rle with old method : 0.1091763973236084 time for calcul the mask position with numpy : 0.04041314125061035 nb_pixel_total : 89664 time to create 1 rle with old method : 0.0966348648071289 time for calcul the mask position with numpy : 0.04131603240966797 nb_pixel_total : 262113 time to create 1 rle with new method : 0.8913054466247559 time for calcul the mask position with numpy : 0.04108786582946777 nb_pixel_total : 162275 time to create 1 rle with new method : 1.0438885688781738 time for calcul the mask position with numpy : 0.04100799560546875 nb_pixel_total : 201688 time to create 1 rle with new method : 0.6901106834411621 time for calcul the mask position with numpy : 0.03731942176818848 nb_pixel_total : 6963 time to create 1 rle with old method : 0.007764577865600586 time for calcul the mask position with numpy : 0.038935184478759766 nb_pixel_total : 31555 time to create 1 rle with old method : 0.03329634666442871 time for calcul the mask position with numpy : 0.03781294822692871 nb_pixel_total : 241 time to create 1 rle with old method : 0.0005586147308349609 time for calcul the mask position with numpy : 0.03770804405212402 nb_pixel_total : 2071 time to create 1 rle with old method : 0.0023453235626220703 time for calcul the mask position with numpy : 0.03794503211975098 nb_pixel_total : 758 time to create 1 rle with old method : 0.0009775161743164062 time for calcul the mask position with numpy : 0.03772854804992676 nb_pixel_total : 172 time to create 1 rle with old method : 0.00026679039001464844 time for calcul the mask position with numpy : 0.04166388511657715 nb_pixel_total : 538420 time to create 1 rle with new method : 0.7234272956848145 time for calcul the mask position with numpy : 0.038333892822265625 nb_pixel_total : 33290 time to create 1 rle with old method : 0.034809112548828125 time for calcul the mask position with numpy : 0.03840017318725586 nb_pixel_total : 10321 time to create 1 rle with old method : 0.011084318161010742 time for calcul the mask position with numpy : 0.03888702392578125 nb_pixel_total : 13416 time to create 1 rle with old method : 0.015450239181518555 time for calcul the mask position with numpy : 0.040801286697387695 nb_pixel_total : 275355 time to create 1 rle with new method : 0.6543035507202148 time for calcul the mask position with numpy : 0.03858041763305664 nb_pixel_total : 129365 time to create 1 rle with old method : 0.1357414722442627 time for calcul the mask position with numpy : 0.03908228874206543 nb_pixel_total : 284 time to create 1 rle with old method : 0.00048732757568359375 time for calcul the mask position with numpy : 0.040978431701660156 nb_pixel_total : 28660 time to create 1 rle with old method : 0.031033992767333984 time for calcul the mask position with numpy : 0.04058551788330078 nb_pixel_total : 29616 time to create 1 rle with old method : 0.03269386291503906 time for calcul the mask position with numpy : 0.04022049903869629 nb_pixel_total : 99068 time to create 1 rle with old method : 0.1056985855102539 time for calcul the mask position with numpy : 0.03896665573120117 nb_pixel_total : 17424 time to create 1 rle with old method : 0.018754959106445312 time for calcul the mask position with numpy : 0.04149055480957031 nb_pixel_total : 321922 time to create 1 rle with new method : 1.2997183799743652 time for calcul the mask position with numpy : 0.03671002388000488 nb_pixel_total : 4089 time to create 1 rle with old method : 0.004471778869628906 time for calcul the mask position with numpy : 0.03753089904785156 nb_pixel_total : 34619 time to create 1 rle with old method : 0.035352230072021484 time for calcul the mask position with numpy : 0.036698102951049805 nb_pixel_total : 12269 time to create 1 rle with old method : 0.013000965118408203 create new chi : 22.58859872817993 time to delete rle : 0.0058782100677490234 batch 1 Loaded 91 chid ids of type : 4855 Number RLEs to save : 58406 TO DO : save crop sub photo not yet done ! save time : 4.101319313049316 nb_obj : 10 nb_hashtags : 3 time to prepare the origin masks : 15.933369874954224 time for calcul the mask position with numpy : 0.035514116287231445 nb_pixel_total : 662081 time to create 1 rle with new method : 1.0371148586273193 time for calcul the mask position with numpy : 0.03406381607055664 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001399517059326172 time for calcul the mask position with numpy : 0.04735589027404785 nb_pixel_total : 186549 time to create 1 rle with new method : 1.0837550163269043 time for calcul the mask position with numpy : 0.049623727798461914 nb_pixel_total : 8808 time to create 1 rle with old method : 0.009813308715820312 time for calcul the mask position with numpy : 0.047290802001953125 nb_pixel_total : 1004 time to create 1 rle with old method : 0.0011730194091796875 time for calcul the mask position with numpy : 0.05371403694152832 nb_pixel_total : 841157 time to create 1 rle with new method : 1.1392338275909424 time for calcul the mask position with numpy : 0.049826622009277344 nb_pixel_total : 2114 time to create 1 rle with old method : 0.0024971961975097656 time for calcul the mask position with numpy : 0.0676267147064209 nb_pixel_total : 1654760 time to create 1 rle with new method : 1.1146674156188965 time for calcul the mask position with numpy : 0.03125882148742676 nb_pixel_total : 17297 time to create 1 rle with old method : 0.019482135772705078 time for calcul the mask position with numpy : 0.04801201820373535 nb_pixel_total : 1584850 time to create 1 rle with new method : 1.1203737258911133 time for calcul the mask position with numpy : 0.2599332332611084 nb_pixel_total : 4775687 time to create 1 rle with new method : 1.0308237075805664 create new chi : 7.497705698013306 time to delete rle : 0.0016880035400390625 batch 1 Loaded 11 chid ids of type : 4855 Number RLEs to save : 16500 TO DO : save crop sub photo not yet done ! save time : 1.0378944873809814 map_output_result : {1379844365: (0.47198516997112333, 'Should be the crop_list due to order', 0.1801301208039972), 1379844317: (0.47198516997112333, 'Should be the crop_list due to order', 0.4083861455502748), 1379844257: (0.47198516997112333, 'Should be the crop_list due to order', 0.4078124364998684), 1379844188: (0.47198516997112333, 'Should be the crop_list due to order', 0.8916119770303529)} 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 [1379844365, 1379844317, 1379844257, 1379844188] Looping around the photos to save general results len do output : 4 /1379844365.Didn't retrieve data . /1379844317.Didn't retrieve data . /1379844257.Didn't retrieve data . /1379844188.