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 : 3706725 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 : ['3623817'] with mtr_portfolio_ids : ['26291509'] and first list_photo_ids : [] new path : /proc/3706725/ 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 , BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 1.203193187713623 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 14:01:29 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 : 5090 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 14:01:33.200804: 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 14:01:33.228538: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 14:01:33.231177: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd36c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 14:01:33.231229: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 14:01:33.236264: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 14:01:33.393709: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xc2d0ef0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 14:01:33.393794: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 14:01:33.395195: 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 14:01:33.395745: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:01:33.399465: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:01:33.402858: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 14:01:33.403376: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 14:01:33.406183: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 14:01:33.407574: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 14:01:33.412612: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 14:01:33.413972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 14:01:33.414081: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:01:33.414739: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 14:01:33.414757: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 14:01:33.414767: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 14:01:33.415963: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4638 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 14:01:33.769243: 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 14:01:33.769331: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:01:33.769352: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:01:33.769370: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 14:01:33.769388: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 14:01:33.769406: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 14:01:33.769424: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 14:01:33.769442: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 14:01:33.770619: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 14:01:33.771924: 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 14:01:33.771990: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:01:33.772012: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:01:33.772033: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 14:01:33.772067: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 14:01:33.772088: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 14:01:33.772107: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 14:01:33.772128: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 14:01:33.773340: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 14:01:33.773378: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 14:01:33.773389: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 14:01:33.773399: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 14:01:33.774531: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4638 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 14:01:47.207753: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:01:47.548030: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 14:01:49.695186: 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 14:01:49.698714: 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 14:01:49.699247: 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 14:01:49.699747: 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 14:01:49.700207: 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 14:01:49.700687: 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 14:01:49.701174: 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 14:01:49.707268: 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 14:01:49.709593: 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 14:01:49.709624: 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 14:01:49.716278: 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 14:01:49.716327: 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 14:01:49.716851: 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 14:01:49.716871: 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 14:01:49.722957: 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 14:01:49.723003: 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 14:01:49.723643: 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 14:01:49.723668: 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 14:01:49.750270: 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 14:01:49.750317: 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 14:01:49.750822: 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 14:01:49.750839: 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 14:01:49.756180: 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 14:01:49.756209: 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 14:01:49.756736: 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 14:01:49.756772: 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 14:01:49.791147: 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 14:01:49.791743: 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 14:01:49.793921: 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 14:01:49.794485: 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 14:01:49.832268: 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 14:01:49.832840: 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 14:01:49.834796: 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 14:01:49.835315: 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 14:01:49.865407: 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 14:01:49.865971: 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 14:01:49.867519: 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 14:01:49.868031: 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 14:01:49.873631: 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 14:01:49.874164: 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 14:01:49.875841: 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 14:01:49.876359: 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 14:01:49.882035: 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 14:01:49.882562: 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 14:01:49.884056: 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 14:01:49.884579: 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 14:01:49.961697: 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 14:01:49.962628: 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 14:01:49.963164: 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 14:01:49.963680: 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 14:01:49.967805: 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 14:01:49.968354: 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 14:01:49.984461: 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 14:01:49.985028: 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 14:01:49.985541: 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 14:01:49.986050: 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 14:01:49.998854: 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 14:01:49.999422: 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 14:01:49.999932: 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 14:01:50.000452: 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 14:01:50.004929: 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 14:01:50.005448: 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 14:01:50.010159: 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 14:01:50.010689: 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 14:01:50.026852: 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 14:01:50.027416: 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 14:01:50.031766: 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 14:01:50.032291: 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 14:01:50.032940: 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 14:01:50.033455: 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 14:01:50.034360: 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 14:01:50.034866: 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 14:01:50.049439: 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 14:01:50.050017: 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 14:01:50.050562: 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 14:01:50.051068: 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 14:01:50.051573: 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 14:01:50.052112: 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 14:01:50.052641: 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 14:01:50.053250: 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 14:01:50.062899: 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 14:01:50.063413: 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 14:01:50.070033: 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 14:01:50.070594: 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 14:01:50.111877: 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 14:01:50.111978: 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 14:01:50.113078: 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 14:01:50.114171: 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 14:01:50.121693: 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 14:01:50.122248: 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 14:01:50.122776: 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 14:01:50.123309: 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 14:01:50.131746: 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 14:01:50.132307: 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 14:01:50.214208: 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 14:01:50.215049: 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 14:01:50.215869: 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 14:01:50.217697: 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 14:01:50.222570: 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 14:01:50.223382: 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 14:01:50.224182: 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 14:01:50.225682: 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 14:01:50.226981: 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 14:01:50.239849: 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 14:01:50.240438: 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 14:01:50.250602: 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 14:01:50.251433: 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 14:01:50.252427: 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 14:01:50.253227: 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 14:01:50.253893: 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 14:01:50.254654: 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 : 5 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 : 15 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 : 16 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 : 21 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 : 3 Detection mask done ! Trying to reset tf kernel 3707010 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 120 tf kernel not reseted sub process len(results) : 5 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 5 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 : 1313 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 : 0.0642850399017334 nb_pixel_total : 298748 time to create 1 rle with new method : 0.027561426162719727 length of segment : 695 time for calcul the mask position with numpy : 0.002744913101196289 nb_pixel_total : 216437 time to create 1 rle with new method : 0.008724451065063477 length of segment : 626 time for calcul the mask position with numpy : 0.019170761108398438 nb_pixel_total : 441878 time to create 1 rle with new method : 0.07362508773803711 length of segment : 1395 time for calcul the mask position with numpy : 0.0007817745208740234 nb_pixel_total : 39451 time to create 1 rle with old method : 0.04466080665588379 length of segment : 250 time for calcul the mask position with numpy : 0.003046751022338867 nb_pixel_total : 130234 time to create 1 rle with old method : 0.14090657234191895 length of segment : 438 time for calcul the mask position with numpy : 0.0009002685546875 nb_pixel_total : 48329 time to create 1 rle with old method : 0.05315804481506348 length of segment : 188 time for calcul the mask position with numpy : 0.002376079559326172 nb_pixel_total : 113087 time to create 1 rle with old method : 0.13184905052185059 length of segment : 394 time for calcul the mask position with numpy : 0.000797271728515625 nb_pixel_total : 41743 time to create 1 rle with old method : 0.047177791595458984 length of segment : 161 time for calcul the mask position with numpy : 0.00029730796813964844 nb_pixel_total : 7663 time to create 1 rle with old method : 0.008499383926391602 length of segment : 132 time for calcul the mask position with numpy : 0.0005319118499755859 nb_pixel_total : 6583 time to create 1 rle with old method : 0.007626056671142578 length of segment : 161 time for calcul the mask position with numpy : 0.0016467571258544922 nb_pixel_total : 83510 time to create 1 rle with old method : 0.0903778076171875 length of segment : 395 time for calcul the mask position with numpy : 0.010608196258544922 nb_pixel_total : 378023 time to create 1 rle with new method : 0.2836146354675293 length of segment : 736 time for calcul the mask position with numpy : 0.0021932125091552734 nb_pixel_total : 96209 time to create 1 rle with old method : 0.11261248588562012 length of segment : 465 time for calcul the mask position with numpy : 0.001416921615600586 nb_pixel_total : 78343 time to create 1 rle with old method : 0.08708572387695312 length of segment : 281 time for calcul the mask position with numpy : 0.0005726814270019531 nb_pixel_total : 20714 time to create 1 rle with old method : 0.030109167098999023 length of segment : 112 time for calcul the mask position with numpy : 0.003461599349975586 nb_pixel_total : 103219 time to create 1 rle with old method : 0.11460566520690918 length of segment : 238 time for calcul the mask position with numpy : 0.0006806850433349609 nb_pixel_total : 27945 time to create 1 rle with old method : 0.03352689743041992 length of segment : 159 time for calcul the mask position with numpy : 0.0022134780883789062 nb_pixel_total : 51269 time to create 1 rle with old method : 0.05826687812805176 length of segment : 205 time for calcul the mask position with numpy : 0.0037109851837158203 nb_pixel_total : 79506 time to create 1 rle with old method : 0.08740091323852539 length of segment : 622 time for calcul the mask position with numpy : 0.0006864070892333984 nb_pixel_total : 20554 time to create 1 rle with old method : 0.023855209350585938 length of segment : 105 time for calcul the mask position with numpy : 0.0009567737579345703 nb_pixel_total : 46516 time to create 1 rle with old method : 0.05189871788024902 length of segment : 225 time for calcul the mask position with numpy : 0.0012192726135253906 nb_pixel_total : 33133 time to create 1 rle with old method : 0.05180835723876953 length of segment : 142 time for calcul the mask position with numpy : 0.0033037662506103516 nb_pixel_total : 104846 time to create 1 rle with old method : 0.12006139755249023 length of segment : 267 time for calcul the mask position with numpy : 0.0038514137268066406 nb_pixel_total : 187326 time to create 1 rle with new method : 0.01101541519165039 length of segment : 408 time for calcul the mask position with numpy : 0.0017130374908447266 nb_pixel_total : 71699 time to create 1 rle with old method : 0.08158111572265625 length of segment : 276 time for calcul the mask position with numpy : 0.0006830692291259766 nb_pixel_total : 18605 time to create 1 rle with old method : 0.022391080856323242 length of segment : 78 time for calcul the mask position with numpy : 0.0022606849670410156 nb_pixel_total : 66936 time to create 1 rle with old method : 0.07694888114929199 length of segment : 280 time for calcul the mask position with numpy : 0.00046515464782714844 nb_pixel_total : 8845 time to create 1 rle with old method : 0.01050114631652832 length of segment : 68 time for calcul the mask position with numpy : 0.0020902156829833984 nb_pixel_total : 52193 time to create 1 rle with old method : 0.05825042724609375 length of segment : 248 time for calcul the mask position with numpy : 0.0015916824340820312 nb_pixel_total : 32353 time to create 1 rle with old method : 0.03687644004821777 length of segment : 173 time for calcul the mask position with numpy : 0.0014276504516601562 nb_pixel_total : 11077 time to create 1 rle with old method : 0.014240026473999023 length of segment : 93 time for calcul the mask position with numpy : 0.0016798973083496094 nb_pixel_total : 90732 time to create 1 rle with old method : 0.10129427909851074 length of segment : 423 time for calcul the mask position with numpy : 0.042543649673461914 nb_pixel_total : 878517 time to create 1 rle with new method : 0.09448838233947754 length of segment : 871 time for calcul the mask position with numpy : 0.002276897430419922 nb_pixel_total : 98549 time to create 1 rle with old method : 0.11350369453430176 length of segment : 377 time for calcul the mask position with numpy : 0.008501768112182617 nb_pixel_total : 234329 time to create 1 rle with new method : 0.013998746871948242 length of segment : 899 time for calcul the mask position with numpy : 0.004441261291503906 nb_pixel_total : 116574 time to create 1 rle with old method : 0.17773890495300293 length of segment : 631 time for calcul the mask position with numpy : 0.002719879150390625 nb_pixel_total : 93883 time to create 1 rle with old method : 0.11266922950744629 length of segment : 433 time for calcul the mask position with numpy : 0.0018842220306396484 nb_pixel_total : 91307 time to create 1 rle with old method : 0.11408448219299316 length of segment : 276 time for calcul the mask position with numpy : 0.004111051559448242 nb_pixel_total : 134987 time to create 1 rle with old method : 0.160538911819458 length of segment : 466 time for calcul the mask position with numpy : 0.0008664131164550781 nb_pixel_total : 27592 time to create 1 rle with old method : 0.03719067573547363 length of segment : 228 time for calcul the mask position with numpy : 0.0009510517120361328 nb_pixel_total : 28347 time to create 1 rle with old method : 0.03218388557434082 length of segment : 257 time for calcul the mask position with numpy : 0.01931166648864746 nb_pixel_total : 572789 time to create 1 rle with new method : 0.14036226272583008 length of segment : 630 time for calcul the mask position with numpy : 0.009528160095214844 nb_pixel_total : 237637 time to create 1 rle with new method : 0.0658559799194336 length of segment : 814 time for calcul the mask position with numpy : 0.003746509552001953 nb_pixel_total : 150208 time to create 1 rle with new method : 0.005989789962768555 length of segment : 449 time for calcul the mask position with numpy : 0.0010411739349365234 nb_pixel_total : 21362 time to create 1 rle with old method : 0.031899452209472656 length of segment : 213 time for calcul the mask position with numpy : 0.004935026168823242 nb_pixel_total : 134521 time to create 1 rle with old method : 0.15867018699645996 length of segment : 714 time for calcul the mask position with numpy : 0.001332998275756836 nb_pixel_total : 30873 time to create 1 rle with old method : 0.03782320022583008 length of segment : 288 time for calcul the mask position with numpy : 0.00915837287902832 nb_pixel_total : 304723 time to create 1 rle with new method : 0.01581573486328125 length of segment : 877 time for calcul the mask position with numpy : 0.003290414810180664 nb_pixel_total : 266760 time to create 1 rle with new method : 0.008372783660888672 length of segment : 727 time for calcul the mask position with numpy : 0.0005655288696289062 nb_pixel_total : 11364 time to create 1 rle with old method : 0.013390302658081055 length of segment : 179 time for calcul the mask position with numpy : 0.001371145248413086 nb_pixel_total : 34295 time to create 1 rle with old method : 0.040991783142089844 length of segment : 318 time for calcul the mask position with numpy : 0.0006964206695556641 nb_pixel_total : 18274 time to create 1 rle with old method : 0.02125835418701172 length of segment : 200 time for calcul the mask position with numpy : 0.0004794597625732422 nb_pixel_total : 31161 time to create 1 rle with old method : 0.03565263748168945 length of segment : 270 time for calcul the mask position with numpy : 0.0008029937744140625 nb_pixel_total : 13957 time to create 1 rle with old method : 0.016510963439941406 length of segment : 200 time for calcul the mask position with numpy : 0.00138092041015625 nb_pixel_total : 37752 time to create 1 rle with old method : 0.04606938362121582 length of segment : 311 time for calcul the mask position with numpy : 0.0009806156158447266 nb_pixel_total : 13939 time to create 1 rle with old method : 0.01651740074157715 length of segment : 185 time for calcul the mask position with numpy : 0.00041961669921875 nb_pixel_total : 14436 time to create 1 rle with old method : 0.0169522762298584 length of segment : 214 time for calcul the mask position with numpy : 0.0006906986236572266 nb_pixel_total : 25223 time to create 1 rle with old method : 0.029949188232421875 length of segment : 179 time for calcul the mask position with numpy : 0.0009000301361083984 nb_pixel_total : 19417 time to create 1 rle with old method : 0.024821043014526367 length of segment : 161 time for calcul the mask position with numpy : 0.0006539821624755859 nb_pixel_total : 19497 time to create 1 rle with old method : 0.02289104461669922 length of segment : 165 time for calcul the mask position with numpy : 0.0037119388580322266 nb_pixel_total : 206845 time to create 1 rle with new method : 0.010517120361328125 length of segment : 685 time for calcul the mask position with numpy : 0.5233349800109863 nb_pixel_total : 1878841 time to create 1 rle with new method : 0.31101322174072266 length of segment : 1498 time for calcul the mask position with numpy : 0.45017528533935547 nb_pixel_total : 2802613 time to create 1 rle with new method : 0.3637685775756836 length of segment : 3021 time for calcul the mask position with numpy : 0.3679499626159668 nb_pixel_total : 5618619 time to create 1 rle with new method : 0.8414154052734375 length of segment : 2139 time spent for convertir_results : 16.26969885826111 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 64 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 66.15821743011475 time spend to save output : 0.387439489364624 total time spend for step 1 : 66.54565691947937 step2:mask_detect Thu Aug 28 14:02:36 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 : 5090 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 14:02:40.432874: 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 14:02:40.464744: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 14:02:40.467021: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd36c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 14:02:40.467101: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 14:02:40.472730: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 14:02:40.649138: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xd8127e0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 14:02:40.649264: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 14:02:40.651309: 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 14:02:40.652481: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:02:40.658745: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:02:40.675831: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 14:02:40.678742: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 14:02:40.686104: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 14:02:40.689669: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 14:02:40.709665: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 14:02:40.711493: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 14:02:40.712101: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:02:40.713021: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 14:02:40.713049: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 14:02:40.713061: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 14:02:40.715116: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4638 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 14:02:40.927555: 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 14:02:40.927703: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:02:40.927732: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:02:40.927752: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 14:02:40.927769: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 14:02:40.927785: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 14:02:40.927801: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 14:02:40.927833: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 14:02:40.928900: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 14:02:40.930612: 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 14:02:40.930744: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 14:02:40.930777: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:02:40.930804: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 14:02:40.930830: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 14:02:40.930856: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 14:02:40.930883: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 14:02:40.930911: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 14:02:40.932120: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 14:02:40.932176: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 14:02:40.932187: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 14:02:40.932196: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 14:02:40.933264: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4638 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 14:02:53.077768: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 14:02:53.438208: 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 : 5 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 : 77 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 : 46 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 : 60 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 : 18 Detection mask done ! Trying to reset tf kernel 3712659 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 22 tf kernel not reseted sub process len(results) : 5 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 5 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 : 5311 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 : 0.015280961990356445 nb_pixel_total : 197093 time to create 1 rle with new method : 0.02452850341796875 length of segment : 629 time for calcul the mask position with numpy : 0.0013937950134277344 nb_pixel_total : 48883 time to create 1 rle with old method : 0.05514669418334961 length of segment : 276 time for calcul the mask position with numpy : 0.005412578582763672 nb_pixel_total : 206443 time to create 1 rle with new method : 0.014622926712036133 length of segment : 675 time for calcul the mask position with numpy : 0.010158300399780273 nb_pixel_total : 459934 time to create 1 rle with new method : 0.04419565200805664 length of segment : 978 time for calcul the mask position with numpy : 0.0021283626556396484 nb_pixel_total : 99899 time to create 1 rle with old method : 0.11297845840454102 length of segment : 334 time for calcul the mask position with numpy : 0.002518892288208008 nb_pixel_total : 93903 time to create 1 rle with old method : 0.10512185096740723 length of segment : 447 time for calcul the mask position with numpy : 0.0019664764404296875 nb_pixel_total : 91174 time to create 1 rle with old method : 0.10377645492553711 length of segment : 302 time for calcul the mask position with numpy : 0.004695415496826172 nb_pixel_total : 194907 time to create 1 rle with new method : 0.01310420036315918 length of segment : 378 time for calcul the mask position with numpy : 0.0010154247283935547 nb_pixel_total : 36325 time to create 1 rle with old method : 0.04226994514465332 length of segment : 219 time for calcul the mask position with numpy : 0.0010912418365478516 nb_pixel_total : 46501 time to create 1 rle with old method : 0.053263187408447266 length of segment : 232 time for calcul the mask position with numpy : 0.00761103630065918 nb_pixel_total : 187622 time to create 1 rle with new method : 0.0184478759765625 length of segment : 724 time for calcul the mask position with numpy : 0.0007624626159667969 nb_pixel_total : 30635 time to create 1 rle with old method : 0.03495645523071289 length of segment : 192 time for calcul the mask position with numpy : 0.0006802082061767578 nb_pixel_total : 27787 time to create 1 rle with old method : 0.03229022026062012 length of segment : 149 time for calcul the mask position with numpy : 0.0017197132110595703 nb_pixel_total : 65205 time to create 1 rle with old method : 0.07358741760253906 length of segment : 335 time for calcul the mask position with numpy : 0.003072500228881836 nb_pixel_total : 145601 time to create 1 rle with old method : 0.1817455291748047 length of segment : 425 time for calcul the mask position with numpy : 0.01770949363708496 nb_pixel_total : 693674 time to create 1 rle with new method : 0.1391003131866455 length of segment : 1650 time for calcul the mask position with numpy : 0.0018258094787597656 nb_pixel_total : 66332 time to create 1 rle with old method : 0.0740354061126709 length of segment : 304 time for calcul the mask position with numpy : 0.0010519027709960938 nb_pixel_total : 39615 time to create 1 rle with old method : 0.04422569274902344 length of segment : 207 time for calcul the mask position with numpy : 0.00421452522277832 nb_pixel_total : 122625 time to create 1 rle with old method : 0.13454437255859375 length of segment : 518 time for calcul the mask position with numpy : 0.0008385181427001953 nb_pixel_total : 26209 time to create 1 rle with old method : 0.02937936782836914 length of segment : 314 time for calcul the mask position with numpy : 0.012937068939208984 nb_pixel_total : 541674 time to create 1 rle with new method : 0.08957386016845703 length of segment : 827 time for calcul the mask position with numpy : 0.005627870559692383 nb_pixel_total : 230729 time to create 1 rle with new method : 0.014910697937011719 length of segment : 1007 time for calcul the mask position with numpy : 0.0048007965087890625 nb_pixel_total : 231408 time to create 1 rle with new method : 0.011779069900512695 length of segment : 537 time for calcul the mask position with numpy : 0.0026242733001708984 nb_pixel_total : 110610 time to create 1 rle with old method : 0.1269536018371582 length of segment : 472 time for calcul the mask position with numpy : 0.019287109375 nb_pixel_total : 78037 time to create 1 rle with old method : 0.08927631378173828 length of segment : 318 time for calcul the mask position with numpy : 0.0006906986236572266 nb_pixel_total : 30968 time to create 1 rle with old method : 0.035689353942871094 length of segment : 209 time for calcul the mask position with numpy : 0.00492548942565918 nb_pixel_total : 269660 time to create 1 rle with new method : 0.014338970184326172 length of segment : 724 time for calcul the mask position with numpy : 0.0011191368103027344 nb_pixel_total : 58826 time to create 1 rle with old method : 0.06386590003967285 length of segment : 339 time for calcul the mask position with numpy : 0.030363082885742188 nb_pixel_total : 1148425 time to create 1 rle with new method : 0.6410894393920898 length of segment : 2010 time for calcul the mask position with numpy : 0.0011341571807861328 nb_pixel_total : 41940 time to create 1 rle with old method : 0.051953792572021484 length of segment : 227 time for calcul the mask position with numpy : 0.004111528396606445 nb_pixel_total : 180655 time to create 1 rle with new method : 0.010189533233642578 length of segment : 676 time for calcul the mask position with numpy : 0.008007287979125977 nb_pixel_total : 344517 time to create 1 rle with new method : 0.021109819412231445 length of segment : 1558 time for calcul the mask position with numpy : 0.01114797592163086 nb_pixel_total : 383822 time to create 1 rle with new method : 0.028660058975219727 length of segment : 1144 time for calcul the mask position with numpy : 0.0011982917785644531 nb_pixel_total : 40358 time to create 1 rle with old method : 0.04336738586425781 length of segment : 267 time for calcul the mask position with numpy : 0.0043277740478515625 nb_pixel_total : 181910 time to create 1 rle with new method : 0.012182474136352539 length of segment : 495 time for calcul the mask position with numpy : 0.021837711334228516 nb_pixel_total : 876335 time to create 1 rle with new method : 0.1264629364013672 length of segment : 1851 time for calcul the mask position with numpy : 0.0008921623229980469 nb_pixel_total : 31090 time to create 1 rle with old method : 0.03604388236999512 length of segment : 229 time for calcul the mask position with numpy : 0.004610300064086914 nb_pixel_total : 185835 time to create 1 rle with new method : 0.014950275421142578 length of segment : 579 time for calcul the mask position with numpy : 0.0030324459075927734 nb_pixel_total : 141454 time to create 1 rle with old method : 0.15832924842834473 length of segment : 588 time for calcul the mask position with numpy : 0.0010445117950439453 nb_pixel_total : 39284 time to create 1 rle with old method : 0.04755353927612305 length of segment : 197 time for calcul the mask position with numpy : 0.00211334228515625 nb_pixel_total : 83899 time to create 1 rle with old method : 0.09930133819580078 length of segment : 329 time for calcul the mask position with numpy : 0.0032515525817871094 nb_pixel_total : 103016 time to create 1 rle with old method : 0.12119269371032715 length of segment : 393 time for calcul the mask position with numpy : 0.0019843578338623047 nb_pixel_total : 46962 time to create 1 rle with old method : 0.057089805603027344 length of segment : 325 time for calcul the mask position with numpy : 0.013017416000366211 nb_pixel_total : 287148 time to create 1 rle with new method : 0.04416298866271973 length of segment : 1045 time for calcul the mask position with numpy : 0.0013175010681152344 nb_pixel_total : 29691 time to create 1 rle with old method : 0.04267764091491699 length of segment : 235 time for calcul the mask position with numpy : 0.005642890930175781 nb_pixel_total : 222016 time to create 1 rle with new method : 0.0155029296875 length of segment : 641 time for calcul the mask position with numpy : 0.0027878284454345703 nb_pixel_total : 93401 time to create 1 rle with old method : 0.11564016342163086 length of segment : 542 time for calcul the mask position with numpy : 0.027921676635742188 nb_pixel_total : 666131 time to create 1 rle with new method : 0.24016499519348145 length of segment : 2112 time for calcul the mask position with numpy : 0.001537322998046875 nb_pixel_total : 61158 time to create 1 rle with old method : 0.06705594062805176 length of segment : 539 time for calcul the mask position with numpy : 0.0014853477478027344 nb_pixel_total : 65506 time to create 1 rle with old method : 0.10084962844848633 length of segment : 309 time for calcul the mask position with numpy : 0.002103567123413086 nb_pixel_total : 76352 time to create 1 rle with old method : 0.09331703186035156 length of segment : 273 time for calcul the mask position with numpy : 0.000640869140625 nb_pixel_total : 16211 time to create 1 rle with old method : 0.020588159561157227 length of segment : 115 time for calcul the mask position with numpy : 0.0029115676879882812 nb_pixel_total : 139910 time