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 : 1634302 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 : ['2626368'] with mtr_portfolio_ids : ['20948718'] and first list_photo_ids : [] new path : /proc/1634302/ 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 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.4853792190551758 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 Sat Mar 1 11:20:30 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 : 5304 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-01 11:20:33.254021: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-01 11:20:33.261740: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-01 11:20:33.263240: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f2b28000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-01 11:20:33.263290: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-01 11:20:33.265645: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-01 11:20:33.434840: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3876a120 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-01 11:20:33.434889: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-01 11:20:33.435929: 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 2025-03-01 11:20:33.436525: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-01 11:20:33.439813: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-01 11:20:33.442723: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-01 11:20:33.443391: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-01 11:20:33.445530: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-01 11:20:33.446546: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-01 11:20:33.453316: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-01 11:20:33.454720: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-01 11:20:33.454820: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-01 11:20:33.455609: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-01 11:20:33.455636: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-01 11:20:33.455649: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-01 11:20:33.456967: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4701 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. 2025-03-01 11:20:33.731096: 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 2025-03-01 11:20:33.731195: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-01 11:20:33.731218: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-01 11:20:33.731238: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-01 11:20:33.731258: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-01 11:20:33.731277: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-01 11:20:33.731296: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-01 11:20:33.731316: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-01 11:20:33.732489: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-01 11:20:33.733612: 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 2025-03-01 11:20:33.733648: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-01 11:20:33.733668: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-01 11:20:33.733687: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-01 11:20:33.733705: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-01 11:20:33.733724: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-01 11:20:33.733743: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-01 11:20:33.733762: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-01 11:20:33.734946: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-01 11:20:33.734978: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-01 11:20:33.734989: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-01 11:20:33.734999: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-01 11:20:33.736219: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4701 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 : [] 2025-03-01 11:20:41.175740: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-01 11:20:41.352957: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-01 11:20:42.594964: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:42.595641: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:42.596300: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.406268: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-03-01 11:20:43.476038: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.476180: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-01 11:20:43.477627: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.477668: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-01 11:20:43.485800: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.485881: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-03-01 11:20:43.486964: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.486991: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB 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. 2025-03-01 11:20:43.519605: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.519771: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 19.91MiB 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. 2025-03-01 11:20:43.519831: 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. 2025-03-01 11:20:43.521708: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.521756: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB 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. 2025-03-01 11:20:43.523223: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.523275: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 16.00MiB 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. 2025-03-01 11:20:43.530890: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.530974: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB 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. 2025-03-01 11:20:43.532023: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.532047: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB 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. 2025-03-01 11:20:43.532882: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.532903: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB 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. 2025-03-01 11:20:43.533813: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.543476: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.544345: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.562869: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.563994: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.564944: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.565740: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.571345: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.572148: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.572941: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.573876: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.575612: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.586557: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.587546: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.598821: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.599967: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.600966: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.601760: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.602562: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-01 11:20:43.603423: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_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 : 4 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: -115.82891 max: 148.90469 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 506 time to create 1 rle with old method : 0.0012772083282470703 length of segment : 30 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00020194053649902344 length of segment : 27 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.0015687942504882812 length of segment : 53 time for calcul the mask position with numpy : 0.00010704994201660156 nb_pixel_total : 896 time to create 1 rle with old method : 0.0018486976623535156 length of segment : 56 length of segment : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.73125 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 : 0.00010132789611816406 nb_pixel_total : 1086 time to create 1 rle with old method : 0.0026929378509521484 length of segment : 41 time for calcul the mask position with numpy : 0.00013589859008789062 nb_pixel_total : 2842 time to create 1 rle with old method : 0.004860401153564453 length of segment : 90 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 1158 time to create 1 rle with old method : 0.0017418861389160156 length of segment : 51 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.00045871734619140625 length of segment : 29 time for calcul the mask position with numpy : 0.00011014938354492188 nb_pixel_total : 3093 time to create 1 rle with old method : 0.004212141036987305 length of segment : 100 time for calcul the mask position with numpy : 0.00013327598571777344 nb_pixel_total : 3609 time to create 1 rle with old method : 0.0049381256103515625 length of segment : 80 time for calcul the mask position with numpy : 0.00013518333435058594 nb_pixel_total : 3938 time to create 1 rle with old method : 0.005524396896362305 length of segment : 71 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 2549 time to create 1 rle with old method : 0.003909111022949219 length of segment : 55 time for calcul the mask position with numpy : 0.00011086463928222656 nb_pixel_total : 2697 time to create 1 rle with old method : 0.0042722225189208984 length of segment : 62 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.35625 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 : 6.031990051269531e-05 nb_pixel_total : 891 time to create 1 rle with old method : 0.0013659000396728516 length of segment : 27 time for calcul the mask position with numpy : 0.00011849403381347656 nb_pixel_total : 5863 time to create 1 rle with old method : 0.007936954498291016 length of segment : 109 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1542 time to create 1 rle with old method : 0.002515077590942383 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.03203 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 : 4.863739013671875e-05 nb_pixel_total : 575 time to create 1 rle with old method : 0.0008075237274169922 length of segment : 39 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.00035381317138671875 length of segment : 22 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0006251335144042969 length of segment : 28 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 976 time to create 1 rle with old method : 0.0012159347534179688 length of segment : 92 time for calcul the mask position with numpy : 0.00013780593872070312 nb_pixel_total : 8015 time to create 1 rle with old method : 0.009769439697265625 length of segment : 123 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 925 time to create 1 rle with old method : 0.0011522769927978516 length of segment : 95 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1569 time to create 1 rle with old method : 0.001965045928955078 length of segment : 94 time for calcul the mask position with numpy : 0.00015091896057128906 nb_pixel_total : 9213 time to create 1 rle with old method : 0.0112457275390625 length of segment : 108 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 1590 time to create 1 rle with old method : 0.0020303726196289062 length of segment : 91 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: 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 : 4.124641418457031e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0007345676422119141 length of segment : 17 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005373954772949219 length of segment : 36 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0019028186798095703 length of segment : 41 time for calcul the mask position with numpy : 0.0006456375122070312 nb_pixel_total : 59960 time to create 1 rle with old method : 0.06905937194824219 length of segment : 343 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 222.00000 molded_images shape: (1, 640, 640, 3) min: -90.69219 max: 93.10000 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: -118.67266 max: 149.45156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 2164 time to create 1 rle with old method : 0.0029654502868652344 length of segment : 50 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0007033348083496094 length of segment : 22 time for calcul the mask position with numpy : 0.00024008750915527344 nb_pixel_total : 9466 time to create 1 rle with old method : 0.011435508728027344 length of segment : 133 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.96172 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 : 4.982948303222656e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007984638214111328 length of segment : 30 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00026416778564453125 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.51641 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004830360412597656 length of segment : 29 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002529621124267578 length of segment : 14 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 1258 time to create 1 rle with old method : 0.0015745162963867188 length of segment : 44 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 2139 time to create 1 rle with old method : 0.002711057662963867 length of segment : 135 time for calcul the mask position with numpy : 0.0001125335693359375 nb_pixel_total : 658 time to create 1 rle with old method : 0.0011420249938964844 length of segment : 64 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 963 time to create 1 rle with old method : 0.0012805461883544922 length of segment : 30 time for calcul the mask position with numpy : 0.00036716461181640625 nb_pixel_total : 7289 time to create 1 rle with old method : 0.008978605270385742 length of segment : 291 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 882 time to create 1 rle with old method : 0.0012123584747314453 length of segment : 25 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 648 time to create 1 rle with old method : 0.0007786750793457031 length of segment : 34 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.0004668235778808594 length of segment : 15 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: 144.95547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1976 time to create 1 rle with old method : 0.0025069713592529297 length of segment : 137 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 2297 time to create 1 rle with old method : 0.002699613571166992 length of segment : 132 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002434253692626953 length of segment : 26 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1575 time to create 1 rle with old method : 0.0018384456634521484 length of segment : 82 time for calcul the mask position with numpy : 0.0001761913299560547 nb_pixel_total : 4067 time to create 1 rle with old method : 0.004814863204956055 length of segment : 197 time for calcul the mask position with numpy : 0.0002448558807373047 nb_pixel_total : 5604 time to create 1 rle with old method : 0.006409406661987305 length of segment : 240 time for calcul the mask position with numpy : 0.00024366378784179688 nb_pixel_total : 5729 time to create 1 rle with old method : 0.006647586822509766 length of segment : 241 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 200.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 86.67812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009210109710693359 nb_pixel_total : 104977 time to create 1 rle with old method : 0.11718034744262695 length of segment : 285 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: 147.98672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 0.0001361370086669922 nb_pixel_total : 3858 time to create 1 rle with old method : 0.006719112396240234 length of segment : 88 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0003769397735595703 length of segment : 17 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1625 time to create 1 rle with old method : 0.0029251575469970703 length of segment : 36 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 65 time to create 1 rle with old method : 0.0001647472381591797 length of segment : 10 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 1101 time to create 1 rle with old method : 0.002009868621826172 length of segment : 60 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1167 time to create 1 rle with old method : 0.0022766590118408203 length of segment : 38 time for calcul the mask position with numpy : 0.00018095970153808594 nb_pixel_total : 715 time to create 1 rle with old method : 0.0016639232635498047 length of segment : 37 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.00037360191345214844 length of segment : 17 time for calcul the mask position with numpy : 0.0001289844512939453 nb_pixel_total : 3270 time to create 1 rle with old method : 0.004703521728515625 length of segment : 83 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0005886554718017578 length of segment : 34 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00037384033203125 length of segment : 17 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 4043 time to create 1 rle with old method : 0.004809856414794922 length of segment : 52 time for calcul the mask position with numpy : 0.00010228157043457031 nb_pixel_total : 1757 time to create 1 rle with old method : 0.002324342727661133 length of segment : 108 time for calcul the mask position with numpy : 0.00010132789611816406 nb_pixel_total : 3616 time to create 1 rle with old method : 0.004370212554931641 length of segment : 91 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 1584 time to create 1 rle with old method : 0.001993417739868164 length of segment : 105 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: 150.71328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 28 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.00031566619873046875 length of segment : 17 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 26 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00044727325439453125 length of segment : 16 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.0002849102020263672 length of segment : 16 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.00042724609375 length of segment : 16 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 964 time to create 1 rle with old method : 0.0016751289367675781 length of segment : 42 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00040650367736816406 length of segment : 26 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.00048089027404785156 length of segment : 23 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.0003247261047363281 length of segment : 17 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.0002391338348388672 length of segment : 14 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00020599365234375 length of segment : 11 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.00045299530029296875 length of segment : 21 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.00016641616821289062 length of segment : 10 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003173351287841797 length of segment : 19 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0013616085052490234 length of segment : 34 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.00030159950256347656 length of segment : 13 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004248619079589844 length of segment : 23 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002522468566894531 length of segment : 16 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.0007262229919433594 length of segment : 24 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00029540061950683594 length of segment : 26 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00021791458129882812 length of segment : 15 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0007023811340332031 length of segment : 28 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003757476806640625 length of segment : 27 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00033092498779296875 length of segment : 21 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002646446228027344 length of segment : 12 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003743171691894531 length of segment : 21 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.00021338462829589844 length of segment : 11 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 627 time to create 1 rle with old method : 0.0007994174957275391 length of segment : 26 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: 146.80312 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0009694099426269531 length of segment : 90 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006756782531738281 length of segment : 29 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00027108192443847656 length of segment : 16 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 24 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002620220184326172 length of segment : 15 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00041174888610839844 length of segment : 29 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0006148815155029297 length of segment : 31 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00026917457580566406 length of segment : 25 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003037452697753906 length of segment : 40 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0007398128509521484 length of segment : 27 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0008051395416259766 length of segment : 29 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008006095886230469 length of segment : 30 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: 137.22500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0006737709045410156 nb_pixel_total : 34483 time to create 1 rle with old method : 0.041306495666503906 length of segment : 255 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: -116.46563 max: 149.74062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0006694793701171875 length of segment : 29 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 829 time to create 1 rle with old method : 0.0011987686157226562 length of segment : 54 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00011801719665527344 length of segment : 23 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 870 time to create 1 rle with old method : 0.001201629638671875 length of segment : 58 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.82109 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 : 6.29425048828125e-05 nb_pixel_total : 989 time to create 1 rle with old method : 0.0013380050659179688 length of segment : 49 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 2882 time to create 1 rle with old method : 0.004331827163696289 length of segment : 98 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003821849822998047 length of segment : 29 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 870 time to create 1 rle with old method : 0.0010986328125 length of segment : 55 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1501 time to create 1 rle with old method : 0.0018639564514160156 length of segment : 36 time for calcul the mask position with numpy : 2.765655517578125e-05 nb_pixel_total : 34 time to create 1 rle with old method : 6.413459777832031e-05 length of segment : 7 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 2481 time to create 1 rle with old method : 0.0030379295349121094 length of segment : 52 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 2416 time to create 1 rle with old method : 0.0029366016387939453 length of segment : 65 time for calcul the mask position with numpy : 0.00015044212341308594 nb_pixel_total : 2959 time to create 1 rle with old method : 0.0035974979400634766 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.35625 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 : 7.772445678710938e-05 nb_pixel_total : 874 time to create 1 rle with old method : 0.0016679763793945312 length of segment : 27 time for calcul the mask position with numpy : 0.00011849403381347656 nb_pixel_total : 6120 time to create 1 rle with old method : 0.008895635604858398 length of segment : 105 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1233 time to create 1 rle with old method : 0.0016350746154785156 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: -117.45391 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 : 0.00011157989501953125 nb_pixel_total : 1084 time to create 1 rle with old method : 0.0014958381652832031 length of segment : 56 time for calcul the mask position with numpy : 0.0002505779266357422 nb_pixel_total : 9473 time to create 1 rle with old method : 0.011643409729003906 length of segment : 87 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 930 time to create 1 rle with old method : 0.0012254714965820312 length of segment : 105 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1026 time to create 1 rle with old method : 0.0013124942779541016 length of segment : 95 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00025963783264160156 length of segment : 21 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0005106925964355469 length of segment : 67 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 1621 time to create 1 rle with old method : 0.0021047592163085938 length of segment : 67 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: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0004954338073730469 length of segment : 37 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0007107257843017578 length of segment : 18 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.0011110305786132812 length of segment : 61 time for calcul the mask position with numpy : 0.0005581378936767578 nb_pixel_total : 59393 time to create 1 rle with old method : 0.06871151924133301 length of segment : 288 time for calcul the mask position with numpy : 0.00047087669372558594 nb_pixel_total : 45894 time to create 1 rle with old method : 0.05425882339477539 length of segment : 250 Processing 1 images image shape: (400, 400, 3) min: 23.00000 max: 214.00000 molded_images shape: (1, 640, 640, 3) min: -89.20000 max: 85.04531 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: -117.20000 max: 149.38906 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1363 time to create 1 rle with old method : 0.001661062240600586 length of segment : 46 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 2415 time to create 1 rle with old method : 0.0029172897338867188 length of segment : 48 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1806 time to create 1 rle with old method : 0.002305269241333008 length of segment : 48 time for calcul the mask position with numpy : 0.000335693359375 nb_pixel_total : 20677 time to create 1 rle with old method : 0.023669719696044922 length of segment : 215 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.80547 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 : 3.9577484130859375e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0006227493286132812 length of segment : 13 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.0002315044403076172 length of segment : 15 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005390644073486328 length of segment : 43 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006561279296875 length of segment : 24 time for calcul the mask position with numpy : 0.0003287792205810547 nb_pixel_total : 15162 time to create 1 rle with old method : 0.017544031143188477 length of segment : 149 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0008513927459716797 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.20000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 1780 time to create 1 rle with old method : 0.002359151840209961 length of segment : 124 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00022411346435546875 length of segment : 14 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 1202 time to create 1 rle with old method : 0.0015392303466796875 length of segment : 38 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 860 time to create 1 rle with old method : 0.001455068588256836 length of segment : 25 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1060 time to create 1 rle with old method : 0.0014050006866455078 length of segment : 29 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1908 time to create 1 rle with old method : 0.0038423538208007812 length of segment : 60 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005960464477539062 length of segment : 18 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 809 time to create 1 rle with old method : 0.0010421276092529297 length of segment : 37 time for calcul the mask position with numpy : 0.0004477500915527344 nb_pixel_total : 8399 time to create 1 rle with old method : 0.009835958480834961 length of segment : 307 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1270 time to create 1 rle with old method : 0.0016472339630126953 length of segment : 40 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: 143.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 1535 time to create 1 rle with old method : 0.0020058155059814453 length of segment : 144 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002703666687011719 length of segment : 27 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 1928 time to create 1 rle with old method : 0.0033850669860839844 length of segment : 161 time for calcul the mask position with numpy : 0.0002465248107910156 nb_pixel_total : 4347 time to create 1 rle with old method : 0.005383968353271484 length of segment : 203 time for calcul the mask position with numpy : 0.00028133392333984375 nb_pixel_total : 5661 time to create 1 rle with old method : 0.006920337677001953 length of segment : 242 time for calcul the mask position with numpy : 0.00030040740966796875 nb_pixel_total : 5879 time to create 1 rle with old method : 0.007233142852783203 length of segment : 256 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 199.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 80.84219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 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: 150.33828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1293 time to create 1 rle with old method : 0.0016133785247802734 length of segment : 70 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 54 time to create 1 rle with old method : 0.00011181831359863281 length of segment : 10 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1602 time to create 1 rle with old method : 0.0021414756774902344 length of segment : 37 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003104209899902344 length of segment : 19 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 1094 time to create 1 rle with old method : 0.0015244483947753906 length of segment : 40 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 3611 time to create 1 rle with old method : 0.0044574737548828125 length of segment : 57 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 2513 time to create 1 rle with old method : 0.003386259078979492 length of segment : 102 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002346038818359375 length of segment : 14 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0008816719055175781 length of segment : 35 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 1861 time to create 1 rle with old method : 0.0026121139526367188 length of segment : 85 time for calcul the mask position with numpy : 0.00010156631469726562 nb_pixel_total : 2727 time to create 1 rle with old method : 0.003586292266845703 length of segment : 114 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.00083160400390625 length of segment : 36 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: 150.59609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.00030517578125 length of segment : 21 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.00035309791564941406 length of segment : 26 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.00022077560424804688 length of segment : 16 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0010063648223876953 