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 : 3865689 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 : ['3623815'] with mtr_portfolio_ids : ['26291506'] and first list_photo_ids : [] new path : /proc/3865689/ 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 , BFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 6 ; length of list_pids : 6 ; length of list_args : 6 time to download the photos : 1.461010217666626 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 15:01:32 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 : 6823 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 15:01:35.754245: 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 15:01:35.784627: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 15:01:35.786782: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fec44000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:01:35.786816: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 15:01:35.792143: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 15:01:35.959506: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x8b1c5b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:01:35.959565: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 15:01:35.960692: 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 15:01:35.961068: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:01:35.963724: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:01:35.966519: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:01:35.966976: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:01:35.970002: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:01:35.971443: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:01:35.977110: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:01:35.978502: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:01:35.978595: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:01:35.979293: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:01:35.979310: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:01:35.979320: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:01:35.980532: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6127 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 15:01:36.355262: 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 15:01:36.355371: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:01:36.355388: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:01:36.355403: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:01:36.355416: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:01:36.355430: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:01:36.355443: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:01:36.355457: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:01:36.356435: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:01:36.357555: 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 15:01:36.357590: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:01:36.357608: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:01:36.357624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:01:36.357653: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:01:36.357669: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:01:36.357685: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:01:36.357700: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:01:36.358724: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:01:36.358757: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:01:36.358765: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:01:36.358773: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:01:36.359778: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6127 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 15:01:50.275515: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:01:50.454791: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:01:51.977383: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.977997: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.978539: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.979087: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3131030784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.979643: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.62G (2817927680 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.980166: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.36G (2536134912 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.980720: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2282521344 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.980747: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:51.981336: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.981353: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:51.988476: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.988504: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:51.989073: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.989089: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:51.995627: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.995650: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:51.996182: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:51.996198: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:52.026804: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.026834: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:52.027366: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.027380: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:52.033161: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.033181: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:52.033714: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.033741: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-08-28 15:01:52.069035: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.069632: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.071449: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.071980: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.115817: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.116475: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.118700: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.119270: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.149496: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.150062: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.151727: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.152284: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.158688: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.159260: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.161140: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.161711: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.169010: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.169581: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.171292: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.171860: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.204087: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.204886: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.205461: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.206027: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.210869: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.211935: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.231291: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.231852: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.232412: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.232981: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.248497: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.249083: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.249649: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.250343: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.254670: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.255212: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.259961: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.260525: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.273482: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.274070: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.278389: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.278929: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.279463: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.279994: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.280815: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.281391: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.292610: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.293182: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.293761: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.294315: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.294846: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.295377: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.295907: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.296449: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.305985: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.306569: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.313035: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.313595: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.338401: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.338476: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-08-28 15:01:52.339467: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.340458: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.347724: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.348299: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.348900: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.349472: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.357513: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.358093: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.376458: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.377038: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.377585: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.378117: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.382129: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.382663: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.383191: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.383718: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.384697: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.394926: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.395456: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.404347: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.404884: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.405444: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.406010: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.406602: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-08-28 15:01:52.407171: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 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 : 6 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 9 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 18 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 19 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 17 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 10 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 6 Detection mask done ! Trying to reset tf kernel 3865951 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5630 tf kernel not reseted sub process len(results) : 6 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 6 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 : 6602 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 : 0.0015838146209716797 nb_pixel_total : 70041 time to create 1 rle with old method : 0.08618354797363281 length of segment : 321 time for calcul the mask position with numpy : 0.00054931640625 nb_pixel_total : 31796 time to create 1 rle with old method : 0.03808283805847168 length of segment : 211 time for calcul the mask position with numpy : 0.0005171298980712891 nb_pixel_total : 32462 time to create 1 rle with old method : 0.0383906364440918 length of segment : 270 time for calcul the mask position with numpy : 0.0008654594421386719 nb_pixel_total : 49263 time to create 1 rle with old method : 0.056703805923461914 length of segment : 404 time for calcul the mask position with numpy : 0.0006394386291503906 nb_pixel_total : 34757 time to create 1 rle with old method : 0.04003572463989258 length of segment : 427 time for calcul the mask position with numpy : 0.0006155967712402344 nb_pixel_total : 48768 time to create 1 rle with old method : 0.057448625564575195 length of segment : 266 time for calcul the mask position with numpy : 0.0003974437713623047 nb_pixel_total : 14830 time to create 1 rle with old method : 0.017784833908081055 length of segment : 155 time for calcul the mask position with numpy : 0.0002887248992919922 nb_pixel_total : 7998 time to create 1 rle with old method : 0.009957313537597656 length of segment : 114 time for calcul the mask position with numpy : 0.0005273818969726562 nb_pixel_total : 34345 time to create 1 rle with old method : 0.04214358329772949 length of segment : 181 time for calcul the mask position with numpy : 0.023808002471923828 nb_pixel_total : 665781 time to create 1 rle with new method : 0.5964956283569336 length of segment : 771 time for calcul the mask position with numpy : 0.00041484832763671875 nb_pixel_total : 10358 time to create 1 rle with old method : 0.012476205825805664 length of segment : 123 time for calcul the mask position with numpy : 0.007760047912597656 nb_pixel_total : 303390 time to create 1 rle with new method : 0.03846120834350586 length of segment : 1221 time for calcul the mask position with numpy : 0.0017044544219970703 nb_pixel_total : 79437 time to create 1 rle with old method : 0.09078240394592285 length of segment : 324 time for calcul the mask position with numpy : 0.0006768703460693359 nb_pixel_total : 31924 time to create 1 rle with old method : 0.03654026985168457 length of segment : 310 time for calcul the mask position with numpy : 0.0012333393096923828 nb_pixel_total : 77526 time to create 1 rle with old method : 0.0888662338256836 length of segment : 347 time for calcul the mask position with numpy : 0.0011019706726074219 nb_pixel_total : 66858 time to create 1 rle with old method : 0.07726812362670898 length of segment : 266 time for calcul the mask position with numpy : 0.0003681182861328125 nb_pixel_total : 16494 time to create 1 rle with old method : 0.01900625228881836 length of segment : 187 time for calcul the mask position with numpy : 0.008666515350341797 nb_pixel_total : 412533 time to create 1 rle with new method : 0.05531477928161621 length of segment : 766 time for calcul the mask position with numpy : 0.0024330615997314453 nb_pixel_total : 101176 time to create 1 rle with old method : 0.11636185646057129 length of segment : 627 time for calcul the mask position with numpy : 0.044184207916259766 nb_pixel_total : 993881 time to create 1 rle with new method : 1.1277754306793213 length of segment : 1039 time for calcul the mask position with numpy : 0.0021288394927978516 nb_pixel_total : 46545 time to create 1 rle with old method : 0.052057504653930664 length of segment : 313 time for calcul the mask position with numpy : 0.005961179733276367 nb_pixel_total : 220891 time to create 1 rle with new method : 0.009385824203491211 length of segment : 636 time for calcul the mask position with numpy : 0.009600639343261719 nb_pixel_total : 359720 time to create 1 rle with new method : 0.015397071838378906 length of segment : 1180 time for calcul the mask position with numpy : 0.0019488334655761719 nb_pixel_total : 38126 time to create 1 rle with old method : 0.045043230056762695 length of segment : 395 time for calcul the mask position with numpy : 0.010242223739624023 nb_pixel_total : 398400 time to create 1 rle with new method : 0.019421100616455078 length of segment : 706 time for calcul the mask position with numpy : 0.0018696784973144531 nb_pixel_total : 63034 time to create 1 rle with old method : 0.07360649108886719 length of segment : 402 time for calcul the mask position with numpy : 0.012104034423828125 nb_pixel_total : 614377 time to create 1 rle with new method : 0.023641586303710938 length of segment : 967 time for calcul the mask position with numpy : 0.008786439895629883 nb_pixel_total : 277586 time to create 1 rle with new method : 0.015166759490966797 length of segment : 820 time for calcul the mask position with numpy : 0.0036895275115966797 nb_pixel_total : 108062 time to create 1 rle with old method : 0.12937331199645996 length of segment : 663 time for calcul the mask position with numpy : 0.016742229461669922 nb_pixel_total : 533927 time to create 1 rle with new method : 0.10272479057312012 length of segment : 900 time for calcul the mask position with numpy : 0.0012524127960205078 nb_pixel_total : 39942 time to create 1 rle with old method : 0.05034065246582031 length of segment : 205 time for calcul the mask position with numpy : 0.0008740425109863281 nb_pixel_total : 36552 time to create 1 rle with old method : 0.046587228775024414 length of segment : 335 time for calcul the mask position with numpy : 0.00136566162109375 nb_pixel_total : 59882 time to create 1 rle with old method : 0.0892636775970459 length of segment : 209 time for calcul the mask position with numpy : 0.0007426738739013672 nb_pixel_total : 17955 time to create 1 rle with old method : 0.02196955680847168 length of segment : 159 time for calcul the mask position with numpy : 0.0005018711090087891 nb_pixel_total : 15417 time to create 1 rle with old method : 0.018923521041870117 length of segment : 210 time for calcul the mask position with numpy : 0.0011086463928222656 nb_pixel_total : 36051 time to create 1 rle with old method : 0.042896270751953125 length of segment : 304 time for calcul the mask position with numpy : 0.0012598037719726562 nb_pixel_total : 32455 time to create 1 rle with old method : 0.0380558967590332 length of segment : 364 time for calcul the mask position with numpy : 0.0008192062377929688 nb_pixel_total : 22551 time to create 1 rle with old method : 0.041283369064331055 length of segment : 201 time for calcul the mask position with numpy : 0.0024614334106445312 nb_pixel_total : 58740 time to create 1 rle with old method : 0.0783534049987793 length of segment : 337 time for calcul the mask position with numpy : 0.00025200843811035156 nb_pixel_total : 2769 time to create 1 rle with old method : 0.0033464431762695312 length of segment : 169 time for calcul the mask position with numpy : 0.002168416976928711 nb_pixel_total : 41314 time to create 1 rle with old method : 0.05672144889831543 length of segment : 376 time for calcul the mask position with numpy : 0.00665283203125 nb_pixel_total : 171839 time to create 1 rle with new method : 0.01829051971435547 length of segment : 543 time for calcul the mask position with numpy : 0.0027353763580322266 nb_pixel_total : 153553 time to create 1 rle with new method : 0.007674217224121094 length of segment : 509 time for calcul the mask position with numpy : 0.0004799365997314453 nb_pixel_total : 11961 time to create 1 rle with old method : 0.014737606048583984 length of segment : 88 time for calcul the mask position with numpy : 0.0006947517395019531 nb_pixel_total : 34211 time to create 1 rle with old method : 0.05336570739746094 length of segment : 253 time for calcul the mask position with numpy : 0.0004558563232421875 nb_pixel_total : 8776 time to create 1 rle with old method : 0.015440225601196289 length of segment : 77 time for calcul the mask position with numpy : 0.0014035701751708984 nb_pixel_total : 25324 time to create 1 rle with old method : 0.046617984771728516 length of segment : 310 time for calcul the mask position with numpy : 0.002109050750732422 nb_pixel_total : 43630 time to create 1 rle with old method : 0.08020210266113281 length of segment : 335 time for calcul the mask position with numpy : 0.0038862228393554688 nb_pixel_total : 134471 time to create 1 rle with old method : 0.23856568336486816 length of segment : 438 time for calcul the mask position with numpy : 0.0008566379547119141 nb_pixel_total : 23798 time to create 1 rle with old method : 0.028577327728271484 length of segment : 218 time for calcul the mask position with numpy : 0.0016815662384033203 nb_pixel_total : 78810 time to create 1 rle with old method : 0.09457588195800781 length of segment : 487 time for calcul the mask position with numpy : 0.0018200874328613281 nb_pixel_total : 61805 time to create 1 rle with old method : 0.0834665298461914 length of segment : 253 time for calcul the mask position with numpy : 0.003787517547607422 nb_pixel_total : 126963 time to create 1 rle with old method : 0.15578937530517578 length of segment : 353 time for calcul the mask position with numpy : 0.0010342597961425781 nb_pixel_total : 38539 time to create 1 rle with old method : 0.04670834541320801 length of segment : 214 time for calcul the mask position with numpy : 0.004122257232666016 nb_pixel_total : 158423 time to create 1 rle with new method : 0.007371425628662109 length of segment : 421 time for calcul the mask position with numpy : 0.0008041858673095703 nb_pixel_total : 16200 time to create 1 rle with old method : 0.021229028701782227 length of segment : 194 time for calcul the mask position with numpy : 0.0013632774353027344 nb_pixel_total : 28548 time to create 1 rle with old method : 0.034224748611450195 length of segment : 177 time for calcul the mask position with numpy : 0.0028426647186279297 nb_pixel_total : 70206 time to create 1 rle with old method : 0.0992898941040039 length of segment : 780 time for calcul the mask position with numpy : 0.002277374267578125 nb_pixel_total : 68795 time to create 1 rle with old method : 0.07956337928771973 length of segment : 213 time for calcul the mask position with numpy : 0.005390644073486328 