to create 1 rle with old method : 0.18587827682495117 length of segment : 358 time for calcul the mask position with numpy : 0.00047135353088378906 nb_pixel_total : 16345 time to create 1 rle with old method : 0.01880621910095215 length of segment : 169 time for calcul the mask position with numpy : 0.002129077911376953 nb_pixel_total : 68590 time to create 1 rle with old method : 0.07697415351867676 length of segment : 322 time for calcul the mask position with numpy : 0.004015684127807617 nb_pixel_total : 149873 time to create 1 rle with old method : 0.17268085479736328 length of segment : 564 time for calcul the mask position with numpy : 0.006481647491455078 nb_pixel_total : 321150 time to create 1 rle with new method : 0.019922733306884766 length of segment : 1302 time for calcul the mask position with numpy : 0.00044989585876464844 nb_pixel_total : 15543 time to create 1 rle with old method : 0.01799774169921875 length of segment : 249 time for calcul the mask position with numpy : 0.0024127960205078125 nb_pixel_total : 89899 time to create 1 rle with old method : 0.10177087783813477 length of segment : 474 time for calcul the mask position with numpy : 0.004126071929931641 nb_pixel_total : 209412 time to create 1 rle with new method : 0.012570858001708984 length of segment : 944 time for calcul the mask position with numpy : 0.002338886260986328 nb_pixel_total : 103991 time to create 1 rle with old method : 0.11626362800598145 length of segment : 352 time for calcul the mask position with numpy : 0.0007653236389160156 nb_pixel_total : 26416 time to create 1 rle with old method : 0.030495643615722656 length of segment : 200 time for calcul the mask position with numpy : 0.0017812252044677734 nb_pixel_total : 57677 time to create 1 rle with old method : 0.06823897361755371 length of segment : 318 time for calcul the mask position with numpy : 0.0013270378112792969 nb_pixel_total : 58404 time to create 1 rle with old method : 0.06586909294128418 length of segment : 307 time for calcul the mask position with numpy : 0.0013365745544433594 nb_pixel_total : 27817 time to create 1 rle with old method : 0.03141522407531738 length of segment : 392 time for calcul the mask position with numpy : 0.0015854835510253906 nb_pixel_total : 84925 time to create 1 rle with old method : 0.09754419326782227 length of segment : 352 time for calcul the mask position with numpy : 0.003724336624145508 nb_pixel_total : 187941 time to create 1 rle with new method : 0.008103132247924805 length of segment : 437 time for calcul the mask position with numpy : 0.0058939456939697266 nb_pixel_total : 196727 time to create 1 rle with new method : 0.019830703735351562 length of segment : 619 time for calcul the mask position with numpy : 0.003952503204345703 nb_pixel_total : 166646 time to create 1 rle with new method : 0.011993408203125 length of segment : 419 time for calcul the mask position with numpy : 0.007982969284057617 nb_pixel_total : 283214 time to create 1 rle with new method : 0.025844335556030273 length of segment : 1199 time for calcul the mask position with numpy : 0.0013957023620605469 nb_pixel_total : 54501 time to create 1 rle with old method : 0.06213521957397461 length of segment : 311 time for calcul the mask position with numpy : 0.0021147727966308594 nb_pixel_total : 86734 time to create 1 rle with old method : 0.09867739677429199 length of segment : 379 time for calcul the mask position with numpy : 0.0032770633697509766 nb_pixel_total : 138156 time to create 1 rle with old method : 0.15436387062072754 length of segment : 593 time for calcul the mask position with numpy : 0.0023598670959472656 nb_pixel_total : 92434 time to create 1 rle with old method : 0.10357403755187988 length of segment : 583 time for calcul the mask position with numpy : 0.00115203857421875 nb_pixel_total : 50971 time to create 1 rle with old method : 0.05852007865905762 length of segment : 266 time for calcul the mask position with numpy : 0.0023224353790283203 nb_pixel_total : 93490 time to create 1 rle with old method : 0.12050938606262207 length of segment : 691 time for calcul the mask position with numpy : 0.003445863723754883 nb_pixel_total : 157083 time to create 1 rle with new method : 0.010622501373291016 length of segment : 406 time for calcul the mask position with numpy : 0.009578227996826172 nb_pixel_total : 468000 time to create 1 rle with new method : 0.04323768615722656 length of segment : 683 time for calcul the mask position with numpy : 0.024018049240112305 nb_pixel_total : 1041941 time to create 1 rle with new method : 0.1772785186767578 length of segment : 1308 time for calcul the mask position with numpy : 0.0016930103302001953 nb_pixel_total : 80949 time to create 1 rle with old method : 0.10017204284667969 length of segment : 278 time for calcul the mask position with numpy : 0.0008034706115722656 nb_pixel_total : 30930 time to create 1 rle with old method : 0.03468012809753418 length of segment : 372 time for calcul the mask position with numpy : 0.0022077560424804688 nb_pixel_total : 107891 time to create 1 rle with old method : 0.11988043785095215 length of segment : 338 time for calcul the mask position with numpy : 0.003876209259033203 nb_pixel_total : 226490 time to create 1 rle with new method : 0.009993553161621094 length of segment : 597 time for calcul the mask position with numpy : 0.0009028911590576172 nb_pixel_total : 41619 time to create 1 rle with old method : 0.047879695892333984 length of segment : 221 time for calcul the mask position with numpy : 0.0009467601776123047 nb_pixel_total : 43067 time to create 1 rle with old method : 0.049936532974243164 length of segment : 213 time for calcul the mask position with numpy : 0.026166200637817383 nb_pixel_total : 1235444 time to create 1 rle with new method : 0.2952401638031006 length of segment : 1936 time for calcul the mask position with numpy : 0.004395723342895508 nb_pixel_total : 271728 time to create 1 rle with new method : 0.01299428939819336 length of segment : 593 time for calcul the mask position with numpy : 0.0006475448608398438 nb_pixel_total : 32874 time to create 1 rle with old method : 0.0379030704498291 length of segment : 253 time for calcul the mask position with numpy : 0.007218837738037109 nb_pixel_total : 403441 time to create 1 rle with new method : 0.018596887588500977 length of segment : 650 time for calcul the mask position with numpy : 0.0007398128509521484 nb_pixel_total : 31004 time to create 1 rle with old method : 0.03758358955383301 length of segment : 240 time for calcul the mask position with numpy : 0.002189159393310547 nb_pixel_total : 111014 time to create 1 rle with old method : 0.13138580322265625 length of segment : 420 time for calcul the mask position with numpy : 0.010431766510009766 nb_pixel_total : 545294 time to create 1 rle with new method : 0.0416722297668457 length of segment : 1254 time for calcul the mask position with numpy : 0.0013580322265625 nb_pixel_total : 55573 time to create 1 rle with old method : 0.06440353393554688 length of segment : 270 time for calcul the mask position with numpy : 0.008800029754638672 nb_pixel_total : 529941 time to create 1 rle with new method : 0.02109837532043457 length of segment : 1026 time for calcul the mask position with numpy : 0.007335186004638672 nb_pixel_total : 441952 time to create 1 rle with new method : 0.01579594612121582 length of segment : 606 time for calcul the mask position with numpy : 0.0022246837615966797 nb_pixel_total : 100983 time to create 1 rle with old method : 0.12045717239379883 length of segment : 619 time for calcul the mask position with numpy : 0.0038366317749023438 nb_pixel_total : 136236 time to create 1 rle with old method : 0.19647836685180664 length of segment : 731 time for calcul the mask position with numpy : 0.0018973350524902344 nb_pixel_total : 96291 time to create 1 rle with old method : 0.10951662063598633 length of segment : 385 time for calcul the mask position with numpy : 0.0003924369812011719 nb_pixel_total : 11312 time to create 1 rle with old method : 0.01309823989868164 length of segment : 109 time for calcul the mask position with numpy : 0.001688241958618164 nb_pixel_total : 95915 time to create 1 rle with old method : 0.10888218879699707 length of segment : 372 time for calcul the mask position with numpy : 0.005985736846923828 nb_pixel_total : 314953 time to create 1 rle with new method : 0.01664900779724121 length of segment : 907 time for calcul the mask position with numpy : 0.00044536590576171875 nb_pixel_total : 14612 time to create 1 rle with old method : 0.016707420349121094 length of segment : 145 time for calcul the mask position with numpy : 0.01063227653503418 nb_pixel_total : 546876 time to create 1 rle with new method : 0.028933048248291016 length of segment : 951 time for calcul the mask position with numpy : 0.0005521774291992188 nb_pixel_total : 16356 time to create 1 rle with old method : 0.019015073776245117 length of segment : 166 time for calcul the mask position with numpy : 0.010318756103515625 nb_pixel_total : 528593 time to create 1 rle with new method : 0.027038097381591797 length of segment : 1454 time for calcul the mask position with numpy : 0.002840757369995117 nb_pixel_total : 139636 time to create 1 rle with old method : 0.16479229927062988 length of segment : 336 time for calcul the mask position with numpy : 0.002925872802734375 nb_pixel_total : 124896 time to create 1 rle with old method : 0.1426703929901123 length of segment : 396 time for calcul the mask position with numpy : 0.0005738735198974609 nb_pixel_total : 19443 time to create 1 rle with old method : 0.022598743438720703 length of segment : 248 time for calcul the mask position with numpy : 0.003311634063720703 nb_pixel_total : 172141 time to create 1 rle with new method : 0.009119033813476562 length of segment : 502 time for calcul the mask position with numpy : 0.02993178367614746 nb_pixel_total : 1564832 time to create 1 rle with new method : 0.24391627311706543 length of segment : 2078 time for calcul the mask position with numpy : 0.0011632442474365234 nb_pixel_total : 24475 time to create 1 rle with old method : 0.03951382637023926 length of segment : 140 time for calcul the mask position with numpy : 0.0007150173187255859 nb_pixel_total : 36407 time to create 1 rle with old method : 0.04068136215209961 length of segment : 184 time for calcul the mask position with numpy : 0.0011677742004394531 nb_pixel_total : 52171 time to create 1 rle with old method : 0.05919289588928223 length of segment : 282 time for calcul the mask position with numpy : 0.0005359649658203125 nb_pixel_total : 29515 time to create 1 rle with old method : 0.03340888023376465 length of segment : 269 time for calcul the mask position with numpy : 0.0031113624572753906 nb_pixel_total : 133684 time to create 1 rle with old method : 0.1689131259918213 length of segment : 817 time for calcul the mask position with numpy : 0.003325939178466797 nb_pixel_total : 204079 time to create 1 rle with new method : 0.00894308090209961 length of segment : 487 time for calcul the mask position with numpy : 0.0031728744506835938 nb_pixel_total : 203961 time to create 1 rle with new method : 0.008050680160522461 length of segment : 522 time for calcul the mask position with numpy : 0.0014660358428955078 nb_pixel_total : 73776 time to create 1 rle with old method : 0.08206582069396973 length of segment : 371 time for calcul the mask position with numpy : 0.0016832351684570312 nb_pixel_total : 96107 time to create 1 rle with old method : 0.10785174369812012 length of segment : 277 time for calcul the mask position with numpy : 0.001325368881225586 nb_pixel_total : 68508 time to create 1 rle with old method : 0.07607793807983398 length of segment : 230 time for calcul the mask position with numpy : 0.0018804073333740234 nb_pixel_total : 115030 time to create 1 rle with old method : 0.1285243034362793 length of segment : 428 time for calcul the mask position with numpy : 0.0072803497314453125 nb_pixel_total : 427544 time to create 1 rle with new method : 0.018418312072753906 length of segment : 584 time for calcul the mask position with numpy : 0.001842498779296875 nb_pixel_total : 95397 time to create 1 rle with old method : 0.10747289657592773 length of segment : 362 time for calcul the mask position with numpy : 0.0071527957916259766 nb_pixel_total : 265933 time to create 1 rle with new method : 0.02197098731994629 length of segment : 929 time for calcul the mask position with numpy : 0.0017638206481933594 nb_pixel_total : 64125 time to create 1 rle with old method : 0.0727388858795166 length of segment : 367 time for calcul the mask position with numpy : 0.003294706344604492 nb_pixel_total : 159735 time to create 1 rle with new method : 0.010312557220458984 length of segment : 519 time for calcul the mask position with numpy : 0.0014960765838623047 nb_pixel_total : 61154 time to create 1 rle with old method : 0.07002758979797363 length of segment : 372 time for calcul the mask position with numpy : 0.0017151832580566406 nb_pixel_total : 86648 time to create 1 rle with old method : 0.10898828506469727 length of segment : 301 time for calcul the mask position with numpy : 0.0025060176849365234 nb_pixel_total : 125506 time to create 1 rle with old method : 0.14806604385375977 length of segment : 431 time for calcul the mask position with numpy : 0.0018885135650634766 nb_pixel_total : 82333 time to create 1 rle with old method : 0.09404945373535156 length of segment : 572 time for calcul the mask position with numpy : 0.0013124942779541016 nb_pixel_total : 58710 time to create 1 rle with old method : 0.06762146949768066 length of segment : 351 time for calcul the mask position with numpy : 0.0015997886657714844 nb_pixel_total : 37584 time to create 1 rle with old method : 0.045203208923339844 length of segment : 354 time for calcul the mask position with numpy : 0.002905607223510742 nb_pixel_total : 117093 time to create 1 rle with old method : 0.1341555118560791 length of segment : 435 time for calcul the mask position with numpy : 0.024271249771118164 nb_pixel_total : 944736 time to create 1 rle with new method : 0.13185524940490723 length of segment : 1495 time for calcul the mask position with numpy : 0.004598140716552734 nb_pixel_total : 202803 time to create 1 rle with new method : 0.015725135803222656 length of segment : 614 time for calcul the mask position with numpy : 0.0009455680847167969 nb_pixel_total : 38183 time to create 1 rle with old method : 0.044062137603759766 length of segment : 257 time for calcul the mask position with numpy : 0.004051685333251953 nb_pixel_total : 211969 time to create 1 rle with new method : 0.012137174606323242 length of segment : 546 time for calcul the mask position with numpy : 0.004503965377807617 nb_pixel_total : 197129 time to create 1 rle with new method : 0.013964414596557617 length of segment : 812 time for calcul the mask position with numpy : 0.0016641616821289062 nb_pixel_total : 80797 time to create 1 rle with old method : 0.09262681007385254 length of segment : 412 time for calcul the mask position with numpy : 0.01493072509765625 nb_pixel_total : 568986 time to create 1 rle with new method : 0.5658555030822754 length of segment : 776 time for calcul the mask position with numpy : 0.028680086135864258 nb_pixel_total : 841871 time to create 1 rle with new method : 0.20682859420776367 length of segment : 1650 time for calcul the mask position with numpy : 0.0007202625274658203 nb_pixel_total : 20161 time to create 1 rle with old method : 0.023221492767333984 length of segment : 188 time for calcul the mask position with numpy : 0.004260540008544922 nb_pixel_total : 212519 time to create 1 rle with new method : 0.012537240982055664 length of segment : 537 time for calcul the mask position with numpy : 0.0014870166778564453 nb_pixel_total : 80096 time to create 1 rle with old method : 0.09051370620727539 length of segment : 315 time for calcul the mask position with numpy : 0.0013403892517089844 nb_pixel_total : 76258 time to create 1 rle with old method : 0.08738327026367188 length of segment : 339 time for calcul the mask position with numpy : 0.0024242401123046875 nb_pixel_total : 88831 time to create 1 rle with old method : 0.10331130027770996 length of segment : 288 time for calcul the mask position with numpy : 0.002427816390991211 nb_pixel_total : 83473 time to create 1 rle with old method : 0.09485459327697754 length of segment : 778 time for calcul the mask position with numpy : 0.027199506759643555 nb_pixel_total : 1302716 time to create 1 rle with new method : 0.16464567184448242 length of segment : 1038 time for calcul the mask position with numpy : 0.0009822845458984375 nb_pixel_total : 49859 time to create 1 rle with old method : 0.05663323402404785 length of segment : 294 time for calcul the mask position with numpy : 0.0018608570098876953 nb_pixel_total : 95082 time to create 1 rle with old method : 0.10723185539245605 length of segment : 545 time for calcul the mask position with numpy : 0.0019893646240234375 nb_pixel_total : 72577 time to create 1 rle with old method : 0.07792997360229492 length of segment : 432 time for calcul the mask position with numpy : 0.002488374710083008 nb_pixel_total : 160604 time to create 1 rle with new method : 0.007110118865966797 length of segment : 472 time for calcul the mask position with numpy : 0.0031397342681884766 nb_pixel_total : 210080 time to create 1 rle with new method : 0.008066415786743164 length of segment : 503 time for calcul the mask position with numpy : 0.0015625953674316406 nb_pixel_total : 81181 time to create 1 rle with old method : 0.08928442001342773 length of segment : 375 time for calcul the mask position with numpy : 0.013981342315673828 nb_pixel_total : 714870 time to create 1 rle with new method : 0.06451773643493652 length of segment : 1432 time for calcul the mask position with numpy : 0.0028367042541503906 nb_pixel_total : 206816 time to create 1 rle with new method : 0.007493495941162109 length of segment : 520 time for calcul the mask position with numpy : 0.0011587142944335938 nb_pixel_total : 50094 time to create 1 rle with old method : 0.057646751403808594 length of segment : 262 time for calcul the mask position with numpy : 0.00078582763671875 nb_pixel_total : 29388 time to create 1 rle with old method : 0.03873729705810547 length of segment : 384 time for calcul the mask