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, '3623725') ('4741', '26290977', '1379844365', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844317', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844257', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844188', None, None, None, None, None, '3623725') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.01698160171508789 save_final save missing photos in datou_result : time spend for datou_step_exec : 808.6128766536713 time spend to save output : 0.021141529083251953 total time spend for step 5 : 808.6340181827545 step6:crop_condition Thu Aug 28 12:17:40 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 : 4 ! batch 1 Loaded 300 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 ! map_result returned by crop_photo_return_map_crop : length : 48 About to insert : list_path_to_insert length 48 new photo from crops ! About to upload 48 photos upload in portfolio : 3015255 init cache_photo without model_param we have 48 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376290_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 48 photos in the portfolio 3015255 time of upload the photos Elapsed time : 12.060600280761719 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 ! map_result returned by crop_photo_return_map_crop : length : 46 About to insert : list_path_to_insert length 46 new photo from crops ! About to upload 46 photos upload in portfolio : 3015255 init cache_photo without model_param we have 46 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376326_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 46 photos in the portfolio 3015255 time of upload the photos Elapsed time : 13.996286153793335 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 ! map_result returned by crop_photo_return_map_crop : length : 7 About to insert : list_path_to_insert length 7 new photo from crops ! About to upload 7 photos upload in portfolio : 3015255 init cache_photo without model_param we have 7 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376342_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 7 photos in the portfolio 3015255 time of upload the photos Elapsed time : 2.4221785068511963 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 21 About to insert : list_path_to_insert length 21 new photo from crops ! About to upload 21 photos upload in portfolio : 3015255 init cache_photo without model_param we have 21 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376350_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 21 photos in the portfolio 3015255 time of upload the photos Elapsed time : 5.911761522293091 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 ! 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/1756376358_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 : 1.2222585678100586 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 ! 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/1756376361_3437029 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 : 0.6217384338378906 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 ! map_result returned by crop_photo_return_map_crop : length : 7 About to insert : list_path_to_insert length 7 new photo from crops ! About to upload 7 photos upload in portfolio : 3015255 init cache_photo without model_param we have 7 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376365_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 7 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.9429223537445068 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 ! 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/1756376370_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 : 1.8598732948303223 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 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/1756376374_3437029 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 : 0.5690193176269531 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 ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 3015255 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376395_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 27 photos in the portfolio 3015255 time of upload the photos Elapsed time : 6.497035026550293 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/1756376403_3437029 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 : 0.5865333080291748 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 ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! About to upload 13 photos upload in portfolio : 3015255 init cache_photo without model_param we have 13 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376409_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 13 photos in the portfolio 3015255 time of upload the photos Elapsed time : 3.660700559616089 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 ! map_result returned by crop_photo_return_map_crop : length : 37 About to insert : list_path_to_insert length 37 new photo from crops ! About to upload 37 photos upload in portfolio : 3015255 init cache_photo without model_param we have 37 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756376453_3437029 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 