nb_pixel_total : 239640 time to create 1 rle with new method : 0.009199380874633789 length of segment : 440 time for calcul the mask position with numpy : 0.0016086101531982422 nb_pixel_total : 28335 time to create 1 rle with old method : 0.03319048881530762 length of segment : 403 time for calcul the mask position with numpy : 0.0020461082458496094 nb_pixel_total : 68241 time to create 1 rle with old method : 0.08927464485168457 length of segment : 393 time for calcul the mask position with numpy : 0.00033926963806152344 nb_pixel_total : 6795 time to create 1 rle with old method : 0.00871586799621582 length of segment : 82 time for calcul the mask position with numpy : 0.00949406623840332 nb_pixel_total : 501051 time to create 1 rle with new method : 0.026781797409057617 length of segment : 997 time for calcul the mask position with numpy : 0.006262779235839844 nb_pixel_total : 318285 time to create 1 rle with new method : 0.010091543197631836 length of segment : 663 time for calcul the mask position with numpy : 0.001768350601196289 nb_pixel_total : 67469 time to create 1 rle with old method : 0.0788266658782959 length of segment : 340 time for calcul the mask position with numpy : 0.0005276203155517578 nb_pixel_total : 19953 time to create 1 rle with old method : 0.023527860641479492 length of segment : 173 time for calcul the mask position with numpy : 0.002790212631225586 nb_pixel_total : 141903 time to create 1 rle with old method : 0.16393733024597168 length of segment : 478 time for calcul the mask position with numpy : 0.0008835792541503906 nb_pixel_total : 26645 time to create 1 rle with old method : 0.030925273895263672 length of segment : 239 time for calcul the mask position with numpy : 0.0011165142059326172 nb_pixel_total : 23142 time to create 1 rle with old method : 0.027916908264160156 length of segment : 237 time for calcul the mask position with numpy : 0.002132892608642578 nb_pixel_total : 58860 time to create 1 rle with old method : 0.06945180892944336 length of segment : 453 time for calcul the mask position with numpy : 0.0011639595031738281 nb_pixel_total : 48915 time to create 1 rle with old method : 0.0728461742401123 length of segment : 205 time for calcul the mask position with numpy : 0.00036525726318359375 nb_pixel_total : 7661 time to create 1 rle with old method : 0.009360790252685547 length of segment : 101 time for calcul the mask position with numpy : 0.33756542205810547 nb_pixel_total : 2342770 time to create 1 rle with new method : 0.43967723846435547 length of segment : 2161 time for calcul the mask position with numpy : 0.016970396041870117 nb_pixel_total : 829821 time to create 1 rle with new method : 0.19707608222961426 length of segment : 511 time for calcul the mask position with numpy : 0.15659594535827637 nb_pixel_total : 4131015 time to create 1 rle with new method : 0.906883716583252 length of segment : 3607 time for calcul the mask position with numpy : 0.4339308738708496 nb_pixel_total : 4052732 time to create 1 rle with new method : 0.29462647438049316 length of segment : 1613 time for calcul the mask position with numpy : 0.34853434562683105 nb_pixel_total : 3102941 time to create 1 rle with new method : 0.477764368057251 length of segment : 1373 time for calcul the mask position with numpy : 0.3822617530822754 nb_pixel_total : 4885247 time to create 1 rle with new method : 1.0852553844451904 length of segment : 2967 time spent for convertir_results : 22.114031314849854 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 79 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 67.58024549484253 time spend to save output : 0.10786199569702148 total time spend for step 1 : 67.68810749053955 step2:mask_detect Thu Aug 28 15:02:39 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 10379 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 15:02:42.806276: 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 15:02:42.832504: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 15:02:42.834681: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fec40000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:02:42.834746: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 15:02:42.839117: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 15:02:42.998850: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x9c75d10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:02:42.998952: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 15:02:43.000753: 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 15:02:43.001363: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:02:43.004860: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:02:43.009118: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:02:43.009515: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:02:43.013255: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:02:43.014445: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:02:43.022946: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:02:43.024906: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:02:43.025119: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:02:43.026210: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:02:43.026230: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:02:43.026241: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:02:43.027946: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9613 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 15:02:43.201727: 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 15:02:43.201911: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:02:43.201948: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:02:43.201978: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:02:43.202008: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:02:43.202037: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:02:43.202072: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:02:43.202103: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:02:43.204176: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:02:43.207197: 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 15:02:43.207324: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:02:43.207354: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:02:43.207382: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:02:43.207408: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:02:43.207453: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:02:43.207480: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:02:43.207507: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:02:43.209633: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:02:43.209686: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:02:43.209698: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:02:43.209709: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:02:43.211353: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9613 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 15:02:55.919539: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:02:56.071136: 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 : 6 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 64 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 47 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 71 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 73 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 82 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 5 Detection mask done ! Trying to reset tf kernel 3870589 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5311 tf kernel not reseted sub process len(results) : 6 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 6 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 : 0.0061876773834228516 nb_pixel_total : 55699 time to create 1 rle with old method : 0.07001471519470215 length of segment : 266 time for calcul the mask position with numpy : 0.0014755725860595703 nb_pixel_total : 76223 time to create 1 rle with old method : 0.08717226982116699 length of segment : 437 time for calcul the mask position with numpy : 0.0014142990112304688 nb_pixel_total : 49511 time to create 1 rle with old method : 0.056719303131103516 length of segment : 365 time for calcul the mask position with numpy : 0.0020530223846435547 nb_pixel_total : 74949 time to create 1 rle with old method : 0.11292386054992676 length of segment : 440 time for calcul the mask position with numpy : 0.003364086151123047 nb_pixel_total : 119181 time to create 1 rle with old method : 0.13477754592895508 length of segment : 482 time for calcul the mask position with numpy : 0.0009801387786865234 nb_pixel_total : 29732 time to create 1 rle with old method : 0.034731149673461914 length of segment : 146 time for calcul the mask position with numpy : 0.00392603874206543 nb_pixel_total : 159369 time to create 1 rle with new method : 0.016214370727539062 length of segment : 551 time for calcul the mask position with numpy : 0.002362489700317383 nb_pixel_total : 114748 time to create 1 rle with old method : 0.13231873512268066 length of segment : 597 time for calcul the mask position with numpy : 0.0023488998413085938 nb_pixel_total : 94953 time to create 1 rle with old method : 0.10854053497314453 length of segment : 382 time for calcul the mask position with numpy : 0.0024280548095703125 nb_pixel_total : 116967 time to create 1 rle with old method : 0.13240957260131836 length of segment : 441 time for calcul the mask position with numpy : 0.0017452239990234375 nb_pixel_total : 71320 time to create 1 rle with old method : 0.08236861228942871 length of segment : 323 time for calcul the mask position with numpy : 0.0009865760803222656 nb_pixel_total : 34454 time to create 1 rle with old method : 0.04116320610046387 length of segment : 270 time for calcul the mask position with numpy : 0.0007975101470947266 nb_pixel_total : 30227 time to create 1 rle with old method : 0.03584456443786621 length of segment : 212 time for calcul the mask position with numpy : 0.005668163299560547 nb_pixel_total : 264992 time to create 1 rle with new method : 0.019598722457885742 length of segment : 636 time for calcul the mask position with numpy : 0.0035915374755859375 nb_pixel_total : 153892 time to create 1 rle with new method : 0.010890007019042969 length of segment : 671 time for calcul the mask position with numpy : 0.0010204315185546875 nb_pixel_total : 49859 time to create 1 rle with old method : 0.05701279640197754 length of segment : 452 time for calcul the mask position with numpy : 0.0012519359588623047 nb_pixel_total : 52749 time to create 1 rle with old method : 0.06137228012084961 length of segment : 383 time for calcul the mask position with numpy : 0.010743141174316406 nb_pixel_total : 506907 time to create 1 rle with new method : 0.05130457878112793 length of segment : 975 time for calcul the mask position with numpy : 0.0008244514465332031 nb_pixel_total : 38440 time to create 1 rle with old method : 0.044406890869140625 length of segment : 275 time for calcul the mask position with numpy : 0.0023140907287597656 nb_pixel_total : 95106 time to create 1 rle with old method : 0.2292640209197998 length of segment : 387 time for calcul the mask position with numpy : 0.001407623291015625 nb_pixel_total : 41233 time to create 1 rle with old method : 0.07645916938781738 length of segment : 293 time for calcul the mask position with numpy : 0.007924079895019531 nb_pixel_total : 222472 time to create 1 rle with new method : 0.018890857696533203 length of segment : 648 time for calcul the mask position with numpy : 0.0009853839874267578 nb_pixel_total : 34348 time to create 1 rle with old method : 0.04149603843688965 length of segment : 222 time for calcul the mask position with numpy : 0.015951871871948242 nb_pixel_total : 641156 time to create 1 rle with new method : 0.04389357566833496 length of segment : 979 time for calcul the mask position with numpy : 0.006433010101318359 nb_pixel_total : 217606 time to create 1 rle with new method : 0.02234172821044922 length of segment : 845 time for calcul the mask position with numpy : 0.0009856224060058594 nb_pixel_total : 25142 time to create 1 rle with old method : 0.030490398406982422 length of segment : 383 time for calcul the mask position with numpy : 0.000705718994140625 nb_pixel_total : 31219 time to create 1 rle with old method : 0.03825640678405762 length of segment : 200 time for calcul the mask position with numpy : 0.0007441043853759766 nb_pixel_total : 36959 time to create 1 rle with old method : 0.04590344429016113 length of segment : 263 time for calcul the mask position with numpy : 0.00396275520324707 nb_pixel_total : 222459 time to create 1 rle with new method : 0.011150121688842773 length of segment : 556 time for calcul the mask position with numpy : 0.0009682178497314453 nb_pixel_total : 36755 time to create 1 rle with old method : 0.04306197166442871 length of segment : 145 time for calcul the mask position with numpy : 0.0021207332611083984 nb_pixel_total : 92527 time to create 1 rle with old method : 0.1179041862487793 length of segment : 387 time for calcul the mask position with numpy : 0.0007944107055664062 nb_pixel_total : 24960 time to create 1 rle with old method : 0.030132293701171875 length of segment : 201 time for calcul the mask position with numpy : 0.0014476776123046875 nb_pixel_total : 82714 time to create 1 rle with old method : 0.10550212860107422 length of segment : 654 time for calcul the mask position with numpy : 0.006539106369018555 nb_pixel_total : 264122 time to create 1 rle with new method : 0.01806497573852539 length of segment : 860 time for calcul the mask position with numpy : 0.0024390220642089844 nb_pixel_total : 56311 time to create 1 rle with old method : 0.06856274604797363 length of segment : 597 time for calcul the mask position with numpy : 0.003279447555541992 nb_pixel_total : 123775 time to create 1 rle with old method : 0.15204095840454102 length of segment : 452 time for calcul the mask position with numpy : 0.0018529891967773438 nb_pixel_total : 77841 time to create 1 rle with old method : 0.11219072341918945 length of segment : 381 time for calcul the mask position with numpy : 0.001020193099975586 nb_pixel_total : 29068 time to create 1 rle with old method : 0.03482365608215332 length of segment : 384 time for calcul the mask position with numpy : 0.0006592273712158203 nb_pixel_total : 23773 time to create 1 rle with old method : 0.028554201126098633 length of segment : 222 time for calcul the mask position with numpy : 0.009263038635253906 nb_pixel_total : 307414 time to create 1 rle with new method : 0.02500128746032715 length of segment : 841 time for calcul the mask position with numpy : 0.002216815948486328 nb_pixel_total : 67101 time to create 1 rle with old method : 0.08115530014038086 length of segment : 300 time for calcul the mask position with numpy : 0.0010738372802734375 nb_pixel_total : 55945 time to create 1 rle with old method : 0.06624603271484375 length of segment : 205 time for calcul the mask position with numpy : 0.002975940704345703 nb_pixel_total : 145489 time to create 1 rle with old method : 0.1773231029510498 length of segment : 478 time for calcul the mask position with numpy : 0.0018041133880615234 nb_pixel_total : 80788 time to create 1 rle with old method : 0.09253144264221191 length of segment : 325 time for calcul the mask position with numpy : 0.0033385753631591797 nb_pixel_total : 133610 time to create 1 rle with old method : 0.156141996383667 length of segment : 657 time for calcul the mask position with numpy : 0.009113311767578125 nb_pixel_total : 235806 time to create 1 rle with new method : 0.026285648345947266 length of segment : 687 time for calcul the mask position with numpy : 0.0019698143005371094 nb_pixel_total : 97194 time to create 1 rle with old method : 0.12483549118041992 length of segment : 556 time for calcul the mask position with numpy : 0.008235692977905273 nb_pixel_total : 365276 time to create 1 rle with new method : 0.028466224670410156 length of segment : 848 time for calcul the mask position with numpy : 0.008843660354614258 nb_pixel_total : 220808 time to create 1 rle with new method : 0.022019386291503906 length of segment : 770 time for calcul the mask position with numpy : 0.0015380382537841797 nb_pixel_total : 56742 time to create 1 rle with old method : 0.06468725204467773 length of segment : 573 time for calcul the mask position with numpy : 0.0025501251220703125 nb_pixel_total : 130207 time to create 1 rle with old method : 0.16614317893981934 length of segment : 660 time for calcul the mask position with numpy : 0.004857063293457031 nb_pixel_total : 240019 time to create 1 rle with new method : 0.013103246688842773 length of segment : 572 time for calcul the mask position with numpy : 0.002215147018432617 nb_pixel_total : 89935 time to create 1 rle with old method : 0.10266947746276855 length of segment : 481 time for calcul the mask position with numpy : 0.0021262168884277344 nb_pixel_total : 97611 time to create 1 rle with old method : 0.11124825477600098 length of segment : 517 time for calcul the mask position with numpy : 0.0006291866302490234 nb_pixel_total : 29789 time to create 1 rle with old method : 0.03436708450317383 length of segment : 151 time for calcul the mask position with numpy : 0.008394956588745117 nb_pixel_total : 356728 time to create 1 rle with new method : 0.02610039710998535 length of segment : 772 time for calcul the mask position with numpy : 0.0013606548309326172 nb_pixel_total : 73356 time to create 1 rle with old method : 0.08474516868591309 length of segment : 357 time for calcul the mask position with numpy : 0.0021369457244873047 nb_pixel_total : 85582 time to create 1 rle with old method : 0.11289238929748535 length of segment : 359 time for calcul the mask position with numpy : 0.0037403106689453125 nb_pixel_total : 138244 time to create 1 rle with old method : 0.15756654739379883 length of segment : 576 time for calcul the mask position with numpy : 0.0020177364349365234 nb_pixel_total : 67443 time to create 1 rle with old method : 0.0775749683380127 length of segment : 345 time for calcul the mask position with numpy : 0.0007460117340087891 nb_pixel_total : 18008 time to create 1 rle with old method : 0.021242141723632812 length of segment : 196 time for calcul the mask position with numpy : 0.0007510185241699219 nb_pixel_total : 15262 time to create 1 rle with old method : 0.01746082305908203 length of segment : 194 time for calcul the mask position with numpy : 0.0023183822631835938 nb_pixel_total : 119268 time to create 1 rle with old method : 0.13736224174499512 length of segment : 374 time for calcul the mask position with numpy : 0.0015673637390136719 nb_pixel_total : 54353 time to create 1 rle with old method : 0.08686280250549316 length of segment : 328 time for calcul the mask position with numpy : 0.004998445510864258 nb_pixel_total : 273996 time to create 1 rle with new method : 0.012730121612548828 length of segment : 746 time for calcul the mask position with numpy : 0.001844644546508789 nb_pixel_total : 67209 time to create 1 rle with old method : 0.07907462120056152 length of segment : 314 time for calcul the mask position with numpy : 0.0007848739624023438 nb_pixel_total : 36512 time to create 1 rle with old method : 0.046726226806640625 length of segment : 382 time for calcul the mask position with numpy : 0.0039637088775634766 nb_pixel_total : 180763 time to create 1 rle with new method : 0.009958267211914062 length of segment : 634 time for calcul the mask position with numpy : 0.004309415817260742 nb_pixel_total : 201452 time to create 1 rle with new method : 0.010497808456420898 length of segment : 412 time for calcul the mask position with numpy : 0.009127140045166016 nb_pixel_total : 478185 time to create 1 rle with new method : 0.02201676368713379 length of segment : 1104 time for calcul the mask position with numpy : 0.0019407272338867188 nb_pixel_total : 103018 time to create 1 rle with old method : 0.1487889289855957 length of segment : 426 time for calcul the mask position with numpy : 0.0059163570404052734 nb_pixel_total : 274230 time to create 1 rle with new method : 0.017004013061523438 length of segment : 514 time for calcul the mask position with numpy : 0.0019383430480957031 nb_pixel_total : 102733 time to create 1 rle with old method : 0.13379335403442383 length of segment : 354 time for calcul the mask position with numpy : 0.0007169246673583984 nb_pixel_total : 36245 time to create 1 rle with old method : 0.04215526580810547 length of segment : 365 time for calcul the mask position with numpy : 0.0019953250885009766 nb_pixel_total : 102149 time to create 1 rle with old method : 0.1204690933227539 length of segment : 410 time for calcul the mask position with numpy : 0.0011425018310546875 nb_pixel_total : 56870 time to create 1 rle with old method : 0.06852865219116211 length of segment : 293 time for calcul the mask position with numpy : 0.007313251495361328 nb_pixel_total : 344062 time to create 1 rle with new method : 0.020532608032226562 length of segment : 908 time for calcul the mask position with numpy : 0.013708114624023438 nb_pixel_total : 677307 time to create 1 rle with new method : 0.04126763343811035 length of segment : 916 time for calcul the mask position with numpy : 0.007885217666625977 nb_pixel_total : 395328 time to create 1 rle with new method : 0.019867420196533203 length of segment : 838 time for calcul the mask position with numpy : 0.0007140636444091797 nb_pixel_total : 34776 time to create 1 rle with old method : 0.040648460388183594 length of segment : 217 time for calcul the mask position with numpy : 0.002207517623901367 nb_pixel_total : 118830 time to create 1 rle with old method : 0.15326642990112305 length of segment : 476 time for calcul the mask position with numpy : 0.0016684532165527344 nb_pixel_total : 105678 time to create 1 rle with old method : 0.11782240867614746 length of segment : 391 time for calcul the mask