python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 10 -a ' -a 4234 -l 5 ' -s datou_current_4234 -M 0 -S 0 -U 95,95,80 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 : 810777 load datou : 4234 # 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! 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 ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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 ? 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 ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl 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 : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 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 : 4234, datou_cur_ids : ['2538732'] with mtr_portfolio_ids : ['20162701'] and first list_photo_ids : [] new path : /proc/810777/ 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! 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 ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! 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 : 0.8089425563812256 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Mon Feb 3 00:20:28 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 : 3133 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-03 00:20:31.021245: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-03 00:20:31.047554: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493020000 Hz 2025-02-03 00:20:31.049821: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa390000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-03 00:20:31.049875: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-03 00:20:31.053693: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-03 00:20:31.320173: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xc3076b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-03 00:20:31.320234: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-03 00:20:31.321284: 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 2025-02-03 00:20:31.321728: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 00:20:31.324784: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 00:20:31.328070: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-03 00:20:31.328571: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-03 00:20:31.331917: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-03 00:20:31.333194: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-03 00:20:31.337666: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-03 00:20:31.338737: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-03 00:20:31.338819: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 00:20:31.339379: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-03 00:20:31.339394: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-03 00:20:31.339403: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-03 00:20:31.340353: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2681 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. 2025-02-03 00:20:31.596851: 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 2025-02-03 00:20:31.596931: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 00:20:31.596951: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 00:20:31.596970: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-03 00:20:31.596987: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-03 00:20:31.597004: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-03 00:20:31.597021: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-03 00:20:31.597039: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-03 00:20:31.598040: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-03 00:20:31.598998: 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 2025-02-03 00:20:31.599036: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-03 00:20:31.599057: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 00:20:31.599077: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-03 00:20:31.599095: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-03 00:20:31.599114: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-03 00:20:31.599133: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-03 00:20:31.599152: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-03 00:20:31.600159: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-03 00:20:31.600190: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-03 00:20:31.600201: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-03 00:20:31.600210: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-03 00:20:31.601252: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2681 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 : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', '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': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', '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': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', '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': 3594, 'photo_desc_type': 5275, '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': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, '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 learn_RUBBIA_REFUS_AMIENS_23 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 : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-03 00:20:39.390690: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-03 00:20:39.580423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-03 00:20:40.842276: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.842328: 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. 2025-02-03 00:20:40.842882: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.842897: 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. 2025-02-03 00:20:40.849941: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.849961: 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. 2025-02-03 00:20:40.850530: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.850546: 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. 2025-02-03 00:20:40.857019: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.857038: 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. 2025-02-03 00:20:40.857581: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.857595: 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. 2025-02-03 00:20:40.888288: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.888312: 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. 2025-02-03 00:20:40.888885: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.888900: 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. 2025-02-03 00:20:40.894689: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.894708: 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. 2025-02-03 00:20:40.895251: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.895266: 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. 2025-02-03 00:20:40.928925: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.929477: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.931304: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.931863: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.977303: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:40.977893: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.008257: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.008814: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.010495: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.011093: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.017452: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.018000: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.019914: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.020462: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.026227: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.026837: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.028428: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.029009: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.054969: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.055551: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.056149: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.056742: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.060267: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.060866: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.076002: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.076559: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.077109: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.077658: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.089663: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.090264: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.090858: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.091413: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.095679: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.096247: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.100730: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.101282: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.113144: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.113705: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.117727: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.118304: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.118896: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.119470: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.120203: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.120801: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.131106: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.131673: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.132235: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.132784: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.133331: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.133876: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.148910: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.149508: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.214515: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.215172: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.230711: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.231317: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.231920: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.232516: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.236595: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.237196: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.237755: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.238317: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.239451: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.239480: 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. 2025-02-03 00:20:41.249825: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.250427: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.259701: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.260281: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.260832: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.261369: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.261913: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-03 00:20:41.262449: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2276327424 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 5 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.36016 max: 149.72109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 893 time to create 1 rle with old method : 0.001688241958618164 length of segment : 37 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 867 time to create 1 rle with old method : 0.0015904903411865234 length of segment : 37 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1941 time to create 1 rle with old method : 0.00337982177734375 length of segment : 40 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0007627010345458984 length of segment : 29 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.0005025863647460938 length of segment : 35 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0014519691467285156 length of segment : 49 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.001239776611328125 length of segment : 50 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 697 time to create 1 rle with old method : 0.0012328624725341797 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.55547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.001033782958984375 length of segment : 38 time for calcul the mask position with numpy : 0.0003764629364013672 nb_pixel_total : 13955 time to create 1 rle with old method : 0.01581096649169922 length of segment : 478 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 2665 time to create 1 rle with old method : 0.0032808780670166016 length of segment : 61 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 927 time to create 1 rle with old method : 0.001129150390625 length of segment : 42 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 2646 time to create 1 rle with old method : 0.003023862838745117 length of segment : 65 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2855 time to create 1 rle with old method : 0.0033609867095947266 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 9.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -96.38750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1704 time to create 1 rle with old method : 0.0021355152130126953 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.02031 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0007505416870117188 length of segment : 27 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003108978271484375 length of segment : 22 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1234 time to create 1 rle with old method : 0.0014281272888183594 length of segment : 73 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.00045871734619140625 length of segment : 20 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 250.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.28359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003800392150878906 length of segment : 19 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0008268356323242188 length of segment : 22 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00024628639221191406 length of segment : 13 time for calcul the mask position with numpy : 0.0005919933319091797 nb_pixel_total : 59028 time to create 1 rle with old method : 0.06390571594238281 length of segment : 255 Processing 1 images image shape: (400, 400, 3) min: 18.00000 max: 195.00000 molded_images shape: (1, 640, 640, 3) min: -88.99688 max: 72.15078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012807846069335938 nb_pixel_total : 151598 time to create 1 rle with new method : 0.0018537044525146484 length of segment : 397 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.12188 max: 150.48281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004622936248779297 length of segment : 15 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1392 time to create 1 rle with old method : 0.0016562938690185547 length of segment : 47 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.00030541419982910156 length of segment : 21 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.00016355514526367188 length of segment : 12 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1500 time to create 1 rle with old method : 0.001766204833984375 length of segment : 44 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006299018859863281 length of segment : 21 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0016508102416992188 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.09844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.00021839141845703125 nb_pixel_total : 12248 time to create 1 rle with old method : 0.013829708099365234 length of segment : 109 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 807 time to create 1 rle with old method : 0.0011186599731445312 length of segment : 39 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0004749298095703125 length of segment : 22 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0008041858673095703 length of segment : 60 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 869 time to create 1 rle with old method : 0.001041412353515625 length of segment : 43 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 57 time to create 1 rle with old method : 0.00010538101196289062 length of segment : 10 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0007779598236083984 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.75078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 2768 time to create 1 rle with old method : 0.0033338069915771484 length of segment : 51 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0007565021514892578 length of segment : 17 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1290 time to create 1 rle with old method : 0.0015497207641601562 length of segment : 41 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 831 time to create 1 rle with old method : 0.0010061264038085938 length of segment : 37 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.00014591217041015625 length of segment : 12 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 1440 time to create 1 rle with old method : 0.0017499923706054688 length of segment : 137 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1169 time to create 1 rle with old method : 0.0015833377838134766 length of segment : 42 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0015742778778076172 length of segment : 41 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 249.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.36953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005731582641601562 length of segment : 39 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0006957054138183594 length of segment : 16 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0006566047668457031 length of segment : 33 time for calcul the mask position with numpy : 0.0002474784851074219 nb_pixel_total : 4707 time to create 1 rle with old method : 0.007430553436279297 length of segment : 228 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 762 time to create 1 rle with old method : 0.0009298324584960938 length of segment : 46 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1539 time to create 1 rle with old method : 0.0018305778503417969 length of segment : 76 Processing 1 images image shape: (280, 400, 3) min: 26.00000 max: 192.