length of segment : 31 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002944469451904297 length of segment : 17 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 699 time to create 1 rle with old method : 0.0009410381317138672 length of segment : 42 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001533031463623047 length of segment : 15 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0005033016204833984 length of segment : 25 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00043487548828125 length of segment : 16 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.00041103363037109375 length of segment : 27 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002357959747314453 length of segment : 16 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0004487037658691406 length of segment : 30 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00028896331787109375 length of segment : 22 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00025773048400878906 length of segment : 12 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005595684051513672 length of segment : 25 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00024199485778808594 length of segment : 12 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00030493736267089844 length of segment : 17 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001671314239501953 length of segment : 17 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006403923034667969 length of segment : 33 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00030922889709472656 length of segment : 19 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00021219253540039062 length of segment : 14 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 824 time to create 1 rle with old method : 0.0011057853698730469 length of segment : 44 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00026416778564453125 length of segment : 12 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003085136413574219 length of segment : 16 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003204345703125 length of segment : 13 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.00042939186096191406 length of segment : 30 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00027823448181152344 length of segment : 12 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.0003266334533691406 length of segment : 15 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0003261566162109375 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: 146.77969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 1607 time to create 1 rle with old method : 0.002424955368041992 length of segment : 87 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004456043243408203 length of segment : 31 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006155967712402344 length of segment : 27 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 217 time to create 1 rle with old method : 0.000308990478515625 length of segment : 17 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.000499725341796875 length of segment : 22 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00031185150146484375 length of segment : 43 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002422332763671875 length of segment : 15 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0006916522979736328 length of segment : 28 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: 134.97500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 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: -116.95000 max: 149.51406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0007455348968505859 length of segment : 30 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.00013518333435058594 length of segment : 24 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0011773109436035156 length of segment : 50 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 872 time to create 1 rle with old method : 0.0012214183807373047 length of segment : 58 length of segment : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.82109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1080 time to create 1 rle with old method : 0.0012524127960205078 length of segment : 37 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 2591 time to create 1 rle with old method : 0.003244161605834961 length of segment : 65 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 3636 time to create 1 rle with old method : 0.004575252532958984 length of segment : 91 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 2628 time to create 1 rle with old method : 0.003438711166381836 length of segment : 57 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 3615 time to create 1 rle with old method : 0.004624843597412109 length of segment : 63 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.04375 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 : 0.00012087821960449219 nb_pixel_total : 5679 time to create 1 rle with old method : 0.006700277328491211 length of segment : 100 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.22734 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 : 7.05718994140625e-05 nb_pixel_total : 1443 time to create 1 rle with old method : 0.0019230842590332031 length of segment : 73 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 739 time to create 1 rle with old method : 0.0010335445404052734 length of segment : 70 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 638 time to create 1 rle with old method : 0.0008783340454101562 length of segment : 57 time for calcul the mask position with numpy : 0.0001678466796875 nb_pixel_total : 9058 time to create 1 rle with old method : 0.01086115837097168 length of segment : 114 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 993 time to create 1 rle with old method : 0.0011911392211914062 length of segment : 97 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002486705780029297 length of segment : 21 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 927 time to create 1 rle with old method : 0.0011854171752929688 length of segment : 95 time for calcul the mask position with numpy : 0.00014019012451171875 nb_pixel_total : 8717 time to create 1 rle with old method : 0.010393857955932617 length of segment : 82 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 1914 time to create 1 rle with old method : 0.002400636672973633 length of segment : 79 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: 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 : 4.696846008300781e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005238056182861328 length of segment : 37 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0007719993591308594 length of segment : 16 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0006835460662841797 length of segment : 47 Processing 1 images image shape: (400, 400, 3) min: 24.00000 max: 207.00000 molded_images shape: (1, 640, 640, 3) min: -92.67266 max: 85.18203 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: -118.57109 max: 149.38906 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 : 379 time to create 1 rle with old method : 0.0007357597351074219 length of segment : 19 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0006921291351318359 length of segment : 26 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0005536079406738281 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.80156 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 : 3.4809112548828125e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0003285408020019531 length of segment : 18 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.0002167224884033203 length of segment : 15 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.001100301742553711 length of segment : 46 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007622241973876953 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.36406 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004687309265136719 length of segment : 29 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00021314620971679688 length of segment : 14 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 2085 time to create 1 rle with old method : 0.002634286880493164 length of segment : 125 time for calcul the mask position with numpy : 0.0001678466796875 nb_pixel_total : 2073 time to create 1 rle with old method : 0.0029854774475097656 length of segment : 62 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1153 time to create 1 rle with old method : 0.0013990402221679688 length of segment : 37 time for calcul the mask position with numpy : 0.00015401840209960938 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0015718936920166016 length of segment : 30 time for calcul the mask position with numpy : 0.0013608932495117188 nb_pixel_total : 6611 time to create 1 rle with old method : 0.009331226348876953 length of segment : 295 time for calcul the mask position with numpy : 0.00019550323486328125 nb_pixel_total : 916 time to create 1 rle with old method : 0.0013835430145263672 length of segment : 24 time for calcul the mask position with numpy : 0.00015997886657714844 nb_pixel_total : 379 time to create 1 rle with old method : 0.0006389617919921875 length of segment : 17 time for calcul the mask position with numpy : 0.0001499652862548828 nb_pixel_total : 757 time to create 1 rle with old method : 0.0010423660278320312 length of segment : 36 time for calcul the mask position with numpy : 0.00016427040100097656 nb_pixel_total : 813 time to create 1 rle with old method : 0.0011568069458007812 length of segment : 36 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: 145.08047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1436 time to create 1 rle with old method : 0.002258777618408203 length of segment : 113 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 169 time to create 1 rle with old method : 0.00028586387634277344 length of segment : 25 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 1492 time to create 1 rle with old method : 0.0021843910217285156 length of segment : 123 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 1203 time to create 1 rle with old method : 0.0023627281188964844 length of segment : 44 time for calcul the mask position with numpy : 0.0022971630096435547 nb_pixel_total : 6530 time to create 1 rle with old method : 0.01062774658203125 length of segment : 271 time for calcul the mask position with numpy : 0.000492095947265625 nb_pixel_total : 4777 time to create 1 rle with old method : 0.0066149234771728516 length of segment : 239 time for calcul the mask position with numpy : 0.00022935867309570312 nb_pixel_total : 5526 time to create 1 rle with old method : 0.006776571273803711 length of segment : 235 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 200.