position with numpy : 0.0008842945098876953 nb_pixel_total : 43323 time to create 1 rle with old method : 0.05008649826049805 length of segment : 190 time for calcul the mask position with numpy : 0.0007491111755371094 nb_pixel_total : 37730 time to create 1 rle with old method : 0.04280257225036621 length of segment : 322 time for calcul the mask position with numpy : 0.006388425827026367 nb_pixel_total : 384012 time to create 1 rle with new method : 0.015553474426269531 length of segment : 730 time for calcul the mask position with numpy : 0.0005412101745605469 nb_pixel_total : 12119 time to create 1 rle with old method : 0.014365911483764648 length of segment : 159 time for calcul the mask position with numpy : 0.0024728775024414062 nb_pixel_total : 130491 time to create 1 rle with old method : 0.1509692668914795 length of segment : 277 time for calcul the mask position with numpy : 0.002459287643432617 nb_pixel_total : 90770 time to create 1 rle with old method : 0.10241389274597168 length of segment : 582 time for calcul the mask position with numpy : 0.0026776790618896484 nb_pixel_total : 150753 time to create 1 rle with new method : 0.007086992263793945 length of segment : 455 time for calcul the mask position with numpy : 0.0016155242919921875 nb_pixel_total : 76067 time to create 1 rle with old method : 0.08687901496887207 length of segment : 447 time for calcul the mask position with numpy : 0.0018603801727294922 nb_pixel_total : 91319 time to create 1 rle with old method : 0.12631750106811523 length of segment : 368 time for calcul the mask position with numpy : 0.002074003219604492 nb_pixel_total : 95862 time to create 1 rle with old method : 0.11352300643920898 length of segment : 413 time for calcul the mask position with numpy : 0.001791238784790039 nb_pixel_total : 91127 time to create 1 rle with old method : 0.10846900939941406 length of segment : 204 time for calcul the mask position with numpy : 0.010654926300048828 nb_pixel_total : 566190 time to create 1 rle with new method : 0.02515554428100586 length of segment : 810 time for calcul the mask position with numpy : 0.008412837982177734 nb_pixel_total : 318250 time to create 1 rle with new method : 0.026519298553466797 length of segment : 900 time for calcul the mask position with numpy : 0.003228425979614258 nb_pixel_total : 183955 time to create 1 rle with new method : 0.008592844009399414 length of segment : 447 time for calcul the mask position with numpy : 0.0008165836334228516 nb_pixel_total : 36496 time to create 1 rle with old method : 0.0605463981628418 length of segment : 259 time for calcul the mask position with numpy : 0.007708072662353516 nb_pixel_total : 332945 time to create 1 rle with new method : 0.022332429885864258 length of segment : 1084 time for calcul the mask position with numpy : 0.002758026123046875 nb_pixel_total : 101247 time to create 1 rle with old method : 0.12018728256225586 length of segment : 612 time for calcul the mask position with numpy : 0.0003631114959716797 nb_pixel_total : 16076 time to create 1 rle with old method : 0.019048213958740234 length of segment : 130 time for calcul the mask position with numpy : 0.004852294921875 nb_pixel_total : 236949 time to create 1 rle with new method : 0.013486385345458984 length of segment : 552 time for calcul the mask position with numpy : 0.009016752243041992 nb_pixel_total : 576385 time to create 1 rle with new method : 0.01964092254638672 length of segment : 700 time for calcul the mask position with numpy : 0.0017571449279785156 nb_pixel_total : 76414 time to create 1 rle with old method : 0.08632111549377441 length of segment : 536 time for calcul the mask position with numpy : 0.0020093917846679688 nb_pixel_total : 108897 time to create 1 rle with old method : 0.12469148635864258 length of segment : 614 time for calcul the mask position with numpy : 0.010770559310913086 nb_pixel_total : 552135 time to create 1 rle with new method : 0.029085159301757812 length of segment : 1234 time for calcul the mask position with numpy : 0.007048368453979492 nb_pixel_total : 393256 time to create 1 rle with new method : 0.018630504608154297 length of segment : 723 time for calcul the mask position with numpy : 0.01911759376525879 nb_pixel_total : 830281 time to create 1 rle with new method : 0.197662353515625 length of segment : 1320 time for calcul the mask position with numpy : 0.011258363723754883 nb_pixel_total : 616888 time to create 1 rle with new method : 0.05818939208984375 length of segment : 784 time for calcul the mask position with numpy : 0.001430511474609375 nb_pixel_total : 83020 time to create 1 rle with old method : 0.09385991096496582 length of segment : 266 time for calcul the mask position with numpy : 0.0018155574798583984 nb_pixel_total : 125749 time to create 1 rle with old method : 0.14346694946289062 length of segment : 447 time for calcul the mask position with numpy : 0.0015985965728759766 nb_pixel_total : 83657 time to create 1 rle with old method : 0.09399819374084473 length of segment : 389 time for calcul the mask position with numpy : 0.0016028881072998047 nb_pixel_total : 70860 time to create 1 rle with old method : 0.0814659595489502 length of segment : 388 time for calcul the mask position with numpy : 0.005936861038208008 nb_pixel_total : 278778 time to create 1 rle with new method : 0.016033411026000977 length of segment : 1009 time for calcul the mask position with numpy : 0.002115011215209961 nb_pixel_total : 106843 time to create 1 rle with old method : 0.14616036415100098 length of segment : 350 time for calcul the mask position with numpy : 0.0020270347595214844 nb_pixel_total : 68301 time to create 1 rle with old method : 0.07711362838745117 length of segment : 447 time for calcul the mask position with numpy : 0.004510164260864258 nb_pixel_total : 181130 time to create 1 rle with new method : 0.014346599578857422 length of segment : 848 time for calcul the mask position with numpy : 0.0018107891082763672 nb_pixel_total : 106053 time to create 1 rle with old method : 0.11841845512390137 length of segment : 333 time for calcul the mask position with numpy : 0.013018369674682617 nb_pixel_total : 615236 time to create 1 rle with new method : 0.029948949813842773 length of segment : 874 time for calcul the mask position with numpy : 0.0014619827270507812 nb_pixel_total : 61499 time to create 1 rle with old method : 0.06944918632507324 length of segment : 430 time for calcul the mask position with numpy : 0.0014047622680664062 nb_pixel_total : 67243 time to create 1 rle with old method : 0.07812333106994629 length of segment : 271 time for calcul the mask position with numpy : 0.0010385513305664062 nb_pixel_total : 54346 time to create 1 rle with old method : 0.062163352966308594 length of segment : 171 time for calcul the mask position with numpy : 0.020584821701049805 nb_pixel_total : 1071452 time to create 1 rle with new method : 0.07857108116149902 length of segment : 1487 time for calcul the mask position with numpy : 0.0012176036834716797 nb_pixel_total : 65296 time to create 1 rle with old method : 0.07231402397155762 length of segment : 231 time for calcul the mask position with numpy : 0.0005929470062255859 nb_pixel_total : 25929 time to create 1 rle with old method : 0.029560565948486328 length of segment : 231 time for calcul the mask position with numpy : 0.0008387565612792969 nb_pixel_total : 40973 time to create 1 rle with old method : 0.04723215103149414 length of segment : 236 time for calcul the mask position with numpy : 0.0013725757598876953 nb_pixel_total : 63663 time to create 1 rle with old method : 0.07244539260864258 length of segment : 229 time for calcul the mask position with numpy : 0.0020210742950439453 nb_pixel_total : 65899 time to create 1 rle with old method : 0.07723212242126465 length of segment : 270 time for calcul the mask position with numpy : 0.0006067752838134766 nb_pixel_total : 23631 time to create 1 rle with old method : 0.027399301528930664 length of segment : 216 time for calcul the mask position with numpy : 0.0009891986846923828 nb_pixel_total : 51716 time to create 1 rle with old method : 0.058563947677612305 length of segment : 321 time for calcul the mask position with numpy : 0.0064013004302978516 nb_pixel_total : 332243 time to create 1 rle with new method : 0.017879247665405273 length of segment : 494 time for calcul the mask position with numpy : 0.002621173858642578 nb_pixel_total : 108608 time to create 1 rle with old method : 0.12236976623535156 length of segment : 502 time for calcul the mask position with numpy : 0.00318145751953125 nb_pixel_total : 148260 time to create 1 rle with old method : 0.16466879844665527 length of segment : 498 time for calcul the mask position with numpy : 0.0007123947143554688 nb_pixel_total : 29813 time to create 1 rle with old method : 0.03462958335876465 length of segment : 262 time for calcul the mask position with numpy : 0.010954618453979492 nb_pixel_total : 514807 time to create 1 rle with new method : 0.04784226417541504 length of segment : 814 time for calcul the mask position with numpy : 0.0047969818115234375 nb_pixel_total : 282930 time to create 1 rle with new method : 0.012837409973144531 length of segment : 940 time for calcul the mask position with numpy : 0.00217437744140625 nb_pixel_total : 84633 time to create 1 rle with old method : 0.12128162384033203 length of segment : 496 time for calcul the mask position with numpy : 0.0021381378173828125 nb_pixel_total : 96301 time to create 1 rle with old method : 0.11417078971862793 length of segment : 225 time for calcul the mask position with numpy : 0.0012612342834472656 nb_pixel_total : 45077 time to create 1 rle with old method : 0.051790475845336914 length of segment : 256 time for calcul the mask position with numpy : 0.0020775794982910156 nb_pixel_total : 55008 time to create 1 rle with old method : 0.061018943786621094 length of segment : 562 time for calcul the mask position with numpy : 0.0008378028869628906 nb_pixel_total : 43139 time to create 1 rle with old method : 0.04684042930603027 length of segment : 188 time for calcul the mask position with numpy : 0.0006034374237060547 nb_pixel_total : 17578 time to create 1 rle with old method : 0.019362211227416992 length of segment : 155 time for calcul the mask position with numpy : 0.0018541812896728516 nb_pixel_total : 77041 time to create 1 rle with old method : 0.086334228515625 length of segment : 408 time for calcul the mask position with numpy : 0.0015349388122558594 nb_pixel_total : 64808 time to create 1 rle with old method : 0.07284259796142578 length of segment : 271 time for calcul the mask position with numpy : 0.004130363464355469 nb_pixel_total : 240945 time to create 1 rle with new method : 0.010226011276245117 length of segment : 594 time for calcul the mask position with numpy : 0.0018434524536132812 nb_pixel_total : 98722 time to create 1 rle with old method : 0.11087274551391602 length of segment : 385 time for calcul the mask position with numpy : 0.001720428466796875 nb_pixel_total : 83729 time to create 1 rle with old method : 0.09766483306884766 length of segment : 332 time for calcul the mask position with numpy : 0.004660367965698242 nb_pixel_total : 206647 time to create 1 rle with new method : 0.012873411178588867 length of segment : 456 time for calcul the mask position with numpy : 0.0010249614715576172 nb_pixel_total : 26052 time to create 1 rle with old method : 0.031035661697387695 length of segment : 212 time for calcul the mask position with numpy : 0.0016264915466308594 nb_pixel_total : 80508 time to create 1 rle with old method : 0.09366750717163086 length of segment : 410 time for calcul the mask position with numpy : 0.003013134002685547 nb_pixel_total : 172180 time to create 1 rle with new method : 0.008201837539672852 length of segment : 854 time for calcul the mask position with numpy : 0.0021507740020751953 nb_pixel_total : 104830 time to create 1 rle with old method : 0.1459050178527832 length of segment : 470 time for calcul the mask position with numpy : 0.0029506683349609375 nb_pixel_total : 177755 time to create 1 rle with new method : 0.008011102676391602 length of segment : 746 time for calcul the mask position with numpy : 0.00407099723815918 nb_pixel_total : 208068 time to create 1 rle with new method : 0.011490345001220703 length of segment : 461 time for calcul the mask position with numpy : 0.0016252994537353516 nb_pixel_total : 82479 time to create 1 rle with old method : 0.09520292282104492 length of segment : 309 time for calcul the mask position with numpy : 0.0008566379547119141 nb_pixel_total : 37241 time to create 1 rle with old method : 0.041991233825683594 length of segment : 361 time for calcul the mask position with numpy : 0.005098104476928711 nb_pixel_total : 294603 time to create 1 rle with new method : 0.014324665069580078 length of segment : 657 time for calcul the mask position with numpy : 0.0007827281951904297 nb_pixel_total : 26473 time to create 1 rle with old method : 0.031651973724365234 length of segment : 208 time for calcul the mask position with numpy : 0.0006649494171142578 nb_pixel_total : 33188 time to create 1 rle with old method : 0.0400850772857666 length of segment : 175 time for calcul the mask position with numpy : 0.003976583480834961 nb_pixel_total : 202400 time to create 1 rle with new method : 0.012044668197631836 length of segment : 574 time for calcul the mask position with numpy : 0.0030045509338378906 nb_pixel_total : 151774 time to create 1 rle with new method : 0.007915735244750977 length of segment : 256 time for calcul the mask position with numpy : 0.0013706684112548828 nb_pixel_total : 54252 time to create 1 rle with old method : 0.06297969818115234 length of segment : 257 time for calcul the mask position with numpy : 0.005384922027587891 nb_pixel_total : 333289 time to create 1 rle with new method : 0.013655662536621094 length of segment : 616 time for calcul the mask position with numpy : 0.001264333724975586 nb_pixel_total : 55377 time to create 1 rle with old method : 0.0819711685180664 length of segment : 389 time for calcul the mask position with numpy : 0.0016870498657226562 nb_pixel_total : 52971 time to create 1 rle with old method : 0.06119966506958008 length of segment : 327 time for calcul the mask position with numpy : 0.0032198429107666016 nb_pixel_total : 154279 time to create 1 rle with new method : 0.009018659591674805 length of segment : 501 time for calcul the mask position with numpy : 0.001676321029663086 nb_pixel_total : 85354 time to create 1 rle with old method : 0.09517693519592285 length of segment : 379 time for calcul the mask position with numpy : 0.0052297115325927734 nb_pixel_total : 252886 time to create 1 rle with new method : 0.015015840530395508 length of segment : 629 time for calcul the mask position with numpy : 0.007141590118408203 nb_pixel_total : 334008 time to create 1 rle with new method : 0.021030902862548828 length of segment : 1291 time for calcul the mask position with numpy : 0.008239030838012695 nb_pixel_total : 459765 time to create 1 rle with new method : 0.020424604415893555 length of segment : 617 time for calcul the mask position with numpy : 0.0015740394592285156 nb_pixel_total : 55548 time to create 1 rle with old method : 0.06218123435974121 length of segment : 286 time for calcul the mask position with numpy : 0.0005488395690917969 nb_pixel_total : 6694 time to create 1 rle with old method : 0.0076541900634765625 length of segment : 131 time for calcul the mask position with numpy : 0.006352901458740234 nb_pixel_total : 273624 time to create 1 rle with new method : 0.020284414291381836 length of segment : 649 time for calcul the mask position with numpy : 0.004874467849731445 nb_pixel_total : 331417 time to create 1 rle with new method : 0.012782573699951172 length of segment : 615 time for calcul the mask position with numpy : 0.002368450164794922 nb_pixel_total : 108380 time to create 1 rle with old method : 0.12443995475769043 length of segment : 333 time for calcul the mask position with numpy : 0.0018274784088134766 nb_pixel_total : 75648 time to create 1 rle with old method : 0.08349347114562988 length of segment : 502 time for calcul the mask position with numpy : 0.007333278656005859 nb_pixel_total : 471605 time to create 1 rle with new method : 0.01873159408569336 length of segment : 747 time for calcul the mask position with numpy : 0.006912708282470703 nb_pixel_total : 256360 time to create 1 rle with new method : 0.022769689559936523 length of segment : 661 time for calcul the mask position with numpy : 0.0008041858673095703 nb_pixel_total : 32748 time to create 1 rle with old method : 0.036958932876586914 length of segment : 248 time for calcul the mask position with numpy : 0.0010578632354736328 nb_pixel_total : 47138 time to create 1 rle with old method : 0.05565786361694336 length of segment : 266 time for calcul the mask position with numpy : 0.015323162078857422 nb_pixel_total : 501909 time to create 1 rle with new method : 0.11469507217407227 length of segment : 850 time for calcul the mask position with numpy : 0.003910064697265625 nb_pixel_total : 153614 time to create 1 rle with new method : 0.012144327163696289 length of segment : 473 time for calcul the mask position with numpy : 0.0031137466430664062 nb_pixel_total : 146794 time to create 1 rle with old method : 0.1743147373199463 length of segment : 486 time for calcul the mask position with numpy : 0.0021479129791259766 nb_pixel_total : 97840 time to create 1 rle with old method : 0.11998844146728516 length of segment : 529 time for calcul the mask position with numpy : 0.003673553466796875 nb_pixel_total : 186362 time to create 1 rle with new method : 0.009367704391479492 length of segment : 496 time for calcul the mask position with numpy : 0.0015692710876464844 nb_pixel_total : 75358 time to create 1 rle with old method : 0.09811925888061523 length of segment : 511 time for calcul the mask position with numpy : 0.0038199424743652344 nb_pixel_total : 195634 time to create 1 rle with new method : 0.01000356674194336 length of segment : 750 time for calcul the mask position with numpy : 0.004074811935424805 nb_pixel_total : 160882 time to create 1 rle with new method : 0.011028766632080078 length of segment : 439 time for calcul the mask position with numpy : 0.0025467872619628906 nb_pixel_total : 114778 time to create 1 rle with old method : 0.13299965858459473 length of segment : 428 time for calcul the mask position with numpy : 0.0012865066528320312 nb_pixel_total : 67660 time to create 1 rle with old method : 0.09102153778076172 length of segment : 285 time for calcul the mask position with numpy : 0.010474681854248047 nb_pixel_total : 439112 time to create 1 rle with new method : 0.4976627826690674 length of segment : 641 time for calcul the mask position with numpy : 0.0012471675872802734 nb_pixel_total : 50712 time to create 1 rle with old method : 0.0590670108795166 length of segment : 261 time for calcul the mask position with numpy : 0.003023386001586914 nb_pixel_total : 137216 time to create 1 rle with old method : 0.15869903564453125 length of segment : 426 time for calcul the mask position with numpy : 0.004281044006347656 nb_pixel_total : 204943 time to create 1 rle with new method : 0.011864900588989258 length of segment : 598 time for calcul the mask position with numpy : 0.004219532012939453 nb_pixel_total : 220603 time to create 1 rle with new method : 0.010793924331665039 length of segment : 483 time for calcul the mask position with numpy : 0.0006804466247558594 nb_pixel_total : 25826 time to create 1 rle with old method : 0.030399799346923828 length of segment : 232 time for calcul the mask position with numpy : 0.002192974090576172 nb_pixel_total : 116332 time to create 1 rle with old method : 0.13482141494750977 length of segment : 340 time for calcul the mask position with numpy : 0.0009019374847412109 nb_pixel_total : 41951 time to create 1 rle with old method : 0.0486910343170166 length of segment : 281 time for calcul the mask position with numpy : 0.003162860870361328 nb_pixel_total : 144513 time to create 1 rle with old method : 0.1685340404510498 length of segment : 449 time for calcul the mask position with numpy : 0.0009970664978027344 nb_pixel_total : 43431 time to create 1 rle with old method : 0.051569223403930664 length of segment : 246 time for calcul the mask position with numpy : 0.0024614334106445312 nb_pixel_total : 101263 time to create 1 rle with old method : 0.11762475967407227 length of segment : 646 time for calcul the mask position with numpy : 0.0007493495941162109 nb_pixel_total : 28862 time to create 1 rle with old method : 0.0332798957824707 length of segment : 462 time for calcul the mask position with numpy : 0.020349979400634766 nb_pixel_total : 624854 time to create 1 rle with new method : 0.14873003959655762 length of segment : 2098 time for calcul the mask position with numpy : 0.004669904708862305 nb_pixel_total : 222226 time to create 1 rle with new method : 0.013679027557373047 length of segment : 1205 time for calcul the mask position with numpy : 0.003268718719482422 nb_pixel_total : 158166 time to create 1 rle with new method : 0.008500814437866211 length of segment : 435 time for calcul the mask position with numpy : 0.0019073486328125 nb_pixel_total : 66028 time to create 1 rle with old method : 0.07638955116271973 length of segment : 465 time for calcul the mask position with numpy : 0.0012938976287841797 nb_pixel_total : 56931 time to create 1 rle with old method : 0.0694117546081543 length of segment : 247 time for calcul the mask position with numpy : 0.0019178390502929688 nb_pixel_total : 101759 time to create 1 rle with old method : 0.12291312217712402 length of segment : 313 time for calcul the mask position with numpy : 0.00045037269592285156 nb_pixel_total : 19859 time to create 1 rle with old method : 0.024239063262939453 length of segment : 107 time for calcul the mask position with numpy : 