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 69.23672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009770393371582031 nb_pixel_total : 106496 time to create 1 rle with old method : 0.11316418647766113 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.45547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00012946128845214844 length of segment : 11 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0004527568817138672 length of segment : 22 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 51 time to create 1 rle with old method : 0.0001251697540283203 length of segment : 18 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.17812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00015354156494140625 length of segment : 10 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 2168 time to create 1 rle with old method : 0.002557039260864258 length of segment : 47 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 2320 time to create 1 rle with old method : 0.0027282238006591797 length of segment : 52 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0015544891357421875 length of segment : 55 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 921 time to create 1 rle with old method : 0.0010941028594970703 length of segment : 45 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 2696 time to create 1 rle with old method : 0.003201723098754883 length of segment : 61 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.0004749298095703125 length of segment : 19 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 2182 time to create 1 rle with old method : 0.0025751590728759766 length of segment : 48 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.0011258125305175781 length of segment : 48 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 148.95547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006134510040283203 length of segment : 81 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005962848663330078 length of segment : 73 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 42 time to create 1 rle with old method : 9.250640869140625e-05 length of segment : 7 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.0001316070556640625 length of segment : 8 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002884864807128906 length of segment : 17 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.97500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1126 time to create 1 rle with old method : 0.0014293193817138672 length of segment : 145 time for calcul the mask position with numpy : 0.0004222393035888672 nb_pixel_total : 36181 time to create 1 rle with old method : 0.03887748718261719 length of segment : 289 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.43047 max: 149.53359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 974 time to create 1 rle with old method : 0.0012226104736328125 length of segment : 36 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 946 time to create 1 rle with old method : 0.0011827945709228516 length of segment : 37 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 856 time to create 1 rle with old method : 0.001107931137084961 length of segment : 47 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0003974437713623047 length of segment : 26 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 852 time to create 1 rle with old method : 0.0011107921600341797 length of segment : 40 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 2086 time to create 1 rle with old method : 0.002516508102416992 length of segment : 32 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1845 time to create 1 rle with old method : 0.002277374267578125 length of segment : 30 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 839 time to create 1 rle with old method : 0.0010707378387451172 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.25469 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.00102996826171875 length of segment : 38 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 2625 time to create 1 rle with old method : 0.003056764602661133 length of segment : 50 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005152225494384766 length of segment : 62 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -95.33281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 3712 time to create 1 rle with old method : 0.004395484924316406 length of segment : 54 time for calcul the mask position with numpy : 0.00011539459228515625 nb_pixel_total : 5841 time to create 1 rle with old method : 0.006501436233520508 length of segment : 101 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.30938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.0008339881896972656 length of segment : 27 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.00031447410583496094 length of segment : 23 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 250.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.22500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0006940364837646484 length of segment : 18 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0006875991821289062 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 201.00000 molded_images shape: (1, 640, 640, 3) min: -87.92656 max: 82.81484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012691020965576172 nb_pixel_total : 151198 time to create 1 rle with new method : 0.0019016265869140625 length of segment : 397 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.62969 max: 150.82656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003180503845214844 length of segment : 11 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0003979206085205078 length of segment : 14 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001461505889892578 length of segment : 11 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00035071372985839844 length of segment : 23 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 7550 time to create 1 rle with old method : 0.008356809616088867 length of segment : 127 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1268 time to create 1 rle with old method : 0.0014913082122802734 length of segment : 46 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1346 time to create 1 rle with old method : 0.0017886161804199219 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.03984 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0011911392211914062 length of segment : 37 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0004706382751464844 length of segment : 23 time for calcul the mask position with numpy : 0.00022077560424804688 nb_pixel_total : 12342 time to create 1 rle with old method : 0.013761758804321289 length of segment : 110 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0009877681732177734 length of segment : 42 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 690 time to create 1 rle with old method : 0.0008649826049804688 length of segment : 29 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 771 time to create 1 rle with old method : 0.0009217262268066406 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.20000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 1986 time to create 1 rle with old method : 0.0023543834686279297 length of segment : 138 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 636 time to create 1 rle with old method : 0.0008783340454101562 length of segment : 18 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0015916824340820312 length of segment : 40 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 2044 time to create 1 rle with old method : 0.0024385452270507812 length of segment : 137 time for calcul the mask position with numpy : 0.0001220703125 nb_pixel_total : 1269 time to create 1 rle with old method : 0.0017573833465576172 length of segment : 45 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 384 time to create 1 rle with old method : 0.0007426738739013672 length of segment : 30 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.00054168701171875 length of segment : 20 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0014121532440185547 length of segment : 36 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.0010867118835449219 length of segment : 38 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 248.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.48281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005292892456054688 length of segment : 37 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1738 time to create 1 rle with old method : 0.002020120620727539 length of segment : 84 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0003733634948730469 length of segment : 33 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 720 time to create 1 rle with old method : 0.0009090900421142578 length of segment : 44 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 777 time to create 1 rle with old method : 0.0009403228759765625 length of segment : 45 time for calcul the mask position with numpy : 0.00015783309936523438 nb_pixel_total : 3467 time to create 1 rle with old method : 0.004027128219604492 length of segment : 227 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 831 time to create 1 rle with old method : 0.0010690689086914062 length of segment : 36 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 611 time to create 1 rle with old method : 0.0007755756378173828 length of segment : 62 Processing 1 images image shape: (280, 400, 3) min: 21.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 72.11953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009570121765136719 nb_pixel_total : 106375 time to create 1 rle with old method : 0.11314177513122559 length of segment : 279 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.39297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.00047588348388671875 length of segment : 21 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0007109642028808594 length of segment : 11 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0012278556823730469 length of segment : 43 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.00041103363037109375 length of segment : 25 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.64297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 2142 time to create 1 rle with old method : 0.0025415420532226562 length of segment : 47 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.000438690185546875 length of segment : 21 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1402 time to create 1 rle with old method : 0.0016808509826660156 length of segment : 52 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 2638 time to create 1 rle with old method : 0.0030744075775146484 length of segment : 55 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 2720 time to create 1 rle with old method : 0.003975868225097656 length of segment : 59 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00014972686767578125 length of segment : 10 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1012 time to create 1 rle with old method : 0.0011937618255615234 length of segment : 47 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.0006229877471923828 length of segment : 26 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.000457763671875 length of segment : 46 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1630 time to create 1 rle with old method : 0.001977682113647461 length of segment : 79 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002512931823730469 length of segment : 16 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.0006959438323974609 length of segment : 56 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.00029969215393066406 length of segment : 26 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.85000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.0004241466522216797 nb_pixel_total : 36044 time to create 1 rle with old method : 0.044554710388183594 length of segment : 247 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005960464477539062 length of segment : 95 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.94609 max: 149.46719 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 869 time to create 1 rle with old method : 0.0011239051818847656 length of segment : 38 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0011072158813476562 length of segment : 50 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.00034928321838378906 length of segment : 25 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 927 time to create 1 rle with old method : 0.0011794567108154297 length of segment : 37 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007493495941162109 length of segment : 56 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 635 time to create 1 rle with old method : 0.0008502006530761719 length of segment : 55 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004241466522216797 length of segment : 32 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 782 time to create 1 rle with old method : 0.0010068416595458984 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.41484 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.0002849102020263672 nb_pixel_total : 14895 time to create 1 rle with old method : 0.01684093475341797 length of segment : 376 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 42 time to create 1 rle with old method : 8.606910705566406e-05 length of segment : 8 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 2217 time to create 1 rle with old method : 0.002752065658569336 length of segment : 51 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 2569 time to create 1 rle with old method : 0.0035414695739746094 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -96.82500 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.000823974609375 length of segment : 15 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 2244 time to create 1 rle with old method : 0.0027480125427246094 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.87422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0007889270782470703 length of segment : 29 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.27187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00045609474182128906 nb_pixel_total : 42297 time to create 1 rle with old method : 0.04553937911987305 length of segment : 253 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.00025534629821777344 length of segment : 15 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006821155548095703 length of segment : 16 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006377696990966797 length of segment : 17 time for calcul the mask position with numpy : 0.0006806850433349609 nb_pixel_total : 65267 time to create 1 rle with old method : 0.06990599632263184 length of segment : 272 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -86.43438 max: 77.98672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012729167938232422 nb_pixel_total : 151534 time to create 1 rle with new method : 0.0018582344055175781 length of segment : 399 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.69219 max: 150.06484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.00043582916259765625 length of segment : 14 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1338 time to create 1 rle with old method : 0.0015895366668701172 length of segment : 48 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003039836883544922 length of segment : 20 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006551742553710938 length of segment : 20 time for calcul the mask position with numpy : 0.00021457672119140625 nb_pixel_total : 12997 time to create 1 rle with old method : 0.014607906341552734 length of segment : 208 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00016617774963378906 length of segment : 12 Processing 1 images image shape: (400, 400, 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: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005786418914794922 length of segment : 26 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 877 time to create 1 rle with old method : 0.0012173652648925781 length of segment : 39 time for calcul the mask position with numpy : 0.0002484321594238281 nb_pixel_total : 11305 time to create 1 rle with old method : 0.012459754943847656 length of segment : 101 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 887 time to create 1 rle with old method : 0.0010502338409423828 length of segment : 44 time for calcul the mask position with numpy : 2.8133392333984375e-05 nb_pixel_total : 65 time to create 1 rle with old method : 0.00011110305786132812 length of segment : 11 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004620552062988281 length of segment : 18 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0009496212005615234 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.16484 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 1986 time to create 1 rle with old method : 0.002161264419555664 length of segment : 152 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1128 time to create 1 rle with old method : 0.0013935565948486328 length of segment : 41 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1331 time to create 1 rle with old method : 0.0015430450439453125 length of segment : 37 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 1477 time to create 1 rle with old method : 0.0016367435455322266 length of segment : 97 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.001234292984008789 length of segment : 81 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 885 time to create 1 rle with old method : 0.0010063648223876953 length of segment : 38 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 1331 time to create 1 rle with old method : 0.0015718936920166016 length of segment : 38 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 246.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.28359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005121231079101562 length of segment : 38 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1590 time to create 1 rle with old method : 0.0018763542175292969 length of segment : 77 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0003993511199951172 length of segment : 17 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.00041937828063964844 length of segment : 32 time for calcul the mask position with numpy : 0.0001583099365234375 nb_pixel_total : 4728 time to create 1 rle with old method : 0.005175352096557617 length of segment : 230 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0011644363403320312 length of segment : 102 time for calcul the mask position with numpy : 0.0001671314239501953 nb_pixel_total : 3845 time to create 1 rle with old method : 0.004292964935302734 length of segment : 196 Processing 1 images image shape: (280, 400, 3) min: 28.00000 max: 192.