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 82.75234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.000911712646484375 nb_pixel_total : 105989 time to create 1 rle with old method : 0.12089204788208008 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: 148.43203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.00028228759765625 length of segment : 18 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0008742809295654297 length of segment : 71 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 50 time to create 1 rle with old method : 9.632110595703125e-05 length of segment : 9 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1506 time to create 1 rle with old method : 0.0020329952239990234 length of segment : 36 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 940 time to create 1 rle with old method : 0.0013065338134765625 length of segment : 40 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 46 time to create 1 rle with old method : 0.00011491775512695312 length of segment : 6 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 1002 time to create 1 rle with old method : 0.002931833267211914 length of segment : 30 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006577968597412109 length of segment : 33 time for calcul the mask position with numpy : 0.00023508071899414062 nb_pixel_total : 7177 time to create 1 rle with old method : 0.008913040161132812 length of segment : 137 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00023865699768066406 length of segment : 12 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 1693 time to create 1 rle with old method : 0.0024666786193847656 length of segment : 105 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 2040 time to create 1 rle with old method : 0.0028009414672851562 length of segment : 100 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 3501 time to create 1 rle with old method : 0.004450559616088867 length of segment : 91 time for calcul the mask position with numpy : 0.00014090538024902344 nb_pixel_total : 3172 time to create 1 rle with old method : 0.004571676254272461 length of segment : 102 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0008854866027832031 length of segment : 36 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1275 time to create 1 rle with old method : 0.0017597675323486328 length of segment : 46 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0008852481842041016 length of segment : 34 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: 150.93203 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0004220008850097656 length of segment : 17 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0005259513854980469 length of segment : 27 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0004134178161621094 length of segment : 16 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0004076957702636719 length of segment : 18 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 860 time to create 1 rle with old method : 0.001550912857055664 length of segment : 55 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00049591064453125 length of segment : 27 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.00043082237243652344 length of segment : 13 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0005879402160644531 length of segment : 18 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.00044655799865722656 length of segment : 24 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.00023603439331054688 length of segment : 16 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.00025153160095214844 length of segment : 12 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 212 time to create 1 rle with old method : 0.0004336833953857422 length of segment : 15 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003559589385986328 length of segment : 22 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0009109973907470703 length of segment : 30 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0006871223449707031 length of segment : 22 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00022912025451660156 length of segment : 7 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0006618499755859375 length of segment : 22 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00040531158447265625 length of segment : 16 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0003466606140136719 length of segment : 12 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0008547306060791016 length of segment : 24 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.00022983551025390625 length of segment : 15 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0006260871887207031 length of segment : 20 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 137 time to create 1 rle with old method : 0.00021505355834960938 length of segment : 15 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00022292137145996094 length of segment : 12 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 29 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 480 time to create 1 rle with old method : 0.0006625652313232422 length of segment : 28 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.00029397010803222656 length of segment : 12 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.0003097057342529297 length of segment : 16 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002067089080810547 length of segment : 15 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003592967987060547 length of segment : 27 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 341 time to create 1 rle with old method : 0.00046539306640625 length of segment : 26 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.00042057037353515625 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: 145.90859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1519 time to create 1 rle with old method : 0.0019314289093017578 length of segment : 79 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003876686096191406 length of segment : 51 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003845691680908203 length of segment : 26 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006170272827148438 length of segment : 26 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.00044918060302734375 length of segment : 18 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 303 time to create 1 rle with old method : 0.00043654441833496094 length of segment : 29 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 549 time to create 1 rle with old method : 0.0007212162017822266 length of segment : 27 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: 135.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0005497932434082031 nb_pixel_total : 41049 time to create 1 rle with old method : 0.04601931571960449 length of segment : 248 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: -120.93047 max: 150.38906 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006721019744873047 length of segment : 29 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.00011897087097167969 length of segment : 26 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 902 time to create 1 rle with old method : 0.0012481212615966797 length of segment : 45 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 967 time to create 1 rle with old method : 0.0013263225555419922 length of segment : 58 length of segment : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.35234 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 : 8.893013000488281e-05 nb_pixel_total : 3187 time to create 1 rle with old method : 0.003912210464477539 length of segment : 54 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0009095668792724609 length of segment : 70 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 2763 time to create 1 rle with old method : 0.0034542083740234375 length of segment : 85 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1239 time to create 1 rle with old method : 0.001688241958618164 length of segment : 60 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 30 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 2976 time to create 1 rle with old method : 0.0037479400634765625 length of segment : 95 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 2912 time to create 1 rle with old method : 0.003696441650390625 length of segment : 54 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 3775 time to create 1 rle with old method : 0.004730939865112305 length of segment : 69 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.04375 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 : 4.863739013671875e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.0011785030364990234 length of segment : 26 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0020372867584228516 length of segment : 25 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1561 time to create 1 rle with old method : 0.0021719932556152344 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: -119.71953 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 : 7.987022399902344e-05 nb_pixel_total : 1610 time to create 1 rle with old method : 0.0019731521606445312 length of segment : 79 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002906322479248047 length of segment : 21 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 982 time to create 1 rle with old method : 0.0011456012725830078 length of segment : 97 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 861 time to create 1 rle with old method : 0.0011782646179199219 length of segment : 66 time for calcul the mask position with numpy : 0.000164031982421875 nb_pixel_total : 8827 time to create 1 rle with old method : 0.010334968566894531 length of segment : 86 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0012998580932617188 length of segment : 97 time for calcul the mask position with numpy : 0.00016617774963378906 nb_pixel_total : 8578 time to create 1 rle with old method : 0.010233163833618164 length of segment : 116 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: 151.10000 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 : 486 time to create 1 rle with old method : 0.0007495880126953125 length of segment : 20 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006103515625 length of segment : 37 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0005819797515869141 length of segment : 37 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1694 time to create 1 rle with old method : 0.002222299575805664 length of segment : 45 time for calcul the mask position with numpy : 0.0004961490631103516 nb_pixel_total : 43139 time to create 1 rle with old method : 0.0477907657623291 length of segment : 311 Processing 1 images image shape: (400, 400, 3) min: 14.00000 max: 208.00000 molded_images shape: (1, 640, 640, 3) min: -96.63359 max: 84.15859 