0.001207590103149414 nb_pixel_total : 46183 time to create 1 rle with old method : 0.05469775199890137 length of segment : 337 time for calcul the mask position with numpy : 0.0037369728088378906 nb_pixel_total : 177795 time to create 1 rle with new method : 0.010223150253295898 length of segment : 416 time for calcul the mask position with numpy : 0.0007309913635253906 nb_pixel_total : 27323 time to create 1 rle with old method : 0.03285956382751465 length of segment : 216 time for calcul the mask position with numpy : 0.0007796287536621094 nb_pixel_total : 36197 time to create 1 rle with old method : 0.042330026626586914 length of segment : 216 time for calcul the mask position with numpy : 0.0007140636444091797 nb_pixel_total : 18929 time to create 1 rle with old method : 0.022347211837768555 length of segment : 321 time for calcul the mask position with numpy : 0.004388093948364258 nb_pixel_total : 191721 time to create 1 rle with new method : 0.013373374938964844 length of segment : 541 time for calcul the mask position with numpy : 0.005307912826538086 nb_pixel_total : 264969 time to create 1 rle with new method : 0.012853384017944336 length of segment : 449 time for calcul the mask position with numpy : 0.001020193099975586 nb_pixel_total : 25623 time to create 1 rle with old method : 0.03037285804748535 length of segment : 168 time for calcul the mask position with numpy : 0.005661725997924805 nb_pixel_total : 255706 time to create 1 rle with new method : 0.015421867370605469 length of segment : 642 time for calcul the mask position with numpy : 0.008071184158325195 nb_pixel_total : 362198 time to create 1 rle with new method : 0.04351353645324707 length of segment : 981 time for calcul the mask position with numpy : 0.002415180206298828 nb_pixel_total : 86695 time to create 1 rle with old method : 0.10212826728820801 length of segment : 630 time for calcul the mask position with numpy : 0.0012879371643066406 nb_pixel_total : 60981 time to create 1 rle with old method : 0.07010889053344727 length of segment : 234 time for calcul the mask position with numpy : 0.0024597644805908203 nb_pixel_total : 100329 time to create 1 rle with old method : 0.11888670921325684 length of segment : 281 time for calcul the mask position with numpy : 0.008436918258666992 nb_pixel_total : 392998 time to create 1 rle with new method : 0.023962020874023438 length of segment : 644 time for calcul the mask position with numpy : 0.001003265380859375 nb_pixel_total : 31848 time to create 1 rle with old method : 0.03701329231262207 length of segment : 264 time for calcul the mask position with numpy : 0.0006144046783447266 nb_pixel_total : 28147 time to create 1 rle with old method : 0.03235316276550293 length of segment : 173 time for calcul the mask position with numpy : 0.0005974769592285156 nb_pixel_total : 23120 time to create 1 rle with old method : 0.026699304580688477 length of segment : 123 time for calcul the mask position with numpy : 0.003281831741333008 nb_pixel_total : 168159 time to create 1 rle with new method : 0.008624553680419922 length of segment : 411 time for calcul the mask position with numpy : 0.0018687248229980469 nb_pixel_total : 56576 time to create 1 rle with old method : 0.06623673439025879 length of segment : 368 time for calcul the mask position with numpy : 0.005250453948974609 nb_pixel_total : 314918 time to create 1 rle with new method : 0.013923168182373047 length of segment : 685 time for calcul the mask position with numpy : 0.0030050277709960938 nb_pixel_total : 133705 time to create 1 rle with old method : 0.15031743049621582 length of segment : 464 time for calcul the mask position with numpy : 0.0020155906677246094 nb_pixel_total : 78507 time to create 1 rle with old method : 0.09149551391601562 length of segment : 333 time for calcul the mask position with numpy : 0.006783008575439453 nb_pixel_total : 263999 time to create 1 rle with new method : 0.02164006233215332 length of segment : 1308 time for calcul the mask position with numpy : 0.003931999206542969 nb_pixel_total : 150828 time to create 1 rle with new method : 0.010830163955688477 length of segment : 447 time for calcul the mask position with numpy : 0.005266427993774414 nb_pixel_total : 261351 time to create 1 rle with new method : 0.014701366424560547 length of segment : 590 time for calcul the mask position with numpy : 0.0009722709655761719 nb_pixel_total : 29209 time to create 1 rle with old method : 0.03368568420410156 length of segment : 183 time for calcul the mask position with numpy : 0.0009953975677490234 nb_pixel_total : 49558 time to create 1 rle with old method : 0.07539200782775879 length of segment : 217 time for calcul the mask position with numpy : 0.0067026615142822266 nb_pixel_total : 272590 time to create 1 rle with new method : 0.021515846252441406 length of segment : 705 time for calcul the mask position with numpy : 0.00555419921875 nb_pixel_total : 267610 time to create 1 rle with new method : 0.01738595962524414 length of segment : 850 time for calcul the mask position with numpy : 0.0311281681060791 nb_pixel_total : 1018326 time to create 1 rle with new method : 0.8772597312927246 length of segment : 1028 time for calcul the mask position with numpy : 0.013834238052368164 nb_pixel_total : 513229 time to create 1 rle with new method : 0.07001352310180664 length of segment : 991 time for calcul the mask position with numpy : 0.0007717609405517578 nb_pixel_total : 33465 time to create 1 rle with old method : 0.04013562202453613 length of segment : 229 time for calcul the mask position with numpy : 0.002503633499145508 nb_pixel_total : 118566 time to create 1 rle with old method : 0.20864081382751465 length of segment : 328 time for calcul the mask position with numpy : 0.001646280288696289 nb_pixel_total : 73858 time to create 1 rle with old method : 0.08656191825866699 length of segment : 303 time for calcul the mask position with numpy : 0.00312042236328125 nb_pixel_total : 145767 time to create 1 rle with old method : 0.17134451866149902 length of segment : 350 time for calcul the mask position with numpy : 0.0027735233306884766 nb_pixel_total : 141522 time to create 1 rle with old method : 0.1615312099456787 length of segment : 355 time for calcul the mask position with numpy : 0.0022726058959960938 nb_pixel_total : 19547 time to create 1 rle with old method : 0.023455142974853516 length of segment : 230 time for calcul the mask position with numpy : 0.0054242610931396484 nb_pixel_total : 206145 time to create 1 rle with new method : 0.017301082611083984 length of segment : 871 time for calcul the mask position with numpy : 0.0018832683563232422 nb_pixel_total : 56977 time to create 1 rle with old method : 0.06667876243591309 length of segment : 289 time for calcul the mask position with numpy : 0.0011701583862304688 nb_pixel_total : 46869 time to create 1 rle with old method : 0.053957223892211914 length of segment : 174 time for calcul the mask position with numpy : 0.0032401084899902344 nb_pixel_total : 140701 time to create 1 rle with old method : 0.1611793041229248 length of segment : 703 time for calcul the mask position with numpy : 0.0026671886444091797 nb_pixel_total : 90000 time to create 1 rle with old method : 0.11827611923217773 length of segment : 454 time for calcul the mask position with numpy : 0.001519918441772461 nb_pixel_total : 58405 time to create 1 rle with old method : 0.06788754463195801 length of segment : 309 time for calcul the mask position with numpy : 0.0045435428619384766 nb_pixel_total : 172175 time to create 1 rle with new method : 0.011384963989257812 length of segment : 504 time for calcul the mask position with numpy : 0.0012323856353759766 nb_pixel_total : 53511 time to create 1 rle with old method : 0.05970430374145508 length of segment : 247 time for calcul the mask position with numpy : 0.0020558834075927734 nb_pixel_total : 106621 time to create 1 rle with old method : 0.1221921443939209 length of segment : 428 time for calcul the mask position with numpy : 0.002276182174682617 nb_pixel_total : 110319 time to create 1 rle with old method : 0.12261080741882324 length of segment : 435 time for calcul the mask position with numpy : 0.0016083717346191406 nb_pixel_total : 56300 time to create 1 rle with old method : 0.06383132934570312 length of segment : 214 time for calcul the mask position with numpy : 0.001995086669921875 nb_pixel_total : 48388 time to create 1 rle with old method : 0.053476810455322266 length of segment : 293 time for calcul the mask position with numpy : 0.003426790237426758 nb_pixel_total : 132949 time to create 1 rle with old method : 0.1469099521636963 length of segment : 434 time for calcul the mask position with numpy : 0.002905607223510742 nb_pixel_total : 108538 time to create 1 rle with old method : 0.11862754821777344 length of segment : 453 time for calcul the mask position with numpy : 0.0010712146759033203 nb_pixel_total : 42665 time to create 1 rle with old method : 0.048113346099853516 length of segment : 216 time for calcul the mask position with numpy : 0.0013837814331054688 nb_pixel_total : 64867 time to create 1 rle with old method : 0.07132697105407715 length of segment : 320 time for calcul the mask position with numpy : 0.002192258834838867 nb_pixel_total : 78484 time to create 1 rle with old method : 0.08699774742126465 length of segment : 481 time for calcul the mask position with numpy : 0.01057887077331543 nb_pixel_total : 537024 time to create 1 rle with new method : 0.026068925857543945 length of segment : 895 time for calcul the mask position with numpy : 0.0025975704193115234 nb_pixel_total : 123433 time to create 1 rle with old method : 0.13710856437683105 length of segment : 451 time for calcul the mask position with numpy : 0.0019681453704833984 nb_pixel_total : 82465 time to create 1 rle with old method : 0.09728693962097168 length of segment : 455 time for calcul the mask position with numpy : 0.002168416976928711 nb_pixel_total : 88570 time to create 1 rle with old method : 0.10345768928527832 length of segment : 359 time for calcul the mask position with numpy : 0.004143238067626953 nb_pixel_total : 196212 time to create 1 rle with new method : 0.011710882186889648 length of segment : 449 time for calcul the mask position with numpy : 0.0031023025512695312 nb_pixel_total : 128687 time to create 1 rle with old method : 0.14406585693359375 length of segment : 470 time for calcul the mask position with numpy : 0.001796722412109375 nb_pixel_total : 58434 time to create 1 rle with old method : 0.06683039665222168 length of segment : 409 time for calcul the mask position with numpy : 0.0019254684448242188 nb_pixel_total : 86066 time to create 1 rle with old method : 0.09783363342285156 length of segment : 359 time for calcul the mask position with numpy : 0.0013380050659179688 nb_pixel_total : 47764 time to create 1 rle with old method : 0.05459141731262207 length of segment : 220 time for calcul the mask position with numpy : 0.0007264614105224609 nb_pixel_total : 25680 time to create 1 rle with old method : 0.029630661010742188 length of segment : 177 time for calcul the mask position with numpy : 0.015835046768188477 nb_pixel_total : 740770 time to create 1 rle with new method : 0.0411834716796875 length of segment : 1187 time for calcul the mask position with numpy : 0.005971670150756836 nb_pixel_total : 270691 time to create 1 rle with new method : 0.019045114517211914 length of segment : 675 time for calcul the mask position with numpy : 0.0007839202880859375 nb_pixel_total : 28829 time to create 1 rle with old method : 0.03325772285461426 length of segment : 194 time for calcul the mask position with numpy : 0.002665996551513672 nb_pixel_total : 90907 time to create 1 rle with old method : 0.10500741004943848 length of segment : 557 time for calcul the mask position with numpy : 0.0020041465759277344 nb_pixel_total : 92123 time to create 1 rle with old method : 0.11945843696594238 length of segment : 481 time for calcul the mask position with numpy : 0.00870370864868164 nb_pixel_total : 388814 time to create 1 rle with new method : 0.025580644607543945 length of segment : 1009 time for calcul the mask position with numpy : 0.0012660026550292969 nb_pixel_total : 55758 time to create 1 rle with old method : 0.06350350379943848 length of segment : 320 time for calcul the mask position with numpy : 0.0046350955963134766 nb_pixel_total : 202564 time to create 1 rle with new method : 0.014243125915527344 length of segment : 673 time for calcul the mask position with numpy : 0.0006921291351318359 nb_pixel_total : 21230 time to create 1 rle with old method : 0.024791479110717773 length of segment : 147 time for calcul the mask position with numpy : 0.002633810043334961 nb_pixel_total : 138293 time to create 1 rle with old method : 0.15689301490783691 length of segment : 532 time for calcul the mask position with numpy : 0.0014448165893554688 nb_pixel_total : 57430 time to create 1 rle with old method : 0.0805656909942627 length of segment : 490 time for calcul the mask position with numpy : 0.00024056434631347656 nb_pixel_total : 7739 time to create 1 rle with old method : 0.008996963500976562 length of segment : 103 time for calcul the mask position with numpy : 0.003179311752319336 nb_pixel_total : 113948 time to create 1 rle with old method : 0.12788867950439453 length of segment : 357 time for calcul the mask position with numpy : 0.002324819564819336 nb_pixel_total : 57878 time to create 1 rle with old method : 0.06623506546020508 length of segment : 391 time for calcul the mask position with numpy : 0.03657102584838867 nb_pixel_total : 1554946 time to create 1 rle with new method : 1.1837506294250488 length of segment : 2507 time for calcul the mask position with numpy : 0.001107931137084961 nb_pixel_total : 39048 time to create 1 rle with old method : 0.04531073570251465 length of segment : 268 time for calcul the mask position with numpy : 0.00037407875061035156 nb_pixel_total : 16421 time to create 1 rle with old method : 0.019704103469848633 length of segment : 167 time for calcul the mask position with numpy : 0.0033676624298095703 nb_pixel_total : 90547 time to create 1 rle with old method : 0.10600066184997559 length of segment : 1164 time for calcul the mask position with numpy : 0.0037102699279785156 nb_pixel_total : 174805 time to create 1 rle with new method : 0.01016378402709961 length of segment : 361 time for calcul the mask position with numpy : 0.0016584396362304688 nb_pixel_total : 81110 time to create 1 rle with old method : 0.09140801429748535 length of segment : 375 time for calcul the mask position with numpy : 0.015302658081054688 nb_pixel_total : 577502 time to create 1 rle with new method : 0.06262874603271484 length of segment : 867 time for calcul the mask position with numpy : 0.00041413307189941406 nb_pixel_total : 466 time to create 1 rle with old method : 0.0009570121765136719 length of segment : 53 time for calcul the mask position with numpy : 0.0008647441864013672 nb_pixel_total : 54148 time to create 1 rle with old method : 0.06287741661071777 length of segment : 207 time for calcul the mask position with numpy : 0.003065824508666992 nb_pixel_total : 152367 time to create 1 rle with new method : 0.008421897888183594 length of segment : 406 time for calcul the mask position with numpy : 0.006005048751831055 nb_pixel_total : 263478 time to create 1 rle with new method : 0.017975807189941406 length of segment : 762 time for calcul the mask position with numpy : 0.0007340908050537109 nb_pixel_total : 38781 time to create 1 rle with old method : 0.044472455978393555 length of segment : 254 time for calcul the mask position with numpy : 0.0012698173522949219 nb_pixel_total : 40038 time to create 1 rle with old method : 0.045926809310913086 length of segment : 161 time for calcul the mask position with numpy : 0.0021178722381591797 nb_pixel_total : 103591 time to create 1 rle with old method : 0.11415338516235352 length of segment : 376 time for calcul the mask position with numpy : 0.002528667449951172 nb_pixel_total : 93381 time to create 1 rle with old method : 0.10392999649047852 length of segment : 559 time for calcul the mask position with numpy : 0.0008697509765625 nb_pixel_total : 38472 time to create 1 rle with old method : 0.04254961013793945 length of segment : 197 time for calcul the mask position with numpy : 0.002414226531982422 nb_pixel_total : 112549 time to create 1 rle with old method : 0.1269972324371338 length of segment : 444 time for calcul the mask position with numpy : 0.0007388591766357422 nb_pixel_total : 24786 time to create 1 rle with old method : 0.028067350387573242 length of segment : 219 time for calcul the mask position with numpy : 0.0005300045013427734 nb_pixel_total : 22432 time to create 1 rle with old method : 0.02612137794494629 length of segment : 178 time for calcul the mask position with numpy : 0.0008711814880371094 nb_pixel_total : 42535 time to create 1 rle with old method : 0.04986119270324707 length of segment : 270 time for calcul the mask position with numpy : 0.021721601486206055 nb_pixel_total : 832809 time to create 1 rle with new method : 0.5087499618530273 length of segment : 1625 time for calcul the mask position with numpy : 0.009799718856811523 nb_pixel_total : 448542 time to create 1 rle with new method : 0.06301617622375488 length of segment : 1058 time for calcul the mask position with numpy : 0.0009436607360839844 nb_pixel_total : 38590 time to create 1 rle with old method : 0.04298591613769531 length of segment : 339 time for calcul the mask position with numpy : 0.0006320476531982422 nb_pixel_total : 24257 time to create 1 rle with old method : 0.02734994888305664 length of segment : 136 time for calcul the mask position with numpy : 0.0021605491638183594 nb_pixel_total : 86382 time to create 1 rle with old method : 0.09709334373474121 length of segment : 300 time for calcul the mask position with numpy : 0.0012087821960449219 nb_pixel_total : 68611 time to create 1 rle with old method : 0.0749197006225586 length of segment : 344 time for calcul the mask position with numpy : 0.002167940139770508 nb_pixel_total : 82738 time to create 1 rle with old method : 0.09370732307434082 length of segment : 373 time for calcul the mask position with numpy : 0.0023040771484375 nb_pixel_total : 107619 time to create 1 rle with old method : 0.12182474136352539 length of segment : 252 time for calcul the mask position with numpy : 0.0012056827545166016 nb_pixel_total : 62453 time to create 1 rle with old method : 0.07158207893371582 length of segment : 277 time for calcul the mask position with numpy : 0.0035622119903564453 nb_pixel_total : 168532 time to create 1 rle with new method : 0.010042905807495117 length of segment : 299 time for calcul the mask position with numpy : 0.0012028217315673828 nb_pixel_total : 42197 time to create 1 rle with old method : 0.04802846908569336 length of segment : 332 time for calcul the mask position with numpy : 0.0017962455749511719 nb_pixel_total : 78325 time to create 1 rle with old method : 0.08644366264343262 length of segment : 431 time for calcul the mask position with numpy : 0.007202625274658203 nb_pixel_total : 309532 time to create 1 rle with new method : 0.021213769912719727 length of segment : 939 time for calcul the mask position with numpy : 0.0023641586303710938 nb_pixel_total : 107243 time to create 1 rle with old method : 0.11727404594421387 length of segment : 462 time for calcul the mask position with numpy : 0.0014908313751220703 nb_pixel_total : 49739 time to create 1 rle with old method : 0.06354880332946777 length of segment : 220 time for calcul the mask position with numpy : 0.0016818046569824219 nb_pixel_total : 68635 time to create 1 rle with old method : 0.08104586601257324 length of segment : 368 time for calcul the mask position with numpy : 0.001004934310913086 nb_pixel_total : 42165 time to create 1 rle with old method : 0.05036187171936035 length of segment : 199 time for calcul the mask position with numpy : 0.0020182132720947266 nb_pixel_total : 80202 time to create 1 rle with old method : 0.09302997589111328 length of segment : 344 time for calcul the mask position with numpy : 0.0008933544158935547 nb_pixel_total : 31412 time to create 1 rle with old method : 0.03505969047546387 length of segment : 238 time for calcul the mask position with numpy : 0.0011532306671142578 nb_pixel_total : 50485 time to create 1 rle with old method : 0.055701255798339844 length of segment : 383 time for calcul the mask position with numpy : 0.0014824867248535156 nb_pixel_total : 59952 time to create 1 rle with old method : 0.06546831130981445 length of segment : 438 time for calcul the mask position with numpy : 0.0015299320220947266 nb_pixel_total : 72710 time to create 1 rle with old method : 0.08147478103637695 length of segment : 393 time for calcul the mask position with numpy : 0.001168966293334961 nb_pixel_total : 54844 time to create 1 rle with old method : 0.060014963150024414 length of segment : 264 time for calcul the mask position with numpy : 0.0024709701538085938 nb_pixel_total : 126582 time to create 1 rle with old method : 0.136749267578125 length of segment : 639 time for calcul the mask position with numpy : 0.0008141994476318359 nb_pixel_total : 32471 time to create 1 rle with old method : 0.03678393363952637 length of segment : 183 time for calcul the mask position with numpy : 0.005659580230712891 nb_pixel_total : 311281 time to create 1 rle with new method : 0.015298128128051758 length of segment : 665 time for calcul the mask position with numpy : 0.0016856193542480469 nb_pixel_total : 69654 time to create 1 rle with old method : 0.08173203468322754 length of segment : 430 time for calcul the mask position with numpy : 0.0012865066528320312 nb_pixel_total : 49657 time to create 1 rle with old method : 0.057039499282836914 length of segment : 384 time for calcul the mask position with numpy : 0.005750417709350586 nb_pixel_total : 319645 time to create 1 rle with new method : 0.01611638069152832 length of segment : 667 time for calcul the mask position with numpy : 0.0023806095123291016 nb_pixel_total : 108150 time to create 1 rle with old method : 0.12609267234802246 length of segment : 368 time for calcul the mask position with numpy : 0.0016603469848632812 nb_pixel_total : 57739 time to create 1 rle with old method : 0.06465363502502441 length of segment : 350 time for calcul the mask position with numpy : 0.19918131828308105 nb_pixel_total : 2980491 time to create 1 rle with new method : 0.633713960647583 length of segment : 3910 time for calcul the mask position with numpy : 0.4386899471282959 nb_pixel_total : 6251442 time to create 1 rle with new method : 0.7893352508544922 length of segment : 3250 time for calcul the mask position with numpy : 0.00023818016052246094 nb_pixel_total : 14580 time to create 1 rle with old method : 0.01606297492980957 length of segment : 174 time for calcul the mask position with numpy : 0.0012290477752685547 nb_pixel_total : 111826 time to create 1 rle with old method : 0.1230916976928711 length of segment : 326 time for calcul the mask position with numpy : 0.0013401508331298828 nb_pixel_total : 104279 time to create 1 rle with old method : 0.1106112003326416 length of segment : 539 time spent for convertir_results : 59.597647190093994 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 421 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 163.48468732833862 time spend to save output : 0.2207479476928711 total time spend for step 2 : 163.7054352760315 step3:blur_detection Thu Aug 28 15:05:23 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 (4160, 3120) 3506.0889004251894 (4160, 3120) 899.0823582448013 (4160, 3120) 2530.132687017643 (4160, 3120) 1910.8582522167574 (4160, 3120) 2070.132166554053 (4160, 3120) 608.3117192298713 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 : 6 time used for this insertion : 0.013985633850097656 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 6 time used for this insertion : 0.017787456512451172 save missing photos in datou_result : time spend for datou_step_exec : 2.7121355533599854 time spend to save output : 0.03589367866516113 total time spend for step 3 : 2.7480292320251465 step4:brightness Thu Aug 28 15:05:26 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/1756386090_3865689_1379845298_d94b222a85f13619fc08ca8d8699fc96.jpg treat image : temp/1756386090_3865689_1379845296_93a449a3364cadab21eab026cab11c2e.jpg treat image : temp/1756386090_3865689_1379845132_a788ce10de4d50fe70316cb9eb629d11.jpg treat image : temp/1756386090_3865689_1379845131_b40785bc4193d9cdc37cce9ba0a3bd8a.jpg treat image : temp/1756386090_3865689_1379845128_381f80e6868cd09e5c365a2999a3ad4c.jpg treat image : temp/1756386090_3865689_1379845123_a80b47de89d9814c6d4d0ff5631fc1af.