37 photos in the portfolio 3015255 time of upload the photos Elapsed time : 10.47962999343872 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 [1379844365, 1379844317, 1379844257, 1379844188] Looping around the photos to save general results len do output : 216 /1379856187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856221Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856226Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856231Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856239Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856241Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856242Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856541Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856542Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856543Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379856963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857408Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857414Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857415Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857417Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857418Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857421Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857422Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857423Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857425Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857426Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857428Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379857449Didn'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, '3623725') ('4741', '26290977', '1379844365', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844317', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844257', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844188', None, None, None, None, None, '3623725') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 652 time used for this insertion : 0.0965890884399414 save_final save missing photos in datou_result : time spend for datou_step_exec : 207.03695368766785 time spend to save output : 0.1059868335723877 total time spend for step 6 : 207.14294052124023 step7:ventilate_hashtags_in_portfolio Thu Aug 28 12:21:07 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 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 : 26290977 get user id for portfolio 26290977 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`=26290977 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`=26290977 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 Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") 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`=26290977 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`=26290977 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://www.fotonower.com/velours/26291856,26291857,26291858,26291859,26291860,26291866,26291868,26291869,26291870,26291871,26291872,26291873,26291875,26291876,26291877,26291878,26291879,26291880,26291881,26291882?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=26290977 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1379844365, 1379844317, 1379844257, 1379844188] Looping around the photos to save general results len do output : 1 /26290977. 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, '3623725') ('4741', '26290977', '1379844365', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844317', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844257', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844188', None, None, None, None, None, '3623725') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.014149188995361328 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.695432901382446 time spend to save output : 0.014400243759155273 total time spend for step 7 : 4.709833145141602 step8:final Thu Aug 28 12:21:12 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 : {1379844365: ('0.33722517685127956',), 1379844317: ('0.33722517685127956',), 1379844257: ('0.33722517685127956',), 1379844188: ('0.33722517685127956',)} new output for save of step final : {1379844365: ('0.33722517685127956',), 1379844317: ('0.33722517685127956',), 1379844257: ('0.33722517685127956',), 1379844188: ('0.33722517685127956',)} [1379844365, 1379844317, 1379844257, 1379844188] Looping around the photos to save general results len do output : 4 /1379844365.Didn't retrieve data . /1379844317.Didn't retrieve data . /1379844257.Didn't retrieve data . /1379844188.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, '3623725') ('4741', '26290977', '1379844365', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844317', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844257', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844188', None, None, None, None, None, '3623725') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.015047073364257812 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.16596031188964844 time spend to save output : 0.04351067543029785 total time spend for step 8 : 0.2094709873199463 step9:velours_tree Thu Aug 28 12:21:12 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 : 1.1691820621490479 time spend to save output : 6.651878356933594e-05 total time spend for step 9 : 1.1692485809326172 step10:send_mail_cod Thu Aug 28 12:21:13 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_P26290977_28-08-2025_12_21_13.pdf 26291830 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 .imagette262918301756376473 26291831 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 .imagette262918311756376475 26291832 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 .imagette262918321756376477 26291833 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 .imagette262918331756376477 26291834 change filename to text .change filename to text .change filename to text .imagette262918341756376479 26291835 change filename to