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: -118.57109 max: 149.24844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 366 time to create 1 rle with old method : 0.0005719661712646484 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.82500 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 : 5.8650970458984375e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.0003139972686767578 length of segment : 18 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0008406639099121094 length of segment : 28 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 564 time to create 1 rle with old method : 0.0007340908050537109 length of segment : 50 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 1137 time to create 1 rle with old method : 0.0014808177947998047 length of segment : 51 time for calcul the mask position with numpy : 0.00031065940856933594 nb_pixel_total : 13301 time to create 1 rle with old method : 0.01512002944946289 length of segment : 135 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0003440380096435547 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.57500 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 : 9.34600830078125e-05 nb_pixel_total : 2311 time to create 1 rle with old method : 0.0027675628662109375 length of segment : 138 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1016 time to create 1 rle with old method : 0.0014224052429199219 length of segment : 27 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1119 time to create 1 rle with old method : 0.0014481544494628906 length of segment : 36 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 418 time to create 1 rle with old method : 0.0005958080291748047 length of segment : 29 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1807 time to create 1 rle with old method : 0.002287149429321289 length of segment : 63 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002529621124267578 length of segment : 14 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 862 time to create 1 rle with old method : 0.0011224746704101562 length of segment : 37 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 936 time to create 1 rle with old method : 0.0012519359588623047 length of segment : 27 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 834 time to create 1 rle with old method : 0.0010669231414794922 length of segment : 36 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: 144.89297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 2485 time to create 1 rle with old method : 0.003195524215698242 length of segment : 141 time for calcul the mask position with numpy : 0.0001304149627685547 nb_pixel_total : 1898 time to create 1 rle with old method : 0.0027332305908203125 length of segment : 142 time for calcul the mask position with numpy : 0.0003681182861328125 nb_pixel_total : 6597 time to create 1 rle with old method : 0.008221149444580078 length of segment : 278 time for calcul the mask position with numpy : 0.00030922889709472656 nb_pixel_total : 4394 time to create 1 rle with old method : 0.005536317825317383 length of segment : 208 time for calcul the mask position with numpy : 0.00026226043701171875 nb_pixel_total : 6011 time to create 1 rle with old method : 0.0074460506439208984 length of segment : 239 Processing 1 images image shape: (280, 400, 3) min: 12.00000 max: 197.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 82.88125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013005733489990234 nb_pixel_total : 105504 time to create 1 rle with old method : 0.12681078910827637 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: 148.61172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 48 time to create 1 rle with old method : 9.989738464355469e-05 length of segment : 9 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0003025531768798828 length of segment : 17 time for calcul the mask position with numpy : 0.00010156631469726562 nb_pixel_total : 3576 time to create 1 rle with old method : 0.004492759704589844 length of segment : 88 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1043 time to create 1 rle with old method : 0.0014004707336425781 length of segment : 46 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00024175643920898438 length of segment : 14 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 988 time to create 1 rle with old method : 0.00138092041015625 length of segment : 42 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00044655799865722656 length of segment : 18 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 2976 time to create 1 rle with old method : 0.0037839412689208984 length of segment : 105 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 54 time to create 1 rle with old method : 0.00013256072998046875 length of segment : 6 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 2648 time to create 1 rle with old method : 0.003474712371826172 length of segment : 104 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003914833068847656 length of segment : 29 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 631 time to create 1 rle with old method : 0.0007693767547607422 length of segment : 36 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 1065 time to create 1 rle with old method : 0.0014007091522216797 length of segment : 35 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006532669067382812 length of segment : 32 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: 150.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003008842468261719 length of segment : 17 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.00042557716369628906 length of segment : 27 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.00019979476928710938 length of segment : 14 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 18 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0006706714630126953 length of segment : 39 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.00038051605224609375 length of segment : 22 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004646778106689453 length of segment : 25 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 15 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00013303756713867188 length of segment : 14 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003879070281982422 length of segment : 17 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00020647048950195312 length of segment : 11 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00033020973205566406 length of segment : 16 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003609657287597656 length of segment : 27 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003108978271484375 length of segment : 17 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00035691261291503906 length of segment : 16 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0004334449768066406 length of segment : 24 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 975 time to create 1 rle with old method : 0.0013492107391357422 length of segment : 34 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003159046173095703 length of segment : 11 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0006325244903564453 length of segment : 24 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008959770202636719 length of segment : 25 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002872943878173828 length of segment : 13 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005915164947509766 length of segment : 61 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0009119510650634766 length of segment : 27 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004830360412597656 length of segment : 23 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006184577941894531 length of segment : 34 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.00037360191345214844 length of segment : 27 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: 146.77578 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.001146554946899414 length of segment : 91 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.000438690185546875 length of segment : 15 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004928112030029297 length of segment : 27 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0005071163177490234 length of segment : 26 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 127 time to create 1 rle with old method : 0.00021505355834960938 length of segment : 25 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006792545318603516 length of segment : 29 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003058910369873047 length of segment : 16 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.00016570091247558594 length of segment : 9 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 564 time to create 1 rle with old method : 0.0007519721984863281 length of segment : 28 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 581 time to create 1 rle with old method : 0.0007860660552978516 length of segment : 28 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 940 time to create 1 rle with old method : 0.0013551712036132812 length of segment : 30 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 554 time to create 1 rle with old method : 0.0007746219635009766 length of segment : 27 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: 133.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Detection mask done ! Trying to reset tf kernel 1634722 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2332 tf kernel not reseted sub process len(results) : 420 len(list_Values) 420 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 420 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 : 559 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 420 chid ids of type : 4228 Number RLEs to save : 23064 save missing photos in datou_result : time spend for datou_step_exec : 29.164547443389893 time spend to save output : 1.506263256072998 total time spend for step 1 : 30.67081069946289 step2:brightness Sat Mar 1 11:21:01 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 calcul brightness treat image : temp/1740824430_1634302_1340356292_4c68eac24bc92212d408318181623368.jpg treat image : temp/1740824430_1634302_1340356289_f8410005230cf970bff745bc8b6a3307.jpg treat image : temp/1740824430_1634302_1340356288_7adccc173560f4eb1568b3cfa3983595.jpg treat image : temp/1740824430_1634302_1340356287_edba6b989dcafb186651e6683817b854.