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 : 6 time used for this insertion : 0.011344194412231445 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 6 time used for this insertion : 0.012686014175415039 save missing photos in datou_result : time spend for datou_step_exec : 9.647972822189331 time spend to save output : 0.028954744338989258 total time spend for step 4 : 9.67692756652832 step5:rle_unique_nms_with_priority Thu Aug 28 15:05:35 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 421 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 73 nb_hashtags : 9 time to prepare the origin masks : 58.09193301200867 time for calcul the mask position with numpy : 0.8697323799133301 nb_pixel_total : 6235683 time to create 1 rle with new method : 1.3394598960876465 time for calcul the mask position with numpy : 0.053577423095703125 nb_pixel_total : 76054 time to create 1 rle with old method : 0.08496308326721191 time for calcul the mask position with numpy : 0.052556514739990234 nb_pixel_total : 48738 time to create 1 rle with old method : 0.05483603477478027 time for calcul the mask position with numpy : 0.05580306053161621 nb_pixel_total : 221888 time to create 1 rle with new method : 1.3315496444702148 time for calcul the mask position with numpy : 0.053525447845458984 nb_pixel_total : 2331 time to create 1 rle with old method : 0.002889871597290039 time for calcul the mask position with numpy : 0.054678916931152344 nb_pixel_total : 204779 time to create 1 rle with new method : 1.28652024269104 time for calcul the mask position with numpy : 0.05301260948181152 nb_pixel_total : 153750 time to create 1 rle with new method : 0.8303234577178955 time for calcul the mask position with numpy : 0.05605959892272949 nb_pixel_total : 56067 time to create 1 rle with old method : 0.0782322883605957 time for calcul the mask position with numpy : 0.05381274223327637 nb_pixel_total : 86286 time to create 1 rle with old method : 0.09934186935424805 time for calcul the mask position with numpy : 0.05399608612060547 nb_pixel_total : 49386 time to create 1 rle with old method : 0.05725288391113281 time for calcul the mask position with numpy : 0.055248260498046875 nb_pixel_total : 293234 time to create 1 rle with new method : 0.9371597766876221 time for calcul the mask position with numpy : 0.0527191162109375 nb_pixel_total : 38327 time to create 1 rle with old method : 0.04492688179016113 time for calcul the mask position with numpy : 0.05557584762573242 nb_pixel_total : 132485 time to create 1 rle with old method : 0.1514573097229004 time for calcul the mask position with numpy : 0.05387425422668457 nb_pixel_total : 52539 time to create 1 rle with old method : 0.06163597106933594 time for calcul the mask position with numpy : 0.05435967445373535 nb_pixel_total : 32414 time to create 1 rle with old method : 0.037392616271972656 time for calcul the mask position with numpy : 0.05383896827697754 nb_pixel_total : 6370 time to create 1 rle with old method : 0.007569551467895508 time for calcul the mask position with numpy : 0.053842782974243164 nb_pixel_total : 85383 time to create 1 rle with old method : 0.10355114936828613 time for calcul the mask position with numpy : 0.05496573448181152 nb_pixel_total : 144469 time to create 1 rle with old method : 0.1658034324645996 time for calcul the mask position with numpy : 0.05458354949951172 nb_pixel_total : 119012 time to create 1 rle with old method : 0.13733744621276855 time for calcul the mask position with numpy : 0.06064128875732422 nb_pixel_total : 29652 time to create 1 rle with old method : 0.03695368766784668 time for calcul the mask position with numpy : 0.05531764030456543 nb_pixel_total : 115627 time to create 1 rle with old method : 0.1412649154663086 time for calcul the mask position with numpy : 0.05417180061340332 nb_pixel_total : 31662 time to create 1 rle with old method : 0.03616213798522949 time for calcul the mask position with numpy : 0.051586151123046875 nb_pixel_total : 3531 time to create 1 rle with old method : 0.004140138626098633 time for calcul the mask position with numpy : 0.055876970291137695 nb_pixel_total : 506305 time to create 1 rle with new method : 1.1343660354614258 time for calcul the mask position with numpy : 0.05191802978515625 nb_pixel_total : 67116 time to create 1 rle with old method : 0.07592511177062988 time for calcul the mask position with numpy : 0.05376124382019043 nb_pixel_total : 82682 time to create 1 rle with old method : 0.12000298500061035 time for calcul the mask position with numpy : 0.05446147918701172 nb_pixel_total : 33067 time to create 1 rle with old method : 0.038199663162231445 time for calcul the mask position with numpy : 0.06380915641784668 nb_pixel_total : 27922 time to create 1 rle with old method : 0.0382387638092041 time for calcul the mask position with numpy : 0.05549311637878418 nb_pixel_total : 54337 time to create 1 rle with old method : 0.06262063980102539 time for calcul the mask position with numpy : 0.05362987518310547 nb_pixel_total : 34422 time to create 1 rle with old method : 0.04026484489440918 time for calcul the mask position with numpy : 0.054770708084106445 nb_pixel_total : 42223 time to create 1 rle with old method : 0.04812335968017578 time for calcul the mask position with numpy : 0.052668094635009766 nb_pixel_total : 58957 time to create 1 rle with old method : 0.06778860092163086 time for calcul the mask position with numpy : 0.05502915382385254 nb_pixel_total : 97541 time to create 1 rle with old method : 0.1203925609588623 time for calcul the mask position with numpy : 0.05658888816833496 nb_pixel_total : 80611 time to create 1 rle with old method : 0.09795856475830078 time for calcul the mask position with numpy : 0.055057525634765625 nb_pixel_total : 24844 time to create 1 rle with old method : 0.029942035675048828 time for calcul the mask position with numpy : 0.05721759796142578 nb_pixel_total : 361526 time to create 1 rle with new method : 1.447849988937378 time for calcul the mask position with numpy : 0.05453348159790039 nb_pixel_total : 26228 time to create 1 rle with old method : 0.03244781494140625 time for calcul the mask position with numpy : 0.05159616470336914 nb_pixel_total : 29442 time to create 1 rle with old method : 0.033483266830444336 time for calcul the mask position with numpy : 0.0527493953704834 nb_pixel_total : 94925 time to create 1 rle with old method : 0.10454177856445312 time for calcul the mask position with numpy : 0.054388999938964844 nb_pixel_total : 29017 time to create 1 rle with old method : 0.03261137008666992 time for calcul the mask position with numpy : 0.05367088317871094 nb_pixel_total : 104799 time to create 1 rle with old method : 0.11463236808776855 time for calcul the mask position with numpy : 0.05248737335205078 nb_pixel_total : 55577 time to create 1 rle with old method : 0.06351256370544434 time for calcul the mask position with numpy : 0.05546092987060547 nb_pixel_total : 145135 time to create 1 rle with old method : 0.16481876373291016 time for calcul the mask position with numpy : 0.052664995193481445 nb_pixel_total : 9281 time to create 1 rle with old method : 0.010375261306762695 time for calcul the mask position with numpy : 0.053276777267456055 nb_pixel_total : 14739 time to create 1 rle with old method : 0.017096281051635742 time for calcul the mask position with numpy : 0.05453348159790039 nb_pixel_total : 94576 time to create 1 rle with old method : 0.10749149322509766 time for calcul the mask position with numpy : 0.053038835525512695 nb_pixel_total : 92273 time to create 1 rle with old method : 0.10048532485961914 time for calcul the mask position with numpy : 0.05346107482910156 nb_pixel_total : 30094 time to create 1 rle with old method : 0.03421759605407715 time for calcul the mask position with numpy : 0.057578086853027344 nb_pixel_total : 635897 time to create 1 rle with new method : 1.2383944988250732 time for calcul the mask position with numpy : 0.05321621894836426 nb_pixel_total : 243045 time to create 1 rle with new method : 1.1905417442321777 time for calcul the mask position with numpy : 0.054573774337768555 nb_pixel_total : 159189 time to create 1 rle with new method : 1.320920467376709 time for calcul the mask position with numpy : 0.05058598518371582 nb_pixel_total : 32893 time to create 1 rle with old method : 0.035584449768066406 time for calcul the mask position with numpy : 0.05321192741394043 nb_pixel_total : 5831 time to create 1 rle with old method : 0.0067937374114990234 time for calcul the mask position with numpy : 0.05094647407531738 nb_pixel_total : 69994 time to create 1 rle with old method : 0.07709789276123047 time for calcul the mask position with numpy : 0.05023479461669922 nb_pixel_total : 23699 time to create 1 rle with old method : 0.025792837142944336 time for calcul the mask position with numpy : 0.05240988731384277 nb_pixel_total : 7931 time to create 1 rle with old method : 0.009404420852661133 time for calcul the mask position with numpy : 0.054067134857177734 nb_pixel_total : 63782 time to create 1 rle with old method : 0.07113790512084961 time for calcul the mask position with numpy : 0.05427432060241699 nb_pixel_total : 56645 time to create 1 rle with old method : 0.06446313858032227 time for calcul the mask position with numpy : 0.0528111457824707 nb_pixel_total : 263349 time to create 1 rle with new method : 1.142486333847046 time for calcul the mask position with numpy : 0.0560908317565918 nb_pixel_total : 35381 time to create 1 rle with old method : 0.040793418884277344 time for calcul the mask position with numpy : 0.05498528480529785 nb_pixel_total : 210085 time to create 1 rle with new method : 1.278935194015503 time for calcul the mask position with numpy : 0.05689191818237305 nb_pixel_total : 5338 time to create 1 rle with old method : 0.006689548492431641 time for calcul the mask position with numpy : 0.05269479751586914 nb_pixel_total : 34211 time to create 1 rle with old method : 0.03882265090942383 time for calcul the mask position with numpy : 0.05292654037475586 nb_pixel_total : 24988 time to create 1 rle with old method : 0.028737306594848633 time for calcul the mask position with numpy : 0.0540006160736084 nb_pixel_total : 57609 time to create 1 rle with old method : 0.06418323516845703 time for calcul the mask position with numpy : 0.05393028259277344 nb_pixel_total : 172559 time to create 1 rle with new method : 1.1992058753967285 time for calcul the mask position with numpy : 0.05429530143737793 nb_pixel_total : 74685 time to create 1 rle with old method : 0.08266901969909668 time for calcul the mask position with numpy : 0.05033540725708008 nb_pixel_total : 52901 time to create 1 rle with old method : 0.057395219802856445 time for calcul the mask position with numpy : 0.050215959548950195 nb_pixel_total : 31142 time to create 1 rle with old method : 0.035463809967041016 time for calcul the mask position with numpy : 0.05136895179748535 nb_pixel_total : 116560 time to create 1 rle with old method : 0.1289503574371338 time for calcul the mask position with numpy : 0.05068850517272949 nb_pixel_total : 77751 time to create 1 rle with old method : 0.08516359329223633 time for calcul the mask position with numpy : 0.05249667167663574 nb_pixel_total : 34679 time to create 1 rle with old method : 0.038788557052612305 time for calcul the mask position with numpy : 0.051804542541503906 nb_pixel_total : 70908 time to create 1 rle with old method : 0.08062243461608887 time for calcul the mask position with numpy : 0.0532379150390625 nb_pixel_total : 842 time to create 1 rle with old method : 0.0013196468353271484 create new chi : 24.88715934753418 time to delete rle : 0.03345489501953125 batch 1 Loaded 74 chid ids of type : 4855 Number RLEs to save : 59093 TO DO : save crop sub photo not yet done ! save time : 3.229856252670288 nb_obj : 64 nb_hashtags : 9 time to prepare the origin masks : 59.019094705581665 time for calcul the mask position with numpy : 1.1701388359069824 nb_pixel_total : 4395641 time to create 1 rle with new method : 1.5416102409362793 time for calcul the mask position with numpy : 0.06024956703186035 nb_pixel_total : 276933 time to create 1 rle with new method : 1.1563847064971924 time for calcul the mask position with numpy : 0.0731816291809082 nb_pixel_total : 664721 time to create 1 rle with new method : 0.994600772857666 time for calcul the mask position with numpy : 0.054329633712768555 nb_pixel_total : 17949 time to create 1 rle with old method : 0.021518468856811523 time for calcul the mask position with numpy : 0.05876040458679199 nb_pixel_total : 660568 time to create 1 rle with new method : 1.1161143779754639 time for calcul the mask position with numpy : 0.05451393127441406 nb_pixel_total : 54060 time to create 1 rle with old method : 0.06489443778991699 time for calcul the mask position with numpy : 0.061144113540649414 nb_pixel_total : 23463 time to create 1 rle with old method : 0.03830385208129883 time for calcul the mask position with numpy : 0.06118607521057129 nb_pixel_total : 273052 time to create 1 rle with new method : 1.038896083831787 time for calcul the mask position with numpy : 0.054723501205444336 nb_pixel_total : 91059 time to create 1 rle with old method : 0.10362648963928223 time for calcul the mask position with numpy : 0.05803799629211426 nb_pixel_total : 130141 time to create 1 rle with old method : 0.15394926071166992 time for calcul the mask position with numpy : 0.053646087646484375 nb_pixel_total : 16430 time to create 1 rle with old method : 0.018985271453857422 time for calcul the mask position with numpy : 0.05444931983947754 nb_pixel_total : 31288 time to create 1 rle with old method : 0.03676199913024902 time for calcul the mask position with numpy : 0.06149554252624512 nb_pixel_total : 667141 time to create 1 rle with new method : 1.1583905220031738 time for calcul the mask position with numpy : 0.05384469032287598 nb_pixel_total : 12068 time to create 1 rle with old method : 0.014066219329833984 time for calcul the mask position with numpy : 0.055351972579956055 nb_pixel_total : 226146 time to create 1 rle with new method : 1.0776889324188232 time for calcul the mask position with numpy : 0.05334115028381348 nb_pixel_total : 56576 time to create 1 rle with old method : 0.06546211242675781 time for calcul the mask position with numpy : 0.056691646575927734 nb_pixel_total : 90725 time to create 1 rle with old method : 0.10177803039550781 time for calcul the mask position with numpy : 0.055870771408081055 nb_pixel_total : 79191 time to create 1 rle with old method : 0.08707308769226074 time for calcul the mask position with numpy : 0.052911996841430664 nb_pixel_total : 79544 time to create 1 rle with old method : 0.08851814270019531 time for calcul the mask position with numpy : 0.053879499435424805 nb_pixel_total : 36440 time to create 1 rle with old method : 0.06009507179260254 time for calcul the mask position with numpy : 0.056844472885131836 nb_pixel_total : 37642 time to create 1 rle with old method : 0.043955326080322266 time for calcul the mask position with numpy : 0.058046817779541016 nb_pixel_total : 301782 time to create 1 rle with new method : 0.8142349720001221 time for calcul the mask position with numpy : 0.05595564842224121 nb_pixel_total : 120378 time to create 1 rle with old method : 0.14137530326843262 time for calcul the mask position with numpy : 0.05511307716369629 nb_pixel_total : 105603 time to create 1 rle with old method : 0.12082076072692871 time for calcul the mask position with numpy : 0.0542299747467041 nb_pixel_total : 31733 time to create 1 rle with old method : 0.03670358657836914 time for calcul the mask position with numpy : 0.053328752517700195 nb_pixel_total : 657 time to create 1 rle with old method : 0.0011456012725830078 time for calcul the mask position with numpy : 0.05506014823913574 nb_pixel_total : 95874 time to create 1 rle with old method : 0.11166119575500488 time for calcul the mask position with numpy : 0.05649065971374512 nb_pixel_total : 102334 time to create 1 rle with old method : 0.11833667755126953 time for calcul the mask position with numpy : 0.05471348762512207 nb_pixel_total : 35524 time to create 1 rle with old method : 0.04051995277404785 time for calcul the mask position with numpy : 0.05493879318237305 nb_pixel_total : 67020 time to create 1 rle with old method : 0.08039331436157227 time for calcul the mask position with numpy : 0.056624650955200195 nb_pixel_total : 150605 time to create 1 rle with new method : 1.022423267364502 time for calcul the mask position with numpy : 0.05562424659729004 nb_pixel_total : 180550 time to create 1 rle with new method : 1.221217393875122 time for calcul the mask position with numpy : 0.0601506233215332 nb_pixel_total : 3297 time to create 1 rle with old method : 0.00570988655090332 time for calcul the mask position with numpy : 0.060866355895996094 nb_pixel_total : 63860 time to create 1 rle with old method : 0.07251453399658203 time for calcul the mask position with numpy : 0.054770708084106445 nb_pixel_total : 237424 time to create 1 rle with new method : 0.912452220916748 time for calcul the mask position with numpy : 0.05466651916503906 nb_pixel_total : 39699 time to create 1 rle with old method : 0.046042680740356445 time for calcul the mask position with numpy : 0.05443596839904785 nb_pixel_total : 183380 time to create 1 rle with new method : 0.9654121398925781 time for calcul the mask position with numpy : 0.06256532669067383 nb_pixel_total : 29773 time to create 1 rle with old method : 0.041005611419677734 time for calcul the mask position with numpy : 0.054944753646850586 nb_pixel_total : 153469 time to create 1 rle with new method : 1.0091736316680908 time for calcul the mask position with numpy : 0.053916215896606445 nb_pixel_total : 1687 time to create 1 rle with old method : 0.002780437469482422 time for calcul the mask position with numpy : 0.05958127975463867 nb_pixel_total : 412302 time to create 1 rle with new method : 0.8868563175201416 time for calcul the mask position with numpy : 0.05848407745361328 nb_pixel_total : 90426 time to create 1 rle with old method : 0.12111377716064453 time for calcul the mask position with numpy : 0.055687665939331055 nb_pixel_total : 46447 time to create 1 rle with old method : 0.054180145263671875 time for calcul the mask position with numpy : 0.05520915985107422 nb_pixel_total : 1488 time to create 1 rle with old method : 0.002040386199951172 time for calcul the mask position with numpy : 0.057929039001464844 nb_pixel_total : 151267 time to create 1 rle with new method : 0.8522601127624512 time for calcul the mask position with numpy : 0.05471634864807129 nb_pixel_total : 14773 time to create 1 rle with old method : 0.017342567443847656 time for calcul the mask position with numpy : 0.05428719520568848 nb_pixel_total : 1395 time to create 1 rle with old method : 0.0017189979553222656 time for calcul the mask position with numpy : 0.05426216125488281 nb_pixel_total : 11835 time to create 1 rle with old method : 0.01446533203125 time for calcul the mask position with numpy : 0.05560803413391113 nb_pixel_total : 383275 time to create 1 