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 68.58437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008821487426757812 nb_pixel_total : 105286 time to create 1 rle with old method : 0.11134672164916992 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.01016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.0001373291015625 length of segment : 11 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.00039839744567871094 length of segment : 32 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.00040721893310546875 length of segment : 22 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 38 time to create 1 rle with old method : 8.916854858398438e-05 length of segment : 8 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.73281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 2137 time to create 1 rle with old method : 0.0024721622467041016 length of segment : 47 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 2464 time to create 1 rle with old method : 0.002974271774291992 length of segment : 60 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1398 time to create 1 rle with old method : 0.001613616943359375 length of segment : 53 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 947 time to create 1 rle with old method : 0.0010592937469482422 length of segment : 46 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 2529 time to create 1 rle with old method : 0.002836942672729492 length of segment : 65 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0016546249389648438 length of segment : 55 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1924 time to create 1 rle with old method : 0.0021409988403320312 length of segment : 43 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0003936290740966797 length of segment : 56 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00032520294189453125 length of segment : 25 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.0011951923370361328 length of segment : 78 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1588 time to create 1 rle with old method : 0.001867055892944336 length of segment : 79 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005276203155517578 length of segment : 50 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 908 time to create 1 rle with old method : 0.0010988712310791016 length of segment : 124 time for calcul the mask position with numpy : 0.00043272972106933594 nb_pixel_total : 42428 time to create 1 rle with old method : 0.04733538627624512 length of segment : 297 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.0012319087982177734 length of segment : 34 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.33672 max: 149.27187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 929 time to create 1 rle with old method : 0.0010907649993896484 length of segment : 35 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.0011973381042480469 length of segment : 36 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004169940948486328 length of segment : 31 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 875 time to create 1 rle with old method : 0.001094818115234375 length of segment : 36 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0006780624389648438 length of segment : 49 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1873 time to create 1 rle with old method : 0.002329111099243164 length of segment : 39 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.0009438991546630859 length of segment : 48 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.18828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 728 time to create 1 rle with old method : 0.0008866786956787109 length of segment : 38 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 2796 time to create 1 rle with old method : 0.0031752586364746094 length of segment : 70 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 1002 time to create 1 rle with old method : 0.001096963882446289 length of segment : 41 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.0010058879852294922 length of segment : 60 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 2552 time to create 1 rle with old method : 0.002752542495727539 length of segment : 50 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 656 time to create 1 rle with old method : 0.0008003711700439453 length of segment : 52 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 961 time to create 1 rle with old method : 0.001058816909790039 length of segment : 44 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 3207 time to create 1 rle with old method : 0.003477811813354492 length of segment : 64 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -98.05547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 2248 time to create 1 rle with old method : 0.0025789737701416016 length of segment : 41 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0004801750183105469 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.63750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0007796287536621094 length of segment : 28 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.00028061866760253906 length of segment : 21 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 253.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.61172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006759166717529297 length of segment : 17 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00024056434631347656 length of segment : 14 time for calcul the mask position with numpy : 0.0004756450653076172 nb_pixel_total : 49749 time to create 1 rle with old method : 0.05459237098693848 length of segment : 240 time for calcul the mask position with numpy : 0.00019025802612304688 nb_pixel_total : 11915 time to create 1 rle with old method : 0.012921571731567383 length of segment : 148 Processing 1 images image shape: (400, 400, 3) min: 26.00000 max: 200.00000 molded_images shape: (1, 640, 640, 3) min: -83.24688 max: 80.02969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.001237630844116211 nb_pixel_total : 150956 time to create 1 rle with new method : 0.0019092559814453125 length of segment : 396 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.03203 max: 149.47891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0005259513854980469 length of segment : 16 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0002989768981933594 length of segment : 22 time for calcul the mask position with numpy : 2.7418136596679688e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00013899803161621094 length of segment : 11 time for calcul the mask position with numpy : 0.0001380443572998047 nb_pixel_total : 9542 time to create 1 rle with old method : 0.009816408157348633 length of segment : 146 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 1333 time to create 1 rle with old method : 0.0014603137969970703 length of segment : 48 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0002951622009277344 length of segment : 11 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0006341934204101562 length of segment : 20 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1415 time to create 1 rle with old method : 0.0018641948699951172 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.77813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 767 time to create 1 rle with old method : 0.0016410350799560547 length of segment : 38 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 727 time to create 1 rle with old method : 0.0017540454864501953 length of segment : 40 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.0005290508270263672 length of segment : 14 time for calcul the mask position with numpy : 0.0002009868621826172 nb_pixel_total : 11813 time to create 1 rle with old method : 0.013792276382446289 length of segment : 105 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.00046753883361816406 length of segment : 29 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.00025844573974609375 length of segment : 20 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.00012969970703125 length of segment : 11 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0007851123809814453 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.20781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 748 time to create 1 rle with old method : 0.0010385513305664062 length of segment : 21 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1991 time to create 1 rle with old method : 0.0023059844970703125 length of segment : 154 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 2069 time to create 1 rle with old method : 0.002416372299194336 length of segment : 130 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 1921 time to create 1 rle with old method : 0.0025510787963867188 length of segment : 92 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1313 time to create 1 rle with old method : 0.0014925003051757812 length of segment : 38 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1341 time to create 1 rle with old method : 0.0018777847290039062 length of segment : 45 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 819 time to create 1 rle with old method : 0.0009167194366455078 length of segment : 37 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1265 time to create 1 rle with old method : 0.001743316650390625 length of segment : 44 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 844 time to create 1 rle with old method : 0.0009946823120117188 length of segment : 36 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 253.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.99844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005314350128173828 length of segment : 35 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.00045108795166015625 length of segment : 17 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 823 time to create 1 rle with old method : 0.001049041748046875 length of segment : 35 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0003802776336669922 length of segment : 32 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1611 time to create 1 rle with old method : 0.001947641372680664 length of segment : 77 time for calcul the mask position with numpy : 0.00016927719116210938 nb_pixel_total : 3982 time to create 1 rle with old method : 0.004601478576660156 length of segment : 215 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 609 time to create 1 rle with old method : 0.0008950233459472656 length of segment : 60 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009360313415527344 length of segment : 45 time for calcul the mask position with numpy : 0.00014519691467285156 nb_pixel_total : 3150 time to create 1 rle with old method : 0.0038611888885498047 length of segment : 181 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 482 time to create 1 rle with old method : 0.0006299018859863281 length of segment : 38 Processing 1 images image shape: (280, 400, 3) min: 15.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 72.69766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008511543273925781 nb_pixel_total : 106216 time to create 1 rle with old method : 0.10885834693908691 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.04922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0004322528839111328 length of segment : 21 time for calcul the mask position with numpy : 2.7418136596679688e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.0001277923583984375 length of segment : 11 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0007326602935791016 length of segment : 11 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 45 time to create 1 rle with old method : 9.608268737792969e-05 length of segment : 8 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.35781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1066 time to create 1 rle with old method : 0.0011868476867675781 length of segment : 49 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 2199 time to create 1 rle with old method : 0.002412557601928711 length of segment : 49 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 1518 time to create 1 rle with old method : 0.0016410350799560547 length of segment : 56 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 2612 time to create 1 rle with old method : 0.003017425537109375 length of segment : 65 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.00044226646423339844 length of segment : 25 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 2856 time to create 1 rle with old method : 0.003038167953491211 length of segment : 71 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 2081 time to create 1 rle with old method : 0.0022058486938476562 length of segment : 45 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0007648468017578125 length of segment : 78 time for calcul the mask position with numpy : 2.8133392333984375e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00014591217041015625 length of segment : 9 time for calcul the mask position with numpy : 2.7179718017578125e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.00013637542724609375 length of segment : 10 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 140.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 696 time to create 1 rle with old method : 0.0008521080017089844 length of segment : 35 time for calcul the mask position with numpy : 0.00041484832763671875 nb_pixel_total : 40458 time to create 1 rle with old method : 0.04077792167663574 length of segment : 242 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 15 time to create 1 rle with old method : 3.790855407714844e-05 length of segment : 9 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.33672 max: 149.27187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 963 time to create 1 rle with old method : 0.00113677978515625 length of segment : 37 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 939 time to create 1 rle with old method : 0.0011243820190429688 length of segment : 40 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.00040340423583984375 length of segment : 33 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 746 time to create 1 rle with old method : 0.0009961128234863281 length of segment : 42 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 876 time to create 1 rle with old method : 0.0010263919830322266 length of segment : 33 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1792 time to create 1 rle with old method : 0.002129793167114258 length of segment : 51 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.00037789344787597656 length of segment : 30 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 557 time to create 1 rle with old method : 0.0006959438323974609 length of segment : 46 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 672 time to create 1 rle with old method : 0.0008087158203125 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.18828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 955 time to create 1 rle with old method : 0.001138448715209961 length of segment : 40 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 2334 time to create 1 rle with old method : 0.002700328826904297 length of segment : 48 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 2567 time to create 1 rle with old method : 0.0029478073120117188 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -99.38359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 776 time to create 1 rle with old method : 0.0009672641754150391 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.39922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0007226467132568359 length of segment : 26 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 1274 time to create 1 rle with old method : 0.0013530254364013672 length of segment : 75 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00029206275939941406 length of segment : 22 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 254.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 138.60391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.0006670951843261719 length of segment : 19 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.00026702880859375 length of segment : 12 time for calcul the mask position with numpy : 0.00038909912109375 nb_pixel_total : 36014 time to create 1 rle with old method : 0.03641533851623535 length of segment : 297 Processing 1 images image shape: (400, 400, 3) min: 24.00000 max: 203.00000 molded_images shape: (1, 640, 640, 3) min: -87.73125 max: 83.50625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.79375 max: 149.95547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0004818439483642578 length of segment : 15 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003428459167480469 length of segment : 21 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 1337 time to create 1 rle with old method : 0.0014965534210205078 length of segment : 46 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0006506443023681641 length of segment : 27 time for calcul the mask position with numpy : 0.00014257431030273438 nb_pixel_total : 9238 time to create 1 rle with old method : 0.010027885437011719 length of segment : 153 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00015306472778320312 length of segment : 11 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00031757354736328125 length of segment : 16 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006568431854248047 length of segment : 21 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1357 time to create 1 rle with old method : 0.0017080307006835938 length of segment : 31 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1895 time to create 1 rle with old method : 0.0021407604217529297 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.75859 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 909 time to create 1 rle with old method : 0.001201629638671875 length of segment : 41 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0006990432739257812 length of segment : 46 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0004749298095703125 length of segment : 25 time for calcul the mask position with numpy : 0.00021982192993164062 nb_pixel_total : 12525 time to create 1 rle with old method : 0.012941360473632812 length of segment : 111 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 728 time to create 1 rle with old method : 0.0008590221405029297 length of segment : 41 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.00011658668518066406 length of segment : 11 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 690 time to create 1 rle with old method : 0.0007534027099609375 length of segment : 29 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002415180206298828 length of segment : 18 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.0002799034118652344 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.92266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006918907165527344 length of segment : 19 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0014278888702392578 length of segment : 36 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1247 time to create 1 rle with old method : 0.0014503002166748047 length of segment : 145 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 2166 time to create 1 rle with old method : 0.0026140213012695312 length of segment : 138 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.00014519691467285156 length of segment : 14 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 1105 time to create 1 rle with old method : 0.0014278888702392578 length of segment : 84 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1193 time to create 1 rle with old method : 0.001611948013305664 length of segment : 42 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0009548664093017578 length of segment : 37 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.0010547637939453125 length of segment : 40 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 248.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.26797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0005011558532714844 length of segment : 36 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1567 time to create 1 rle with old method : 0.0016880035400390625 length of segment : 79 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003643035888671875 length of segment : 30 time for calcul the mask position with numpy : 0.00014281272888183594 nb_pixel_total : 4255 time to create 1 rle with old method : 0.0045795440673828125 length of segment : 228 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 854 time to create 1 rle with old method : 0.0009989738464355469 length of segment : 36 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.0005855560302734375 length of segment : 48 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 686 time to create 1 rle with old method : 0.0007948875427246094 length of segment : 46 Processing 1 images image shape: (280, 400, 3) min: 16.00000 max: 189.