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 4 time used for this insertion : 0.2095174789428711 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.012572765350341797 save missing photos in datou_result : time spend for datou_step_exec : 0.9423749446868896 time spend to save output : 0.22687029838562012 total time spend for step 2 : 1.1692452430725098 step3:blur_detection Sat Mar 1 11:21:02 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/1740824430_1634302_1340356292_4c68eac24bc92212d408318181623368.jpg resize: (1080, 1920) 1340356292 -7.7870928953995335 treat image : temp/1740824430_1634302_1340356289_f8410005230cf970bff745bc8b6a3307.jpg resize: (1080, 1920) 1340356289 -7.792525584728253 treat image : temp/1740824430_1634302_1340356288_7adccc173560f4eb1568b3cfa3983595.jpg resize: (1080, 1920) 1340356288 -7.785146695104479 treat image : temp/1740824430_1634302_1340356287_edba6b989dcafb186651e6683817b854.jpg resize: (1080, 1920) 1340356287 -7.79264560180095 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 4 time used for this insertion : 0.015728235244750977 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.010945558547973633 save missing photos in datou_result : time spend for datou_step_exec : 3.500047445297241 time spend to save output : 0.031046152114868164 total time spend for step 3 : 3.5310935974121094 step4:rle_unique_nms_with_priority Sat Mar 1 11:21:06 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 420 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 108 nb_hashtags : 7 time to prepare the origin masks : 1.0484933853149414 time for calcul the mask position with numpy : 0.09128808975219727 nb_pixel_total : 1771022 time to create 1 rle with new method : 0.0854945182800293 time for calcul the mask position with numpy : 0.007894754409790039 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006875991821289062 time for calcul the mask position with numpy : 0.007715463638305664 nb_pixel_total : 2861 time to create 1 rle with old method : 0.0031082630157470703 time for calcul the mask position with numpy : 0.007967948913574219 nb_pixel_total : 317 time to create 1 rle with old method : 0.00035309791564941406 time for calcul the mask position with numpy : 0.008034467697143555 nb_pixel_total : 59960 time to create 1 rle with old method : 0.062255859375 time for calcul the mask position with numpy : 0.007822751998901367 nb_pixel_total : 1086 time to create 1 rle with old method : 0.001104593276977539 time for calcul the mask position with numpy : 0.007620096206665039 nb_pixel_total : 506 time to create 1 rle with old method : 0.0005257129669189453 time for calcul the mask position with numpy : 0.0075719356536865234 nb_pixel_total : 1158 time to create 1 rle with old method : 0.0012080669403076172 time for calcul the mask position with numpy : 0.007569313049316406 nb_pixel_total : 85 time to create 1 rle with old method : 9.107589721679688e-05 time for calcul the mask position with numpy : 0.007600307464599609 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.0075910091400146484 nb_pixel_total : 764 time to create 1 rle with old method : 0.0007927417755126953 time for calcul the mask position with numpy : 0.007953643798828125 nb_pixel_total : 3938 time to create 1 rle with old method : 0.0041239261627197266 time for calcul the mask position with numpy : 0.007936239242553711 nb_pixel_total : 9 time to create 1 rle with old method : 6.771087646484375e-05 time for calcul the mask position with numpy : 0.007882118225097656 nb_pixel_total : 13 time to create 1 rle with old method : 6.4849853515625e-05 time for calcul the mask position with numpy : 0.007887125015258789 nb_pixel_total : 48 time to create 1 rle with old method : 7.200241088867188e-05 time for calcul the mask position with numpy : 0.007963180541992188 nb_pixel_total : 976 time to create 1 rle with old method : 0.0011327266693115234 time for calcul the mask position with numpy : 0.00783991813659668 nb_pixel_total : 233 time to create 1 rle with old method : 0.0002956390380859375 time for calcul the mask position with numpy : 0.007822036743164062 nb_pixel_total : 409 time to create 1 rle with old method : 0.0004494190216064453 time for calcul the mask position with numpy : 0.008055925369262695 nb_pixel_total : 2842 time to create 1 rle with old method : 0.0032901763916015625 time for calcul the mask position with numpy : 0.007932424545288086 nb_pixel_total : 66 time to create 1 rle with old method : 8.20159912109375e-05 time for calcul the mask position with numpy : 0.008248090744018555 nb_pixel_total : 1569 time to create 1 rle with old method : 0.0015985965728759766 time for calcul the mask position with numpy : 0.007983207702636719 nb_pixel_total : 891 time to create 1 rle with old method : 0.001010894775390625 time for calcul the mask position with numpy : 0.008043527603149414 nb_pixel_total : 1542 time to create 1 rle with old method : 0.0017843246459960938 time for calcul the mask position with numpy : 0.007883310317993164 nb_pixel_total : 5863 time to create 1 rle with old method : 0.006433010101318359 time for calcul the mask position with numpy : 0.0077970027923583984 nb_pixel_total : 1285 time to create 1 rle with old method : 0.001552581787109375 time for calcul the mask position with numpy : 0.007721662521362305 nb_pixel_total : 8015 time to create 1 rle with old method : 0.008345365524291992 time for calcul the mask position with numpy : 0.007944583892822266 nb_pixel_total : 47 time to create 1 rle with old method : 6.556510925292969e-05 time for calcul the mask position with numpy : 0.007841348648071289 nb_pixel_total : 575 time to create 1 rle with old method : 0.0006430149078369141 time for calcul the mask position with numpy : 0.008039712905883789 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0014424324035644531 time for calcul the mask position with numpy : 0.008017301559448242 nb_pixel_total : 508 time to create 1 rle with old method : 0.0005769729614257812 time for calcul the mask position with numpy : 0.007883071899414062 nb_pixel_total : 658 time to create 1 rle with old method : 0.0007710456848144531 time for calcul the mask position with numpy : 0.007783651351928711 nb_pixel_total : 7119 time to create 1 rle with old method : 0.008246660232543945 time for calcul the mask position with numpy : 0.008027791976928711 nb_pixel_total : 648 time to create 1 rle with old method : 0.0007541179656982422 time for calcul the mask position with numpy : 0.0080108642578125 nb_pixel_total : 598 time to create 1 rle with old method : 0.0006868839263916016 time for calcul the mask position with numpy : 0.008097410202026367 nb_pixel_total : 137 time to create 1 rle with old method : 0.00016951560974121094 time for calcul the mask position with numpy : 0.008163928985595703 nb_pixel_total : 1258 time to create 1 rle with old method : 0.0014007091522216797 time for calcul the mask position with numpy : 0.007982254028320312 nb_pixel_total : 356 time to create 1 rle with old method : 0.0005717277526855469 time for calcul the mask position with numpy : 0.008071184158325195 nb_pixel_total : 7700 time to create 1 rle with old method : 0.008452653884887695 time for calcul the mask position with numpy : 0.008266448974609375 nb_pixel_total : 179 time to create 1 rle with old method : 0.00026679039001464844 time for calcul the mask position with numpy : 0.008173942565917969 nb_pixel_total : 178 time to create 1 rle with old method : 0.00020885467529296875 time for calcul the mask position with numpy : 0.008173465728759766 nb_pixel_total : 464 time to create 1 rle with old method : 0.0006041526794433594 time for calcul the mask position with numpy : 0.008106470108032227 nb_pixel_total : 1976 time to create 1 rle with old method : 0.0020384788513183594 time for calcul the mask position with numpy : 0.008268356323242188 nb_pixel_total : 1695 time to create 1 rle with old method : 0.0020377635955810547 time for calcul the mask position with numpy : 0.008276939392089844 nb_pixel_total : 4067 time to create 1 rle with old method : 0.004536867141723633 time for calcul the mask position with numpy : 0.00820302963256836 nb_pixel_total : 320 time to create 1 rle with old method : 0.0003566741943359375 time for calcul the mask position with numpy : 0.008057832717895508 nb_pixel_total : 2139 time to create 1 rle with old method : 0.0023894309997558594 time for calcul the mask position with numpy : 0.008251667022705078 nb_pixel_total : 2164 time to create 1 rle with old method : 0.002461671829223633 time for calcul the mask position with numpy : 0.008195877075195312 nb_pixel_total : 146 time to create 1 rle with old method : 0.00016355514526367188 time for calcul the mask position with numpy : 0.008200407028198242 nb_pixel_total : 1575 time to create 1 rle with old method : 0.0017518997192382812 time for calcul the mask position with numpy : 0.008038759231567383 nb_pixel_total : 351 time to create 1 rle with old method : 0.00037407875061035156 time for calcul the mask position with numpy : 0.00828862190246582 nb_pixel_total : 963 time to create 1 rle with old method : 0.001028299331665039 time for calcul the mask position with numpy : 0.008182287216186523 nb_pixel_total : 41 time to create 1 rle with old method : 8.130073547363281e-05 time for calcul the mask position with numpy : 0.008324861526489258 nb_pixel_total : 104977 time to create 1 rle with old method : 0.11232328414916992 time for calcul the mask position with numpy : 0.008311033248901367 nb_pixel_total : 1304 time to create 1 rle with old method : 0.0014843940734863281 time for calcul the mask position with numpy : 0.00821542739868164 nb_pixel_total : 271 time to create 1 rle with old method : 0.0003604888916015625 time for calcul the mask position with numpy : 0.008047342300415039 nb_pixel_total : 204 time to create 1 rle with old method : 0.00021576881408691406 time for calcul the mask position with numpy : 0.008121967315673828 nb_pixel_total : 161 time to create 1 rle with old method : 0.0001761913299560547 time for calcul the mask position with numpy : 0.008003711700439453 nb_pixel_total : 135 time to create 1 rle with old method : 0.000148773193359375 time for calcul the mask position with numpy : 0.008021116256713867 nb_pixel_total : 1101 time to create 1 rle with old method : 0.0012431144714355469 time for calcul the mask position with numpy : 0.00794219970703125 nb_pixel_total : 463 time to create 1 rle with old method : 0.0005223751068115234 time for calcul the mask position with numpy : 0.007884502410888672 nb_pixel_total : 193 time to create 1 rle with old method : 0.00022602081298828125 time for calcul the mask position with numpy : 0.008178472518920898 nb_pixel_total : 34483 time to create 1 rle with old method : 0.0362093448638916 time for calcul the mask position with numpy : 0.008034229278564453 nb_pixel_total : 1167 time to create 1 rle with old method : 0.0012123584747314453 time for calcul the mask position with numpy : 0.008001327514648438 nb_pixel_total : 213 time to create 1 rle with old method : 0.00024271011352539062 time for calcul the mask position with numpy : 0.008066654205322266 nb_pixel_total : 184 time to create 1 rle with old method : 0.00019693374633789062 time for calcul the mask