rle with new method : 1.0431687831878662 time for calcul the mask position with numpy : 0.05464625358581543 nb_pixel_total : 102915 time to create 1 rle with old method : 0.1183321475982666 time for calcul the mask position with numpy : 0.05433368682861328 nb_pixel_total : 72342 time to create 1 rle with old method : 0.08395195007324219 time for calcul the mask position with numpy : 0.056771039962768555 nb_pixel_total : 10313 time to create 1 rle with old method : 0.0121307373046875 time for calcul the mask position with numpy : 0.054527997970581055 nb_pixel_total : 75326 time to create 1 rle with old method : 0.0891571044921875 time for calcul the mask position with numpy : 0.054879188537597656 nb_pixel_total : 94098 time to create 1 rle with old method : 0.10785984992980957 time for calcul the mask position with numpy : 0.054834842681884766 nb_pixel_total : 5829 time to create 1 rle with old method : 0.0068721771240234375 time for calcul the mask position with numpy : 0.05239415168762207 nb_pixel_total : 200857 time to create 1 rle with new method : 2.175706386566162 time for calcul the mask position with numpy : 0.07516860961914062 nb_pixel_total : 478247 time to create 1 rle with new method : 1.7500791549682617 time for calcul the mask position with numpy : 0.07142925262451172 nb_pixel_total : 343490 time to create 1 rle with new method : 1.6000258922576904 time for calcul the mask position with numpy : 0.05453753471374512 nb_pixel_total : 158536 time to create 1 rle with new method : 1.296990156173706 time for calcul the mask position with numpy : 0.05577588081359863 nb_pixel_total : 273649 time to create 1 rle with new method : 1.4132168292999268 time for calcul the mask position with numpy : 0.05366325378417969 nb_pixel_total : 1893 time to create 1 rle with old method : 0.0024268627166748047 time for calcul the mask position with numpy : 0.053610801696777344 nb_pixel_total : 43110 time to create 1 rle with old method : 0.0477750301361084 time for calcul the mask position with numpy : 0.05352425575256348 nb_pixel_total : 101924 time to create 1 rle with old method : 0.11611104011535645 time for calcul the mask position with numpy : 0.05478668212890625 nb_pixel_total : 77445 time to create 1 rle with old method : 0.08866333961486816 time for calcul the mask position with numpy : 0.05384469032287598 nb_pixel_total : 591 time to create 1 rle with old method : 0.000982522964477539 create new chi : 33.401386737823486 time to delete rle : 0.005745410919189453 batch 1 Loaded 65 chid ids of type : 4855 Number RLEs to save : 56384 TO DO : save crop sub photo not yet done ! save time : 3.2128140926361084 nb_obj : 89 nb_hashtags : 9 time to prepare the origin masks : 66.73137593269348 time for calcul the mask position with numpy : 0.29007935523986816 nb_pixel_total : 3962689 time to create 1 rle with new method : 1.385577917098999 time for calcul the mask position with numpy : 0.05429506301879883 nb_pixel_total : 105894 time to create 1 rle with old method : 0.11899852752685547 time for calcul the mask position with numpy : 0.05539417266845703 nb_pixel_total : 1067 time to create 1 rle with old method : 0.0015842914581298828 time for calcul the mask position with numpy : 0.0632932186126709 nb_pixel_total : 92094 time to create 1 rle with old method : 0.10286140441894531 time for calcul the mask position with numpy : 0.053865671157836914 nb_pixel_total : 11860 time to create 1 rle with old method : 0.013796567916870117 time for calcul the mask position with numpy : 0.05200648307800293 nb_pixel_total : 59611 time to create 1 rle with old method : 0.06682658195495605 time for calcul the mask position with numpy : 0.051325082778930664 nb_pixel_total : 2178 time to create 1 rle with old method : 0.0028777122497558594 time for calcul the mask position with numpy : 0.051338911056518555 nb_pixel_total : 3085 time to create 1 rle with old method : 0.003536224365234375 time for calcul the mask position with numpy : 0.052143096923828125 nb_pixel_total : 54133 time to create 1 rle with old method : 0.06020402908325195 time for calcul the mask position with numpy : 0.05127859115600586 nb_pixel_total : 65175 time to create 1 rle with old method : 0.07289314270019531 time for calcul the mask position with numpy : 0.05208420753479004 nb_pixel_total : 11210 time to create 1 rle with old method : 0.012946367263793945 time for calcul the mask position with numpy : 0.05112719535827637 nb_pixel_total : 18189 time to create 1 rle with old method : 0.020998001098632812 time for calcul the mask position with numpy : 0.06470274925231934 nb_pixel_total : 532849 time to create 1 rle with new method : 1.1565592288970947 time for calcul the mask position with numpy : 0.05250978469848633 nb_pixel_total : 82320 time to create 1 rle with old method : 0.09047532081604004 time for calcul the mask position with numpy : 0.05164337158203125 nb_pixel_total : 63437 time to create 1 rle with old method : 0.07055091857910156 time for calcul the mask position with numpy : 0.05231785774230957 nb_pixel_total : 40931 time to create 1 rle with old method : 0.04714703559875488 time for calcul the mask position with numpy : 0.0540766716003418 nb_pixel_total : 330711 time to create 1 rle with new method : 1.208531141281128 time for calcul the mask position with numpy : 0.056272268295288086 nb_pixel_total : 55481 time to create 1 rle with old method : 0.0636296272277832 time for calcul the mask position with numpy : 0.05810976028442383 nb_pixel_total : 62 time to create 1 rle with old method : 0.0003466606140136719 time for calcul the mask position with numpy : 0.05282187461853027 nb_pixel_total : 17496 time to create 1 rle with old method : 0.020046234130859375 time for calcul the mask position with numpy : 0.0543975830078125 nb_pixel_total : 74722 time to create 1 rle with old method : 0.08288145065307617 time for calcul the mask position with numpy : 0.055635690689086914 nb_pixel_total : 140228 time to create 1 rle with old method : 0.16135668754577637 time for calcul the mask position with numpy : 0.05269598960876465 nb_pixel_total : 106512 time to create 1 rle with old method : 0.12119889259338379 time for calcul the mask position with numpy : 0.05471158027648926 nb_pixel_total : 165440 time to create 1 rle with new method : 0.9877991676330566 time for calcul the mask position with numpy : 0.05415987968444824 nb_pixel_total : 29747 time to create 1 rle with old method : 0.03384995460510254 time for calcul the mask position with numpy : 0.051552772521972656 nb_pixel_total : 80732 time to create 1 rle with old method : 0.08889317512512207 time for calcul the mask position with numpy : 0.05145835876464844 nb_pixel_total : 24683 time to create 1 rle with old method : 0.02711963653564453 time for calcul the mask position with numpy : 0.05147147178649902 nb_pixel_total : 15349 time to create 1 rle with old method : 0.017229557037353516 time for calcul the mask position with numpy : 0.052301645278930664 nb_pixel_total : 15527 time to create 1 rle with old method : 0.017635107040405273 time for calcul the mask position with numpy : 0.0511932373046875 nb_pixel_total : 37189 time to create 1 rle with old method : 0.041742801666259766 time for calcul the mask position with numpy : 0.051911354064941406 nb_pixel_total : 17890 time to create 1 rle with old method : 0.019404888153076172 time for calcul the mask position with numpy : 0.05216836929321289 nb_pixel_total : 2130 time to create 1 rle with old method : 0.002880096435546875 time for calcul the mask position with numpy : 0.05275893211364746 nb_pixel_total : 154197 time to create 1 rle with new method : 0.9972822666168213 time for calcul the mask position with numpy : 0.05931973457336426 nb_pixel_total : 40803 time to create 1 rle with old method : 0.05826282501220703 time for calcul the mask position with numpy : 0.05419421195983887 nb_pixel_total : 64663 time to create 1 rle with old method : 0.07029390335083008 time for calcul the mask position with numpy : 0.05216193199157715 nb_pixel_total : 230448 time to create 1 rle with new method : 1.3016176223754883 time for calcul the mask position with numpy : 0.05393552780151367 nb_pixel_total : 32330 time to create 1 rle with old method : 0.03675031661987305 time for calcul the mask position with numpy : 0.05586600303649902 nb_pixel_total : 239337 time to create 1 rle with new method : 1.04286527633667 time for calcul the mask position with numpy : 0.05117607116699219 nb_pixel_total : 52207 time to create 1 rle with old method : 0.06038522720336914 time for calcul the mask position with numpy : 0.052945852279663086 nb_pixel_total : 65475 time to create 1 rle with old method : 0.07299947738647461 time for calcul the mask position with numpy : 0.052979469299316406 nb_pixel_total : 35960 time to create 1 rle with old method : 0.04011845588684082 time for calcul the mask position with numpy : 0.051107168197631836 nb_pixel_total : 1403 time to create 1 rle with old method : 0.0017898082733154297 time for calcul the mask position with numpy : 0.05434775352478027 nb_pixel_total : 148041 time to create 1 rle with old method : 0.16499066352844238 time for calcul the mask position with numpy : 0.05121016502380371 nb_pixel_total : 107749 time to create 1 rle with old method : 0.1220085620880127 time for calcul the mask position with numpy : 0.05497574806213379 nb_pixel_total : 144566 time to create 1 rle with old method : 0.16637730598449707 time for calcul the mask position with numpy : 0.05637526512145996 nb_pixel_total : 514163 time to create 1 rle with new method : 1.2027623653411865 time for calcul the mask position with numpy : 0.051885128021240234 nb_pixel_total : 76589 time to create 1 rle with old method : 0.0838613510131836 time for calcul the mask position with numpy : 0.05121350288391113 nb_pixel_total : 40194 time to create 1 rle with old method : 0.045560359954833984 time for calcul the mask position with numpy : 0.05758070945739746 nb_pixel_total : 615443 time to create 1 rle with new method : 1.6813714504241943 time for calcul the mask position with numpy : 0.05115509033203125 nb_pixel_total : 915 time to create 1 rle with old method : 0.0011222362518310547 time for calcul the mask position with numpy : 0.05173516273498535 nb_pixel_total : 44939 time to create 1 rle with old method : 0.0511014461517334 time for calcul the mask position with numpy : 0.05274319648742676 nb_pixel_total : 23187 time to create 1 rle with old method : 0.025684356689453125 time for calcul the mask position with numpy : 0.057921409606933594 nb_pixel_total : 97471 time to create 1 rle with old method : 0.10978031158447266 time for calcul the mask position with numpy : 0.05139446258544922 nb_pixel_total : 4217 time to create 1 rle with old method : 0.0054454803466796875 time for calcul the mask position with numpy : 0.05173754692077637 nb_pixel_total : 171226 time to create 1 rle with new method : 0.9953196048736572 time for calcul the mask position with numpy : 0.052900075912475586 nb_pixel_total : 32582 time to create 1 rle with old method : 0.036675214767456055 time for calcul the mask position with numpy : 0.05266690254211426 nb_pixel_total : 96780 time to create 1 rle with old method : 0.1075434684753418 time for calcul the mask position with numpy : 0.05440354347229004 nb_pixel_total : 7780 time to create 1 rle with old method : 0.009487152099609375 time for calcul the mask position with numpy : 0.05405426025390625 nb_pixel_total : 282864 time to create 1 rle with new method : 1.243755578994751 time for calcul the mask position with numpy : 0.052777767181396484 nb_pixel_total : 45254 time to create 1 rle with old method : 0.05092144012451172 time for calcul the mask position with numpy : 0.05457115173339844 nb_pixel_total : 294113 time to create 1 rle with new method : 1.0863454341888428 time for calcul the mask position with numpy : 0.05135154724121094 nb_pixel_total : 23577 time to create 1 rle with old method : 0.025876760482788086 time for calcul the mask position with numpy : 0.05133843421936035 nb_pixel_total : 66563 time to create 1 rle with old method : 0.07602787017822266 time for calcul the mask position with numpy : 0.050975799560546875 nb_pixel_total : 1018 time to create 1 rle with old method : 0.00135040283203125 time for calcul the mask position with numpy : 0.05153083801269531 nb_pixel_total : 68140 time to create 1 rle with old method : 0.0746004581451416 time for calcul the mask position with numpy : 0.05344390869140625 nb_pixel_total : 84373 time to create 1 rle with old method : 0.09237861633300781 time for calcul the mask position with numpy : 0.05181312561035156 nb_pixel_total : 32388 time to create 1 rle with old method : 0.03561973571777344 time for calcul the mask position with numpy : 0.052438974380493164 nb_pixel_total : 761 time to create 1 rle with old method : 0.001043558120727539 time for calcul the mask position with numpy : 0.05084586143493652 nb_pixel_total : 8824 time to create 1 rle with old method : 0.00960993766784668 time for calcul the mask position with numpy : 0.07513689994812012 nb_pixel_total : 1070602 time to create 1 rle with new method : 1.0657012462615967 time for calcul the mask position with numpy : 0.056491851806640625 nb_pixel_total : 107244 time to create 1 rle with old method : 0.1437075138092041 time for calcul the mask position with numpy : 0.05392289161682129 nb_pixel_total : 1837 time to create 1 rle with old method : 0.002354145050048828 time for calcul the mask position with numpy : 0.05686473846435547 nb_pixel_total : 332905 time to create 1 rle with new method : 1.2903611660003662 time for calcul the mask position with numpy : 0.05200386047363281 nb_pixel_total : 4982 time to create 1 rle with old method : 0.006215095520019531 time for calcul the mask position with numpy : 0.052886962890625 nb_pixel_total : 4511 time to create 1 rle with old method : 0.0055315494537353516 time for calcul the mask position with numpy : 0.0518946647644043 nb_pixel_total : 59172 time to create 1 rle with old method : 0.06658697128295898 time for calcul the mask position with numpy : 0.05376148223876953 nb_pixel_total : 104580 time to create 1 rle with old method : 0.11498141288757324 time for calcul the mask position with numpy : 0.05587291717529297 nb_pixel_total : 174995 time to create 1 rle with new method : 1.092294454574585 time for calcul the mask position with numpy : 0.05271196365356445 nb_pixel_total : 193186 time to create 1 rle with new method : 1.1191082000732422 time for calcul the mask position with numpy : 0.05396747589111328 nb_pixel_total : 277569 time to create 1 rle with new method : 1.0927667617797852 time for calcul the mask position with numpy : 0.05173754692077637 nb_pixel_total : 22599 time to create 1 rle with old method : 0.024762392044067383 time for calcul the mask position with numpy : 0.05116581916809082 nb_pixel_total : 4 time to create 1 rle with old method : 4.0531158447265625e-05 time for calcul the mask position with numpy : 0.05106163024902344 nb_pixel_total : 2276 time to create 1 rle with old method : 0.003171205520629883 time for calcul the mask position with numpy : 0.052959442138671875 nb_pixel_total : 205860 time to create 1 rle with new method : 1.224606990814209 time for calcul the mask position with numpy : 0.05878186225891113 nb_pixel_total : 40203 time to create 1 rle with old method : 0.043769121170043945 time for calcul the mask position with numpy : 0.05112743377685547 nb_pixel_total : 642 time to create 1 rle with old method : 0.0008339881896972656 time for calcul the mask position with numpy : 0.05356550216674805 nb_pixel_total : 39808 time to create 1 rle with old method : 0.044838905334472656 time for calcul the mask position with numpy : 0.052866458892822266 nb_pixel_total : 70774 time to create 1 rle with old method : 0.07826638221740723 time for calcul the mask position with numpy : 0.052060842514038086 nb_pixel_total : 52701 time to create 1 rle with old method : 0.059165239334106445 time for calcul the mask position with numpy : 0.05239439010620117 nb_pixel_total : 41589 time to create 1 rle with old method : 0.047692060470581055 create new chi : 30.69955825805664 time to delete rle : 0.007952213287353516 batch 1 Loaded 90 chid ids of type : 4855 Number RLEs to save : 64129 TO DO : save crop sub photo not yet done ! save time : 3.486393451690674 nb_obj : 89 nb_hashtags : 9 time to prepare the origin masks : 78.75863552093506 time for calcul the mask position with numpy : 0.3623647689819336 nb_pixel_total : 4410182 time to create 1 rle with new method : 1.115900993347168 time for calcul the mask position with numpy : 0.05308270454406738 nb_pixel_total : 134291 time to create 1 rle with old method : 0.1490933895111084 time for calcul the mask position with numpy : 0.053015947341918945 nb_pixel_total : 9770 time to create 1 rle with old method : 0.011562824249267578 time for calcul the mask position with numpy : 0.05459451675415039 nb_pixel_total : 20163 time to create 1 rle with old method : 0.02403402328491211 time for calcul the mask position with numpy : 0.05608367919921875 nb_pixel_total : 75271 time to create 1 rle with old method : 0.08622074127197266 time for calcul the mask position with numpy : 0.05324125289916992 nb_pixel_total : 19815 time to create 1 rle with old method : 0.023607969284057617 time for calcul the mask position with numpy : 0.057616472244262695 nb_pixel_total : 40944 time to create 1 rle with old method : 0.04648900032043457 time for calcul the mask position with numpy : 0.05731797218322754 nb_pixel_total : 177327 time to create 1 rle with new method : 1.0297045707702637 time for calcul the mask position with numpy : 0.05445146560668945 nb_pixel_total : 4741 time to create 1 rle with old method : 0.006037712097167969 time for calcul the mask position with numpy : 0.05624961853027344 nb_pixel_total : 139503 time to create 1 rle with old method : 0.17374873161315918 time for calcul the mask position with numpy : 0.05993509292602539 nb_pixel_total : 34628 time to create 1 rle with old method : 0.039917707443237305 time for calcul the mask position with numpy : 0.05269002914428711 nb_pixel_total : 7236 time to create 1 rle with old method : 0.008038997650146484 time for calcul the mask position with numpy : 0.05170297622680664 nb_pixel_total : 100997 time to create 1 rle with old method : 0.11143183708190918 time for calcul the mask position with numpy : 0.05414748191833496 nb_pixel_total : 260901 time to create 1 rle with new method : 1.258068323135376 time for calcul the mask position with numpy : 0.05271768569946289 nb_pixel_total : 4590 time to create 1 rle with old method : 0.005816936492919922 time for calcul the mask position with numpy : 0.05348801612854004 nb_pixel_total : 61650 time to create 1 rle with old method : 0.06952428817749023 time for calcul the mask position with numpy : 0.06113839149475098 nb_pixel_total : 622776 time to create 1 rle with new method : 1.0590574741363525 time for calcul the mask position with numpy : 0.05336165428161621 nb_pixel_total : 358130 time to create 1 rle with new method : 1.078139305114746 time for calcul the mask position with numpy : 0.051549434661865234 nb_pixel_total : 3506 time to create 1 rle with old method : 0.004174709320068359 time for calcul the mask position with numpy : 0.0545651912689209 nb_pixel_total : 127905 time to create 1 rle with old method : 0.1444711685180664 time for calcul the mask position with numpy : 0.052568912506103516 nb_pixel_total : 16127 time to create 1 rle with old method : 0.019438505172729492 time for calcul the mask position with numpy : 0.05292081832885742 nb_pixel_total : 137004 time to create 1 rle with old method : 0.16658902168273926 time for calcul the mask position with numpy : 0.05366635322570801 nb_pixel_total : 388189 time to create 1 rle with new method : 1.257688045501709 time for calcul the mask position with numpy : 0.05215263366699219 nb_pixel_total : 221537 time to create 1 rle with new method : 1.009998083114624 time for calcul the mask position with numpy : 0.053462982177734375 nb_pixel_total : 1944 time to create 1 rle with old method : 0.003027200698852539 time for calcul the mask position with numpy : 0.054338693618774414 nb_pixel_total : 44976 time to create 1 rle with old method : 0.054131507873535156 time for calcul the mask position with numpy : 0.05548906326293945 nb_pixel_total : 196445 time to create 1 rle with new method : 0.9059562683105469 time for calcul the mask position with numpy : 0.05612373352050781 nb_pixel_total : 36121 time to create 1 rle with old method : 0.0418241024017334 time for calcul the mask position with numpy : 0.053817033767700195 nb_pixel_total : 20124 time to create 1 rle with old method : 0.023591995239257812 time for calcul the mask position with numpy : 0.05476069450378418 nb_pixel_total : 255335 time to create 1 rle with new method : 1.1959450244903564 time for calcul the mask position with numpy : 0.05289268493652344 nb_pixel_total : 30517 time to create 1 rle with old method : 0.034702301025390625 time for calcul the mask position with numpy : 0.052983999252319336 nb_pixel_total : 26915 time to create 1 rle with old method : 0.030392885208129883 time for calcul the mask position with numpy : 0.055974483489990234 nb_pixel_total : 438271 time to create 1 rle with new method : 1.0245678424835205 time for calcul the mask position with numpy : 0.05248761177062988 nb_pixel_total : 41802 time to create 1 rle with old method : 0.048391103744506836 time for calcul the mask position with numpy : 0.05194401741027832 nb_pixel_total : 27565 time to create 1 rle with old method : 0.031219482421875 time for calcul the mask position with numpy : 0.05181550979614258 nb_pixel_total : 1533 time to create 1 rle with old method : 0.0018353462219238281 time for calcul the mask position with numpy : 0.05279278755187988 nb_pixel_total : 170232 time to create 1 rle with new method : 1.4257750511169434 time for calcul the mask position with numpy : 0.060135602951049805 nb_pixel_total : 204858 time to create 1 rle with new method : 1.282038688659668 time for calcul the mask position with numpy : 0.05483078956604004 nb_pixel_total : 126749 time to create 1 rle with old method : 0.15176057815551758 time for calcul the mask position with numpy : 0.05416679382324219 nb_pixel_total : 1361 time to create 1 rle with old method : 0.0022084712982177734 time for calcul the mask position with numpy : 0.054343223571777344 nb_pixel_total : 20269 time to create 1 rle with old method : 0.024207115173339844 time for calcul the mask position with numpy : 0.05553579330444336 nb_pixel_total : 191116 time to create 1 rle with new method : 1.2113478183746338 time for calcul the mask position with numpy : 0.05418705940246582 nb_pixel_total : 167849 time to create 1 rle with new method : 1.2055459022521973 time for calcul the mask position with numpy : 0.053861141204833984 nb_pixel_total : 65805 time to create 1 rle with old method : 0.07480549812316895 time for calcul the mask position with numpy : 0.05396103858947754 nb_pixel_total : 4823 time to create 1 rle with old method : 0.005841493606567383 time for calcul the mask position with numpy : 0.05437612533569336 nb_pixel_total : 43562 time to create 1 rle with old method : 0.05037641525268555 time for calcul the mask position with numpy : 0.05369281768798828 nb_pixel_total : 4980 time to create 1 rle with old method : 0.00583338737487793 time for calcul the mask position with numpy : 0.05373072624206543 nb_pixel_total : 23764 time to create 1 rle with old method : 0.027591943740844727 time for calcul the mask position with numpy : 0.05510592460632324 nb_pixel_total : 150546 time to create 1 rle with new method : 1.5501995086669922 time for calcul the mask position with numpy : 0.05492258071899414 nb_pixel_total : 67496 time to create 1 rle with old method : 0.07943224906921387 time for calcul the mask position with numpy : 0.053705453872680664 nb_pixel_total : 106436 time to create 1 rle with old method : 0.16253256797790527 time for calcul the mask position with numpy : 0.07251834869384766 nb_pixel_total : 66327 time to create 1 rle with old method : 0.12360095977783203 time for calcul the mask position with numpy : 0.07259893417358398 nb_pixel_total : 33414 time to create 1 rle with old method : 0.05847311019897461 time for calcul the mask position with numpy : 0.0654458999633789 nb_pixel_total : 56823 time to create 1 rle with old method : 0.08378171920776367 time for calcul the mask position with numpy : 0.05624270439147949 nb_pixel_total : 73 time to create 1 rle with old method : 0.0003743171691894531 time for calcul the mask position with numpy : 0.05407094955444336 nb_pixel_total : 25763 time to create 1 rle with old method : 0.031027555465698242 time for calcul the mask position with numpy : 0.0541386604309082 nb_pixel_total : 5510 time to create 1 rle with old method : 0.006684780120849609 time for calcul the mask position with numpy : 0.0543370246887207 nb_pixel_total : 38490 time to create 1 rle with old method : 0.04435253143310547 time for calcul the mask position with numpy : 0.05538487434387207 nb_pixel_total : 99844 time to create 1 rle with old method : 0.11452507972717285 time for calcul the mask position with numpy : 0.05453634262084961 nb_pixel_total : 28331 time to create 1 rle with old method : 0.03293108940124512 time for calcul the mask position with numpy : 0.0544123649597168 nb_pixel_total : 3110 time to create 1 rle with old method : 0.003778696060180664 time for calcul the mask position with numpy : 0.05567359924316406 nb_pixel_total : 218174 time to create 1 rle with new method : 2.1162054538726807 time for calcul the mask position with numpy : 0.05524921417236328 nb_pixel_total : 186129 time to create 1 rle with new method : 1.4388556480407715 time for calcul the mask position with numpy : 0.05331683158874512 nb_pixel_total : 97918 time to create 1 rle with old method : 0.10958194732666016 time for calcul the mask position with numpy : 0.05431222915649414 nb_pixel_total : 269810 time to create 1 rle with new method : 1.2257349491119385 time for calcul the mask position with numpy : 0.05395770072937012 nb_pixel_total : 25549 time to create 1 rle with old method : 0.02945542335510254 time for calcul the mask position with numpy : 0.053922176361083984 nb_pixel_total : 86101 time to create 1 rle with old method : 0.10062527656555176 time for calcul the mask position with numpy : 0.052968502044677734 nb_pixel_total : 64043 time to create 1 rle with old method : 0.07340550422668457 time for calcul the mask position with numpy : 0.053907155990600586 nb_pixel_total : 98574 time to create 1 rle with old method : 0.1110389232635498 time for calcul the mask position with numpy : 0.05428743362426758 nb_pixel_total : 220273 time to create 1 rle with new method : 1.4677250385284424 time for calcul the mask position with numpy : 0.05199170112609863 nb_pixel_total : 160573 time to create 1 rle with new method : 1.3032240867614746 time for calcul the mask position with numpy : 0.053373098373413086 nb_pixel_total : 172005 time to create 1 rle with new method : 1.3995661735534668 time for calcul the mask position with numpy : 0.05095982551574707 nb_pixel_total : 2682 time to create 1 rle with old method : 0.0032165050506591797 time for calcul the mask position with numpy : 0.05148959159851074 nb_pixel_total : 4065 time to create 1 rle with old method : 0.005055665969848633 time for calcul the mask position with numpy : 0.05099129676818848 nb_pixel_total : 195455 time to create 1 rle with new method : 1.155733585357666 time for calcul the mask position with numpy : 0.053144216537475586 nb_pixel_total : 50527 time to create 1 rle with old method : 0.057570457458496094 time for calcul the mask position with numpy : 0.051859140396118164 nb_pixel_total : 28837 time to create 1 rle with old method : 0.03206300735473633 time for calcul the mask position with numpy : 0.05289053916931152 nb_pixel_total : 25458 time to create 1 rle with old method : 0.029061555862426758 time for calcul the mask position with numpy : 0.05180788040161133 nb_pixel_total : 11889 time to create 1 rle with old method : 0.015981674194335938 time for calcul the mask position with numpy : 0.05432939529418945 nb_pixel_total : 113337 time to create 1 rle with old method : 0.13312721252441406 time for calcul the mask position with numpy : 0.05574989318847656 nb_pixel_total : 114605 time to create 1 rle with old method : 0.1331644058227539 time for calcul the mask position with numpy : 0.0531618595123291 nb_pixel_total : 411 time to create 1 rle with old method : 0.0007078647613525391 time for calcul the mask position with numpy : 0.06024026870727539 nb_pixel_total : 264461 time to create 1 rle with new method : 1.3161969184875488 time for calcul the mask position with numpy : 0.05427813529968262 nb_pixel_total : 109 time to create 1 rle with old method : 0.00043892860412597656 time for calcul the mask position with numpy : 0.055532217025756836 nb_pixel_total : 20024 time to create 1 rle with old method : 0.023775339126586914 time for calcul the mask position with numpy : 0.05462765693664551 nb_pixel_total : 61736 time to create 1 rle with old method : 0.07384777069091797 time for calcul the mask position with numpy : 0.054070472717285156 nb_pixel_total : 153207 time to create 1 rle with new method : 1.2443368434906006 time for calcul the mask position with numpy : 0.05283021926879883 nb_pixel_total : 28254 time to create 1 rle with old method : 0.03335165977478027 time for calcul the mask position with numpy : 0.05417442321777344 nb_pixel_total : 73569 time to create 1 rle with old method : 0.08336949348449707 time for calcul the mask position with numpy : 0.05203890800476074 nb_pixel_total : 25163 time to create 1 rle with old method : 0.028950929641723633 create new chi : 40.067277908325195 time to delete rle : 0.005918741226196289 batch 1 Loaded 90 chid ids of type : 4855 Number RLEs to save : 67678 TO DO : save crop sub photo not yet done ! save time : 3.6953930854797363 nb_obj : 88 nb_hashtags : 10 time to prepare the origin masks : 70.8499367237091 time for calcul the mask position with numpy : 0.5670948028564453 nb_pixel_total : 3849897 time to create 1 rle with new method : 1.704186201095581 time for calcul the mask position with numpy : 0.05583763122558594 nb_pixel_total : 52871 time to create 1 rle with old method : 0.06360316276550293 time for calcul the mask position with numpy : 0.05422711372375488 nb_pixel_total : 21194 time to create 1 rle with old method : 0.024860620498657227 time for calcul the mask position with numpy : 0.055098533630371094 nb_pixel_total : 88252 time to create 1 rle with old method : 0.10119080543518066 time for calcul the mask position with numpy : 0.05315756797790527 nb_pixel_total : 37909 time to create 1 rle with old method : 0.05235409736633301 time for calcul the mask position with numpy : 0.05874156951904297 nb_pixel_total : 15496 time to create 1 rle with old method : 0.020079374313354492 time for calcul the mask position with numpy : 0.056203365325927734 nb_pixel_total : 49738 time to create 1 rle with old method : 0.057035207748413086 time for calcul the mask position with numpy : 0.0547940731048584 nb_pixel_total : 80955 time to create 1 rle with old method : 0.09224510192871094 time for calcul the mask position with numpy : 0.053867340087890625 nb_pixel_total : 31544 time to create 1 rle with old method : 0.03575420379638672 time for calcul the mask position with numpy : 0.0546567440032959 nb_pixel_total : 133890 time to create 1 rle with old method : 0.15015769004821777 time for calcul the mask position with numpy : 0.051253318786621094 nb_pixel_total : 23069 time to create 1 rle with old method : 0.02601790428161621 time for calcul the mask position with numpy : 0.4516892433166504 nb_pixel_total : 1504059 time to create 1 rle with new method : 1.69734525680542 time for calcul the mask position with numpy : 0.05226421356201172 nb_pixel_total : 9277 time to create 1 rle with old method : 0.010306596755981445 time for calcul the mask position with numpy : 0.05483293533325195 nb_pixel_total : 590912 time to create 1 rle with new method : 1.110733985900879 time for calcul the mask position with numpy : 0.05356454849243164 nb_pixel_total : 90769 time to create 1 rle with old method : 0.10410165786743164 time for calcul the mask position with numpy : 0.053893089294433594 nb_pixel_total : 47515 time to create 1 rle with old method : 0.05370497703552246 time for calcul the mask position with numpy : 0.05397367477416992 nb_pixel_total : 356 time to create 1 rle with old method : 0.0007178783416748047 time for calcul the mask position with numpy : 0.05226612091064453 nb_pixel_total : 128454 time to create 1 rle with old method : 0.14224576950073242 time for calcul the mask position with numpy : 0.0542302131652832 nb_pixel_total : 61469 time to create 1 rle with old method : 0.0710604190826416 time for calcul the mask position with numpy : 0.05369853973388672 nb_pixel_total : 458 time to create 1 rle with old method : 0.0006341934204101562 time for calcul the mask position with numpy : 0.057181596755981445 nb_pixel_total : 388393 time to create 1 rle with new method : 1.4983313083648682 time for calcul the mask position with numpy : 0.054909467697143555 nb_pixel_total : 151973 time to create 1 rle with new method : 1.2867867946624756 time for calcul the mask position with numpy : 0.05211067199707031 nb_pixel_total : 82600 time to create 1 rle with old method : 0.09078812599182129 time for calcul the mask position with numpy : 0.05126023292541504 nb_pixel_total : 70964 time to create 1 rle with old method : 0.07760453224182129 time for calcul the mask position with numpy : 0.05143904685974121 nb_pixel_total : 67141 time to create 1 rle with old method : 0.07594180107116699 time for calcul the mask position with numpy : 0.05160665512084961 nb_pixel_total : 13159 time to create 1 rle with old method : 0.014433145523071289 time for calcul the mask position with numpy : 0.05303788185119629 nb_pixel_total : 57477 time to create 1 rle with old method : 0.06727361679077148 time for calcul the mask position with numpy : 0.053933143615722656 nb_pixel_total : 78331 time to create 1 rle with old method : 0.08988833427429199 time for calcul the mask position with numpy : 0.0538632869720459 nb_pixel_total : 79 time to create 1 rle with old method : 0.00013017654418945312 time for calcul the mask position with numpy : 0.05450320243835449 nb_pixel_total : 195775 time to create 1 rle with new method : 1.3954336643218994 time for calcul the mask position with numpy : 0.05423164367675781 nb_pixel_total : 42481 time to create 1 rle with old method : 0.04879474639892578 time for calcul the mask position with numpy : 0.0536954402923584 nb_pixel_total : 10050 time to create 1 rle with old method : 0.011751890182495117 time for calcul the mask position with numpy : 0.05439138412475586 nb_pixel_total : 123067 time to create 1 rle with old method : 0.1403183937072754 time for calcul the mask position with numpy : 0.05402374267578125 nb_pixel_total : 15746 time to create 1 rle with old method : 0.018198251724243164 time for calcul the mask position with numpy : 0.05370759963989258 nb_pixel_total : 38490 time to create 1 rle with old method : 0.0449376106262207 time for calcul the mask position with numpy : 0.05400991439819336 nb_pixel_total : 57286 time to create 1 rle with old method : 0.0661766529083252 time for calcul the mask position with numpy : 0.05407357215881348 nb_pixel_total : 41873 time to create 1 rle with old method : 0.04862833023071289 time for calcul the mask position with numpy : 0.05432724952697754 nb_pixel_total : 174755 time to create 1 rle with new method : 2.202251672744751 time for calcul the mask position with numpy : 0.05381131172180176 nb_pixel_total : 384129 time to create 1 rle with new method : 1.1445987224578857 time for calcul the mask position with numpy : 0.05923628807067871 nb_pixel_total : 141478 time to create 1 rle with old method : 0.1676487922668457 time for calcul the mask position with numpy : 0.05396747589111328 nb_pixel_total : 32204 time to create 1 rle with old method : 0.03746175765991211 time for calcul the mask position with numpy : 0.054175376892089844 nb_pixel_total : 63345 time to create 1 rle with old method : 0.07332348823547363 time for calcul the mask position with numpy : 0.054346561431884766 nb_pixel_total : 108117 time to create 1 rle with old method : 0.11872696876525879 time for calcul the mask position with numpy : 0.051605224609375 nb_pixel_total : 14605 time to create 1 rle with old method : 0.01590442657470703 time for calcul the mask position with numpy : 0.050615549087524414 nb_pixel_total : 90154 time to create 1 rle with old method : 0.09902548789978027 time for calcul the mask position with numpy : 0.05179262161254883 nb_pixel_total : 174356 time to create 1 rle with new method : 0.9271912574768066 time for calcul the mask position with numpy : 0.05002450942993164 nb_pixel_total : 7103 time to create 1 rle with old method : 0.008135795593261719 time for calcul the mask position with numpy : 0.049836158752441406 nb_pixel_total : 6772 time to create 1 rle with old method : 0.007570028305053711 time for calcul the mask position with numpy : 0.05035996437072754 nb_pixel_total : 6662 time to create 1 rle with old method : 0.0075800418853759766 time for calcul the mask position with numpy : 0.05066967010498047 nb_pixel_total : 19930 time to create 1 rle with old method : 0.021390914916992188 time for calcul the mask position with numpy : 0.05025315284729004 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002639293670654297 time for calcul the mask position with numpy : 0.05005621910095215 nb_pixel_total : 22673 time to create 1 rle with old method : 0.024680614471435547 time for calcul the mask position with numpy : 0.04996848106384277 nb_pixel_total : 56138 time to create 1 rle with old method : 0.061933279037475586 time for calcul the mask position with numpy : 0.05119514465332031 nb_pixel_total : 226184 time to create 1 rle with new method : 0.9255335330963135 time for calcul the mask position with numpy : 0.05040931701660156 nb_pixel_total : 24722 time to create 1 rle with old method : 0.026688098907470703 time for calcul the mask position with numpy : 0.05005812644958496 nb_pixel_total : 57274 time to create 1 rle with old method : 0.06159257888793945 time for calcul the mask position with numpy : 0.04991936683654785 nb_pixel_total : 25510 time to create 1 rle with old method : 0.0279541015625 time for calcul the mask position with numpy : 0.04983806610107422 nb_pixel_total : 58265 time to create 1 rle with old method : 0.06467151641845703 time for calcul the mask position with numpy : 0.04984259605407715 nb_pixel_total : 91879 time to create 1 rle with old method : 0.09964108467102051 time for calcul the mask position with numpy : 0.04998421669006348 nb_pixel_total : 7496 time to create 1 rle with old method : 0.00856161117553711 time for calcul the mask position with numpy : 0.05010819435119629 nb_pixel_total : 5226 time to create 1 rle with old method : 0.006211996078491211 time for calcul the mask position with numpy : 0.05070066452026367 nb_pixel_total : 318042 time to create 1 rle with new method : 1.1355786323547363 time for calcul the mask position with numpy : 0.05084109306335449 nb_pixel_total : 39879 time to create 1 rle with old method : 0.04477882385253906 time for calcul the mask position with numpy : 0.0526125431060791 nb_pixel_total : 4637 time to create 1 rle with old method : 0.00537872314453125 time for calcul the mask position with numpy : 0.051703691482543945 nb_pixel_total : 11249 time to create 1 rle with old method : 0.012787580490112305 time for calcul the mask position with numpy : 0.050408363342285156 nb_pixel_total : 39694 time to create 1 rle with old method : 0.0436253547668457 time for calcul the mask position with numpy : 0.05622673034667969 nb_pixel_total : 511615 time to create 1 rle with new method : 0.9332234859466553 time for calcul the mask position with numpy : 0.05851936340332031 nb_pixel_total : 739253 time to create 1 rle with new method : 1.06319260597229 time for calcul the mask position with numpy : 0.051218509674072266 nb_pixel_total : 3192 time to create 1 rle with old method : 0.0035660266876220703 time for calcul the mask position with numpy : 0.052607059478759766 nb_pixel_total : 284484 time to create 1 rle with new method : 0.8691344261169434 time for calcul the mask position with numpy : 0.05122256278991699 nb_pixel_total : 8029 time to create 1 rle with old method : 0.009069442749023438 time for calcul the mask position with numpy : 0.05093789100646973 nb_pixel_total : 93 time to create 1 rle with old method : 0.00017595291137695312 time for calcul the mask position with numpy : 0.0516054630279541 nb_pixel_total : 31382 time to create 1 rle with old method : 0.03409433364868164 time for calcul the mask position with numpy : 0.05096864700317383 nb_pixel_total : 48095 time to create 1 rle with old method : 0.05261492729187012 time for calcul the mask position with numpy : 0.05200672149658203 nb_pixel_total : 3950 time to create 1 rle with old method : 0.004566669464111328 time for calcul the mask position with numpy : 0.05119895935058594 nb_pixel_total : 316 time to create 1 rle with old method : 0.00038695335388183594 time for calcul the mask position with numpy : 0.052736520767211914 nb_pixel_total : 132656 time to create 1 rle with old method : 0.14519047737121582 time for calcul the mask position with numpy : 0.05221438407897949 nb_pixel_total : 82333 time to create 1 rle with old method : 0.09115934371948242 time for calcul the mask position with numpy : 0.052387237548828125 nb_pixel_total : 18657 time to create 1 rle with old method : 0.021387577056884766 time for calcul the mask position with numpy : 0.057181596755981445 nb_pixel_total : 64274 time to create 1 rle with old method : 0.08444595336914062 time for calcul the mask position with numpy : 0.06359362602233887 nb_pixel_total : 85713 time to create 1 rle with old method : 0.09815764427185059 time for calcul the mask position with numpy : 0.05554461479187012 nb_pixel_total : 33929 time to create 1 rle with old method : 0.03938627243041992 time for calcul the mask position with numpy : 0.055623769760131836 nb_pixel_total : 202008 time to create 1 rle with new method : 1.0025267601013184 time for calcul the mask position with numpy : 0.05224609375 nb_pixel_total : 26847 time to create 1 rle with old method : 0.031250715255737305 time for calcul the mask position with numpy : 0.059847354888916016 nb_pixel_total : 75041 time to create 1 rle with old method : 0.08556747436523438 time for calcul the mask position with numpy : 0.05315852165222168 nb_pixel_total : 62329 time to create 1 rle with old method : 0.07064461708068848 time for calcul the mask position with numpy : 0.05304574966430664 nb_pixel_total : 53905 time to create 1 rle with old method : 0.0602874755859375 time for calcul the mask position with numpy : 0.05240917205810547 nb_pixel_total : 22996 time to create 1 rle with old method : 0.027789831161499023 time for calcul the mask position with numpy : 0.05284261703491211 nb_pixel_total : 22510 time to create 1 rle with old method : 0.025576353073120117 create new chi : 29.056684732437134 time to delete rle : 0.007528543472290039 batch 1 Loaded 89 chid ids of type : 4855 Number RLEs to save : 64589 TO DO : save crop sub photo not yet done ! save time : 3.481111526489258 nb_obj : 10 nb_hashtags : 5 time to prepare the origin masks : 21.09220576286316 time for calcul the mask position with numpy : 0.12104439735412598 nb_pixel_total : 1539199 time to create 1 rle with new method : 1.1261136531829834 time for calcul the mask position with numpy : 0.07957339286804199 nb_pixel_total : 199538 time to create 1 rle with new method : 1.1315619945526123 time for calcul the mask position with numpy : 0.06434321403503418 nb_pixel_total : 23367 time to create 1 rle with old method : 0.02800130844116211 time for calcul the mask position with numpy : 0.059937477111816406 nb_pixel_total : 22561 time to create 1 rle with old method : 0.02515435218811035 time for calcul the mask position with numpy : 0.06460809707641602 nb_pixel_total : 91584 time to create 1 rle with old method : 0.10664844512939453 time for calcul the mask position with numpy : 0.07014083862304688 nb_pixel_total : 1287756 time to create 1 rle with new method : 2.088693380355835 time for calcul the mask position with numpy : 0.0471799373626709 nb_pixel_total : 14556 time to create 1 rle with old method : 0.016538381576538086 time for calcul the mask position with numpy : 0.27872157096862793 nb_pixel_total : 3973781 time to create 1 rle with new method : 1.1780180931091309 time for calcul the mask position with numpy : 0.06516098976135254 nb_pixel_total : 510212 time to create 1 rle with new method : 1.1885921955108643 time for calcul the mask position with numpy : 0.5896148681640625 nb_pixel_total : 2340321 time to create 1 rle with new method : 1.0831494331359863 time for calcul the mask position with numpy : 0.19406747817993164 nb_pixel_total : 2976325 time to create 1 rle with new method : 1.3093745708465576 create new chi : 11.252146005630493 time to delete rle : 0.003275632858276367 batch 1 Loaded 11 chid ids of type : 4855 Number RLEs to save : 28478 TO DO : save crop sub photo not yet done ! save time : 1.507033109664917 map_output_result : {1379845298: (0.48271874378232266, 'Should be the crop_list due to order', 0.23672266439233428), 1379845296: (0.48271874378232266, 'Should be the crop_list due to order', 0.4191911296097256), 1379845132: (0.48271874378232266, 'Should be the crop_list due to order', 0.2025620158197315), 1379845131: (0.48271874378232266, 'Should be the crop_list due to order', 0.4521519493577475), 1379845128: (0.48271874378232266, 'Should be the crop_list due to order', 0.5915782313228115), 1379845123: (0.48271874378232266, 'Should be the crop_list due to order', 0.9941064721915858)} 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 [1379845298, 1379845296, 1379845132, 1379845131, 1379845128, 1379845123] Looping around the photos to save general results len do output : 6 /1379845298.Didn't retrieve data . /1379845296.Didn't retrieve data . /1379845132.Didn't retrieve data . /1379845131.Didn't retrieve data . /1379845128.Didn't retrieve data . /1379845123.