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 65.49844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008325576782226562 nb_pixel_total : 105362 time to create 1 rle with old method : 0.10981607437133789 length of segment : 281 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.27969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.00036907196044921875 length of segment : 32 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.00012946128845214844 length of segment : 11 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.0006365776062011719 length of segment : 11 time for calcul the mask position with numpy : 2.6702880859375e-05 nb_pixel_total : 47 time to create 1 rle with old method : 9.131431579589844e-05 length of segment : 9 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003752708435058594 length of segment : 16 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.84219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 2074 time to create 1 rle with old method : 0.002408742904663086 length of segment : 48 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001308917999267578 length of segment : 8 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 2595 time to create 1 rle with old method : 0.003044605255126953 length of segment : 57 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0012128353118896484 length of segment : 50 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 2811 time to create 1 rle with old method : 0.0031697750091552734 length of segment : 60 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1330 time to create 1 rle with old method : 0.0015952587127685547 length of segment : 49 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0004100799560546875 length of segment : 21 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 1304 time to create 1 rle with old method : 0.0015497207641601562 length of segment : 48 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.00035643577575683594 length of segment : 16 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.0005457401275634766 length of segment : 46 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0008368492126464844 length of segment : 70 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.0001354217529296875 length of segment : 26 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002474784851074219 length of segment : 22 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006363391876220703 length of segment : 53 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002181529998779297 length of segment : 21 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.22500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00035858154296875 length of segment : 61 time for calcul the mask position with numpy : 0.0004534721374511719 nb_pixel_total : 39519 time to create 1 rle with old method : 0.0429227352142334 length of segment : 246 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0013952255249023438 length of segment : 33 Detection mask done ! Trying to reset tf kernel 811289 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1940 tf kernel not reseted sub process len(results) : 363 len(list_Values) 363 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 363 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 : 3133 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Catched exception ! Connect or reconnect ! Number saved : None batch 1 Loaded 363 chid ids of type : 4228 Number RLEs to save : 22355 save missing photos in datou_result : time spend for datou_step_exec : 29.610400915145874 time spend to save output : 1.9055819511413574 total time spend for step 1 : 31.51598286628723 step2:brightness Mon Feb 3 00:20:59 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 inside step calcul brightness treat image : temp/1738538427_810777_1333957964_542148f78b1e97dd3b9c5257e38171be.jpg treat image : temp/1738538427_810777_1333957943_3747e7e87f0d69fe37108f17c0d0ddb9.jpg treat image : temp/1738538427_810777_1333957941_a6ee0172c774593836f61a930654e847.jpg treat image : temp/1738538427_810777_1333957922_3b6431fb4fa0d0b0b025c116c7e9f0d5.jpg treat image : temp/1738538427_810777_1333957864_754b114b905a935c32c094f733525653.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 : 0.012492179870605469 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 : 0.011728763580322266 save missing photos in datou_result : time spend for datou_step_exec : 1.676767110824585 time spend to save output : 0.030083894729614258 total time spend for step 2 : 1.7068510055541992 step3:blur_detection Mon Feb 3 00:21:01 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 inside step blur_detection methode: ratio et variance treat image : temp/1738538427_810777_1333957964_542148f78b1e97dd3b9c5257e38171be.jpg resize: (1080, 1920) 1333957964 -7.736959908026764 treat image : temp/1738538427_810777_1333957943_3747e7e87f0d69fe37108f17c0d0ddb9.jpg resize: (1080, 1920) 1333957943 -7.737405985906943 treat image : temp/1738538427_810777_1333957941_a6ee0172c774593836f61a930654e847.jpg resize: (1080, 1920) 1333957941 -7.741401548510373 treat image : temp/1738538427_810777_1333957922_3b6431fb4fa0d0b0b025c116c7e9f0d5.jpg resize: (1080, 1920) 1333957922 -7.732699181677737 treat image : temp/1738538427_810777_1333957864_754b114b905a935c32c094f733525653.jpg resize: (1080, 1920) 1333957864 -7.722290510243807 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 : 0.012876749038696289 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 : 0.011945247650146484 save missing photos in datou_result : time spend for datou_step_exec : 5.140660047531128 time spend to save output : 0.030460357666015625 total time spend for step 3 : 5.1711204051971436 step4:rle_unique_nms_with_priority Mon Feb 3 00:21:06 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 363 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 72 nb_hashtags : 6 time to prepare the origin masks : 1.0697886943817139 time for calcul the mask position with numpy : 0.5801582336425781 nb_pixel_total : 1644331 time to create 1 rle with new method : 0.08168816566467285 time for calcul the mask position with numpy : 0.008871078491210938 nb_pixel_total : 59028 time to create 1 rle with old method : 0.06686735153198242 time for calcul the mask position with numpy : 0.008157014846801758 nb_pixel_total : 152 time to create 1 rle with old method : 0.00039315223693847656 time for calcul the mask position with numpy : 0.008301973342895508 nb_pixel_total : 394 time to create 1 rle with old method : 0.0004620552062988281 time for calcul the mask position with numpy : 0.008060455322265625 nb_pixel_total : 1941 time to create 1 rle with old method : 0.0021636486053466797 time for calcul the mask position with numpy : 0.008153200149536133 nb_pixel_total : 413 time to create 1 rle with old method : 0.0004169940948486328 time for calcul the mask position with numpy : 0.007870674133300781 nb_pixel_total : 795 time to create 1 rle with old method : 0.0008363723754882812 time for calcul the mask position with numpy : 0.007936954498291016 nb_pixel_total : 893 time to create 1 rle with old method : 0.0009334087371826172 time for calcul the mask position with numpy : 0.008168935775756836 nb_pixel_total : 13 time to create 1 rle with old method : 4.267692565917969e-05 time for calcul the mask position with numpy : 0.008113861083984375 nb_pixel_total : 263 time to create 1 rle with old method : 0.00029730796813964844 time for calcul the mask position with numpy : 0.008182048797607422 nb_pixel_total : 526 time to create 1 rle with old method : 0.0006270408630371094 time for calcul the mask position with numpy : 0.008096694946289062 nb_pixel_total : 166 time to create 1 rle with old method : 0.00025272369384765625 time for calcul the mask position with numpy : 0.008025884628295898 nb_pixel_total : 2665 time to create 1 rle with old method : 0.0028429031372070312 time for calcul the mask position with numpy : 0.007886409759521484 nb_pixel_total : 372 time to create 1 rle with old method : 0.0004439353942871094 time for calcul the mask position with numpy : 0.007734060287475586 nb_pixel_total : 13955 time to create 1 rle with old method : 0.014736652374267578 time for calcul the mask position with numpy : 0.00775599479675293 nb_pixel_total : 1234 time to create 1 rle with old method : 0.0012562274932861328 time for calcul the mask position with numpy : 0.007802486419677734 nb_pixel_total : 226 time to create 1 rle with old method : 0.00023293495178222656 time for calcul the mask position with numpy : 0.007741689682006836 nb_pixel_total : 348 time to create 1 rle with old method : 0.00035071372985839844 time for calcul the mask position with numpy : 0.00785684585571289 nb_pixel_total : 927 time to create 1 rle with old method : 0.0010151863098144531 time for calcul the mask position with numpy : 0.008036375045776367 nb_pixel_total : 478 time to create 1 rle with old method : 0.0005705356597900391 time for calcul the mask position with numpy : 0.008170604705810547 nb_pixel_total : 1704 time to create 1 rle with old method : 0.0017371177673339844 time for calcul the mask position with numpy : 0.00791168212890625 nb_pixel_total : 154 time to create 1 rle with old method : 0.00016427040100097656 time for calcul the mask position with numpy : 0.008246898651123047 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003139972686767578 time for calcul the mask position with numpy : 0.008104085922241211 nb_pixel_total : 625 time to create 1 rle with old method : 0.0007054805755615234 time for calcul the mask position with numpy : 0.009200572967529297 nb_pixel_total : 151598 time to create 1 rle with new method : 0.5878243446350098 time for calcul the mask position with numpy : 0.008207559585571289 nb_pixel_total : 630 time to create 1 rle with old method : 0.0006425380706787109 time for calcul the mask position with numpy : 0.008285284042358398 nb_pixel_total : 831 time to create 1 rle with old method : 0.0009598731994628906 time for calcul the mask position with numpy : 0.008201122283935547 nb_pixel_total : 323 time to create 1 rle with old method : 0.0003409385681152344 time for calcul the mask position with numpy : 0.00808858871459961 nb_pixel_total : 1290 time to create 1 rle with old method : 0.0014417171478271484 time for calcul the mask position with numpy : 0.00826120376586914 nb_pixel_total : 46 time to create 1 rle with old method : 6.937980651855469e-05 time for calcul the mask position with numpy : 0.0081024169921875 nb_pixel_total : 762 time to create 1 rle with old method : 0.0008175373077392578 time for calcul the mask position with numpy : 0.008200645446777344 nb_pixel_total : 324 time to create 1 rle with old method : 0.0003609657287597656 time for calcul the mask position with numpy : 0.008384466171264648 nb_pixel_total : 12248 time to create 1 rle with old method : 0.013072729110717773 time for calcul the mask position with numpy : 0.008351802825927734 nb_pixel_total : 87 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.008305788040161133 nb_pixel_total : 1392 time to create 1 rle with old method : 0.0013687610626220703 time for calcul the mask position with numpy : 0.008246898651123047 nb_pixel_total : 519 time to create 1 rle with old method : 0.0005421638488769531 time for calcul the mask position with numpy : 0.008162736892700195 nb_pixel_total : 2768 time to create 1 rle with old method : 0.002889871597290039 time for calcul the mask position with numpy : 0.008069992065429688 nb_pixel_total : 4707 time to create 1 rle with old method : 0.004839420318603516 time for calcul the mask position with numpy : 0.007907867431640625 nb_pixel_total : 795 time to create 1 rle with old method : 0.0008993148803710938 time for calcul the mask position with numpy : 0.008240461349487305 nb_pixel_total : 301 time to create 1 rle with old method : 0.0003333091735839844 time for calcul the mask position with numpy : 0.008088111877441406 nb_pixel_total : 1440 time to create 1 rle with old method : 0.0015411376953125 time for calcul the mask position with numpy : 0.00819253921508789 nb_pixel_total : 617 time to create 1 rle with old method : 0.0006275177001953125 time for calcul the mask position with numpy : 0.008272886276245117 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0013461112976074219 time for calcul the mask position with numpy : 0.008224725723266602 nb_pixel_total : 1169 time to create 1 rle with old method : 0.0012402534484863281 time for calcul the mask position with numpy : 0.008151054382324219 nb_pixel_total : 457 time to create 1 rle with old method : 0.00046372413635253906 time for calcul the mask position with numpy : 0.008285045623779297 nb_pixel_total : 1539 time to create 1 rle with old method : 0.0017726421356201172 time for calcul the mask position with numpy : 0.008023738861083984 nb_pixel_total : 57 time to create 1 rle with old method : 7.152557373046875e-05 time for calcul the mask position with numpy : 0.00794672966003418 nb_pixel_total : 869 time to create 1 rle with old method : 0.0008730888366699219 time for calcul the mask position with numpy : 0.007712364196777344 nb_pixel_total : 450 time to create 1 rle with old method : 0.0004649162292480469 time for calcul the mask position with numpy : 0.007657766342163086 nb_pixel_total : 1500 time to create 1 rle with old method : 0.0014829635620117188 time for calcul the mask position with numpy : 0.007934808731079102 nb_pixel_total : 103 time to create 1 rle with old method : 0.00011157989501953125 time for calcul the mask position with numpy : 0.00797128677368164 nb_pixel_total : 368 time to create 1 rle with old method : 0.0003769397735595703 time for calcul the mask position with numpy : 0.008177042007446289 nb_pixel_total : 225 time to create 1 rle with old method : 0.0002503395080566406 time for calcul the mask position with numpy : 0.008545160293579102 nb_pixel_total : 106496 time to create 1 rle with old method : 0.1100013256072998 time for calcul the mask position with numpy : 0.007838010787963867 nb_pixel_total : 1126 time to create 1 rle with old method : 0.0012052059173583984 time for calcul the mask position with numpy : 0.00800180435180664 nb_pixel_total : 73 time to create 1 rle with old method : 8.916854858398438e-05 time for calcul the mask position with numpy : 0.007765054702758789 nb_pixel_total : 51 time to create 1 rle with old method : 7.62939453125e-05 time for calcul the mask position with numpy : 0.00795888900756836 nb_pixel_total : 36175 time to create 1 rle with old method : 0.03634285926818848 time for calcul the mask position with numpy : 0.007903337478637695 nb_pixel_total : 335 time to create 1 rle with old method : 0.0003733634948730469 time for calcul the mask position with numpy : 0.00805354118347168 nb_pixel_total : 461 time to create 1 rle with old method : 0.0004775524139404297 time for calcul the mask position with numpy : 0.0077021121978759766 nb_pixel_total : 1309 time to create 1 rle with old method : 0.001306772232055664 time for calcul the mask position with numpy : 0.007828474044799805 nb_pixel_total : 341 time to create 1 rle with old method : 0.0003464221954345703 time for calcul the mask position with numpy : 0.007695436477661133 nb_pixel_total : 382 time to create 1 rle with old method : 0.0004248619079589844 time for calcul the mask position with numpy : 0.007699251174926758 nb_pixel_total : 2320 time to create 1 rle with old method : 0.0023145675659179688 time for calcul the mask position with numpy : 0.007658958435058594 nb_pixel_total : 394 time to create 1 rle with old method : 0.00042057037353515625 time for calcul the mask position with numpy : 0.007975101470947266 nb_pixel_total : 77 time to create 1 rle with old method : 8.821487426757812e-05 time for calcul the mask position with numpy : 0.007726192474365234 nb_pixel_total : 42 time to create 1 rle with old method : 4.982948303222656e-05 time for calcul the mask position with numpy : 0.007840394973754883 nb_pixel_total : 72 time to create 1 rle with old method : 0.00010323524475097656 time for calcul the mask position with numpy : 0.008041620254516602 nb_pixel_total : 921 time to create 1 rle with old method : 0.0010526180267333984 time for calcul the mask position with numpy : 0.007991790771484375 nb_pixel_total : 2168 time to create 1 rle with old method : 0.002177000045776367 time for calcul the mask position with numpy : 0.00793910026550293 nb_pixel_total : 81 time to create 1 rle with old method : 8.96453857421875e-05 time for calcul the mask position with numpy : 0.007999181747436523 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002269744873046875 time for calcul the mask position with numpy : 0.007818460464477539 nb_pixel_total : 52 time to create 1 rle with old method : 7.82012939453125e-05 create new chi : 2.1408064365386963 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.010154008865356445 batch 1 Loaded 73 chid ids of type : 4230 Number RLEs to save : 9773 TO DO : save crop sub photo not yet done ! save time : 0.6537837982177734 nb_obj : 68 nb_hashtags : 5 time to prepare the origin masks : 1.708132028579712 time for calcul the mask position with numpy : 0.030138731002807617 nb_pixel_total : 1705078 time to create 1 rle with new method : 0.09816408157348633 time for calcul the mask position with numpy : 0.00605010986328125 nb_pixel_total : 392 time to create 1 rle with old method : 0.0004715919494628906 time for calcul the mask position with numpy : 0.006158590316772461 nb_pixel_total : 974 time to create 1 rle with old method : 0.0011265277862548828 time for calcul the mask position with numpy : 0.0062580108642578125 nb_pixel_total : 856 time to create 1 rle with old method : 0.0010061264038085938 time for calcul the mask position with numpy : 0.007117748260498047 nb_pixel_total : 2086 time to create 1 rle with old method : 0.0024847984313964844 time for calcul the mask position with numpy : 0.0067293643951416016 nb_pixel_total : 293 time to create 1 rle with old method : 0.0003466606140136719 time for calcul the mask position with numpy : 0.0060312747955322266 nb_pixel_total : 23 time to create 1 rle with old method : 7.843971252441406e-05 time for calcul the mask position with numpy : 0.007022380828857422 nb_pixel_total : 66 time to create 1 rle with old method : 0.00012183189392089844 time for calcul the mask position with numpy : 0.0060596466064453125 nb_pixel_total : 43 time to create 1 rle with old method : 9.942054748535156e-05 time for calcul the mask position with numpy : 0.00605010986328125 nb_pixel_total : 21 time to create 1 rle with old method : 6.198883056640625e-05 time for calcul the mask position with numpy : 0.006055116653442383 nb_pixel_total : 2625 time to create 1 rle with old method : 0.002896547317504883 time for calcul the mask position with numpy : 0.0060193538665771484 nb_pixel_total : 229 time to create 1 rle with old method : 0.00029778480529785156 time for calcul the mask position with numpy : 0.00597071647644043 nb_pixel_total : 834 time to create 1 rle with old method : 0.0009098052978515625 time for calcul the mask position with numpy : 0.005759000778198242 nb_pixel_total : 488 time to create 1 rle with old method : 0.0006585121154785156 time for calcul the mask position with numpy : 0.005975246429443359 nb_pixel_total : 3712 time to create 1 rle with old method : 0.00449061393737793 time for calcul the mask position with numpy : 0.006471872329711914 nb_pixel_total : 5841 time to create 1 rle with old method : 0.0064890384674072266 time for calcul the mask position with numpy : 0.005881071090698242 nb_pixel_total : 39 time to create 1 rle with old