position with numpy : 0.0019457340240478516 nb_pixel_total : 90100 time to create 1 rle with old method : 0.11573338508605957 length of segment : 346 time for calcul the mask position with numpy : 0.0010395050048828125 nb_pixel_total : 62029 time to create 1 rle with old method : 0.07219696044921875 length of segment : 307 time for calcul the mask position with numpy : 0.0024254322052001953 nb_pixel_total : 140565 time to create 1 rle with old method : 0.1582183837890625 length of segment : 469 time for calcul the mask position with numpy : 0.003673076629638672 nb_pixel_total : 165717 time to create 1 rle with new method : 0.01113271713256836 length of segment : 534 time for calcul the mask position with numpy : 0.0013761520385742188 nb_pixel_total : 53477 time to create 1 rle with old method : 0.05947542190551758 length of segment : 355 time for calcul the mask position with numpy : 0.003240346908569336 nb_pixel_total : 151591 time to create 1 rle with new method : 0.009875774383544922 length of segment : 706 time for calcul the mask position with numpy : 0.0026693344116210938 nb_pixel_total : 134736 time to create 1 rle with old method : 0.1478888988494873 length of segment : 727 time for calcul the mask position with numpy : 0.001314401626586914 nb_pixel_total : 60929 time to create 1 rle with old method : 0.06672263145446777 length of segment : 332 time for calcul the mask position with numpy : 0.002042055130004883 nb_pixel_total : 121805 time to create 1 rle with old method : 0.1338789463043213 length of segment : 425 time for calcul the mask position with numpy : 0.013458728790283203 nb_pixel_total : 628417 time to create 1 rle with new method : 0.03276991844177246 length of segment : 851 time for calcul the mask position with numpy : 0.004353523254394531 nb_pixel_total : 263963 time to create 1 rle with new method : 0.012610435485839844 length of segment : 951 time for calcul the mask position with numpy : 0.0018532276153564453 nb_pixel_total : 84500 time to create 1 rle with old method : 0.09668684005737305 length of segment : 300 time for calcul the mask position with numpy : 0.0034415721893310547 nb_pixel_total : 172665 time to create 1 rle with new method : 0.009546518325805664 length of segment : 436 time for calcul the mask position with numpy : 0.0005509853363037109 nb_pixel_total : 21014 time to create 1 rle with old method : 0.023755788803100586 length of segment : 149 time for calcul the mask position with numpy : 0.00226593017578125 nb_pixel_total : 128455 time to create 1 rle with old method : 0.143479585647583 length of segment : 389 time for calcul the mask position with numpy : 0.0020253658294677734 nb_pixel_total : 86251 time to create 1 rle with old method : 0.09814620018005371 length of segment : 299 time for calcul the mask position with numpy : 0.002502918243408203 nb_pixel_total : 144047 time to create 1 rle with old method : 0.16209053993225098 length of segment : 475 time for calcul the mask position with numpy : 0.003398418426513672 nb_pixel_total : 193169 time to create 1 rle with new method : 0.009276628494262695 length of segment : 710 time for calcul the mask position with numpy : 0.003945589065551758 nb_pixel_total : 108541 time to create 1 rle with old method : 0.12267231941223145 length of segment : 783 time for calcul the mask position with numpy : 0.026230335235595703 nb_pixel_total : 690245 time to create 1 rle with new method : 0.9948859214782715 length of segment : 1541 time for calcul the mask position with numpy : 0.0016236305236816406 nb_pixel_total : 76068 time to create 1 rle with old method : 0.08594226837158203 length of segment : 308 time for calcul the mask position with numpy : 0.0019428730010986328 nb_pixel_total : 92341 time to create 1 rle with old method : 0.10545659065246582 length of segment : 451 time for calcul the mask position with numpy : 0.00637054443359375 nb_pixel_total : 148032 time to create 1 rle with old method : 0.16994786262512207 length of segment : 946 time for calcul the mask position with numpy : 0.0025284290313720703 nb_pixel_total : 108901 time to create 1 rle with old method : 0.11873006820678711 length of segment : 347 time for calcul the mask position with numpy : 0.0030646324157714844 nb_pixel_total : 142932 time to create 1 rle with old method : 0.15745258331298828 length of segment : 575 time for calcul the mask position with numpy : 0.003373861312866211 nb_pixel_total : 203556 time to create 1 rle with new method : 0.009744405746459961 length of segment : 613 time for calcul the mask position with numpy : 0.0009644031524658203 nb_pixel_total : 47742 time to create 1 rle with old method : 0.05294537544250488 length of segment : 193 time for calcul the mask position with numpy : 0.00333404541015625 nb_pixel_total : 195366 time to create 1 rle with new method : 0.009778738021850586 length of segment : 733 time for calcul the mask position with numpy : 0.008891820907592773 nb_pixel_total : 250090 time to create 1 rle with new method : 0.027253150939941406 length of segment : 1683 time for calcul the mask position with numpy : 0.003988504409790039 nb_pixel_total : 161396 time to create 1 rle with new method : 0.012041091918945312 length of segment : 518 time for calcul the mask position with numpy : 0.007197380065917969 nb_pixel_total : 374752 time to create 1 rle with new method : 0.015009641647338867 length of segment : 568 time for calcul the mask position with numpy : 0.0011432170867919922 nb_pixel_total : 50378 time to create 1 rle with old method : 0.05524325370788574 length of segment : 262 time for calcul the mask position with numpy : 0.0029692649841308594 nb_pixel_total : 173039 time to create 1 rle with new method : 0.007807016372680664 length of segment : 479 time for calcul the mask position with numpy : 0.013356924057006836 nb_pixel_total : 309881 time to create 1 rle with new method : 0.054271697998046875 length of segment : 1383 time for calcul the mask position with numpy : 0.0017514228820800781 nb_pixel_total : 66734 time to create 1 rle with old method : 0.08877682685852051 length of segment : 395 time for calcul the mask position with numpy : 0.0018846988677978516 nb_pixel_total : 102322 time to create 1 rle with old method : 0.11536765098571777 length of segment : 389 time for calcul the mask position with numpy : 0.0057866573333740234 nb_pixel_total : 152406 time to create 1 rle with new method : 0.006407976150512695 length of segment : 489 time for calcul the mask position with numpy : 0.006773710250854492 nb_pixel_total : 355433 time to create 1 rle with new method : 0.019439220428466797 length of segment : 627 time for calcul the mask position with numpy : 0.004099130630493164 nb_pixel_total : 254554 time to create 1 rle with new method : 0.010290861129760742 length of segment : 591 time for calcul the mask position with numpy : 0.0036802291870117188 nb_pixel_total : 148120 time to create 1 rle with old method : 0.16536760330200195 length of segment : 836 time for calcul the mask position with numpy : 0.003172636032104492 nb_pixel_total : 90797 time to create 1 rle with old method : 0.10816478729248047 length of segment : 531 time for calcul the mask position with numpy : 0.010073184967041016 nb_pixel_total : 186178 time to create 1 rle with new method : 0.011744260787963867 length of segment : 483 time for calcul the mask position with numpy : 0.002767324447631836 nb_pixel_total : 49024 time to create 1 rle with old method : 0.05611777305603027 length of segment : 246 time for calcul the mask position with numpy : 0.001623392105102539 nb_pixel_total : 88616 time to create 1 rle with old method : 0.10241031646728516 length of segment : 434 time for calcul the mask position with numpy : 0.008533239364624023 nb_pixel_total : 345159 time to create 1 rle with new method : 0.025491714477539062 length of segment : 602 time for calcul the mask position with numpy : 0.0030786991119384766 nb_pixel_total : 126393 time to create 1 rle with old method : 0.1414024829864502 length of segment : 734 time for calcul the mask position with numpy : 0.0007243156433105469 nb_pixel_total : 26249 time to create 1 rle with old method : 0.029632568359375 length of segment : 272 time for calcul the mask position with numpy : 0.018248319625854492 nb_pixel_total : 286091 time to create 1 rle with new method : 0.011167049407958984 length of segment : 475 time for calcul the mask position with numpy : 0.0161283016204834 nb_pixel_total : 841626 time to create 1 rle with new method : 0.040349721908569336 length of segment : 1346 time for calcul the mask position with numpy : 0.0012667179107666016 nb_pixel_total : 27957 time to create 1 rle with old method : 0.03165411949157715 length of segment : 228 time for calcul the mask position with numpy : 0.0009541511535644531 nb_pixel_total : 26193 time to create 1 rle with old method : 0.02959895133972168 length of segment : 270 time for calcul the mask position with numpy : 0.005560398101806641 nb_pixel_total : 201999 time to create 1 rle with new method : 0.012270689010620117 length of segment : 646 time for calcul the mask position with numpy : 0.013037443161010742 nb_pixel_total : 226723 time to create 1 rle with new method : 0.013911724090576172 length of segment : 813 time for calcul the mask position with numpy : 0.0019485950469970703 nb_pixel_total : 74318 time to create 1 rle with old method : 0.08414888381958008 length of segment : 288 time for calcul the mask position with numpy : 0.0009546279907226562 nb_pixel_total : 23505 time to create 1 rle with old method : 0.025948524475097656 length of segment : 213 time for calcul the mask position with numpy : 0.005114316940307617 nb_pixel_total : 67738 time to create 1 rle with old method : 0.07677316665649414 length of segment : 243 time for calcul the mask position with numpy : 0.00776982307434082 nb_pixel_total : 95402 time to create 1 rle with old method : 0.10886955261230469 length of segment : 421 time for calcul the mask position with numpy : 0.0012116432189941406 nb_pixel_total : 17261 time to create 1 rle with old method : 0.019744873046875 length of segment : 137 time for calcul the mask position with numpy : 0.057318687438964844 nb_pixel_total : 111241 time to create 1 rle with old method : 0.12700700759887695 length of segment : 904 time for calcul the mask position with numpy : 0.13320016860961914 nb_pixel_total : 121647 time to create 1 rle with old method : 0.13510441780090332 length of segment : 294 time for calcul the mask position with numpy : 0.003335237503051758 nb_pixel_total : 22875 time to create 1 rle with old method : 0.02999734878540039 length of segment : 150 time for calcul the mask position with numpy : 0.0020449161529541016 nb_pixel_total : 22716 time to create 1 rle with old method : 0.025928020477294922 length of segment : 275 time for calcul the mask position with numpy : 0.0025184154510498047 nb_pixel_total : 14773 time to create 1 rle with old method : 0.017266273498535156 length of segment : 341 time for calcul the mask position with numpy : 0.0706634521484375 nb_pixel_total : 485177 time to create 1 rle with new method : 0.05779242515563965 length of segment : 1035 time for calcul the mask position with numpy : 0.022344589233398438 nb_pixel_total : 38424 time to create 1 rle with old method : 0.04806113243103027 length of segment : 228 time for calcul the mask position with numpy : 0.0031974315643310547 nb_pixel_total : 128151 time to create 1 rle with old method : 0.14738988876342773 length of segment : 523 time for calcul the mask position with numpy : 0.007157802581787109 nb_pixel_total : 62948 time to create 1 rle with old method : 0.0701596736907959 length of segment : 494 time for calcul the mask position with numpy : 0.008779764175415039 nb_pixel_total : 45040 time to create 1 rle with old method : 0.053663015365600586 length of segment : 468 time for calcul the mask position with numpy : 0.08358955383300781 nb_pixel_total : 236056 time to create 1 rle with new method : 0.034317970275878906 length of segment : 622 time for calcul the mask position with numpy : 0.0004897117614746094 nb_pixel_total : 14036 time to create 1 rle with old method : 0.02451157569885254 length of segment : 166 time for calcul the mask position with numpy : 0.011642217636108398 nb_pixel_total : 138446 time to create 1 rle with old method : 0.17451071739196777 length of segment : 565 time for calcul the mask position with numpy : 0.023272275924682617 nb_pixel_total : 140343 time to create 1 rle with old method : 0.16042804718017578 length of segment : 524 time for calcul the mask position with numpy : 0.038132667541503906 nb_pixel_total : 247295 time to create 1 rle with new method : 0.0183258056640625 length of segment : 710 time for calcul the mask position with numpy : 0.0050618648529052734 nb_pixel_total : 28722 time to create 1 rle with old method : 0.03496146202087402 length of segment : 275 time for calcul the mask position with numpy : 0.014879226684570312 nb_pixel_total : 39097 time to create 1 rle with old method : 0.048413991928100586 length of segment : 163 time for calcul the mask position with numpy : 0.026276350021362305 nb_pixel_total : 167169 time to create 1 rle with new method : 0.010818004608154297 length of segment : 940 time for calcul the mask position with numpy : 0.002839803695678711 nb_pixel_total : 44177 time to create 1 rle with old method : 0.052648067474365234 length of segment : 273 time for calcul the mask position with numpy : 0.0009160041809082031 nb_pixel_total : 29370 time to create 1 rle with old method : 0.033722639083862305 length of segment : 258 time for calcul the mask position with numpy : 0.03550148010253906 nb_pixel_total : 178577 time to create 1 rle with new method : 0.009775400161743164 length of segment : 751 time for calcul the mask position with numpy : 0.009554147720336914 nb_pixel_total : 212446 time to create 1 rle with new method : 0.014027595520019531 length of segment : 1090 time for calcul the mask position with numpy : 0.011969804763793945 nb_pixel_total : 122052 time to create 1 rle with old method : 0.1610255241394043 length of segment : 512 time for calcul the mask position with numpy : 0.008175134658813477 nb_pixel_total : 92307 time to create 1 rle with old method : 0.10577940940856934 length of segment : 328 time for calcul the mask position with numpy : 0.003568410873413086 nb_pixel_total : 139383 time to create 1 rle with old method : 0.1567094326019287 length of segment : 455 time for calcul the mask position with numpy : 0.0024504661560058594 nb_pixel_total : 119672 time to create 1 rle with old method : 0.1347665786743164 length of segment : 622 time for calcul the mask position with numpy : 0.01894521713256836 nb_pixel_total : 515317 time to create 1 rle with new method : 0.16437816619873047 length of segment : 1976 time for calcul the mask position with numpy : 0.003095865249633789 nb_pixel_total : 56548 time to create 1 rle with old method : 0.07225322723388672 length of segment : 249 time for calcul the mask position with numpy : 0.09799599647521973 nb_pixel_total : 131372 time to create 1 rle with old method : 0.15057158470153809 length of segment : 429 time for calcul the mask position with numpy : 0.005738019943237305 nb_pixel_total : 20616 time to create 1 rle with old method : 0.025285720825195312 length of segment : 711 time for calcul the mask position with numpy : 0.006082773208618164 nb_pixel_total : 165767 time to create 1 rle with new method : 0.0143280029296875 length of segment : 585 time for calcul the mask position with numpy : 0.008773088455200195 nb_pixel_total : 82675 time to create 1 rle with old method : 0.09718990325927734 length of segment : 386 time for calcul the mask position with numpy : 0.001207113265991211 nb_pixel_total : 31996 time to create 1 rle with old method : 0.03683876991271973 length of segment : 301 time for calcul the mask position with numpy : 0.07039403915405273 nb_pixel_total : 520879 time to create 1 rle with new method : 0.17386770248413086 length of segment : 1708 time for calcul the mask position with numpy : 0.00916743278503418 nb_pixel_total : 62158 time to create 1 rle with old method : 0.07235121726989746 length of segment : 301 time for calcul the mask position with numpy : 0.0019464492797851562 nb_pixel_total : 70946 time to create 1 rle with old method : 0.07954955101013184 length of segment : 263 time for calcul the mask position with numpy : 0.002470254898071289 nb_pixel_total : 64121 time to create 1 rle with old method : 0.07287073135375977 length of segment : 185 time for calcul the mask position with numpy : 0.0014758110046386719 nb_pixel_total : 69681 time to create 1 rle with old method : 0.07781171798706055 length of segment : 215 time for calcul the mask position with numpy : 3.3530313968658447 nb_pixel_total : 7400145 time to create 1 rle with new method : 1.4738433361053467 length of segment : 5664 time for calcul the mask position with numpy : 0.0004596710205078125 nb_pixel_total : 25695 time to create 1 rle with old method : 0.02898693084716797 length of segment : 231 time for calcul the mask position with numpy : 0.04504227638244629 nb_pixel_total : 66850 time to create 1 rle with old method : 0.0791780948638916 length of segment : 248 time for calcul the mask position with numpy : 0.0022983551025390625 nb_pixel_total : 45622 time to create 1 rle with old method : 0.04940056800842285 length of segment : 183 time for calcul the mask position with numpy : 0.0009655952453613281 nb_pixel_total : 62403 time to create 1 rle with old method : 0.06842446327209473 length of segment : 225 time for calcul the mask position with numpy : 0.017447233200073242 nb_pixel_total : 1292495 time to create 1 rle with new method : 0.08948016166687012 length of segment : 1455 time for calcul the mask position with numpy : 0.0005526542663574219 nb_pixel_total : 36103 time to create 1 rle with old method : 0.04221796989440918 length of segment : 162 time for calcul the mask position with numpy : 0.002998828887939453 nb_pixel_total : 189047 time to create 1 rle with new method : 0.008872032165527344 length of segment : 636 time for calcul the mask position with numpy : 0.15442967414855957 nb_pixel_total : 2062899 time to create 1 rle with new method : 0.22554421424865723 length of segment : 2428 time for calcul the mask position with numpy : 0.0008234977722167969 nb_pixel_total : 53242 time to create 1 rle with old method : 0.058828115463256836 length of