text .imagette262918351756376479 26291836 imagette262918361756376479 26291837 imagette262918371756376479 26291838 imagette262918381756376479 26291839 imagette262918391756376479 26291840 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 .imagette262918401756376479 26291841 change filename to text .change filename to text .change filename to text .change filename to text .imagette262918411756376479 26291842 change filename to text .imagette262918421756376480 26291843 imagette262918431756376480 26291844 imagette262918441756376480 26291845 imagette262918451756376480 26291846 imagette262918461756376480 26291847 change filename to text .imagette262918471756376480 26291848 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 .imagette262918481756376480 26291850 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 .imagette262918501756376481 26291851 imagette262918511756376482 26291852 imagette262918521756376482 26291853 imagette262918531756376482 26291854 imagette262918541756376482 26291855 imagette262918551756376482 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=26290977 and hashtag_type = 4855 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/26291856,26291857,26291858,26291859,26291860,26291866,26291868,26291869,26291870,26291871,26291872,26291873,26291875,26291876,26291877,26291878,26291879,26291880,26291881,26291882?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=26290977 your option no_mail is active, we will not send the real mail to your client args[1379844365] : ((1379844365, 526.6879437976122, 492688767), (1379844365, -0.2590102256231313, 496442774), '0.33722517685127956') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379844317] : ((1379844317, 634.390056119049, 492688767), (1379844317, -0.19565286027631734, 496442774), '0.33722517685127956') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379844257] : ((1379844257, 526.3504021908315, 492688767), (1379844257, -0.16025740694254006, 496442774), '0.33722517685127956') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379844188] : ((1379844188, 154.10252365459004, 492688767), (1379844188, -1.4107755664269053, 501862349), '0.33722517685127956') We are sending mail with results at report@fotonower.com,cod@fotonower.com refus_total : 0.33722517685127956 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_P26290977_28-08-2025_12_21_13.pdf results_Auto_P26290977_28-08-2025_12_21_13.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26290977_28-08-2025_12_21_13.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','26290977','results_Auto_P26290977_28-08-2025_12_21_13.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26290977_28-08-2025_12_21_13.pdf','pdf','','1.59','0.33722517685127956') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1379844365, 1379844317, 1379844257, 1379844188] 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, '3623725') ('4741', '26290977', '1379844365', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844317', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844257', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844188', None, None, None, None, None, '3623725') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.013621091842651367 save_final save missing photos in datou_result : time spend for datou_step_exec : 11.365333318710327 time spend to save output : 0.01388859748840332 total time spend for step 10 : 11.37922191619873 step11:split_time_score Thu Aug 28 12:21:25 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 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'}] (('37', 3), ('38', 1)) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 22082025 26290977 Nombre de photos uploadées : 4 / 23040 (0%) 22082025 26290977 Nombre de photos taguées (types de déchets): 0 / 4 (0%) 22082025 26290977 Nombre de photos taguées (volume) : 0 / 4 (0%) elapsed_time : load_data_split_time_score 3.814697265625e-06 elapsed_time : order_list_meta_photo_and_scores 1.0967254638671875e-05 ???? elapsed_time : fill_and_build_computed_from_old_data 0.00040340423583984375 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.20179367065429688 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 : 0.33722517685127956 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26290977_28-08-2025_12_21_13.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26290977 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`=26290977 AND mptpi.`type`=4855 To do Qualite : 0.28105211116339807 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26290978_28-08-2025_11_51_20.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26290978 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`=26290978 AND mptpi.`type`=4855 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26290980 order by id desc limit 1 NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'22082025': {'nb_upload': 4, '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 [1379844365, 1379844317, 1379844257, 1379844188] Looping around the photos to save general results len do output : 1 /26290977Didn'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, '3623725') ('4741', '26290977', '1379844365', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844317', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844257', None, None, None, None, None, '3623725') ('4741', None, None, None, None, None, None, None, '3623725') ('4741', '26290977', '1379844188', None, None, None, None, None, '3623725') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.01430821418762207 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.8197383880615234 time spend to save output : 0.01447296142578125 total time spend for step 11 : 1.8342113494873047 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 4 set_done_treatment 395.94user 184.40system 20:01.44elapsed 48%CPU (0avgtext+0avgdata 6635576maxresident)k 1465352inputs+333744outputs (22141major+30468942minor)pagefaults 0swaps