method : 8.058547973632812e-05 time for calcul the mask position with numpy : 0.006094217300415039 nb_pixel_total : 493 time to create 1 rle with old method : 0.0005578994750976562 time for calcul the mask position with numpy : 0.0070247650146484375 nb_pixel_total : 151198 time to create 1 rle with new method : 0.03760099411010742 time for calcul the mask position with numpy : 0.006132841110229492 nb_pixel_total : 2044 time to create 1 rle with old method : 0.002374410629272461 time for calcul the mask position with numpy : 0.006004810333251953 nb_pixel_total : 690 time to create 1 rle with old method : 0.0007646083831787109 time for calcul the mask position with numpy : 0.006031990051269531 nb_pixel_total : 879 time to create 1 rle with old method : 0.0009944438934326172 time for calcul the mask position with numpy : 0.006256103515625 nb_pixel_total : 288 time to create 1 rle with old method : 0.0003333091735839844 time for calcul the mask position with numpy : 0.006037235260009766 nb_pixel_total : 64 time to create 1 rle with old method : 0.000118255615234375 time for calcul the mask position with numpy : 0.010020732879638672 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0016245841979980469 time for calcul the mask position with numpy : 0.011563301086425781 nb_pixel_total : 777 time to create 1 rle with old method : 0.0010461807250976562 time for calcul the mask position with numpy : 0.011341571807861328 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004839897155761719 time for calcul the mask position with numpy : 0.011990785598754883 nb_pixel_total : 12339 time to create 1 rle with old method : 0.015882492065429688 time for calcul the mask position with numpy : 0.01341557502746582 nb_pixel_total : 291 time to create 1 rle with old method : 0.00044417381286621094 time for calcul the mask position with numpy : 0.012006521224975586 nb_pixel_total : 636 time to create 1 rle with old method : 0.0007727146148681641 time for calcul the mask position with numpy : 0.010085344314575195 nb_pixel_total : 145 time to create 1 rle with old method : 0.00019621849060058594 time for calcul the mask position with numpy : 0.010216236114501953 nb_pixel_total : 7550 time to create 1 rle with old method : 0.008283376693725586 time for calcul the mask position with numpy : 0.00998544692993164 nb_pixel_total : 831 time to create 1 rle with old method : 0.0009543895721435547 time for calcul the mask position with numpy : 0.00969696044921875 nb_pixel_total : 720 time to create 1 rle with old method : 0.0007467269897460938 time for calcul the mask position with numpy : 0.009666681289672852 nb_pixel_total : 3467 time to create 1 rle with old method : 0.003686666488647461 time for calcul the mask position with numpy : 0.009976625442504883 nb_pixel_total : 794 time to create 1 rle with old method : 0.0008876323699951172 time for calcul the mask position with numpy : 0.01011967658996582 nb_pixel_total : 610 time to create 1 rle with old method : 0.0012540817260742188 time for calcul the mask position with numpy : 0.01573324203491211 nb_pixel_total : 1986 time to create 1 rle with old method : 0.002440929412841797 time for calcul the mask position with numpy : 0.009994983673095703 nb_pixel_total : 384 time to create 1 rle with old method : 0.0004487037658691406 time for calcul the mask position with numpy : 0.009273290634155273 nb_pixel_total : 196 time to create 1 rle with old method : 0.00026226043701171875 time for calcul the mask position with numpy : 0.0060291290283203125 nb_pixel_total : 1346 time to create 1 rle with old method : 0.0015544891357421875 time for calcul the mask position with numpy : 0.00643610954284668 nb_pixel_total : 1269 time to create 1 rle with old method : 0.00150299072265625 time for calcul the mask position with numpy : 0.005937814712524414 nb_pixel_total : 422 time to create 1 rle with old method : 0.0004875659942626953 time for calcul the mask position with numpy : 0.005979061126708984 nb_pixel_total : 1738 time to create 1 rle with old method : 0.0019228458404541016 time for calcul the mask position with numpy : 0.006041288375854492 nb_pixel_total : 806 time to create 1 rle with old method : 0.0008955001831054688 time for calcul the mask position with numpy : 0.0059587955474853516 nb_pixel_total : 13 time to create 1 rle with old method : 4.3392181396484375e-05 time for calcul the mask position with numpy : 0.00604557991027832 nb_pixel_total : 90 time to create 1 rle with old method : 0.00012350082397460938 time for calcul the mask position with numpy : 0.00571441650390625 nb_pixel_total : 364 time to create 1 rle with old method : 0.000385284423828125 time for calcul the mask position with numpy : 0.005629062652587891 nb_pixel_total : 265 time to create 1 rle with old method : 0.00031447410583496094 time for calcul the mask position with numpy : 0.005559206008911133 nb_pixel_total : 472 time to create 1 rle with old method : 0.0005195140838623047 time for calcul the mask position with numpy : 0.006296396255493164 nb_pixel_total : 106375 time to create 1 rle with old method : 0.11360287666320801 time for calcul the mask position with numpy : 0.006148815155029297 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005030632019042969 time for calcul the mask position with numpy : 0.005936861038208008 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002048015594482422 time for calcul the mask position with numpy : 0.00608062744140625 nb_pixel_total : 36044 time to create 1 rle with old method : 0.03841280937194824 time for calcul the mask position with numpy : 0.006049156188964844 nb_pixel_total : 355 time to create 1 rle with old method : 0.0004067420959472656 time for calcul the mask position with numpy : 0.006006717681884766 nb_pixel_total : 580 time to create 1 rle with old method : 0.0006601810455322266 time for calcul the mask position with numpy : 0.006012439727783203 nb_pixel_total : 283 time to create 1 rle with old method : 0.00034332275390625 time for calcul the mask position with numpy : 0.00600743293762207 nb_pixel_total : 1402 time to create 1 rle with old method : 0.0015716552734375 time for calcul the mask position with numpy : 0.00613713264465332 nb_pixel_total : 312 time to create 1 rle with old method : 0.0003764629364013672 time for calcul the mask position with numpy : 0.005993843078613281 nb_pixel_total : 102 time to create 1 rle with old method : 0.00017714500427246094 time for calcul the mask position with numpy : 0.005982160568237305 nb_pixel_total : 2638 time to create 1 rle with old method : 0.002952098846435547 time for calcul the mask position with numpy : 0.006186246871948242 nb_pixel_total : 1630 time to create 1 rle with old method : 0.001836538314819336 time for calcul the mask position with numpy : 0.006062984466552734 nb_pixel_total : 37 time to create 1 rle with old method : 7.939338684082031e-05 time for calcul the mask position with numpy : 0.007072925567626953 nb_pixel_total : 314 time to create 1 rle with old method : 0.00037169456481933594 time for calcul the mask position with numpy : 0.0068912506103515625 nb_pixel_total : 1008 time to create 1 rle with old method : 0.0011250972747802734 time for calcul the mask position with numpy : 0.006392955780029297 nb_pixel_total : 1012 time to create 1 rle with old method : 0.0011134147644042969 time for calcul the mask position with numpy : 0.005999088287353516 nb_pixel_total : 234 time to create 1 rle with old method : 0.00028395652770996094 time for calcul the mask position with numpy : 0.006228446960449219 nb_pixel_total : 2142 time to create 1 rle with old method : 0.002359628677368164 time for calcul the mask position with numpy : 0.006231784820556641 nb_pixel_total : 85 time to create 1 rle with old method : 0.00011539459228515625 create new chi : 0.9040780067443848 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.001177072525024414 batch 1 Loaded 69 chid ids of type : 4230 Number RLEs to save : 8458 TO DO : save crop sub photo not yet done ! save time : 0.522796630859375 nb_obj : 67 nb_hashtags : 7 time to prepare the origin masks : 1.312795877456665 time for calcul the mask position with numpy : 0.017491817474365234 nb_pixel_total : 1626887 time to create 1 rle with new method : 0.0514225959777832 time for calcul the mask position with numpy : 0.006390571594238281 nb_pixel_total : 23945 time to create 1 rle with old method : 0.02665996551513672 time for calcul the mask position with numpy : 0.00602269172668457 nb_pixel_total : 88 time to create 1 rle with old method : 0.00015425682067871094 time for calcul the mask position with numpy : 0.00597691535949707 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009069442749023438 time for calcul the mask position with numpy : 0.006003618240356445 nb_pixel_total : 869 time to create 1 rle with old method : 0.0009922981262207031 time for calcul the mask position with numpy : 0.005872488021850586 nb_pixel_total : 67 time to create 1 rle with old method : 0.00013947486877441406 time for calcul the mask position with numpy : 0.00613093376159668 nb_pixel_total : 29 time to create 1 rle with old method : 7.963180541992188e-05 time for calcul the mask position with numpy : 0.005914926528930664 nb_pixel_total : 313 time to create 1 rle with old method : 0.0003399848937988281 time for calcul the mask position with numpy : 0.006025075912475586 nb_pixel_total : 42297 time to create 1 rle with old method : 0.045526981353759766 time for calcul the mask position with numpy : 0.0061206817626953125 nb_pixel_total : 492 time to create 1 rle with old method : 0.0007302761077880859 time for calcul the mask position with numpy : 0.006987810134887695 nb_pixel_total : 2217 time to create 1 rle with old method : 0.0024373531341552734 time for calcul the mask position with numpy : 0.0066869258880615234 nb_pixel_total : 42 time to create 1 rle with old method : 9.179115295410156e-05 time for calcul the mask position with numpy : 0.006081581115722656 nb_pixel_total : 14895 time to create 1 rle with old method : 0.016057968139648438 time for calcul the mask position with numpy : 0.006311655044555664 nb_pixel_total : 598 time to create 1 rle with old method : 0.0006432533264160156 time for calcul the mask position with numpy : 0.005990743637084961 nb_pixel_total : 2244 time to create 1 rle with old method : 0.002336740493774414 time for calcul the mask position with numpy : 0.005857706069946289 nb_pixel_total : 515 time to create 1 rle with old method : 0.0005679130554199219 time for calcul the mask position with numpy : 0.005571126937866211 nb_pixel_total : 566 time to create 1 rle with old method : 0.0005886554718017578 time for calcul the mask position with numpy : 0.005654335021972656 nb_pixel_total : 166 time to create 1 rle with old method : 0.00018930435180664062 time for calcul the mask position with numpy : 0.005608558654785156 nb_pixel_total : 505 time to create 1 rle with old method : 0.0005552768707275391 time for calcul the mask position with numpy : 0.005666971206665039 nb_pixel_total : 6 time to create 1 rle with old method : 2.5987625122070312e-05 time for calcul the mask position with numpy : 0.006557941436767578 nb_pixel_total : 151534 time to create 1 rle with new method : 0.027122974395751953 time for calcul the mask position with numpy : 0.006007194519042969 nb_pixel_total : 611 time to create 1 rle with old method : 0.0007328987121582031 time for calcul the mask position with numpy : 0.005963802337646484 nb_pixel_total : 702 time to create 1 rle with old method : 0.0007686614990234375 time for calcul the mask position with numpy : 0.0059659481048583984 nb_pixel_total : 1477 time to create 1 rle with old method : 0.0016722679138183594 time for calcul the mask position with numpy : 0.005927085876464844 nb_pixel_total : 885 time to create 1 rle with old method : 0.000986337661743164 time for calcul the mask position with numpy : 0.005939483642578125 nb_pixel_total : 308 time to create 1 rle with old method : 0.00036072731018066406 time for calcul the mask position with numpy : 0.005945682525634766 nb_pixel_total : 108 time to create 1 rle with old method : 0.00016069412231445312 time for calcul the mask position with numpy : 0.005913257598876953 nb_pixel_total : 1331 time to create 1 rle with old method : 0.0014605522155761719 time for calcul the mask position with numpy : 0.006003379821777344 nb_pixel_total : 11305 time to create 1 rle with old method : 0.012369394302368164 time for calcul the mask position with numpy : 0.006200313568115234 nb_pixel_total : 331 time to create 1 rle with old method : 0.0003795623779296875 time for calcul the mask position with numpy : 0.005898475646972656 nb_pixel_total : 1338 time to create 1 rle with old method : 0.001398324966430664 time for calcul the mask position with numpy : 0.00574183464050293 nb_pixel_total : 11803 time to create 1 rle with old method : 0.01212453842163086 time for calcul the mask position with numpy : 0.005990028381347656 nb_pixel_total : 834 time to create 1 rle with old method : 0.00096893310546875 time for calcul the mask position with numpy : 0.005872964859008789 nb_pixel_total : 4728 time to create 1 rle with old method : 0.005010366439819336 time for calcul the mask position with numpy : 0.005978822708129883 nb_pixel_total : 877 time to create 1 rle with old method : 0.0009558200836181641 time for calcul the mask position with numpy : 0.0058917999267578125 nb_pixel_total : 287 time to create 1 rle with old method : 0.00033926963806152344 time for calcul the mask position with numpy : 0.0061876773834228516 nb_pixel_total : 1986 time to create 1 rle with old method : 0.002177715301513672 time for calcul the mask position with numpy : 0.006099700927734375 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002493858337402344 time for calcul the mask position with numpy : 0.006791353225708008 nb_pixel_total : 1128 time to create 1 rle with old method : 0.0012924671173095703 time for calcul the mask position with numpy : 0.006674528121948242 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005037784576416016 time for calcul the mask position with numpy : 0.00579524040222168 nb_pixel_total : 1590 time to create 1 rle with old method : 0.0016775131225585938 time for calcul the mask position with numpy : 0.0060122013092041016 nb_pixel_total : 65 time to create 1 rle with old method : 9.679794311523438e-05 time for calcul the mask position with numpy : 0.006037712097167969 nb_pixel_total : 296 time to create 1 rle with old method : 0.00034689903259277344 time for calcul the mask position with numpy : 0.006070852279663086 nb_pixel_total : 887 time to create 1 rle with old method : 0.0009837150573730469 time for calcul the mask position with numpy : 0.006156206130981445 nb_pixel_total : 473 time to create 1 rle with old method : 0.0005412101745605469 time for calcul the mask position with numpy : 0.006277322769165039 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005145072937011719 time for calcul the mask position with numpy : 0.007140159606933594 nb_pixel_total : 101 time to create 1 rle with old method : 0.00016260147094726562 time for calcul the mask position with numpy : 0.006029844284057617 nb_pixel_total : 224 time to create 1 rle with old method : 0.00026535987854003906 time for calcul the mask position with numpy : 0.0064239501953125 nb_pixel_total : 105286 time to create 1 rle with old method : 0.11360907554626465 time for calcul the mask position with numpy : 0.006261587142944336 nb_pixel_total : 908 time to create 1 rle with old method : 0.0010542869567871094 time for calcul the mask position with numpy : 0.006108999252319336 nb_pixel_total : 1588 time to create 1 rle with old method : 0.0017783641815185547 time for calcul the mask position with numpy : 0.006346940994262695 nb_pixel_total : 42428 time to create 1 rle with old method : 0.04562187194824219 time for calcul the mask position with numpy : 0.005942106246948242 nb_pixel_total : 328 time to create 1 rle with old method : 0.00034999847412109375 time for calcul the mask position with numpy : 0.006047487258911133 nb_pixel_total : 330 time to create 1 rle with old method : 0.00038313865661621094 time for calcul the mask position with numpy : 0.005829334259033203 nb_pixel_total : 24 time to create 1 rle with old method : 5.412101745605469e-05 time for calcul the mask position with numpy : 0.0057375431060791016 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002155303955078125 time for calcul the mask position with numpy : 0.005778789520263672 nb_pixel_total : 302 time to create 1 rle with old method : 0.00036072731018066406 time for calcul the mask position with numpy : 0.006127834320068359 nb_pixel_total : 54 time to create 1 rle with old method : 0.00017452239990234375 time for calcul the mask position with numpy : 0.006028413772583008 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0015745162963867188 time for calcul the mask position with numpy : 0.006766796112060547 nb_pixel_total : 242 time to create 1 rle with old method : 0.0002856254577636719 time for calcul the mask position with numpy : 0.006744861602783203 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002512931823730469 time for calcul the mask position with numpy : 0.0063593387603759766 nb_pixel_total : 2464 time to create 1 rle with old method : 0.002691507339477539 time for calcul the mask position with numpy : 0.0059850215911865234 nb_pixel_total : 78 time to create 1 rle with old method : 0.00010895729064941406 time for calcul the mask position with numpy : 0.0060882568359375 nb_pixel_total : 913 time to create 1 rle with old method : 0.0010399818420410156 time for calcul the mask position with numpy : 0.006162405014038086 nb_pixel_total : 43 time to create 1 rle with old method : 6.818771362304688e-05 time for calcul the mask position with numpy : 0.0060465335845947266 nb_pixel_total : 947 time to create 1 rle with old method : 0.0010402202606201172 time for calcul the mask position with numpy : 0.00596928596496582 nb_pixel_total : 2137 time to create 1 rle with old method : 0.002341747283935547 time for calcul the mask position with numpy : 0.005967140197753906 nb_pixel_total : 24 time to create 1 rle with old method : 8.916854858398438e-05 create new chi : 0.8278625011444092 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.0013110637664794922 batch 1 Loaded 68 chid ids of type : 4230 Number RLEs to save : 10268 TO DO : save crop sub photo not yet done ! save time : 0.6903414726257324 nb_obj : 77 nb_hashtags : 5 time to prepare the origin masks : 1.2748911380767822 time for calcul the mask position with numpy : 0.04904794692993164 nb_pixel_total : 1641672 time to create 1 rle with new method : 0.10360217094421387 time for calcul the mask position with numpy : 0.006208658218383789 nb_pixel_total : 876 time to create 1 rle with old method : 0.0009834766387939453 time for calcul the mask position with numpy : 0.005671024322509766 nb_pixel_total : 875 time to create 1 rle with old method : 0.0010025501251220703 time for calcul the mask position with numpy : 0.005918025970458984 nb_pixel_total : 1873 time to create 1 rle with old method : 0.0019257068634033203 time for calcul the mask position with numpy : 0.005869388580322266 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004010200500488281 time for calcul the mask position with numpy : 0.00574493408203125 nb_pixel_total : 929 time to create 1 rle with old method : 0.0010285377502441406 time for calcul the mask position with numpy : 0.009763479232788086 nb_pixel_total : 26 time to create 1 rle with old method : 8.845329284667969e-05 time for calcul the mask