segment : 298 time for calcul the mask position with numpy : 0.00080108642578125 nb_pixel_total : 46501 time to create 1 rle with old method : 0.05112290382385254 length of segment : 285 time for calcul the mask position with numpy : 0.0008497238159179688 nb_pixel_total : 68014 time to create 1 rle with old method : 0.0739893913269043 length of segment : 307 time for calcul the mask position with numpy : 0.13774681091308594 nb_pixel_total : 37322 time to create 1 rle with old method : 0.04635119438171387 length of segment : 198 time for calcul the mask position with numpy : 0.0004811286926269531 nb_pixel_total : 37399 time to create 1 rle with old method : 0.05643963813781738 length of segment : 192 time for calcul the mask position with numpy : 0.001922607421875 nb_pixel_total : 114347 time to create 1 rle with old method : 0.13063311576843262 length of segment : 309 time for calcul the mask position with numpy : 0.0017964839935302734 nb_pixel_total : 147160 time to create 1 rle with old method : 0.1682436466217041 length of segment : 424 time for calcul the mask position with numpy : 0.0031027793884277344 nb_pixel_total : 143062 time to create 1 rle with old method : 0.180161714553833 length of segment : 411 time for calcul the mask position with numpy : 0.0016939640045166016 nb_pixel_total : 136708 time to create 1 rle with old method : 0.1640300750732422 length of segment : 424 time spent for convertir_results : 63.687360525131226 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 336 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 164.5668261051178 time spend to save output : 0.48632025718688965 total time spend for step 2 : 165.0531463623047 step3:blur_detection Thu Aug 28 14:05:21 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) 1773.6252242616872 (4160, 3120) 1016.3004479730051 (4160, 3120) 1238.7115172956499 (4160, 3120) 3037.5463784145245 (4160, 3120) 800.904448496635 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 : 5 time used for this insertion : 0.01563858985900879 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.012221813201904297 save missing photos in datou_result : time spend for datou_step_exec : 3.18526554107666 time spend to save output : 0.03191733360290527 total time spend for step 3 : 3.2171828746795654 step4:brightness Thu Aug 28 14:05:24 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/1756382488_3706725_1379845456_dd983883e85af4be4de7708f3a5b6f98.jpg treat image : temp/1756382488_3706725_1379845453_cd9f5674049f52f5b35c396b74ad4464.jpg treat image : temp/1756382488_3706725_1379845433_91ed3c3cd3482ef884af20d48729e23d.jpg treat image : temp/1756382488_3706725_1379845432_3f2c9401f8b11a59b523299bac2843bd.jpg treat image : temp/1756382488_3706725_1379845431_8b109f626e18906ddc5bed53762bf432.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 : 5 time used for this insertion : 0.012160301208496094 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.011927127838134766 save missing photos in datou_result : time spend for datou_step_exec : 7.9991960525512695 time spend to save output : 0.028583288192749023 total time spend for step 4 : 8.027779340744019 step5:rle_unique_nms_with_priority Thu Aug 28 14:05:32 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 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 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 336 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 91 nb_hashtags : 12 time to prepare the origin masks : 63.71723222732544 time for calcul the mask position with numpy : 0.45370960235595703 nb_pixel_total : 3480049 time to create 1 rle with new method : 1.1524710655212402 time for calcul the mask position with numpy : 0.05648374557495117 nb_pixel_total : 48223 time to create 1 rle with old method : 0.05510377883911133 time for calcul the mask position with numpy : 0.05670881271362305 nb_pixel_total : 130011 time to create 1 rle with old method : 0.14769649505615234 time for calcul the mask position with numpy : 0.05532264709472656 nb_pixel_total : 20011 time to create 1 rle with old method : 0.0232388973236084 time for calcul the mask position with numpy : 0.05496931076049805 nb_pixel_total : 30940 time to create 1 rle with old method : 0.04610919952392578 time for calcul the mask position with numpy : 0.15767645835876465 nb_pixel_total : 1023765 time to create 1 rle with new method : 0.9977591037750244 time for calcul the mask position with numpy : 0.05405306816101074 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0015871524810791016 time for calcul the mask position with numpy : 0.054739952087402344 nb_pixel_total : 75851 time to create 1 rle with old method : 0.08507442474365234 time for calcul the mask position with numpy : 0.055196285247802734 nb_pixel_total : 39071 time to create 1 rle with old method : 0.04382944107055664 time for calcul the mask position with numpy : 0.054915666580200195 nb_pixel_total : 15489 time to create 1 rle with old method : 0.017585039138793945 time for calcul the mask position with numpy : 0.05529594421386719 nb_pixel_total : 26195 time to create 1 rle with old method : 0.029709577560424805 time for calcul the mask position with numpy : 0.054290771484375 nb_pixel_total : 11781 time to create 1 rle with old method : 0.0130462646484375 time for calcul the mask position with numpy : 0.05479264259338379 nb_pixel_total : 67256 time to create 1 rle with old method : 0.07558250427246094 time for calcul the mask position with numpy : 0.05837583541870117 nb_pixel_total : 553686 time to create 1 rle with new method : 0.9810655117034912 time for calcul the mask position with numpy : 0.05317831039428711 nb_pixel_total : 77796 time to create 1 rle with old method : 0.11046338081359863 time for calcul the mask position with numpy : 0.055227041244506836 nb_pixel_total : 30573 time to create 1 rle with old method : 0.03468942642211914 time for calcul the mask position with numpy : 0.055066823959350586 nb_pixel_total : 66123 time to create 1 rle with old method : 0.07375979423522949 time for calcul the mask position with numpy : 0.054785728454589844 nb_pixel_total : 23764 time to create 1 rle with old method : 0.026261568069458008 time for calcul the mask position with numpy : 0.05366206169128418 nb_pixel_total : 117767 time to create 1 rle with old method : 0.13250446319580078 time for calcul the mask position with numpy : 0.05484938621520996 nb_pixel_total : 175 time to create 1 rle with old method : 0.00030350685119628906 time for calcul the mask position with numpy : 0.053263187408447266 nb_pixel_total : 777 time to create 1 rle with old method : 0.0010023117065429688 time for calcul the mask position with numpy : 0.05415058135986328 nb_pixel_total : 39268 time to create 1 rle with old method : 0.04494047164916992 time for calcul the mask position with numpy : 0.05440187454223633 nb_pixel_total : 46345 time to create 1 rle with old method : 0.052237510681152344 time for calcul the mask position with numpy : 0.05630183219909668 nb_pixel_total : 230968 time to create 1 rle with new method : 0.9001741409301758 time for calcul the mask position with numpy : 0.05320596694946289 nb_pixel_total : 5516 time to create 1 rle with old method : 0.006043195724487305 time for calcul the mask position with numpy : 0.05367612838745117 nb_pixel_total : 40219 time to create 1 rle with old method : 0.04423403739929199 time for calcul the mask position with numpy : 0.053977251052856445 nb_pixel_total : 48685 time to create 1 rle with old method : 0.054755210876464844 time for calcul the mask position with numpy : 0.054776668548583984 nb_pixel_total : 297781 time to create 1 rle with new method : 0.9727001190185547 time for calcul the mask position with numpy : 0.053929805755615234 nb_pixel_total : 65150 time to create 1 rle with old method : 0.07208466529846191 time for calcul the mask position with numpy : 0.05340433120727539 nb_pixel_total : 83727 time to create 1 rle with old method : 0.0907588005065918 time for calcul the mask position with numpy : 0.05280137062072754 nb_pixel_total : 36182 time to create 1 rle with old method : 0.03960847854614258 time for calcul the mask position with numpy : 0.05480527877807617 nb_pixel_total : 27690 time to create 1 rle with old method : 0.0311734676361084 time for calcul the mask position with numpy : 0.05520772933959961 nb_pixel_total : 90955 time to create 1 rle with old method : 0.09784841537475586 time for calcul the mask position with numpy : 0.05489492416381836 nb_pixel_total : 227 time to create 1 rle with old method : 0.0004317760467529297 time for calcul the mask position with numpy : 0.05576515197753906 nb_pixel_total : 122572 time to create 1 rle with old method : 0.13165569305419922 time for calcul the mask position with numpy : 0.05634760856628418 nb_pixel_total : 504059 time to create 1 rle with new method : 0.8778886795043945 time for calcul the mask position with numpy : 0.057433128356933594 nb_pixel_total : 58736 time to create 1 rle with old method : 0.06556320190429688 time for calcul the mask position with numpy : 0.055116891860961914 nb_pixel_total : 5470 time to create 1 rle with old method : 0.006365299224853516 time for calcul the mask position with numpy : 0.054730892181396484 nb_pixel_total : 5677 time to create 1 rle with old method : 0.0067043304443359375 time for calcul the mask position with numpy : 0.05612993240356445 nb_pixel_total : 339443 time to create 1 rle with new method : 0.8777430057525635 time for calcul the mask position with numpy : 0.05713844299316406 nb_pixel_total : 194249 time to create 1 rle with new method : 0.8169844150543213 time for calcul the mask position with numpy : 0.05214285850524902 nb_pixel_total : 46577 time to create 1 rle with old method : 0.050444841384887695 time for calcul the mask position with numpy : 0.05299663543701172 nb_pixel_total : 9583 time to create 1 rle with old method : 0.01116633415222168 time for calcul the mask position with numpy : 0.05798816680908203 nb_pixel_total : 230517 time to create 1 rle with new method : 0.8438634872436523 time for calcul the mask position with numpy : 0.05417156219482422 nb_pixel_total : 1237 time to create 1 rle with old method : 0.0016815662384033203 time for calcul the mask position with numpy : 0.05141782760620117 nb_pixel_total : 112880 time to create 1 rle with old method : 0.12625503540039062 time for calcul the mask position with numpy : 0.052869319915771484 nb_pixel_total : 110323 time to create 1 rle with old method : 0.12322783470153809 time for calcul the mask position with numpy : 0.06110978126525879 nb_pixel_total : 2857 time to create 1 rle with old method : 0.0034210681915283203 time for calcul the mask position with numpy : 0.053391456604003906 nb_pixel_total : 2935 time to create 1 rle with old method : 0.003911256790161133 time for calcul the mask position with numpy : 0.054381370544433594 nb_pixel_total : 160167 time to create 1 rle with new method : 0.7616899013519287 time for calcul the mask position with numpy : 0.0579676628112793 nb_pixel_total : 459998 time to create 1 rle with new method : 0.7195932865142822 time for calcul the mask position with numpy : 0.053963661193847656 nb_pixel_total : 196544 time to create 1 rle with new method : 0.6529467105865479 time for calcul the mask position with numpy : 0.05565357208251953 nb_pixel_total : 216184 time to create 1 rle with new method : 0.978503942489624 time for calcul the mask position with numpy : 0.05436253547668457 nb_pixel_total : 17024 time to create 1 rle with old method : 0.019392967224121094 time for calcul the mask position with numpy : 0.05404019355773926 nb_pixel_total : 59808 time to create 1 rle with old method : 0.06438374519348145 time for calcul the mask position with numpy : 0.05394887924194336 nb_pixel_total : 206240 time to create 1 rle with new method : 0.8495981693267822 time for calcul the mask position with numpy : 0.05400443077087402 nb_pixel_total : 46686 time to create 1 rle with old method : 0.05178070068359375 time for calcul the mask position with numpy : 0.055226802825927734 nb_pixel_total : 19 time to create 1 rle with old method : 0.000125885009765625 time for calcul the mask position with numpy : 0.060781002044677734 nb_pixel_total : 180239 time to create 1 rle with new method : 0.7398593425750732 time for calcul the mask position with numpy : 0.05289864540100098 nb_pixel_total : 8 time to create 1 rle with old method : 4.267692565917969e-05 time for calcul the mask position with numpy : 0.05345964431762695 nb_pixel_total : 5734 time to create 1 rle with old method : 0.008284568786621094 time for calcul the mask position with numpy : 0.05400252342224121 nb_pixel_total : 5963 time to create 1 rle with old method : 0.006693601608276367 time for calcul the mask position with numpy : 0.05380892753601074 nb_pixel_total : 214199 time to create 1 rle with new method : 0.8285939693450928 time for calcul the mask position with numpy : 0.059790849685668945 nb_pixel_total : 234684 time to create 1 rle with new method : 3.251434326171875 time for calcul the mask position with numpy : 0.053168296813964844 nb_pixel_total : 441289 time to create 1 rle with new method : 1.0098764896392822 time for calcul the mask position with numpy : 0.054532527923583984 nb_pixel_total : 188082 time to create 1 rle with new method : 1.0500617027282715 time for calcul the mask position with numpy : 0.05264472961425781 nb_pixel_total : 723 time to create 1 rle with old method : 0.0008440017700195312 time for calcul the mask position with numpy : 0.05425119400024414 nb_pixel_total : 308931 time to create 1 rle with new method : 1.0584397315979004 time for calcul the mask position with numpy : 0.052580833435058594 nb_pixel_total : 8067 time to create 1 rle with old method : 0.009116888046264648 time for calcul the mask position with numpy : 0.0521237850189209 nb_pixel_total : 48803 time to create 1 rle with old method : 0.052783966064453125 time for calcul the mask position with numpy : 0.05240058898925781 nb_pixel_total : 15396 time to create 1 rle with old method : 0.016843318939208984 time for calcul the mask position with numpy : 0.05393576622009277 nb_pixel_total : 25368 time to create 1 rle with old method : 0.028181076049804688 time for calcul the mask position with numpy : 0.053743600845336914 nb_pixel_total : 39548 time to create 1 rle with old method : 0.0432736873626709 time for calcul the mask position with numpy : 0.0528416633605957 nb_pixel_total : 181822 time to create 1 rle with new method : 1.058612585067749 time for calcul the mask position with numpy : 0.052762508392333984 nb_pixel_total : 83408 time to create 1 rle with old method : 0.08887195587158203 time for calcul the mask position with numpy : 0.0522303581237793 nb_pixel_total : 15403 time to create 1 rle with old method : 0.01720881462097168 time for calcul the mask position with numpy : 0.05222201347351074 nb_pixel_total : 385 time to create 1 rle with old method : 0.0004849433898925781 time for calcul the mask position with numpy : 0.055441856384277344 nb_pixel_total : 186718 time to create 1 rle with new method : 0.8658649921417236 time for calcul the mask position with numpy : 0.055887460708618164 nb_pixel_total : 135148 time to create 1 rle with old method : 0.14850282669067383 time for calcul the mask position with numpy : 0.0530545711517334 nb_pixel_total : 30297 time to create 1 rle with old method : 0.03340768814086914 time for calcul the mask position with numpy : 0.05278301239013672 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003192424774169922 time for calcul the mask position with numpy : 0.05298733711242676 nb_pixel_total : 89920 time to create 1 rle with old method : 0.11931705474853516 time for calcul the mask position with numpy : 0.05795407295227051 nb_pixel_total : 145389 time to create 1 rle with old method : 0.16129636764526367 time for calcul the mask position with numpy : 0.052108049392700195 nb_pixel_total : 93718 time to create 1 rle with old method : 0.10242033004760742 time for calcul the mask position with numpy : 0.05370497703552246 nb_pixel_total : 45987 time to create 1 rle with old method : 0.05135035514831543 time for calcul the mask position with numpy : 0.053046464920043945 nb_pixel_total : 64975 time to create 1 rle with old method : 0.07167577743530273 time for calcul the mask position with numpy : 0.055084943771362305 nb_pixel_total : 57480 time to create 1 rle with old method : 0.06210899353027344 time for calcul the mask position with numpy : 0.05232548713684082 nb_pixel_total : 57935 time to create 1 rle with old method : 0.06290578842163086 time for calcul the mask position with numpy : 0.05188608169555664 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006680488586425781 time for calcul the mask position with numpy : 0.05212283134460449 nb_pixel_total : 93 time to create 1 rle with old method : 0.00018715858459472656 time for calcul the mask position with numpy : 0.05415701866149902 nb_pixel_total : 68433 time to create 1 rle with old method : 0.07483220100402832 time for calcul the mask position with numpy : 0.05410170555114746 nb_pixel_total : 41602 time to create 1 rle with old method : 0.04588031768798828 create new chi : 32.076902866363525 time to delete rle : 0.02348780632019043 batch 1 Loaded 92 chid ids of type : 4855 Number RLEs to save : 68803 TO DO : save crop sub photo not yet done ! save time : 4.886003017425537 nb_obj : 59 nb_hashtags : 12 time to prepare the origin masks : 54.2416205406189 time for calcul the mask position with numpy : 0.48163342475891113 nb_pixel_total : 4861924 time to create 1 rle with new method : 1.4917936325073242 time for calcul the mask position with numpy : 0.055361270904541016 nb_pixel_total : 104037 time to create 1 rle with old method : 0.11599540710449219 time for calcul the mask position with numpy : 0.05959177017211914 nb_pixel_total : 102880 time to create 1 rle with old method : 0.11714601516723633 time for calcul the mask position with numpy : 0.05598187446594238 nb_pixel_total : 51168 time to create 1 rle with old method : 0.05778002738952637 time for calcul the mask position with numpy : 0.05400729179382324 nb_pixel_total : 11051 time to create 1 rle with old method : 0.012633562088012695 time for calcul the mask position with numpy : 0.05419015884399414 nb_pixel_total : 41453 time to create 1 rle with old method : 0.045206546783447266 time for calcul the mask position with numpy : 0.054201364517211914 nb_pixel_total : 18 