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, '3623815') ('4741', '26291506', '1379845298', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845296', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845132', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845131', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845128', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845123', None, None, None, None, None, '3623815') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 18 time used for this insertion : 0.013930082321166992 save_final save missing photos in datou_result : time spend for datou_step_exec : 545.0209760665894 time spend to save output : 0.016651153564453125 total time spend for step 5 : 545.0376272201538 step6:crop_condition Thu Aug 28 15:14:41 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 6 ! batch 1 Loaded 419 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 ! map_result returned by crop_photo_return_map_crop : length : 41 About to insert : list_path_to_insert length 41 new photo from crops ! About to upload 41 photos upload in portfolio : 3015255 init cache_photo without model_param we have 41 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756386912_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 41 photos in the portfolio 3015255 time of upload the photos Elapsed time : 12.505981922149658 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.1} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 102 About to insert : list_path_to_insert length 102 new photo from crops ! About to upload 102 photos upload in portfolio : 3015255 init cache_photo without model_param we have 102 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756386988_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 102 photos in the portfolio 3015255 time of upload the photos Elapsed time : 27.611040353775024 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.1} filtre for class : metal hashtag_id of this class : 492628673 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 29 About to insert : list_path_to_insert length 29 new photo from crops ! About to upload 29 photos upload in portfolio : 3015255 init cache_photo without model_param we have 29 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387027_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 29 photos in the portfolio 3015255 time of upload the photos Elapsed time : 7.58010721206665 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 ! map_result returned by crop_photo_return_map_crop : length : 11 About to insert : list_path_to_insert length 11 new photo from crops ! About to upload 11 photos upload in portfolio : 3015255 init cache_photo without model_param we have 11 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387042_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 11 photos in the portfolio 3015255 time of upload the photos Elapsed time : 3.0020980834960938 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/1756387049_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 : 1.2914252281188965 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 begin to crop the class : sac param for this class : {'min_score': 0.1} filtre for class : sac hashtag_id of this class : 492618350 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 25 About to insert : list_path_to_insert length 25 new photo from crops ! About to upload 25 photos upload in portfolio : 3015255 init cache_photo without model_param we have 25 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387064_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 25 photos in the portfolio 3015255 time of upload the photos Elapsed time : 8.470355033874512 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 ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 3015255 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387076_3865689 batch_size : 0, verbose : False, strat_bulk_insert : 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 2 photos in the portfolio 3015255 time of upload the photos Elapsed time : 0.9509768486022949 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 begin to crop the class : organique param for this class : {'min_score': 0.1} filtre for class : organique hashtag_id of this class : 530726390 begin to crop the class : dasri param for this class : {'min_score': 0.1} filtre for class : dasri hashtag_id of this class : 1608424396 begin to crop the class : masque param for this class : {'min_score': 0.1} filtre for class : masque hashtag_id of this class : 492626781 begin to crop the class : encombrant param for this class : {'min_score': 0.1} filtre for class : encombrant hashtag_id of this class : 605975549 begin to crop the class : autre param for this class : {'min_score': 0.1} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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/1756387124_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 : 12.649955749511719 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/1756387140_3865689 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 : 0.5657250881195068 we have finished the crop for the class : autre_emballage begin to crop the class : autre_non_emballage param for this class : {'min_score': 0.1} filtre for class : autre_non_emballage hashtag_id of this class : 2107760329 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 new photo from crops ! About to upload 14 photos upload in portfolio : 3015255 init cache_photo without model_param we have 14 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387158_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 14 photos in the portfolio 3015255 time of upload the photos Elapsed time : 4.187307596206665 we have finished the crop for the class : autre_non_emballage begin to crop the class : environnement param for this class : {'min_score': 0.1} filtre for class : environnement hashtag_id of this class : 493012381 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 43 About to insert : list_path_to_insert length 43 new photo from crops ! About to upload 43 photos upload in portfolio : 3015255 init cache_photo without model_param we have 43 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387299_3865689 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 43 photos in the portfolio 3015255 time of upload the photos Elapsed time : 14.136753797531128 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 [1379845298, 1379845296, 1379845132, 1379845131, 1379845128, 1379845123] Looping around the photos to save general results len do output : 317 /1379890159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890315Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890392Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890394Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890396Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890398Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890401Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890405Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890408Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890412Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890413Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890414Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890941Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890943Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890978Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379890979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379891843Didn'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, '3623815') ('4741', '26291506', '1379845298', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845296', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845132', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845131', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845128', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845123', None, None, None, None, None, '3623815') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 957 time used for this insertion : 0.1348259449005127 save_final save missing photos in datou_result : time spend for datou_step_exec : 436.8614900112152 time spend to save output : 0.14586400985717773 total time spend for step 6 : 437.0073540210724 step7:ventilate_hashtags_in_portfolio Thu Aug 28 15:21:58 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 : 26291506 get user id for portfolio 26291506 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`=26291506 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`=26291506 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`=26291506 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`=26291506 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/26295589,26295590,26295591,26295592,26295593,26295598,26295600,26295601,26295602,26295603,26295604,26295605,26295607,26295608,26295609,26295610,26295611,26295612,26295613,26295614?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=26291506 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1379845298, 1379845296, 1379845132, 1379845131, 1379845128, 1379845123] Looping around the photos to save general results len do output : 1 /26291506. 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, '3623815') ('4741', '26291506', '1379845298', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845296', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845132', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845131', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845128', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845123', None, None, None, None, None, '3623815') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 7 time used for this insertion : 0.015182018280029297 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.016993761062622 time spend to save output : 0.018912553787231445 total time spend for step 7 : 5.0359063148498535 step8:final Thu Aug 28 15:22:03 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 : {1379845298: ('0.42566700782808753',), 1379845296: ('0.42566700782808753',), 1379845132: ('0.42566700782808753',), 1379845131: ('0.42566700782808753',), 1379845128: ('0.42566700782808753',), 1379845123: ('0.42566700782808753',)} new output for save of step final : {1379845298: ('0.42566700782808753',), 1379845296: ('0.42566700782808753',), 1379845132: ('0.42566700782808753',), 1379845131: ('0.42566700782808753',), 1379845128: ('0.42566700782808753',), 1379845123: ('0.42566700782808753',)} [1379845298, 1379845296, 1379845132, 1379845131, 1379845128, 1379845123] Looping around the photos to save general results len do output : 6 /1379845298.Didn't retrieve data . /1379845296.Didn't retrieve data . /1379845132.Didn't retrieve data . /1379845131.Didn't retrieve data . /1379845128.Didn't retrieve data . /1379845123.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, '3623815') ('4741', '26291506', '1379845298', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845296', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845132', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845131', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845128', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845123', None, None, None, None, None, '3623815') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 18 time used for this insertion : 0.015097856521606445 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12288403511047363 time spend to save output : 0.015650033950805664 total time spend for step 8 : 0.1385340690612793 step9:velours_tree Thu Aug 28 15:22:03 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 : 1.2007193565368652 time spend to save output : 3.695487976074219e-05 total time spend for step 9 : 1.200756311416626 step10:send_mail_cod Thu Aug 28 15:22:04 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_P26291506_28-08-2025_15_22_04.pdf 26295563 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 .imagette262955631756387324 26295564 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 .imagette262955641756387326 26295565 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 .imagette262955651756387327 26295566 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 .imagette262955661756387329 26295567 change filename to text .change filename to text .change filename to text .imagette262955671756387330 26295568 imagette262955681756387330 26295569 imagette262955691756387330 26295570 imagette262955701756387330 26295571 imagette262955711756387330 26295572 imagette262955721756387330 26295573 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 .imagette262955731756387330 26295574 change filename to text .change filename to text .imagette262955741756387332 26295575 imagette262955751756387332 26295576 imagette262955761756387332 26295577 imagette262955771756387332 26295578 imagette262955781756387332 26295579 imagette262955791756387332 26295580 change filename to text .imagette262955801756387332 26295581 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 .imagette262955811756387332 26295583 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 .imagette262955831756387333 26295584 imagette262955841756387335 26295585 imagette262955851756387335 26295586 imagette262955861756387335 26295587 imagette262955871756387335 26295588 imagette262955881756387335 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=26291506 and hashtag_type = 4855 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/26295589,26295590,26295591,26295592,26295593,26295598,26295600,26295601,26295602,26295603,26295604,26295605,26295607,26295608,26295609,26295610,26295611,26295612,26295613,26295614?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=26291506 your option no_mail is active, we will not send the real mail to your client args[1379845298] : ((1379845298, 3506.0889004251894, 492609224), (1379845298, -0.22888609452880188, 496442774), '0.42566700782808753') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845296] : ((1379845296, 899.0823582448013, 2107751945), (1379845296, -0.40008455735376297, 496442774), '0.42566700782808753') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845132] : ((1379845132, 2530.132687017643, 492609224), (1379845132, -0.3932092754340075, 496442774), '0.42566700782808753') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845131] : ((1379845131, 1910.8582522167574, 2107751945), (1379845131, -0.3865280676519457, 496442774), '0.42566700782808753') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845128] : ((1379845128, 2070.132166554053, 492609224), (1379845128, -0.20063544317070545, 496442774), '0.42566700782808753') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845123] : ((1379845123, 608.3117192298713, 492688767), (1379845123, -0.1903094269379332, 496442774), '0.42566700782808753') We are sending mail with results at report@fotonower.com,cod@fotonower.com refus_total : 0.42566700782808753 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_P26291506_28-08-2025_15_22_04.pdf results_Auto_P26291506_28-08-2025_15_22_04.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291506_28-08-2025_15_22_04.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','26291506','results_Auto_P26291506_28-08-2025_15_22_04.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291506_28-08-2025_15_22_04.pdf','pdf','','2.96','0.42566700782808753') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1379845298, 1379845296, 1379845132, 1379845131, 1379845128, 1379845123] 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, '3623815') ('4741', '26291506', '1379845298', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845296', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845132', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845131', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845128', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845123', None, None, None, None, None, '3623815') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.016249418258666992 save_final save missing photos in datou_result : time spend for datou_step_exec : 15.077186584472656 time spend to save output : 0.016452789306640625 total time spend for step 10 : 15.093639373779297 step11:split_time_score Thu Aug 28 15:22:19 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array 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'}] (('42', 2), ('43', 4)) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 26082025 26291506 Nombre de photos uploadées : 6 / 23040 (0%) 26082025 26291506 Nombre de photos taguées (types de déchets): 0 / 6 (0%) 26082025 26291506 Nombre de photos taguées (volume) : 0 / 6 (0%) elapsed_time : load_data_split_time_score 4.291534423828125e-06 elapsed_time : order_list_meta_photo_and_scores 1.1920928955078125e-05 ?????? elapsed_time : fill_and_build_computed_from_old_data 0.0004229545593261719 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.2069227695465088 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291504 order by id desc limit 1 Qualite : 0.35901833075514267 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291505_28-08-2025_14_55_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291505 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`=26291505 AND mptpi.`type`=4855 To do Qualite : 0.42566700782808753 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291506_28-08-2025_15_22_04.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291506 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`=26291506 AND mptpi.`type`=4855 To do Qualite : 0.2567984737532319 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291507_28-08-2025_14_35_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291507 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`=26291507 AND mptpi.`type`=4855 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291508 order by id desc limit 1 Qualite : 0.44521359328707644 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291509_28-08-2025_14_18_17.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291509 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`=26291509 AND mptpi.`type`=4855 To do Qualite : 0.5227519267425498 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291510_28-08-2025_12_42_57.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291510 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`=26291510 AND mptpi.`type`=4855 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'26082025': {'nb_upload': 6, '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 [1379845298, 1379845296, 1379845132, 1379845131, 1379845128, 1379845123] Looping around the photos to save general results len do output : 1 /26291506Didn'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, '3623815') ('4741', '26291506', '1379845298', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845296', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845132', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845131', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845128', None, None, None, None, None, '3623815') ('4741', None, None, None, None, None, None, None, '3623815') ('4741', '26291506', '1379845123', None, None, None, None, None, '3623815') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 7 time used for this insertion : 0.015022754669189453 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.545578956604004 time spend to save output : 0.015266656875610352 total time spend for step 11 : 2.5608456134796143 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 6 set_done_treatment 757.78user 417.97system 20:56.48elapsed 93%CPU (0avgtext+0avgdata 8402684maxresident)k 1781472inputs+825840outputs (32640major+64315363minor)pagefaults 0swaps