position with numpy : 0.009669780731201172 nb_pixel_total : 54 time to create 1 rle with old method : 9.799003601074219e-05 time for calcul the mask position with numpy : 0.010047674179077148 nb_pixel_total : 9 time to create 1 rle with old method : 6.389617919921875e-05 time for calcul the mask position with numpy : 0.00973963737487793 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004863739013671875 time for calcul the mask position with numpy : 0.011073827743530273 nb_pixel_total : 270 time to create 1 rle with old method : 0.000400543212890625 time for calcul the mask position with numpy : 0.010557413101196289 nb_pixel_total : 2796 time to create 1 rle with old method : 0.003194570541381836 time for calcul the mask position with numpy : 0.009644746780395508 nb_pixel_total : 458 time to create 1 rle with old method : 0.0005197525024414062 time for calcul the mask position with numpy : 0.0061969757080078125 nb_pixel_total : 49749 time to create 1 rle with old method : 0.05237603187561035 time for calcul the mask position with numpy : 0.006158351898193359 nb_pixel_total : 728 time to create 1 rle with old method : 0.0007808208465576172 time for calcul the mask position with numpy : 0.006066799163818359 nb_pixel_total : 229 time to create 1 rle with old method : 0.0002696514129638672 time for calcul the mask position with numpy : 0.005821943283081055 nb_pixel_total : 24 time to create 1 rle with old method : 6.175041198730469e-05 time for calcul the mask position with numpy : 0.005633831024169922 nb_pixel_total : 1002 time to create 1 rle with old method : 0.0011208057403564453 time for calcul the mask position with numpy : 0.0059430599212646484 nb_pixel_total : 2248 time to create 1 rle with old method : 0.0023903846740722656 time for calcul the mask position with numpy : 0.0058841705322265625 nb_pixel_total : 505 time to create 1 rle with old method : 0.0005943775177001953 time for calcul the mask position with numpy : 0.005800962448120117 nb_pixel_total : 376 time to create 1 rle with old method : 0.0004055500030517578 time for calcul the mask position with numpy : 0.005714893341064453 nb_pixel_total : 11915 time to create 1 rle with old method : 0.012314319610595703 time for calcul the mask position with numpy : 0.006000995635986328 nb_pixel_total : 154 time to create 1 rle with old method : 0.00019788742065429688 time for calcul the mask position with numpy : 0.006060123443603516 nb_pixel_total : 497 time to create 1 rle with old method : 0.0005733966827392578 time for calcul the mask position with numpy : 0.00699305534362793 nb_pixel_total : 150956 time to create 1 rle with new method : 0.0889744758605957 time for calcul the mask position with numpy : 0.006153583526611328 nb_pixel_total : 2069 time to create 1 rle with old method : 0.0022509098052978516 time for calcul the mask position with numpy : 0.005888938903808594 nb_pixel_total : 1921 time to create 1 rle with old method : 0.0021965503692626953 time for calcul the mask position with numpy : 0.006458759307861328 nb_pixel_total : 639 time to create 1 rle with old method : 0.0007219314575195312 time for calcul the mask position with numpy : 0.005699872970581055 nb_pixel_total : 819 time to create 1 rle with old method : 0.0008559226989746094 time for calcul the mask position with numpy : 0.005867719650268555 nb_pixel_total : 38 time to create 1 rle with old method : 7.963180541992188e-05 time for calcul the mask position with numpy : 0.0056231021881103516 nb_pixel_total : 335 time to create 1 rle with old method : 0.0003952980041503906 time for calcul the mask position with numpy : 0.005925655364990234 nb_pixel_total : 172 time to create 1 rle with old method : 0.00020051002502441406 time for calcul the mask position with numpy : 0.0058400630950927734 nb_pixel_total : 760 time to create 1 rle with old method : 0.0008714199066162109 time for calcul the mask position with numpy : 0.005669593811035156 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002734661102294922 time for calcul the mask position with numpy : 0.005797386169433594 nb_pixel_total : 11813 time to create 1 rle with old method : 0.012133121490478516 time for calcul the mask position with numpy : 0.0058481693267822266 nb_pixel_total : 297 time to create 1 rle with old method : 0.0003223419189453125 time for calcul the mask position with numpy : 0.005746126174926758 nb_pixel_total : 748 time to create 1 rle with old method : 0.0008628368377685547 time for calcul the mask position with numpy : 0.006028175354003906 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002281665802001953 time for calcul the mask position with numpy : 0.005927324295043945 nb_pixel_total : 9542 time to create 1 rle with old method : 0.010076761245727539 time for calcul the mask position with numpy : 0.005643606185913086 nb_pixel_total : 823 time to create 1 rle with old method : 0.0008497238159179688 time for calcul the mask position with numpy : 0.005904674530029297 nb_pixel_total : 363 time to create 1 rle with old method : 0.00048089027404785156 time for calcul the mask position with numpy : 0.005905628204345703 nb_pixel_total : 767 time to create 1 rle with old method : 0.0008730888366699219 time for calcul the mask position with numpy : 0.00583648681640625 nb_pixel_total : 3982 time to create 1 rle with old method : 0.004179716110229492 time for calcul the mask position with numpy : 0.0061528682708740234 nb_pixel_total : 304 time to create 1 rle with old method : 0.0003314018249511719 time for calcul the mask position with numpy : 0.0062885284423828125 nb_pixel_total : 609 time to create 1 rle with old method : 0.0006852149963378906 time for calcul the mask position with numpy : 0.0064544677734375 nb_pixel_total : 1991 time to create 1 rle with old method : 0.0022373199462890625 time for calcul the mask position with numpy : 0.0059032440185546875 nb_pixel_total : 179 time to create 1 rle with old method : 0.00021886825561523438 time for calcul the mask position with numpy : 0.0066509246826171875 nb_pixel_total : 164 time to create 1 rle with old method : 0.00024080276489257812 time for calcul the mask position with numpy : 0.005857706069946289 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002067089080810547 time for calcul the mask position with numpy : 0.005807161331176758 nb_pixel_total : 1415 time to create 1 rle with old method : 0.0015301704406738281 time for calcul the mask position with numpy : 0.005922794342041016 nb_pixel_total : 1341 time to create 1 rle with old method : 0.0015034675598144531 time for calcul the mask position with numpy : 0.005893230438232422 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004248619079589844 time for calcul the mask position with numpy : 0.005766868591308594 nb_pixel_total : 22 time to create 1 rle with old method : 8.130073547363281e-05 time for calcul the mask position with numpy : 0.005725383758544922 nb_pixel_total : 1611 time to create 1 rle with old method : 0.0017154216766357422 time for calcul the mask position with numpy : 0.005683183670043945 nb_pixel_total : 64 time to create 1 rle with old method : 8.726119995117188e-05 time for calcul the mask position with numpy : 0.005706787109375 nb_pixel_total : 727 time to create 1 rle with old method : 0.0007543563842773438 time for calcul the mask position with numpy : 0.006386756896972656 nb_pixel_total : 510 time to create 1 rle with old method : 0.0005433559417724609 time for calcul the mask position with numpy : 0.005926370620727539 nb_pixel_total : 397 time to create 1 rle with old method : 0.0004837512969970703 time for calcul the mask position with numpy : 0.00651860237121582 nb_pixel_total : 97 time to create 1 rle with old method : 0.00012755393981933594 time for calcul the mask position with numpy : 0.00592803955078125 nb_pixel_total : 231 time to create 1 rle with old method : 0.0002655982971191406 time for calcul the mask position with numpy : 0.006476879119873047 nb_pixel_total : 106216 time to create 1 rle with old method : 0.10978150367736816 time for calcul the mask position with numpy : 0.008280038833618164 nb_pixel_total : 447 time to create 1 rle with old method : 0.000560760498046875 time for calcul the mask position with numpy : 0.005873203277587891 nb_pixel_total : 83 time to create 1 rle with old method : 0.00011181831359863281 time for calcul the mask position with numpy : 0.006920814514160156 nb_pixel_total : 15 time to create 1 rle with old method : 4.100799560546875e-05 time for calcul the mask position with numpy : 0.007111310958862305 nb_pixel_total : 39896 time to create 1 rle with old method : 0.04121994972229004 time for calcul the mask position with numpy : 0.0060918331146240234 nb_pixel_total : 309 time to create 1 rle with old method : 0.00036072731018066406 time for calcul the mask position with numpy : 0.006256103515625 nb_pixel_total : 31 time to create 1 rle with old method : 5.888938903808594e-05 time for calcul the mask position with numpy : 0.005911827087402344 nb_pixel_total : 479 time to create 1 rle with old method : 0.0005433559417724609 time for calcul the mask position with numpy : 0.006151914596557617 nb_pixel_total : 1518 time to create 1 rle with old method : 0.0016758441925048828 time for calcul the mask position with numpy : 0.005774974822998047 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004036426544189453 time for calcul the mask position with numpy : 0.010314226150512695 nb_pixel_total : 2612 time to create 1 rle with old method : 0.0027179718017578125 time for calcul the mask position with numpy : 0.008196353912353516 nb_pixel_total : 77 time to create 1 rle with old method : 9.131431579589844e-05 time for calcul the mask position with numpy : 0.008132219314575195 nb_pixel_total : 83 time to create 1 rle with old method : 8.821487426757812e-05 time for calcul the mask position with numpy : 0.00820302963256836 nb_pixel_total : 696 time to create 1 rle with old method : 0.0006949901580810547 time for calcul the mask position with numpy : 0.008122682571411133 nb_pixel_total : 2856 time to create 1 rle with old method : 0.0028281211853027344 time for calcul the mask position with numpy : 0.008046627044677734 nb_pixel_total : 1066 time to create 1 rle with old method : 0.0010745525360107422 time for calcul the mask position with numpy : 0.008152484893798828 nb_pixel_total : 34 time to create 1 rle with old method : 9.012222290039062e-05 time for calcul the mask position with numpy : 0.00834345817565918 nb_pixel_total : 2199 time to create 1 rle with old method : 0.0024275779724121094 create new chi : 1.0610251426696777 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.0012333393096923828 batch 1 Loaded 78 chid ids of type : 4230 Number RLEs to save : 9311 TO DO : save crop sub photo not yet done ! save time : 0.6325812339782715 nb_obj : 78 nb_hashtags : 5 time to prepare the origin masks : 1.2011263370513916 time for calcul the mask position with numpy : 0.018475055694580078 nb_pixel_total : 1823057 time to create 1 rle with new method : 0.2266368865966797 time for calcul the mask position with numpy : 0.006147861480712891 nb_pixel_total : 39 time to create 1 rle with old method : 9.131431579589844e-05 time for calcul the mask position with numpy : 0.00602412223815918 nb_pixel_total : 963 time to create 1 rle with old method : 0.0010781288146972656 time for calcul the mask position with numpy : 0.005959033966064453 nb_pixel_total : 1792 time to create 1 rle with old method : 0.002002239227294922 time for calcul the mask position with numpy : 0.00610661506652832 nb_pixel_total : 255 time to create 1 rle with old method : 0.00042057037353515625 time for calcul the mask position with numpy : 0.006081581115722656 nb_pixel_total : 78 time to create 1 rle with old method : 0.00018215179443359375 time for calcul the mask position with numpy : 0.006211519241333008 nb_pixel_total : 308 time to create 1 rle with old method : 0.0003924369812011719 time for calcul the mask position with numpy : 0.005976676940917969 nb_pixel_total : 338 time to create 1 rle with old method : 0.00036406517028808594 time for calcul the mask position with numpy : 0.0061075687408447266 nb_pixel_total : 746 time to create 1 rle with old method : 0.0007932186126708984 time for calcul the mask position with numpy : 0.0061054229736328125 nb_pixel_total : 270 time to create 1 rle with old method : 0.00036716461181640625 time for calcul the mask position with numpy : 0.005928754806518555 nb_pixel_total : 2334 time to create 1 rle with old method : 0.002568960189819336 time for calcul the mask position with numpy : 0.005997180938720703 nb_pixel_total : 10 time to create 1 rle with old method : 3.719329833984375e-05 time for calcul the mask position with numpy : 0.006200313568115234 nb_pixel_total : 36014 time to create 1 rle with old method : 0.0391237735748291 time for calcul the mask position with numpy : 0.006304264068603516 nb_pixel_total : 1274 time to create 1 rle with old method : 0.001477956771850586 time for calcul the mask position with numpy : 0.0059931278228759766 nb_pixel_total : 237 time to create 1 rle with old method : 0.0002777576446533203 time for calcul the mask position with numpy : 0.006006956100463867 nb_pixel_total : 955 time to create 1 rle with old method : 0.0010457038879394531 time for calcul the mask position with numpy : 0.006512880325317383 nb_pixel_total : 776 time to create 1 rle with old method : 0.0008172988891601562 time for calcul the mask position with numpy : 0.005847454071044922 nb_pixel_total : 474 time to create 1 rle with old method : 0.0005269050598144531 time for calcul the mask position with numpy : 0.005907535552978516 nb_pixel_total : 153 time to create 1 rle with old method : 0.0001747608184814453 time for calcul the mask position with numpy : 0.005827903747558594 nb_pixel_total : 538 time to create 1 rle with old method : 0.0006151199340820312 time for calcul the mask position with numpy : 0.005843639373779297 nb_pixel_total : 2166 time to create 1 rle with old method : 0.0023102760314941406 time for calcul the mask position with numpy : 0.0058252811431884766 nb_pixel_total : 806 time to create 1 rle with old method : 0.0008690357208251953 time for calcul the mask position with numpy : 0.005986213684082031 nb_pixel_total : 690 time to create 1 rle with old method : 0.0007169246673583984 time for calcul the mask position with numpy : 0.005820751190185547 nb_pixel_total : 78 time to create 1 rle with old method : 0.0001277923583984375 time for calcul the mask position with numpy : 0.005888700485229492 nb_pixel_total : 806 time to create 1 rle with old method : 0.0008120536804199219 time for calcul the mask position with numpy : 0.007081747055053711 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005042552947998047 time for calcul the mask position with numpy : 0.00725865364074707 nb_pixel_total : 686 time to create 1 rle with old method : 0.0009603500366210938 time for calcul the mask position with numpy : 0.006017208099365234 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0014045238494873047 time for calcul the mask position with numpy : 0.0059661865234375 nb_pixel_total : 92 time to create 1 rle with old method : 0.00012421607971191406 time for calcul the mask position with numpy : 0.0057294368743896484 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003197193145751953 time for calcul the mask position with numpy : 0.006658077239990234 nb_pixel_total : 12470 time to create 1 rle with old method : 0.012865066528320312 time for calcul the mask position with numpy : 0.006025791168212891 nb_pixel_total : 498 time to create 1 rle with old method : 0.0005829334259033203 time for calcul the mask position with numpy : 0.005606174468994141 nb_pixel_total : 1337 time to create 1 rle with old method : 0.0015769004821777344 time for calcul the mask position with numpy : 0.0059778690338134766 nb_pixel_total : 7867 time to create 1 rle with old method : 0.008544445037841797 time for calcul the mask position with numpy : 0.00608372688293457 nb_pixel_total : 854 time to create 1 rle with old method : 0.0009069442749023438 time for calcul the mask position with numpy : 0.006293535232543945 nb_pixel_total : 445 time to create 1 rle with old method : 0.0005259513854980469 time for calcul the mask position with numpy : 0.006042003631591797 nb_pixel_total : 4255 time to create 1 rle with old method : 0.0044934749603271484 time for calcul the mask position with numpy : 0.006129264831542969 nb_pixel_total : 909 time to create 1 rle with old method : 0.0010325908660888672 time for calcul the mask position with numpy : 0.0059146881103515625 nb_pixel_total : 1247 time to create 1 rle with old method : 0.0013973712921142578 time for calcul the mask position with numpy : 0.0064563751220703125 nb_pixel_total : 595 time to create 1 rle with old method : 0.0007319450378417969 time for calcul the mask position with numpy : 0.00585627555847168 nb_pixel_total : 171 time to create 1 rle with old method : 0.00021767616271972656 time for calcul the mask position with numpy : 0.005938529968261719 nb_pixel_total : 213 time to create 1 rle with old method : 0.0002644062042236328 time for calcul the mask position with numpy : 0.006036043167114258 nb_pixel_total : 465 time to create 1 rle with old method : 0.0005614757537841797 time for calcul the mask position with numpy : 0.005999088287353516 nb_pixel_total : 1357 time to create 1 rle with old method : 0.0015413761138916016 time for calcul the mask position with numpy : 0.006064176559448242 nb_pixel_total : 1193 time to create 1 rle with old method : 0.0012805461883544922 time for calcul the mask position with numpy : 0.005957365036010742 nb_pixel_total : 240 time to create 1 rle with old method : 0.00028896331787109375 time for calcul the mask position with numpy : 0.005791664123535156 nb_pixel_total : 421 time to create 1 rle with old method : 0.0004584789276123047 time for calcul the mask position with numpy : 0.00593113899230957 nb_pixel_total : 1567 time to create 1 rle with old method : 0.001745462417602539 time for calcul the mask position with numpy : 0.006078004837036133 nb_pixel_total : 63 time to create 1 rle with old method : 9.632110595703125e-05 time for calcul the mask position with numpy : 0.005762815475463867 nb_pixel_total : 728 time to create 1 rle with old method : 0.0007700920104980469 time for calcul the mask position with numpy : 0.005921363830566406 nb_pixel_total : 479 time to create 1 rle with old method : 0.0005216598510742188 time for calcul the mask position with numpy : 0.006033897399902344 nb_pixel_total : 1895 time to create 1 rle with old method : 0.002092123031616211 time for calcul the mask position with numpy : 0.00593113899230957 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001366138458251953 time for calcul the mask position with numpy : 0.005899190902709961 nb_pixel_total : 401 time to create 1 rle with old method : 0.00041985511779785156 time for calcul the mask position with numpy : 0.0060672760009765625 nb_pixel_total : 245 time to create 1 rle with old method : 0.00028705596923828125 time for calcul the mask position with numpy : 0.005974769592285156 nb_pixel_total : 456 time to create 1 rle with old method : 0.0005505084991455078 time for calcul the mask position with numpy : 0.006559610366821289 nb_pixel_total : 105362 time to create 1 rle with old method : 0.1066598892211914 time for calcul the mask position with numpy : 0.005613803863525391 nb_pixel_total : 157 time to create 1 rle with old method : 0.00021076202392578125 time for calcul the mask position with numpy : 0.005713462829589844 nb_pixel_total : 