time to create 1 rle with old method : 5.936622619628906e-05 time for calcul the mask position with numpy : 0.06450939178466797 nb_pixel_total : 402246 time to create 1 rle with new method : 1.3511772155761719 time for calcul the mask position with numpy : 0.0594630241394043 nb_pixel_total : 466276 time to create 1 rle with new method : 1.4138925075531006 time for calcul the mask position with numpy : 0.06531262397766113 nb_pixel_total : 893123 time to create 1 rle with new method : 1.2612261772155762 time for calcul the mask position with numpy : 0.054833412170410156 nb_pixel_total : 145226 time to create 1 rle with old method : 0.16362643241882324 time for calcul the mask position with numpy : 0.05611753463745117 nb_pixel_total : 32275 time to create 1 rle with old method : 0.0363764762878418 time for calcul the mask position with numpy : 0.056041717529296875 nb_pixel_total : 3122 time to create 1 rle with old method : 0.003979206085205078 time for calcul the mask position with numpy : 0.057544708251953125 nb_pixel_total : 225792 time to create 1 rle with new method : 1.0803236961364746 time for calcul the mask position with numpy : 0.0547487735748291 nb_pixel_total : 126317 time to create 1 rle with old method : 0.1419384479522705 time for calcul the mask position with numpy : 0.054936885833740234 nb_pixel_total : 3857 time to create 1 rle with old method : 0.0046405792236328125 time for calcul the mask position with numpy : 0.05557656288146973 nb_pixel_total : 169397 time to create 1 rle with new method : 1.3873701095581055 time for calcul the mask position with numpy : 0.05938911437988281 nb_pixel_total : 313849 time to create 1 rle with new method : 1.3065531253814697 time for calcul the mask position with numpy : 0.05835366249084473 nb_pixel_total : 30839 time to create 1 rle with old method : 0.03495907783508301 time for calcul the mask position with numpy : 0.05520939826965332 nb_pixel_total : 11234 time to create 1 rle with old method : 0.012637138366699219 time for calcul the mask position with numpy : 0.05526900291442871 nb_pixel_total : 52852 time to create 1 rle with old method : 0.06087923049926758 time for calcul the mask position with numpy : 0.05393171310424805 nb_pixel_total : 134439 time to create 1 rle with old method : 0.15046286582946777 time for calcul the mask position with numpy : 0.055058956146240234 nb_pixel_total : 4200 time to create 1 rle with old method : 0.0048863887786865234 time for calcul the mask position with numpy : 0.05541515350341797 nb_pixel_total : 96153 time to create 1 rle with old method : 0.10805845260620117 time for calcul the mask position with numpy : 0.05519890785217285 nb_pixel_total : 15027 time to create 1 rle with old method : 0.017328739166259766 time for calcul the mask position with numpy : 0.055541038513183594 nb_pixel_total : 139329 time to create 1 rle with old method : 0.1559290885925293 time for calcul the mask position with numpy : 0.05629301071166992 nb_pixel_total : 32794 time to create 1 rle with old method : 0.03996109962463379 time for calcul the mask position with numpy : 0.05486130714416504 nb_pixel_total : 187000 time to create 1 rle with new method : 1.305011510848999 time for calcul the mask position with numpy : 0.05505490303039551 nb_pixel_total : 5368 time to create 1 rle with old method : 0.0065021514892578125 time for calcul the mask position with numpy : 0.05568337440490723 nb_pixel_total : 16330 time to create 1 rle with old method : 0.018535614013671875 time for calcul the mask position with numpy : 0.05758237838745117 nb_pixel_total : 441067 time to create 1 rle with new method : 0.8719329833984375 time for calcul the mask position with numpy : 0.06505203247070312 nb_pixel_total : 1039875 time to create 1 rle with new method : 0.9124679565429688 time for calcul the mask position with numpy : 0.0680994987487793 nb_pixel_total : 2335 time to create 1 rle with old method : 0.003743410110473633 time for calcul the mask position with numpy : 0.06910586357116699 nb_pixel_total : 14532 time to create 1 rle with old method : 0.022195100784301758 time for calcul the mask position with numpy : 0.06267166137695312 nb_pixel_total : 20735 time to create 1 rle with old method : 0.024091005325317383 time for calcul the mask position with numpy : 0.0559239387512207 nb_pixel_total : 51525 time to create 1 rle with old method : 0.05838155746459961 time for calcul the mask position with numpy : 0.055686235427856445 nb_pixel_total : 32822 time to create 1 rle with old method : 0.0427250862121582 time for calcul the mask position with numpy : 0.05878305435180664 nb_pixel_total : 107541 time to create 1 rle with old method : 0.13038849830627441 time for calcul the mask position with numpy : 0.05528831481933594 nb_pixel_total : 30969 time to create 1 rle with old method : 0.0365748405456543 time for calcul the mask position with numpy : 0.06547021865844727 nb_pixel_total : 1551 time to create 1 rle with old method : 0.0028717517852783203 time for calcul the mask position with numpy : 0.0658731460571289 nb_pixel_total : 110721 time to create 1 rle with old method : 0.17429018020629883 time for calcul the mask position with numpy : 0.05684542655944824 nb_pixel_total : 930 time to create 1 rle with old method : 0.0014791488647460938 time for calcul the mask position with numpy : 0.05610466003417969 nb_pixel_total : 95691 time to create 1 rle with old method : 0.10946798324584961 time for calcul the mask position with numpy : 0.05525541305541992 nb_pixel_total : 7909 time to create 1 rle with old method : 0.00944066047668457 time for calcul the mask position with numpy : 0.05718731880187988 nb_pixel_total : 101646 time to create 1 rle with old method : 0.1096036434173584 time for calcul the mask position with numpy : 0.05429387092590332 nb_pixel_total : 47623 time to create 1 rle with old method : 0.052991390228271484 time for calcul the mask position with numpy : 0.05632948875427246 nb_pixel_total : 304605 time to create 1 rle with new method : 1.3802220821380615 time for calcul the mask position with numpy : 0.1441195011138916 nb_pixel_total : 1230575 time to create 1 rle with new method : 2.0982425212860107 time for calcul the mask position with numpy : 0.05561947822570801 nb_pixel_total : 91828 time to create 1 rle with old method : 0.10245943069458008 time for calcul the mask position with numpy : 0.05648231506347656 nb_pixel_total : 19361 time to create 1 rle with old method : 0.020968914031982422 time for calcul the mask position with numpy : 0.05616116523742676 nb_pixel_total : 117048 time to create 1 rle with old method : 0.13043618202209473 time for calcul the mask position with numpy : 0.05601859092712402 nb_pixel_total : 271229 time to create 1 rle with new method : 0.9197840690612793 time for calcul the mask position with numpy : 0.053743600845336914 nb_pixel_total : 380 time to create 1 rle with old method : 0.0008234977722167969 time for calcul the mask position with numpy : 0.05401730537414551 nb_pixel_total : 53760 time to create 1 rle with old method : 0.06128573417663574 time for calcul the mask position with numpy : 0.05377912521362305 nb_pixel_total : 34279 time to create 1 rle with old method : 0.03908586502075195 time for calcul the mask position with numpy : 0.0633552074432373 nb_pixel_total : 2974 time to create 1 rle with old method : 0.0051724910736083984 time for calcul the mask position with numpy : 0.05730700492858887 nb_pixel_total : 20401 time to create 1 rle with old method : 0.023314237594604492 time for calcul the mask position with numpy : 0.05740761756896973 nb_pixel_total : 27748 time to create 1 rle with old method : 0.03149294853210449 time for calcul the mask position with numpy : 0.055299997329711914 nb_pixel_total : 241 time to create 1 rle with old method : 0.0005428791046142578 time for calcul the mask position with numpy : 0.053667545318603516 nb_pixel_total : 17723 time to create 1 rle with old method : 0.021054983139038086 create new chi : 23.91117811203003 time to delete rle : 0.0038225650787353516 batch 1 Loaded 60 chid ids of type : 4855 Number RLEs to save : 44730 TO DO : save crop sub photo not yet done ! save time : 4.060086011886597 nb_obj : 80 nb_hashtags : 9 time to prepare the origin masks : 57.791932106018066 time for calcul the mask position with numpy : 0.2093663215637207 nb_pixel_total : 2798430 time to create 1 rle with new method : 1.3847801685333252 time for calcul the mask position with numpy : 0.05476236343383789 nb_pixel_total : 61890 time to create 1 rle with old method : 0.06855654716491699 time for calcul the mask position with numpy : 0.05514168739318848 nb_pixel_total : 278008 time to create 1 rle with new method : 1.2087414264678955 time for calcul the mask position with numpy : 0.1038205623626709 nb_pixel_total : 877707 time to create 1 rle with new method : 1.080265760421753 time for calcul the mask position with numpy : 0.05728602409362793 nb_pixel_total : 20968 time to create 1 rle with old method : 0.02373194694519043 time for calcul the mask position with numpy : 0.05515289306640625 nb_pixel_total : 14319 time to create 1 rle with old method : 0.015869855880737305 time for calcul the mask position with numpy : 0.05554008483886719 nb_pixel_total : 134559 time to create 1 rle with old method : 0.14821958541870117 time for calcul the mask position with numpy : 0.05517148971557617 nb_pixel_total : 86448 time to create 1 rle with old method : 0.09655237197875977 time for calcul the mask position with numpy : 0.05548906326293945 nb_pixel_total : 63989 time to create 1 rle with old method : 0.07221508026123047 time for calcul the mask position with numpy : 0.05556941032409668 nb_pixel_total : 12456 time to create 1 rle with old method : 0.014490842819213867 time for calcul the mask position with numpy : 0.056333065032958984 nb_pixel_total : 17602 time to create 1 rle with old method : 0.020539045333862305 time for calcul the mask position with numpy : 0.05518317222595215 nb_pixel_total : 86084 time to create 1 rle with old method : 0.0962984561920166 time for calcul the mask position with numpy : 0.05684399604797363 nb_pixel_total : 264358 time to create 1 rle with new method : 1.1115708351135254 time for calcul the mask position with numpy : 0.05725216865539551 nb_pixel_total : 464710 time to create 1 rle with new method : 0.9038012027740479 time for calcul the mask position with numpy : 0.057918548583984375 nb_pixel_total : 80804 time to create 1 rle with old method : 0.09084796905517578 time for calcul the mask position with numpy : 0.05784869194030762 nb_pixel_total : 90511 time to create 1 rle with old method : 0.10035991668701172 time for calcul the mask position with numpy : 0.054013967514038086 nb_pixel_total : 116611 time to create 1 rle with old method : 0.12896966934204102 time for calcul the mask position with numpy : 0.05457901954650879 nb_pixel_total : 47576 time to create 1 rle with old method : 0.052806854248046875 time for calcul the mask position with numpy : 0.05759239196777344 nb_pixel_total : 782530 time to create 1 rle with new method : 1.0906989574432373 time for calcul the mask position with numpy : 0.05569100379943848 nb_pixel_total : 9607 time to create 1 rle with old method : 0.011256933212280273 time for calcul the mask position with numpy : 0.05357217788696289 nb_pixel_total : 83443 time to create 1 rle with old method : 0.09283852577209473 time for calcul the mask position with numpy : 0.05491828918457031 nb_pixel_total : 87848 time to create 1 rle with old method : 0.09815073013305664 time for calcul the mask position with numpy : 0.053704261779785156 nb_pixel_total : 2863 time to create 1 rle with old method : 0.0036160945892333984 time for calcul the mask position with numpy : 0.05458807945251465 nb_pixel_total : 32434 time to create 1 rle with old method : 0.036829233169555664 time for calcul the mask position with numpy : 0.055268049240112305 nb_pixel_total : 74852 time to create 1 rle with old method : 0.08334565162658691 time for calcul the mask position with numpy : 0.05524897575378418 nb_pixel_total : 60875 time to create 1 rle with old method : 0.06764507293701172 time for calcul the mask position with numpy : 0.0548250675201416 nb_pixel_total : 1703 time to create 1 rle with old method : 0.0024869441986083984 time for calcul the mask position with numpy : 0.055039405822753906 nb_pixel_total : 34553 time to create 1 rle with old method : 0.042696475982666016 time for calcul the mask position with numpy : 0.055748701095581055 nb_pixel_total : 159493 time to create 1 rle with new method : 0.9460549354553223 time for calcul the mask position with numpy : 0.05517721176147461 nb_pixel_total : 2390 time to create 1 rle with old method : 0.0029418468475341797 time for calcul the mask position with numpy : 0.05455899238586426 nb_pixel_total : 80007 time to create 1 rle with old method : 0.09190702438354492 time for calcul the mask position with numpy : 0.06405234336853027 nb_pixel_total : 11970 time to create 1 rle with old method : 0.015595197677612305 time for calcul the mask position with numpy : 0.053841590881347656 nb_pixel_total : 2495 time to create 1 rle with old method : 0.0029418468475341797 time for calcul the mask position with numpy : 0.057556867599487305 nb_pixel_total : 898143 time to create 1 rle with new method : 1.1769399642944336 time for calcul the mask position with numpy : 0.05531191825866699 nb_pixel_total : 88436 time to create 1 rle with old method : 0.09502315521240234 time for calcul the mask position with numpy : 0.0525362491607666 nb_pixel_total : 21181 time to create 1 rle with old method : 0.023577213287353516 time for calcul the mask position with numpy : 0.054322004318237305 nb_pixel_total : 116374 time to create 1 rle with old method : 0.1288747787475586 time for calcul the mask position with numpy : 0.055580854415893555 nb_pixel_total : 510991 time to create 1 rle with new method : 1.0073373317718506 time for calcul the mask position with numpy : 0.05527019500732422 nb_pixel_total : 64117 time to create 1 rle with old method : 0.07268714904785156 time for calcul the mask position with numpy : 0.055167436599731445 nb_pixel_total : 9290 time to create 1 rle with old method : 0.010764360427856445 time for calcul the mask position with numpy : 0.05523991584777832 nb_pixel_total : 98265 time to create 1 rle with old method : 0.11047172546386719 time for calcul the mask position with numpy : 0.0527653694152832 nb_pixel_total : 16248 time to create 1 rle with old method : 0.01772332191467285 time for calcul the mask position with numpy : 0.05446362495422363 nb_pixel_total : 234083 time to create 1 rle with new method : 1.1078555583953857 time for calcul the mask position with numpy : 0.05337810516357422 nb_pixel_total : 23159 time to create 1 rle with old method : 0.025902509689331055 time for calcul the mask position with numpy : 0.053174734115600586 nb_pixel_total : 196043 time to create 1 rle with new method : 0.909031867980957 time for calcul the mask position with numpy : 0.053612709045410156 nb_pixel_total : 212078 time to create 1 rle with new method : 1.0479695796966553 time for calcul the mask position with numpy : 0.05511879920959473 nb_pixel_total : 72407 time to create 1 rle with old method : 0.08072829246520996 time for calcul the mask position with numpy : 0.05513596534729004 nb_pixel_total : 71498 time to create 1 rle with old method : 0.08081603050231934 time for calcul the mask position with numpy : 0.05465102195739746 nb_pixel_total : 3344 time to create 1 rle with old method : 0.004065275192260742 time for calcul the mask position with numpy : 0.052800893783569336 nb_pixel_total : 93750 time to create 1 rle with old method : 0.1019442081451416 time for calcul the mask position with numpy : 0.05508279800415039 nb_pixel_total : 37415 time to create 1 rle with old method : 0.0423274040222168 time for calcul the mask position with numpy : 0.05421328544616699 nb_pixel_total : 80946 time to create 1 rle with old method : 0.09123039245605469 time for calcul the mask position with numpy : 0.05456352233886719 nb_pixel_total : 5913 time to create 1 rle with old method : 0.007066249847412109 time for calcul the mask position with numpy : 0.05435800552368164 nb_pixel_total : 21938 time to create 1 rle with old method : 0.025243043899536133 time for calcul the mask position with numpy : 0.0543370246887207 nb_pixel_total : 128081 time to create 1 rle with old method : 0.14065313339233398 time for calcul the mask position with numpy : 0.05499672889709473 nb_pixel_total : 191164 time to create 1 rle with new method : 1.0820531845092773 time for calcul the mask position with numpy : 0.05541205406188965 nb_pixel_total : 149503 time to create 1 rle with old method : 0.16368913650512695 time for calcul the mask position with numpy : 0.05502676963806152 nb_pixel_total : 58675 time to create 1 rle with old method : 0.06492924690246582 time for calcul the mask position with numpy : 0.05630183219909668 nb_pixel_total : 53315 time to create 1 rle with old method : 0.06137847900390625 time for calcul the mask position with numpy : 0.055977582931518555 nb_pixel_total : 94863 time to create 1 rle with old method : 0.10305643081665039 time for calcul the mask position with numpy : 0.05436110496520996 nb_pixel_total : 124717 time to create 1 rle with old method : 0.1343369483947754 time for calcul the mask position with numpy : 0.05425262451171875 nb_pixel_total : 1907 time to create 1 rle with old method : 0.0026361942291259766 time for calcul the mask position with numpy : 0.05464601516723633 nb_pixel_total : 11030 time to create 1 rle with old method : 0.012552022933959961 time for calcul the mask position with numpy : 0.05467653274536133 nb_pixel_total : 202552 time to create 1 rle with new method : 1.150132417678833 time for calcul the mask position with numpy : 0.05686688423156738 nb_pixel_total : 28386 time to create 1 rle with old method : 0.03177928924560547 time for calcul the mask position with numpy : 0.055393218994140625 nb_pixel_total : 462 time to create 1 rle with old method : 0.0007910728454589844 time for calcul the mask position with numpy : 0.0552828311920166 nb_pixel_total : 81094 time to create 1 rle with old method : 0.08868026733398438 time for calcul the mask position with numpy : 0.06270408630371094 nb_pixel_total : 1079743 time to create 1 rle with new method : 0.9324231147766113 time for calcul the mask position with numpy : 0.055254220962524414 nb_pixel_total : 49795 time to create 1 rle with old method : 0.05590248107910156 time for calcul the mask position with numpy : 0.055002689361572266 nb_pixel_total : 32622 time to create 1 rle with old method : 0.03650522232055664 time for calcul the mask position with numpy : 0.05437612533569336 nb_pixel_total : 125245 time to create 1 rle with old method : 0.1360781192779541 time for calcul the mask position with numpy : 0.05398058891296387 nb_pixel_total : 13925 time to create 1 rle with old method : 0.016019344329833984 time for calcul the mask position with numpy : 0.054419755935668945 nb_pixel_total : 38131 time to create 1 rle with old method : 0.04118537902832031 time for calcul the mask position with numpy : 0.05516934394836426 nb_pixel_total : 91967 time to create 1 rle with old method : 0.12361764907836914 time for calcul the mask position with numpy : 0.05562853813171387 nb_pixel_total : 20049 time to create 1 rle with old method : 0.02257823944091797 time for calcul the mask position with numpy : 0.05646228790283203 nb_pixel_total : 211544 time to create 1 rle with new method : 0.9604816436767578 time for calcul the mask position with numpy : 0.05315566062927246 nb_pixel_total : 3152 time to create 1 rle with old method : 0.003972768783569336 time for calcul the mask position with numpy : 0.05469012260437012 nb_pixel_total : 209632 time to create 1 rle with new method : 1.2757785320281982 time for calcul the mask position with numpy : 0.062744140625 nb_pixel_total : 81710 time to create 1 rle with old method : 0.09093832969665527 time for calcul the mask position with numpy : 0.05712389945983887 nb_pixel_total : 76187 time to create 1 rle with old method : 0.0858604907989502 time for calcul the mask position with numpy : 0.054872989654541016 nb_pixel_total : 37 time to create 1 rle with old method : 7.319450378417969e-05 create new chi : 27.63625192642212 time to delete rle : 0.0066678524017333984 batch 1 Loaded 81 chid ids of type : 4855 Number RLEs to save : 68537 TO DO : save crop sub photo not yet done ! save time : 5.1832685470581055 nb_obj : 81 nb_hashtags : 11 time to prepare the origin masks : 65.3658857345581 time for calcul the mask position with numpy : 0.23206043243408203 nb_pixel_total : 5459298 time to create 1 rle with new method : 1.0237705707550049 time for calcul the mask position with numpy : 0.05318403244018555 nb_pixel_total : 202333 time to create 1 rle with new method : 0.877561092376709 time for calcul the mask position with numpy : 0.05404305458068848 nb_pixel_total : 974 time to create 1 rle with old method : 0.00140380859375 time for calcul the mask position with numpy : 0.05522799491882324 nb_pixel_total : 7189 time to create 1 rle with old method : 0.008462190628051758 time for calcul the mask position with numpy : 0.05501914024353027 nb_pixel_total : 161709 time to create 1 rle with new method : 0.9066569805145264 time for calcul the mask position with numpy : 0.0685267448425293 nb_pixel_total : 571425 time to create 1 rle with new method : 0.9139173030853271 time for calcul the mask position with numpy : 0.0550382137298584 nb_pixel_total : 40604 time to create 1 rle with old method : 0.04636573791503906 time for calcul the mask position with numpy : 0.055141448974609375 nb_pixel_total : 18468 time to create 1 rle with old method : 0.02232670783996582 time for calcul the mask position with numpy : 0.06064748764038086 nb_pixel_total : 2163 time to create 1 rle with old method : 0.003700733184814453 time for calcul the mask position with numpy : 0.05706143379211426 nb_pixel_total : 152225 time to create 1 rle with new method : 0.8995671272277832 time for calcul the mask position with numpy : 0.05426812171936035 nb_pixel_total : 28118 time to create 1 rle with old method : 0.03167128562927246 time for calcul the mask position with numpy : 0.05531668663024902 nb_pixel_total : 64975 time to create 1 rle with old method : 0.07241988182067871 time for calcul the mask position with numpy : 0.05405306816101074 nb_pixel_total : 92211 time to create 1 rle with old method : 0.10209822654724121 time for calcul the mask position with numpy : 0.05425286293029785 nb_pixel_total : 3434 time to create 1 rle with old method : 0.004264116287231445 time for calcul the mask position with numpy : 0.05526900291442871 nb_pixel_total : 10156 time to create 1 rle with old method : 0.012053251266479492 time for calcul the mask position with numpy : 0.05468559265136719 nb_pixel_total : 11313 time to create 1 rle with old method : 0.012516975402832031 time for calcul the mask position with numpy : 0.054654598236083984 nb_pixel_total : 48841 time to create 1 rle with old method : 0.0547490119934082 time for calcul the mask position with numpy : 0.055129051208496094 nb_pixel_total : 13870 time to create 1 rle with old method : 0.015835285186767578 time for calcul the mask position with numpy : 0.05435442924499512 nb_pixel_total : 27529 time to create 1 rle with old method : 0.03113389015197754 time for calcul the mask position with numpy : 0.0578770637512207 nb_pixel_total : 246465 time to create 1 rle with new method : 0.7332532405853271 time for calcul the mask position with numpy : 0.05522465705871582 nb_pixel_total : 185731 time to create 1 rle with new method : 0.8919274806976318 time for calcul the mask position with numpy : 0.056252241134643555 nb_pixel_total : 95300 time to create 1 rle with old method : 0.10690569877624512 time for calcul the mask position with numpy : 0.05512380599975586 nb_pixel_total : 90679 time to create 1 rle with old method : 0.10220956802368164 time for calcul the mask position with numpy : 0.05117058753967285 nb_pixel_total : 14682 time to create 1 rle with old method : 0.01634359359741211 time for calcul the mask position with numpy : 0.053751230239868164 nb_pixel_total : 64039 time to create 1 rle with old method : 0.06895112991333008 time for calcul the mask position with numpy : 0.05344867706298828 nb_pixel_total : 17127 time to create 1 rle with old method : 0.019133806228637695 time for calcul the mask position with numpy : 0.05486869812011719 nb_pixel_total : 74109 time to create 1 rle with old method : 0.08115339279174805 time for calcul the mask position with numpy : 0.05297088623046875 nb_pixel_total : 20509 time to create 1 rle with old method : 0.02262258529663086 time for calcul the mask position with numpy : 0.053600311279296875 nb_pixel_total : 21342 time to create 1 rle with old method : 0.02393937110900879 time for calcul the mask position with numpy : 0.054036617279052734 nb_pixel_total : 3669 time to create 1 rle with old method : 0.004361391067504883 time for calcul the mask position with numpy : 0.05401277542114258 nb_pixel_total : 2880 time to create 1 rle with old method : 0.0037653446197509766 time for calcul the mask position with numpy : 0.05347394943237305 nb_pixel_total : 27892 time to create 1 rle with old method : 0.03094196319580078 time for calcul the mask position with numpy : 0.05546259880065918 nb_pixel_total : 11657 time to create 1 rle with old method : 0.013355493545532227 time for calcul the mask position with numpy : 0.05511283874511719 nb_pixel_total : 509 time to create 1 rle with old method : 0.0007419586181640625 time for calcul the mask position with numpy : 0.05529308319091797 nb_pixel_total : 19328 time to create 1 rle with old method : 0.021638870239257812 time for calcul the mask position with numpy : 0.05450296401977539 nb_pixel_total : 138085 time to create 1 rle with old method : 0.1531388759613037 time for calcul the mask position with numpy : 0.06607675552368164 nb_pixel_total : 34172 time to create 1 rle with old method : 0.04230809211730957 time for calcul the mask position with numpy : 0.05786919593811035 nb_pixel_total : 234985 time to create 1 rle with new method : 1.051100492477417 time for calcul the mask position with numpy : 0.05904054641723633 nb_pixel_total : 100736 time to create 1 rle with old method : 0.11406540870666504 time for calcul the mask position with numpy : 0.056055307388305664 nb_pixel_total : 131061 time to create 1 rle with old method : 0.14613699913024902 time for calcul the mask position with numpy : 0.05742812156677246 nb_pixel_total : 147194 time to create 1 rle with old method : 0.16315889358520508 time for calcul the mask position with numpy : 0.11526632308959961 nb_pixel_total : 840961 time to create 1 rle with new method : 0.8611984252929688 time for calcul the mask position with numpy : 0.059491634368896484 nb_pixel_total : 41857 time to create 1 rle with old method : 0.048597097396850586 time for calcul the mask position with numpy : 0.05677604675292969 nb_pixel_total : 18269 time to create 1 rle with old method : 0.020922183990478516 time for calcul the mask position with numpy : 0.05555891990661621 nb_pixel_total : 28322 time to create 1 rle with old method : 0.032063961029052734 time for calcul the mask position with numpy : 0.055510520935058594 nb_pixel_total : 26136 time to create 1 rle with old method : 0.03314018249511719 time for calcul the mask position with numpy : 0.055083513259887695 nb_pixel_total : 5676 time to create 1 rle with old method : 0.006399393081665039 time for calcul the mask position with numpy : 0.056487083435058594 nb_pixel_total : 2275 time to create 1 rle with old method : 0.002708911895751953 time for calcul the mask position with numpy : 0.05567216873168945 nb_pixel_total : 121239 time to create 1 rle with old method : 0.13509654998779297 time for calcul the mask position with numpy : 0.05596303939819336 nb_pixel_total : 201648 time to create 1 rle with new method : 0.740720272064209 time for calcul the mask position with numpy : 0.054715871810913086 nb_pixel_total : 38988 time to create 1 rle with old method : 0.04967355728149414 time for calcul the mask position with numpy : 0.05657553672790527 nb_pixel_total : 344804 time to create 1 rle with new method : 0.8629193305969238 time for calcul the mask position with numpy : 0.054032325744628906 nb_pixel_total : 73585 time to create 1 rle with old method : 0.08305478096008301 time for calcul the mask position with numpy : 0.05431032180786133 nb_pixel_total : 23455 time to create 1 rle with old method : 0.026285409927368164 time for calcul the mask position with numpy : 0.055820465087890625 nb_pixel_total : 970 time to create 1 rle with old method : 0.0017657279968261719 time for calcul the mask position with numpy : 0.061121463775634766 nb_pixel_total : 25241 time to create 1 rle with old method : 0.03200387954711914 time for calcul the mask position with numpy : 0.05568194389343262 nb_pixel_total : 266447 time to create 1 rle with new method : 0.628760814666748 time for calcul the mask position with numpy : 0.054572343826293945 nb_pixel_total : 148103 time to create 1 rle with old method : 0.16924786567687988 time for calcul the mask position with numpy : 0.059706926345825195 nb_pixel_total : 96 time to create 1 rle with old method : 0.00022292137145996094 time for calcul the mask position with numpy : 0.05872082710266113 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006005764007568359 time for calcul the mask position with numpy : 0.05670905113220215 nb_pixel_total : 8482 time to create 1 rle with old method : 0.009846210479736328 time for calcul the mask position with numpy : 0.05575919151306152 nb_pixel_total : 226132 time to create 1 rle with new method : 0.890385627746582 time for calcul the mask position with numpy : 0.05356097221374512 nb_pixel_total : 61830 time to create 1 rle with old method : 0.0698995590209961 time for calcul the mask position with numpy : 0.055042266845703125 nb_pixel_total : 254310 time to create 1 rle with new method : 0.7616546154022217 time for calcul the mask position with numpy : 0.05680537223815918 nb_pixel_total : 302427 time to create 1 rle with new method : 0.8625764846801758 time for calcul the mask position with numpy : 0.05629253387451172 nb_pixel_total : 126449 time to create 1 rle with old method : 0.1814563274383545 time for calcul the mask position with numpy : 0.0556950569152832 nb_pixel_total : 5535 time to create 1 rle with old method : 0.009660005569458008 time for calcul the mask position with numpy : 0.06079816818237305 nb_pixel_total : 31141 time to create 1 rle with old method : 0.03643012046813965 time for calcul the mask position with numpy : 0.05994915962219238 nb_pixel_total : 88545 time to create 1 rle with old method : 0.10721468925476074 time for calcul the mask position with numpy : 0.058338165283203125 nb_pixel_total : 30828 time to create 1 rle with old method : 0.03668928146362305 time for calcul the mask position with numpy : 0.05538582801818848 nb_pixel_total : 175988 time to create 1 rle with new method : 0.6253530979156494 time for calcul the mask position with numpy : 0.05542612075805664 nb_pixel_total : 13999 time to create 1 rle with old method : 0.01584482192993164 time for calcul the mask position with numpy : 0.05894041061401367 nb_pixel_total : 354721 time to create 1 rle with new method : 0.5921869277954102 time for calcul the mask position with numpy : 0.05459332466125488 nb_pixel_total : 523 time to create 1 rle with old method : 0.0007548332214355469 time for calcul the mask position with numpy : 0.05571699142456055 nb_pixel_total : 6635 time to create 1 rle with old method : 0.008821249008178711 time for calcul the mask position with numpy : 0.055915117263793945 nb_pixel_total : 22659 time to create 1 rle with old method : 0.025979995727539062 time for calcul the mask position with numpy : 0.05436539649963379 nb_pixel_total : 637 time to create 1 rle with old method : 0.000978231430053711 time for calcul the mask position with numpy : 0.056302547454833984 nb_pixel_total : 285807 time to create 1 rle with new method : 0.5390324592590332 time for calcul the mask position with numpy : 0.05880904197692871 nb_pixel_total : 67420 time to create 1 rle with old method : 0.07610034942626953 time for calcul the mask position with numpy : 0.05720043182373047 nb_pixel_total : 44922 time to create 1 rle with old method : 0.054166316986083984 time for calcul the mask position with numpy : 0.055677175521850586 nb_pixel_total : 37492 time to create 1 rle with old method : 0.04238295555114746 time for calcul the mask position with numpy : 0.05468559265136719 nb_pixel_total : 25224 time to create 1 rle with old method : 0.028773069381713867 create new chi : 23.260290384292603 time to delete rle : 0.00638270378112793 batch 1 Loaded 82 chid ids of type : 4855 Number RLEs to save : 59982 TO DO : save crop sub photo not yet done ! save time : 4.963131904602051 nb_obj : 18 nb_hashtags : 7 time to prepare the origin masks : 27.594711542129517 time for calcul the mask position with numpy : 0.24898481369018555 nb_pixel_total : 1588370 time to create 1 rle with new method : 1.3446967601776123 time for calcul the mask position with numpy : 0.07139420509338379 nb_pixel_total : 47 time to create 1 rle with old method : 0.00013017654418945312 time for calcul the mask position with numpy : 0.0803680419921875 nb_pixel_total : 776 time to create 1 rle with old method : 0.0013091564178466797 time for calcul the mask position with numpy : 0.08107471466064453 nb_pixel_total : 20419 time to create 1 rle with old method : 0.024407625198364258 time for calcul the mask position with numpy : 0.06571650505065918 nb_pixel_total : 759 time to create 1 rle with old method : 0.0008518695831298828 time for calcul the mask position with numpy : 0.08268237113952637 nb_pixel_total : 37233 time to create 1 rle with old method : 0.04489946365356445 time for calcul the mask position with numpy : 0.07395267486572266 nb_pixel_total : 4347 time to create 1 rle with old method : 0.005644321441650391 time for calcul the mask position with numpy : 0.06861186027526855 nb_pixel_total : 25354 time to create 1 rle with old method : 0.02900981903076172 time for calcul the mask position with numpy : 0.04722452163696289 nb_pixel_total : 80230 time to create 1 rle with old method : 0.09126853942871094 time for calcul the mask position with numpy : 0.12280106544494629 nb_pixel_total : 2302490 time to create 1 rle with new method : 0.7996582984924316 time for calcul the mask position with numpy : 0.05377459526062012 nb_pixel_total : 312386 time to create 1 rle with new method : 0.7958047389984131 time for calcul the mask position with numpy : 0.044442176818847656 nb_pixel_total : 14869 time to create 1 rle with old method : 0.016560792922973633 time for calcul the mask position with numpy : 0.04372549057006836 nb_pixel_total : 213807 time to create 1 rle with new method : 0.8933100700378418 time for calcul the mask position with numpy : 0.04764747619628906 nb_pixel_total : 5518 time to create 1 rle with old method : 0.00629115104675293 time for calcul the mask position with numpy : 0.07897448539733887 nb_pixel_total : 881366 time to create 1 rle with new method : 0.7650296688079834 time for calcul the mask position with numpy : 0.06721663475036621 nb_pixel_total : 21405 time to create 1 rle with old method : 0.02393174171447754 time for calcul the mask position with numpy : 0.06261825561523438 nb_pixel_total : 66596 time to create 1 rle with old method : 0.07429957389831543 time for calcul the mask position with numpy : 0.05947375297546387 nb_pixel_total : 2827 time to create 1 rle with old method : 0.003281116485595703 time for calcul the mask position with numpy : 0.4286618232727051 nb_pixel_total : 7400401 time to create 1 rle with new method : 0.7544851303100586 create new chi : 7.826869010925293 time to delete rle : 0.002063274383544922 batch 1 Loaded 19 chid ids of type : 4855 Number RLEs to save : 22494 TO DO : save crop sub photo not yet done ! save time : 1.9115033149719238 map_output_result : {1379845456: (0.5050133907204348, 'Should be the crop_list due to order', 0.6350695741250794), 1379845453: (0.5050133907204348, 'Should be the crop_list due to order', 0.27378060547121297), 1379845433: (0.5050133907204348, 'Should be the crop_list due to order', 0.3136240288197582), 1379845432: (0.5050133907204348, 'Should be the crop_list due to order', 0.3731522203537061), 1379845431: (0.5050133907204348, 'Should be the crop_list due to order', 0.9294405248324175)} 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 [1379845456, 1379845453, 1379845433, 1379845432, 1379845431] Looping around the photos to save general results len do output : 5 /1379845456.Didn't retrieve data . /1379845453.Didn't retrieve data . /1379845433.Didn't retrieve data . /1379845432.Didn't retrieve data . /1379845431.