39519 time to create 1 rle with old method : 0.03862357139587402 time for calcul the mask position with numpy : 0.005617618560791016 nb_pixel_total : 172 time to create 1 rle with old method : 0.00020742416381835938 time for calcul the mask position with numpy : 0.005524158477783203 nb_pixel_total : 309 time to create 1 rle with old method : 0.0003669261932373047 time for calcul the mask position with numpy : 0.005783796310424805 nb_pixel_total : 519 time to create 1 rle with old method : 0.0005881786346435547 time for calcul the mask position with numpy : 0.0056722164154052734 nb_pixel_total : 47 time to create 1 rle with old method : 7.724761962890625e-05 time for calcul the mask position with numpy : 0.005445241928100586 nb_pixel_total : 294 time to create 1 rle with old method : 0.0003211498260498047 time for calcul the mask position with numpy : 0.005488157272338867 nb_pixel_total : 1330 time to create 1 rle with old method : 0.001325845718383789 time for calcul the mask position with numpy : 0.0055506229400634766 nb_pixel_total : 35 time to create 1 rle with old method : 7.796287536621094e-05 time for calcul the mask position with numpy : 0.005429267883300781 nb_pixel_total : 288 time to create 1 rle with old method : 0.00031375885009765625 time for calcul the mask position with numpy : 0.005568504333496094 nb_pixel_total : 225 time to create 1 rle with old method : 0.00037741661071777344 time for calcul the mask position with numpy : 0.005669355392456055 nb_pixel_total : 225 time to create 1 rle with old method : 0.00029850006103515625 time for calcul the mask position with numpy : 0.005585670471191406 nb_pixel_total : 2595 time to create 1 rle with old method : 0.0025577545166015625 time for calcul the mask position with numpy : 0.005475759506225586 nb_pixel_total : 87 time to create 1 rle with old method : 0.00011134147644042969 time for calcul the mask position with numpy : 0.00545811653137207 nb_pixel_total : 171 time to create 1 rle with old method : 0.00019669532775878906 time for calcul the mask position with numpy : 0.005446910858154297 nb_pixel_total : 634 time to create 1 rle with old method : 0.0007305145263671875 time for calcul the mask position with numpy : 0.005478382110595703 nb_pixel_total : 12 time to create 1 rle with old method : 4.076957702636719e-05 time for calcul the mask position with numpy : 0.0055866241455078125 nb_pixel_total : 80 time to create 1 rle with old method : 9.679794311523438e-05 time for calcul the mask position with numpy : 0.005558967590332031 nb_pixel_total : 62 time to create 1 rle with old method : 8.320808410644531e-05 time for calcul the mask position with numpy : 0.005461215972900391 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0010650157928466797 time for calcul the mask position with numpy : 0.005790233612060547 nb_pixel_total : 2074 time to create 1 rle with old method : 0.002127408981323242 time for calcul the mask position with numpy : 0.005980968475341797 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001049041748046875 create new chi : 0.9812941551208496 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.0020062923431396484 batch 1 Loaded 79 chid ids of type : 4230 Number RLEs to save : 8587 TO DO : save crop sub photo not yet done ! save time : 0.5978803634643555 map_output_result : {1333957964: (0.0, 'Should be the crop_list due to order', 0.0), 1333957943: (0.0, 'Should be the crop_list due to order', 0.0), 1333957941: (0.0, 'Should be the crop_list due to order', 0.0), 1333957922: (0.0, 'Should be the crop_list due to order', 0.0), 1333957864: (0.0, 'Should be the crop_list due to order', 0.0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1333957964, 1333957943, 1333957941, 1333957922, 1333957864] Looping around the photos to save general results len do output : 5 /1333957964.Didn't retrieve data . /1333957943.Didn't retrieve data . /1333957941.Didn't retrieve data . /1333957922.Didn't retrieve data . /1333957864.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 ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957964', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957943', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957941', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957922', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957864', None, None, None, None, None, '2538732') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.013874053955078125 save_final save missing photos in datou_result : time spend for datou_step_exec : 16.056960344314575 time spend to save output : 0.014185905456542969 total time spend for step 4 : 16.071146249771118 step5:crop_condition Mon Feb 3 00:21:22 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 : 4230 Loading chi in step crop for list_pids : 5 ! batch 1 Loaded 367 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 107 About to insert : list_path_to_insert length 107 new photo from crops ! About to upload 107 photos upload in portfolio : 4869462 init cache_photo without model_param we have 107 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738538485_810777 we have uploaded 107 photos in the portfolio 4869462 time of upload the photos Elapsed time : 36.893550872802734 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} 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 ! map_result returned by crop_photo_return_map_crop : length : 48 About to insert : list_path_to_insert length 48 new photo from crops ! About to upload 48 photos upload in portfolio : 4869462 init cache_photo without model_param we have 48 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738538523_810777 we have uploaded 48 photos in the portfolio 4869462 time of upload the photos Elapsed time : 19.32095432281494 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 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 : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738538542_810777 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.655221700668335 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 24 About to insert : list_path_to_insert length 24 new photo from crops ! About to upload 24 photos upload in portfolio : 4869462 init cache_photo without model_param we have 24 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738538543_810777 we have uploaded 24 photos in the portfolio 4869462 time of upload the photos Elapsed time : 8.23013186454773 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 55 About to insert : list_path_to_insert length 55 new photo from crops ! About to upload 55 photos upload in portfolio : 4869462 init cache_photo without model_param we have 55 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738538553_810777 we have uploaded 55 photos in the portfolio 4869462 time of upload the photos Elapsed time : 14.345284700393677 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1333957964, 1333957943, 1333957941, 1333957922, 1333957864] Looping around the photos to save general results len do output : 236 /1334035567Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035580Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035582Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035583Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035584Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035585Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035586Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035587Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035588Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035589Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035608Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035620Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035621Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035622Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035623Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035624Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035625Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035626Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035627Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035628Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035629Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035630Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035631Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035632Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035633Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035634Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035635Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035636Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035637Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035638Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035639Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035640Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035641Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035642Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035643Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035644Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035645Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035646Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035647Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035648Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035649Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035650Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035651Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334035999Didn'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 ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957964', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957943', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957941', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957922', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957864', None, None, None, None, None, '2538732') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 713 time used for this insertion : 0.04494905471801758 save_final save missing photos in datou_result : time spend for datou_step_exec : 84.76934003829956 time spend to save output : 0.059601545333862305 total time spend for step 5 : 84.82894158363342 step6:thcl Mon Feb 3 00:22:47 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 Beginning of datou step Thcl ! we are using the classfication for only one thcl 3237 time to import caffe and check if the image exist : 0.015773534774780273 time to convert the images to numpy array : 0.08155083656311035 time to import caffe and check if the image exist : 0.01454472541809082 time to convert the images to numpy array : 0.08258223533630371 time to import caffe and check if the image exist : 0.024227619171142578 time to convert the images to numpy array : 0.0760202407836914 time to import caffe and check if the image exist : 0.012848138809204102 time to convert the images to numpy array : 0.08960509300231934 time to import caffe and check if the image exist : 0.01750969886779785 time to convert the images to numpy array : 0.08585810661315918 time to import caffe and check if the image exist : 0.014480829238891602 time to convert the images to numpy array : 0.08750224113464355 time to import caffe and check if the image exist : 0.014695167541503906 time to convert the images to numpy array : 0.09083390235900879 time to import caffe and check if the image exist : 0.02344369888305664 time to convert the images to numpy array : 0.08365535736083984 time to import caffe and check if the image exist : 0.024847984313964844 time to convert the images to numpy array : 0.08371877670288086 time to import caffe and check if the image exist : 0.022329330444335938 time to convert the images to numpy array : 0.0857856273651123 total time to convert the images to numpy array : 0.3385326862335205 list photo_ids error: [] list photo_ids correct : [1334035665, 1334035666, 1334035667, 1334035668, 1334035669, 1334035670, 1334035671, 1334035672, 1334035673, 1334035674, 1334035675, 1334035678, 1334035680, 1334035682, 1334035684, 1334035686, 1334035688, 1334035690, 1334035691, 1334035693, 1334035695, 1334035697, 1334035699, 1334035701, 1334035980, 1334035981, 1334035982, 1334035983, 1334035984, 1334035985, 1334035986, 1334035987, 1334035988, 1334035989, 1334035990, 1334035991, 1334035992, 1334035993, 1334035994, 1334035995, 1334035996, 1334035997, 1334035998, 1334035999, 1334035703, 1334035704, 1334035706, 1334035708, 1334035710, 1334035712, 1334035714, 1334035716, 1334035718, 1334035720, 1334035722, 1334035724, 1334035727, 1334035729, 1334035731, 1334035733, 1334035735, 1334035737, 1334035740, 1334035743, 1334035744, 1334035746, 1334035748, 1334035750, 1334035567, 1334035569, 1334035570, 1334035571, 1334035572, 1334035573, 1334035574, 1334035575, 1334035576, 1334035577, 1334035578, 1334035579, 1334035580, 1334035581, 1334035582, 1334035583, 1334035584, 1334035585, 1334035586, 1334035587, 1334035588, 1334035589, 1334035590, 1334035591, 1334035641, 1334035642, 1334035643, 1334035644, 1334035645, 1334035646, 1334035647, 1334035648, 1334035649, 1334035650, 1334035651, 1334035652, 1334035653, 1334035654, 1334035655, 1334035656, 1334035657, 1334035658, 1334035659, 1334035660, 1334035661, 1334035662, 1334035663, 1334035664, 1334035955, 1334035956, 1334035957, 1334035958, 1334035959, 1334035960, 1334035961, 1334035962, 1334035963, 1334035964, 1334035965, 1334035966, 1334035967, 1334035968, 1334035969, 1334035970, 1334035971, 1334035972, 1334035973, 1334035974, 1334035975, 1334035976, 1334035977, 1334035979, 1334035752, 1334035755, 1334035756, 1334035758, 1334035760, 1334035762, 1334035764, 1334035766, 1334035768, 1334035769, 1334035771, 1334035791, 1334035793, 1334035860, 1334035861, 1334035862, 1334035863, 1334035864, 1334035865, 1334035866, 1334035867, 1334035868, 1334035869, 1334035870, 1334035617, 1334035618, 1334035619, 1334035620, 1334035621, 1334035622, 1334035623, 1334035624, 1334035625, 1334035626, 1334035627, 1334035628, 1334035629, 1334035630, 1334035631, 1334035632, 1334035633, 1334035634, 1334035635, 1334035636, 1334035637, 1334035638, 1334035639, 1334035640, 1334035592, 1334035593, 1334035595, 1334035596, 1334035597, 1334035598, 1334035599, 1334035600, 1334035601, 1334035602, 1334035603, 1334035604, 1334035605, 1334035606, 1334035607, 1334035608, 1334035609, 1334035610, 1334035611, 1334035612, 1334035613, 1334035614, 1334035615, 1334035616, 1334035871, 1334035872, 1334035873, 1334035874, 1334035875, 1334035876, 1334035877, 1334035878, 1334035879, 1334035880, 1334035881, 1334035882, 1334035883, 1334035944, 1334035945, 1334035946, 1334035947, 1334035948, 1334035949, 1334035950, 1334035951, 1334035952, 1334035953, 1334035954] number of photos to traite : 236 try to delete the photos incorrect in DB tagging for thcl : 3237 To do loadFromThcl(), then load ParamDescType : thcl3237 thcls : [{'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'}] thcl {'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'} Update svm_hashtag_type_desc : 5561 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) To loadFromThcl() : net_5561 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3354 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_rubbia_refus_2500 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_rubbia_refus_2500 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_rubbia_refus_2500 /data/models_weight/learn_rubbia_refus_2500/caffemodel size_local : 94358479 size in s3 : 94358479 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:16 caffemodel already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:15 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:09:52 mean.npy already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/synset_words.txt size_local : 334 size in s3 : 334 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:10:06 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /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/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt caffemodel_filename : /data/models_weight/learn_rubbia_refus_2500/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3135 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.0504021644592285 time used to do the prediction : 1.2421691417694092 save descriptor for thcl : 3237 time to traite the descriptors : 1.2397279739379883 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1334035665 To insert : 1334035666 To insert : 1334035667 To insert : 1334035668 To insert : 1334035669 To insert : 1334035670 To insert : 1334035671 To insert : 1334035672 To insert : 1334035673 To insert : 1334035674 To insert : 1334035675 To insert : 1334035678 To insert : 1334035680 To insert : 1334035682 To insert : 1334035684 To insert : 1334035686 To insert : 1334035688 To insert : 1334035690 To insert : 1334035691 To insert : 1334035693 To insert : 1334035695 To insert : 1334035697 To insert : 1334035699 To insert : 1334035701 To insert : 1334035980 To insert : 1334035981 To insert : 1334035982 To insert : 1334035983 To insert : 1334035984 To insert : 1334035985 To insert : 1334035986 To insert : 1334035987 To insert : 1334035988 To insert : 1334035989 To insert : 1334035990 To insert : 1334035991 To insert : 1334035992 To insert : 1334035993 To insert : 1334035994 To insert : 1334035995 To insert : 1334035996 To insert : 1334035997 To insert : 1334035998 To insert : 1334035999 To insert : 1334035703 To insert : 1334035704 To insert : 1334035706 To insert : 1334035708 To insert : 1334035710 To insert : 1334035712 To insert : 1334035714 To insert : 1334035716 To insert : 1334035718 To insert : 1334035720 To insert : 1334035722 To insert : 1334035724 To insert : 1334035727 To insert : 1334035729 To insert : 1334035731 To insert : 1334035733 To insert : 1334035735 To insert : 1334035737 To insert : 1334035740 To insert : 1334035743 To insert : 1334035744 To insert : 1334035746 To insert : 1334035748 To insert : 1334035750 To insert : 1334035567 To insert : 1334035569 To insert : 1334035570 To insert : 1334035571 To insert : 1334035572 To insert : 1334035573 To insert : 1334035574 To insert : 1334035575 To insert : 1334035576 To insert : 1334035577 To insert : 1334035578 To insert : 1334035579 To insert : 1334035580 To insert : 1334035581 To insert : 1334035582 To insert : 1334035583 To insert : 1334035584 To insert : 1334035585 To insert : 1334035586 To insert : 1334035587 To insert : 1334035588 To insert : 1334035589 To insert : 1334035590 To insert : 1334035591 To insert : 1334035641 To insert : 1334035642 To insert : 1334035643 To insert : 1334035644 To insert : 1334035645 To insert : 1334035646 To insert : 1334035647 To insert : 1334035648 To insert : 1334035649 To insert : 1334035650 To insert : 1334035651 To insert : 1334035652 To insert : 1334035653 To insert : 1334035654 To insert : 1334035655 To insert : 1334035656 To insert : 1334035657 To insert : 1334035658 To insert : 1334035659 To insert : 1334035660 To insert : 1334035661 To insert : 1334035662 To insert : 1334035663 To insert : 1334035664 To insert : 1334035955 To insert : 1334035956 To insert : 1334035957 To insert : 1334035958 To insert : 1334035959 To insert : 1334035960 To insert : 1334035961 To insert : 1334035962 To insert : 1334035963 To insert : 1334035964 To insert : 1334035965 To insert : 1334035966 To insert : 1334035967 To insert : 1334035968 To insert : 1334035969 To insert : 1334035970 To insert : 1334035971 To insert : 1334035972 To insert : 1334035973 To insert : 1334035974 To insert : 1334035975 To insert : 1334035976 To insert : 1334035977 To insert : 1334035979 To insert : 1334035752 To insert : 1334035755 To insert : 1334035756 To insert : 1334035758 To insert : 1334035760 To insert : 1334035762 To insert : 1334035764 To insert : 1334035766 To insert : 1334035768 To insert : 1334035769 To insert : 1334035771 To insert : 1334035791 To insert : 1334035793 To insert : 1334035860 To insert : 1334035861 To insert : 1334035862 To insert : 1334035863 To insert : 1334035864 To insert : 1334035865 To insert : 1334035866 To insert : 1334035867 To insert : 1334035868 To insert : 1334035869 To insert : 1334035870 To insert : 1334035617 To insert : 1334035618 To insert : 1334035619 To insert : 1334035620 To insert : 1334035621 To insert : 1334035622 To insert : 1334035623 To insert : 1334035624 To insert : 1334035625 To insert : 1334035626 To insert : 1334035627 To insert : 1334035628 To insert : 1334035629 To insert : 1334035630 To insert : 1334035631 To insert : 1334035632 To insert : 1334035633 To insert : 1334035634 To insert : 1334035635 To insert : 1334035636 To insert : 1334035637 To insert : 1334035638 To insert : 1334035639 To insert : 1334035640 To insert : 1334035592 To insert : 1334035593 To insert : 1334035595 To insert : 1334035596 To insert : 1334035597 To insert : 1334035598 To insert : 1334035599 To insert : 1334035600 To insert : 1334035601 To insert : 1334035602 To insert : 1334035603 To insert : 1334035604 To insert : 1334035605 To insert : 1334035606 To insert : 1334035607 To insert : 1334035608 To insert : 1334035609 To insert : 1334035610 To insert : 1334035611 To insert : 1334035612 To insert : 1334035613 To insert : 1334035614 To insert : 1334035615 To insert : 1334035616 To insert : 1334035871 To insert : 1334035872 To insert : 1334035873 To insert : 1334035874 To insert : 1334035875 To insert : 1334035876 To insert : 1334035877 To insert : 1334035878 To insert : 1334035879 To insert : 1334035880 To insert : 1334035881 To insert : 1334035882 To insert : 1334035883 To insert : 1334035944 To insert : 1334035945 To insert : 1334035946 To insert : 1334035947 To insert : 1334035948 To insert : 1334035949 To insert : 1334035950 To insert : 1334035951 To insert : 1334035952 To insert : 1334035953 To insert : 1334035954 time to insert the descriptors : 40.304343461990356 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos SAVE THCL : begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 360 time used for this insertion : 0.029851675033569336 save missing photos in datou_result : time spend for datou_step_exec : 47.94598436355591 time spend to save output : 0.08421874046325684 total time spend for step 6 : 48.030203104019165 step7:ventilate_hashtags_in_portfolio Mon Feb 3 00:23:35 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 20162701 get user id for portfolio 20162701 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`=20162701 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_fonce','refus','mal_croppe','metal','autre','environnement','Tetrapak','PET_clair','Film_plastique','Carton','papier','PET_fonce','Papier','pet_clair','flou','carton','pehd','PEHD')) AND mptpi.`min_score`=0.6 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`=20162701 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_fonce','refus','mal_croppe','metal','autre','environnement','Tetrapak','PET_clair','Film_plastique','Carton','papier','PET_fonce','Papier','pet_clair','flou','carton','pehd','PEHD')) AND mptpi.`min_score`=0.6 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") 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`=20162701 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_fonce','refus','mal_croppe','metal','autre','environnement','Tetrapak','PET_clair','Film_plastique','Carton','papier','PET_fonce','Papier','pet_clair','flou','carton','pehd','PEHD')) AND mptpi.`min_score`=0.6 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`=20162701 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('pet_fonce','refus','mal_croppe','metal','autre','environnement','Tetrapak','PET_clair','Film_plastique','Carton','papier','PET_fonce','Papier','pet_clair','flou','carton','pehd','PEHD')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20163000,20162990,20162991,20162992,20162993,20162994,20162995,20163002,20162997,20163004,20163001,20163003,20163006?tags=pet_fonce,refus,mal_croppe,metal,autre,environnement,tetrapak,pet_clair,film_plastique,carton,papier,flou,pehd&datou_id_consolidate=4235&port_consolidate=20162701 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1333957964, 1333957943, 1333957941, 1333957922, 1333957864] Looping around the photos to save general results len do output : 1 /20162701. 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 ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957964', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957943', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957941', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957922', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957864', None, None, None, None, None, '2538732') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.013710260391235352 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.17624568939209 time spend to save output : 0.01398158073425293 total time spend for step 7 : 4.190227270126343 step8:final Mon Feb 3 00:23:39 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : {1333957964: ('0.21157504534527558',), 1333957943: ('0.21157504534527558',), 1333957941: ('0.21157504534527558',), 1333957922: ('0.21157504534527558',), 1333957864: ('0.21157504534527558',)} new output for save of step final : {1333957964: ('0.21157504534527558',), 1333957943: ('0.21157504534527558',), 1333957941: ('0.21157504534527558',), 1333957922: ('0.21157504534527558',), 1333957864: ('0.21157504534527558',)} [1333957964, 1333957943, 1333957941, 1333957922, 1333957864] Looping around the photos to save general results len do output : 5 /1333957964.Didn't retrieve data . /1333957943.Didn't retrieve data . /1333957941.Didn't retrieve data . /1333957922.Didn't retrieve data . /1333957864.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 ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957964', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957943', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957941', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957922', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957864', None, None, None, None, None, '2538732') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.012905359268188477 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.13819670677185059 time spend to save output : 0.013312101364135742 total time spend for step 8 : 0.15150880813598633 step9:velours_tree Mon Feb 3 00:23:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure list_portfolios : 20163000,20162990,20162991,20162992,20162993,20162994,20162995,20163002,20162997,20163004,20163001,20163003,20163006 photo desc type : 5561 - Retrieving photos to tag... query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20163000 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162990 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162991 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162992 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162993 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162994 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162995 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20163002 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162997 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20163004 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20163001 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20163003 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20163006 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 236 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [1 0 4 0 0 0 1 1 5 4 1 0 2 1 1 1 1 1 2 0 1 4 0 0 4 0 0 0 1 4 5 0 2 4 1 1 2 2 0 4 0 0 1 0 0 4 4 0 0 1 5 4 1 2 1 2 2 0 0 4 1 1 0 0 0 1 1 4 5 0 4 0 0 4 2 1 1 2 2 0 4 0 2 0 0 0 4 4 1 0 1 1 4 5 4 1 2 4 1 1 1 1 2 2 0 1 0 2 3 3 3 0 2 4 2 0 0 3 3 0 0 1 2 4 0 4 0 2 0 1 2 4 2 2 0 0 3 3 0 4 0 1 1 0 0 3 0 0 1 2 2 2 0 0 0 0 0 4 4 1 0 4 0 2 4 1 1 4 0 0 2 4 1 2 0 0 0 2 4 0 2 3 0 1 1 1 0 2 2 0 2 1 0 2 3 1 1 2 2 0 2 3 3 1 1 1 1 1 2 0 2 2 1 2 1 1 1 2 0 2 1 2 2 2 1 1 1 0 1 2 2 0 2 1 2 2] Elapsed time: 0.03358316421508789 graph_id used : 75539 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20163000,20162990,20162991,20162992,20162993,20162994,20162995,20163002,20162997,20163004,20163001,20163003,20163006?tags=pet_fonce,refus,mal_croppe,metal,autre,environnement,tetrapak,pet_clair,film_plastique,carton,papier,flou,pehd&datou_id_consolidate=4235&port_consolidate=20162701&tree_id=75539 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1333957964, 1333957943, 1333957941, 1333957922, 1333957864] Looping around the photos to save general results len do output : 1 /20162701Didn'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 ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957964', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957943', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957941', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957922', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957864', None, None, None, None, None, '2538732') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.012140035629272461 save_final save missing photos in datou_result : time spend for datou_step_exec : 22.957923412322998 time spend to save output : 0.012357473373413086 total time spend for step 9 : 22.97028088569641 step10:send_mail_cod Mon Feb 3 00:24:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 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 2 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_Qualipapia_P20162701_03-02-2025_00_24_03.pdf 20162982 imagette201629821738538643 20162972 imagette201629721738538643 20162973 imagette201629731738538643 20162974 change filename to text .change filename to text .imagette201629741738538643 20162975 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette201629751738538643 20162977 imagette201629771738538644 20162984 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette201629841738538644 20162979 imagette201629791738538645 20162986 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette201629861738538645 20162983 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette201629831738538646 20162985 imagette201629851738538647 20162988 imagette201629881738538647 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20162701 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20163000,20162990,20162991,20162992,20162993,20162994,20162995,20163002,20162997,20163004,20163001,20163003,20163006?tags=pet_fonce,refus,mal_croppe,metal,autre,environnement,tetrapak,pet_clair,film_plastique,carton,papier,flou,pehd&datou_id_consolidate=4235&port_consolidate=20162701&tree_id=75539 your option no_mail is active, we will not send the real mail to your client args[1333957964] : ((1333957964, -7.736959908026764, 492609224), (1333957964, -0.3354345091902157, 496442774), '0.21157504534527558') We are sending mail with results at cod@fotonower.com args[1333957943] : ((1333957943, -7.737405985906943, 492609224), (1333957943, -0.3156755808491856, 496442774), '0.21157504534527558') We are sending mail with results at cod@fotonower.com args[1333957941] : ((1333957941, -7.741401548510373, 492609224), (1333957941, -0.33239996511471703, 496442774), '0.21157504534527558') We are sending mail with results at cod@fotonower.com args[1333957922] : ((1333957922, -7.732699181677737, 492609224), (1333957922, -0.3347130988463866, 496442774), '0.21157504534527558') We are sending mail with results at cod@fotonower.com args[1333957864] : ((1333957864, -7.722290510243807, 492609224), (1333957864, -0.371431627922687, 496442774), '0.21157504534527558') We are sending mail with results at cod@fotonower.com refus_total : 0.21157504534527558 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=20162701 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20162701_03-02-2025_00_24_03.pdf results_Qualipapia_P20162701_03-02-2025_00_24_03.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20162701_03-02-2025_00_24_03.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4234','20162701','results_Qualipapia_P20162701_03-02-2025_00_24_03.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20162701_03-02-2025_00_24_03.pdf','pdf','','0.19','0.21157504534527558') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1333957964, 1333957943, 1333957941, 1333957922, 1333957864] 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 ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957964', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957943', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957941', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957922', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957864', None, None, None, None, None, '2538732') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012506246566772461 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.343153476715088 time spend to save output : 0.01271820068359375 total time spend for step 10 : 5.355871677398682 step11:split_time_score Mon Feb 3 00:24:08 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 begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3442, 'mtr_user_id': 31, 'name': 'classifieur_2camions_valcor_021122_v1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'deux_camions,camion_droite,camion_gauche,pas_de_camion', 'svm_portfolios_learning': '7659379,7659034,7657685,7657114', 'photo_hashtag_type': 4458, 'photo_desc_type': 5723, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107760533,2107760534,2107760535,2107760536'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('15', 5),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 02022025 20162701 Nombre de photos uploadées : 5 / 23040 (0%) 02022025 20162701 Nombre de photos taguées (types de déchets): 5 / 5 (100%) 02022025 20162701 Nombre de photos taguées (volume) : 0 / 5 (0%) elapsed_time : load_data_split_time_score 3.0994415283203125e-06 elapsed_time : order_list_meta_photo_and_scores 8.344650268554688e-06 ????? elapsed_time : fill_and_build_computed_from_old_data 0.0003349781036376953 elapsed_time : insert_dashboard_record_day_entry 0.022506237030029297 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 = 20162644 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162662 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162664 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162665 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162666 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162667 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162668 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162669 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162670 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162671 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162672 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162673 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162674 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162675 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162676 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162677 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162678 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162679 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162680 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162681 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162682 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162683 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162684 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162685 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162686 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162687 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162688 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162689 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162690 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162691 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162692 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162693 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162694 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162695 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162696 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162697 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162698 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162699 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162700 order by id desc limit 1 Qualite : 0.21157504534527558 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20162701_03-02-2025_00_24_03.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162701 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! 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 ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20162701 AND mptpi.`type`=4230 To do Qualite : 0.19050968855918649 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20162702_03-02-2025_00_18_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162702 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! 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 ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20162702 AND mptpi.`type`=4230 To do Qualite : 0.21383786583408712 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20162703_03-02-2025_00_16_36.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162703 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! 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 ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20162703 AND mptpi.`type`=4230 To do Qualite : 0.16928211545032903 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20162704_03-02-2025_00_10_23.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20162704 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 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! 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 ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 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`=20162704 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'02022025': {'nb_upload': 5, 'nb_taggue_class': 5, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1333957964, 1333957943, 1333957941, 1333957922, 1333957864] Looping around the photos to save general results len do output : 1 /20162701Didn'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 ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957964', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957943', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957941', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957922', None, None, None, None, None, '2538732') ('4234', None, None, None, None, None, None, None, '2538732') ('4234', '20162701', '1333957864', None, None, None, None, None, '2538732') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.013746500015258789 save_final save missing photos in datou_result : time spend for datou_step_exec : 29.12151288986206 time spend to save output : 0.013936758041381836 total time spend for step 11 : 29.135449647903442 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 51.93user 35.81system 4:13.36elapsed 34%CPU (0avgtext+0avgdata 2431668maxresident)k 4296inputs+19200outputs (13major+2329794minor)pagefaults 0swaps