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, '3623817') ('4741', '26291509', '1379845456', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845453', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845433', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845432', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845431', None, None, None, None, None, '3623817') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.028037548065185547 save_final save missing photos in datou_result : time spend for datou_step_exec : 406.41706132888794 time spend to save output : 0.04891014099121094 total time spend for step 5 : 406.46597146987915 step6:crop_condition Thu Aug 28 14:12:19 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 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 : 5 ! batch 1 Loaded 334 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 ! map_result returned by crop_photo_return_map_crop : length : 40 About to insert : list_path_to_insert length 40 new photo from crops ! About to upload 40 photos upload in portfolio : 3015255 init cache_photo without model_param we have 40 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756383193_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 40 photos in the portfolio 3015255 time of upload the photos Elapsed time : 10.421073198318481 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 ! map_result returned by crop_photo_return_map_crop : length : 51 About to insert : list_path_to_insert length 51 new photo from crops ! About to upload 51 photos upload in portfolio : 3015255 init cache_photo without model_param we have 51 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756383229_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 51 photos in the portfolio 3015255 time of upload the photos Elapsed time : 14.134970664978027 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 ! map_result returned by crop_photo_return_map_crop : length : 17 About to insert : list_path_to_insert length 17 new photo from crops ! About to upload 17 photos upload in portfolio : 3015255 init cache_photo without model_param we have 17 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756383250_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 17 photos in the portfolio 3015255 time of upload the photos Elapsed time : 5.087206602096558 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 ! map_result returned by crop_photo_return_map_crop : length : 8 About to insert : list_path_to_insert length 8 new photo from crops ! About to upload 8 photos upload in portfolio : 3015255 init cache_photo without model_param we have 8 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756383261_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 8 photos in the portfolio 3015255 time of upload the photos Elapsed time : 2.5139858722686768 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/1756383269_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 : 0.9993541240692139 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.1} filtre for class : pet_fonce hashtag_id of this class : 2107755900 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3015255 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756383273_3706725 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 : 0.6508729457855225 we have finished the crop for the class : pet_fonce begin to crop the class : sac param for this class : {'min_score': 0.1} filtre for class : sac hashtag_id of this class : 492618350 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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/1756383285_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 : 4.7010204792022705 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 ! 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/1756383292_3706725 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 : 0.5034580230712891 we have finished the crop for the class : textiles begin to crop the class : verre param for this class : {'min_score': 0.1} filtre for class : verre hashtag_id of this class : 492631919 map_result returned by crop_photo_return_map_crop : length : 0 About to insert : list_path_to_insert length 0 new photo from crops ! About to upload 0 photos WARNING : list_path_to_insert is empty, cannot upload ! we have finished the crop for the class : verre begin to crop the class : organique param for this class : {'min_score': 0.1} filtre for class : organique hashtag_id of this class : 530726390 begin to crop the class : dasri param for this class : {'min_score': 0.1} filtre for class : dasri hashtag_id of this class : 1608424396 begin to crop the class : masque param for this class : {'min_score': 0.1} filtre for class : masque hashtag_id of this class : 492626781 begin to crop the class : encombrant param for this class : {'min_score': 0.1} filtre for class : encombrant hashtag_id of this class : 605975549 begin to crop the class : autre param for this class : {'min_score': 0.1} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 36 About to insert : list_path_to_insert length 36 new photo from crops ! About to upload 36 photos upload in portfolio : 3015255 init cache_photo without model_param we have 36 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756383334_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 36 photos in the portfolio 3015255 time of upload the photos Elapsed time : 9.607093095779419 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 ! 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/1756383358_3706725 batch_size : 0, verbose : False, strat_bulk_insert : 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 : 1.027250051498413 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 ! 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/1756383366_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 : 3.4183273315429688 we have finished the crop for the class : autre_non_emballage begin to crop the class : environnement param for this class : {'min_score': 0.1} filtre for class : environnement hashtag_id of this class : 493012381 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 47 About to insert : list_path_to_insert length 47 new photo from crops ! About to upload 47 photos upload in portfolio : 3015255 init cache_photo without model_param we have 47 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756383474_3706725 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : 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 47 photos in the portfolio 3015255 time of upload the photos Elapsed time : 12.972161293029785 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 [1379845456, 1379845453, 1379845433, 1379845432, 1379845431] Looping around the photos to save general results len do output : 231 /1379880263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880297Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880392Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880393Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880394Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880395Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880396Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880397Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880398Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880399Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880400Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880402Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880403Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880404Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880406Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880407Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880409Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880410Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880411Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880418Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880419Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880420Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880555Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379880796Didn'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, '3623817') ('4741', '26291509', '1379845456', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845453', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845433', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845432', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845431', None, None, None, None, None, '3623817') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 698 time used for this insertion : 0.07616496086120605 save_final save missing photos in datou_result : time spend for datou_step_exec : 352.2304058074951 time spend to save output : 0.08378815650939941 total time spend for step 6 : 352.3141939640045 step7:ventilate_hashtags_in_portfolio Thu Aug 28 14:18:11 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 : 26291509 get user id for portfolio 26291509 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 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`=26291509 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`=26291509 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`=26291509 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/26294209,26294210,26294211,26294212,26294213,26294218,26294220,26294221,26294222,26294223,26294224,26294225,26294227,26294228,26294229,26294230,26294231,26294232,26294233,26294234?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=26291509 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1379845456, 1379845453, 1379845433, 1379845432, 1379845431] Looping around the photos to save general results len do output : 1 /26291509. 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, '3623817') ('4741', '26291509', '1379845456', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845453', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845433', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845432', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845431', None, None, None, None, None, '3623817') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.015231609344482422 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.745972156524658 time spend to save output : 0.015436410903930664 total time spend for step 7 : 4.761408567428589 step8:final Thu Aug 28 14:18:16 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 : {1379845456: ('0.44521359328707644',), 1379845453: ('0.44521359328707644',), 1379845433: ('0.44521359328707644',), 1379845432: ('0.44521359328707644',), 1379845431: ('0.44521359328707644',)} new output for save of step final : {1379845456: ('0.44521359328707644',), 1379845453: ('0.44521359328707644',), 1379845433: ('0.44521359328707644',), 1379845432: ('0.44521359328707644',), 1379845431: ('0.44521359328707644',)} [1379845456, 1379845453, 1379845433, 1379845432, 1379845431] Looping around the photos to save general results len do output : 5 /1379845456.Didn't retrieve data . /1379845453.Didn't retrieve data . /1379845433.Didn't retrieve data . /1379845432.Didn't retrieve data . /1379845431.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, '3623817') ('4741', '26291509', '1379845456', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845453', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845433', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845432', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845431', None, None, None, None, None, '3623817') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.01353597640991211 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12136173248291016 time spend to save output : 0.013976812362670898 total time spend for step 8 : 0.13533854484558105 step9:velours_tree Thu Aug 28 14:18:16 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 0.2987079620361328 time spend to save output : 3.6716461181640625e-05 total time spend for step 9 : 0.29874467849731445 step10:send_mail_cod Thu Aug 28 14:18:16 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_P26291509_28-08-2025_14_18_17.pdf 26294183 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 .imagette262941831756383497 26294184 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 .imagette262941841756383499 26294185 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 .imagette262941851756383501 26294186 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 .imagette262941861756383503 26294187 change filename to text .change filename to text .change filename to text .imagette262941871756383503 26294188 change filename to text .imagette262941881756383504 26294189 imagette262941891756383504 26294190 imagette262941901756383504 26294191 imagette262941911756383504 26294192 imagette262941921756383504 26294193 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 .imagette262941931756383504 26294194 change filename to text .imagette262941941756383505 26294195 imagette262941951756383505 26294196 imagette262941961756383505 26294197 imagette262941971756383505 26294198 imagette262941981756383505 26294199 imagette262941991756383505 26294200 change filename to text .change filename to text .imagette262942001756383505 26294201 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 .imagette262942011756383506 26294203 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 .imagette262942031756383507 26294204 imagette262942041756383508 26294205 imagette262942051756383508 26294206 imagette262942061756383508 26294207 imagette262942071756383508 26294208 imagette262942081756383508 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=26291509 and hashtag_type = 4855 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/26294209,26294210,26294211,26294212,26294213,26294218,26294220,26294221,26294222,26294223,26294224,26294225,26294227,26294228,26294229,26294230,26294231,26294232,26294233,26294234?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=26291509 your option no_mail is active, we will not send the real mail to your client args[1379845456] : ((1379845456, 1773.6252242616872, 2107751945), (1379845456, -0.415651059852151, 496442774), '0.44521359328707644') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845453] : ((1379845453, 1016.3004479730051, 2107751945), (1379845453, -0.3243333036550514, 496442774), '0.44521359328707644') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845433] : ((1379845433, 1238.7115172956499, 2107751945), (1379845433, -0.41280299736070636, 496442774), '0.44521359328707644') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845432] : ((1379845432, 3037.5463784145245, 492609224), (1379845432, -0.39777772603817496, 496442774), '0.44521359328707644') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379845431] : ((1379845431, 800.904448496635, 2107751945), (1379845431, -0.5271797341867177, 501862349), '0.44521359328707644') We are sending mail with results at report@fotonower.com,cod@fotonower.com refus_total : 0.44521359328707644 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_P26291509_28-08-2025_14_18_17.pdf results_Auto_P26291509_28-08-2025_14_18_17.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291509_28-08-2025_14_18_17.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','26291509','results_Auto_P26291509_28-08-2025_14_18_17.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291509_28-08-2025_14_18_17.pdf','pdf','','2.59','0.44521359328707644') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1379845456, 1379845453, 1379845433, 1379845432, 1379845431] 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, '3623817') ('4741', '26291509', '1379845456', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845453', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845433', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845432', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845431', None, None, None, None, None, '3623817') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.015832185745239258 save_final save missing photos in datou_result : time spend for datou_step_exec : 15.73979640007019 time spend to save output : 0.016028642654418945 total time spend for step 10 : 15.75582504272461 step11:split_time_score Thu Aug 28 14:18:32 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 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 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'}] (('39', 1), ('40', 4)) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 26082025 26291509 Nombre de photos uploadées : 5 / 23040 (0%) 26082025 26291509 Nombre de photos taguées (types de déchets): 0 / 5 (0%) 26082025 26291509 Nombre de photos taguées (volume) : 0 / 5 (0%) elapsed_time : load_data_split_time_score 1.430511474609375e-06 elapsed_time : order_list_meta_photo_and_scores 4.291534423828125e-06 ????? elapsed_time : fill_and_build_computed_from_old_data 0.0002999305725097656 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.2030620574951172 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 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291505 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291506 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291507 order by id desc limit 1 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': 5, '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 [1379845456, 1379845453, 1379845433, 1379845432, 1379845431] Looping around the photos to save general results len do output : 1 /26291509Didn'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, '3623817') ('4741', '26291509', '1379845456', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845453', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845433', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845432', None, None, None, None, None, '3623817') ('4741', None, None, None, None, None, None, None, '3623817') ('4741', '26291509', '1379845431', None, None, None, None, None, '3623817') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.016699552536010742 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.509365558624268 time spend to save output : 0.016911029815673828 total time spend for step 11 : 5.526276588439941 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 5 set_done_treatment 643.74user 312.41system 17:13.56elapsed 92%CPU (0avgtext+0avgdata 6312720maxresident)k 5010640inputs+650696outputs (114718major+55449003minor)pagefaults 0swaps