position with numpy : 0.00820469856262207 nb_pixel_total : 127 time to create 1 rle with old method : 0.00014972686767578125 time for calcul the mask position with numpy : 0.008388280868530273 nb_pixel_total : 255 time to create 1 rle with old method : 0.0002918243408203125 time for calcul the mask position with numpy : 0.008179187774658203 nb_pixel_total : 95 time to create 1 rle with old method : 0.000118255615234375 time for calcul the mask position with numpy : 0.008089303970336914 nb_pixel_total : 65 time to create 1 rle with old method : 8.034706115722656e-05 time for calcul the mask position with numpy : 0.008093595504760742 nb_pixel_total : 4043 time to create 1 rle with old method : 0.004288911819458008 time for calcul the mask position with numpy : 0.008079767227172852 nb_pixel_total : 159 time to create 1 rle with old method : 0.00018787384033203125 time for calcul the mask position with numpy : 0.00805211067199707 nb_pixel_total : 139 time to create 1 rle with old method : 0.00015354156494140625 time for calcul the mask position with numpy : 0.008192300796508789 nb_pixel_total : 627 time to create 1 rle with old method : 0.0006608963012695312 time for calcul the mask position with numpy : 0.00805807113647461 nb_pixel_total : 174 time to create 1 rle with old method : 0.00020360946655273438 time for calcul the mask position with numpy : 0.008081197738647461 nb_pixel_total : 338 time to create 1 rle with old method : 0.0003635883331298828 time for calcul the mask position with numpy : 0.008015632629394531 nb_pixel_total : 195 time to create 1 rle with old method : 0.00021505355834960938 time for calcul the mask position with numpy : 0.00811910629272461 nb_pixel_total : 3858 time to create 1 rle with old method : 0.00408625602722168 time for calcul the mask position with numpy : 0.007936954498291016 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0011522769927978516 time for calcul the mask position with numpy : 0.008109331130981445 nb_pixel_total : 228 time to create 1 rle with old method : 0.00026488304138183594 time for calcul the mask position with numpy : 0.007966041564941406 nb_pixel_total : 715 time to create 1 rle with old method : 0.0007572174072265625 time for calcul the mask position with numpy : 0.0081329345703125 nb_pixel_total : 221 time to create 1 rle with old method : 0.00024080276489257812 time for calcul the mask position with numpy : 0.008048057556152344 nb_pixel_total : 197 time to create 1 rle with old method : 0.00021409988403320312 time for calcul the mask position with numpy : 0.00793147087097168 nb_pixel_total : 497 time to create 1 rle with old method : 0.0005588531494140625 time for calcul the mask position with numpy : 0.008026361465454102 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003173351287841797 time for calcul the mask position with numpy : 0.007986783981323242 nb_pixel_total : 1625 time to create 1 rle with old method : 0.0017955303192138672 time for calcul the mask position with numpy : 0.008055686950683594 nb_pixel_total : 524 time to create 1 rle with old method : 0.0005528926849365234 time for calcul the mask position with numpy : 0.008075475692749023 nb_pixel_total : 634 time to create 1 rle with old method : 0.0007221698760986328 time for calcul the mask position with numpy : 0.007886648178100586 nb_pixel_total : 176 time to create 1 rle with old method : 0.0001971721649169922 time for calcul the mask position with numpy : 0.007918596267700195 nb_pixel_total : 508 time to create 1 rle with old method : 0.0005784034729003906 time for calcul the mask position with numpy : 0.007752895355224609 nb_pixel_total : 221 time to create 1 rle with old method : 0.0002396106719970703 time for calcul the mask position with numpy : 0.007708549499511719 nb_pixel_total : 319 time to create 1 rle with old method : 0.00036144256591796875 time for calcul the mask position with numpy : 0.007857561111450195 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003209114074707031 time for calcul the mask position with numpy : 0.00782322883605957 nb_pixel_total : 15 time to create 1 rle with old method : 3.123283386230469e-05 time for calcul the mask position with numpy : 0.008356571197509766 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004975795745849609 time for calcul the mask position with numpy : 0.009614706039428711 nb_pixel_total : 228 time to create 1 rle with old method : 0.000370025634765625 time for calcul the mask position with numpy : 0.009595155715942383 nb_pixel_total : 3270 time to create 1 rle with old method : 0.005272626876831055 time for calcul the mask position with numpy : 0.009610652923583984 nb_pixel_total : 684 time to create 1 rle with old method : 0.0012218952178955078 time for calcul the mask position with numpy : 0.009648561477661133 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003085136413574219 time for calcul the mask position with numpy : 0.009665250778198242 nb_pixel_total : 159 time to create 1 rle with old method : 0.00027060508728027344 time for calcul the mask position with numpy : 0.009590864181518555 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002391338348388672 time for calcul the mask position with numpy : 0.009653568267822266 nb_pixel_total : 367 time to create 1 rle with old method : 0.0006420612335205078 time for calcul the mask position with numpy : 0.009020805358886719 nb_pixel_total : 155 time to create 1 rle with old method : 0.00016355514526367188 time for calcul the mask position with numpy : 0.008094072341918945 nb_pixel_total : 263 time to create 1 rle with old method : 0.0002932548522949219 time for calcul the mask position with numpy : 0.007999897003173828 nb_pixel_total : 964 time to create 1 rle with old method : 0.0009870529174804688 time for calcul the mask position with numpy : 0.007937192916870117 nb_pixel_total : 276 time to create 1 rle with old method : 0.00029015541076660156 time for calcul the mask position with numpy : 0.007871627807617188 nb_pixel_total : 9 time to create 1 rle with old method : 2.0503997802734375e-05 time for calcul the mask position with numpy : 0.00789022445678711 nb_pixel_total : 587 time to create 1 rle with old method : 0.0006020069122314453 time for calcul the mask position with numpy : 0.007881879806518555 nb_pixel_total : 150 time to create 1 rle with old method : 0.00015807151794433594 time for calcul the mask position with numpy : 0.007963180541992188 nb_pixel_total : 20 time to create 1 rle with old method : 3.552436828613281e-05 create new chi : 1.4000880718231201 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 : 0.01038217544555664 batch 1 Loaded 109 chid ids of type : 4230 Number RLEs to save : 11640 TO DO : save crop sub photo not yet done ! save time : 0.6904029846191406 nb_obj : 103 nb_hashtags : 6 time to prepare the origin masks : 1.9144320487976074 time for calcul the mask position with numpy : 0.0328369140625 nb_pixel_total : 1882915 time to create 1 rle with new method : 0.06014108657836914 time for calcul the mask position with numpy : 0.009546041488647461 nb_pixel_total : 2135 time to create 1 rle with old method : 0.002284526824951172 time for calcul the mask position with numpy : 0.009287357330322266 nb_pixel_total : 290 time to create 1 rle with old method : 0.00033354759216308594 time for calcul the mask position with numpy : 0.008052349090576172 nb_pixel_total : 59393 time to create 1 rle with old method : 0.061767578125 time for calcul the mask position with numpy : 0.009760141372680664 nb_pixel_total : 989 time to create 1 rle with old method : 0.0010313987731933594 time for calcul the mask position with numpy : 0.009534358978271484 nb_pixel_total : 1501 time to create 1 rle with old method : 0.0017080307006835938 time for calcul the mask position with numpy : 0.009609699249267578 nb_pixel_total : 494 time to create 1 rle with old method : 0.0005729198455810547 time for calcul the mask position with numpy : 0.0055751800537109375 nb_pixel_total : 73 time to create 1 rle with old method : 9.965896606445312e-05 time for calcul the mask position with numpy : 0.005576133728027344 nb_pixel_total : 870 time to create 1 rle with old method : 0.0010380744934082031 time for calcul the mask position with numpy : 0.0055065155029296875 nb_pixel_total : 116 time to create 1 rle with old method : 0.00017023086547851562 time for calcul the mask position with numpy : 0.005488157272338867 nb_pixel_total : 829 time to create 1 rle with old method : 0.0010743141174316406 time for calcul the mask position with numpy : 0.005503416061401367 nb_pixel_total : 478 time to create 1 rle with old method : 0.0005795955657958984 time for calcul the mask position with numpy : 0.005608558654785156 nb_pixel_total : 2481 time to create 1 rle with old method : 0.0027878284454345703 time for calcul the mask position with numpy : 0.005706787109375 nb_pixel_total : 34 time to create 1 rle with old method : 5.4836273193359375e-05 time for calcul the mask position with numpy : 0.005659341812133789 nb_pixel_total : 881 time to create 1 rle with old method : 0.0009067058563232422 time for calcul the mask position with numpy : 0.005613565444946289 nb_pixel_total : 4882 time to create 1 rle with old method : 0.004991054534912109 time for calcul the mask position with numpy : 0.005559444427490234 nb_pixel_total : 1233 time to create 1 rle with old method : 0.001253366470336914 time for calcul the mask position with numpy : 0.005507469177246094 nb_pixel_total : 1026 time to create 1 rle with old method : 0.001026153564453125 time for calcul the mask position with numpy : 0.005578279495239258 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004949569702148438 time for calcul the mask position with numpy : 0.005491018295288086 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002048015594482422 time for calcul the mask position with numpy : 0.005446434020996094 nb_pixel_total : 403 time to create 1 rle with old method : 0.00044035911560058594 time for calcul the mask position with numpy : 0.0054705142974853516 nb_pixel_total : 2882 time to create 1 rle with old method : 0.0030617713928222656 time for calcul the mask position with numpy : 0.005576610565185547 nb_pixel_total : 930 time to create 1 rle with old method : 0.0010194778442382812 time for calcul the mask position with numpy : 0.00546717643737793 nb_pixel_total : 874 time to create 1 rle with old method : 0.0009555816650390625 time for calcul the mask position with numpy : 0.005453824996948242 nb_pixel_total : 6120 time to create 1 rle with old method : 0.00648188591003418 time for calcul the mask position with numpy : 0.00547027587890625 nb_pixel_total : 9473 time to create 1 rle with old method : 0.010234594345092773 time for calcul the mask position with numpy : 0.0059659481048583984 nb_pixel_total : 1084 time to create 1 rle with old method : 0.0011653900146484375 time for calcul the mask position with numpy : 0.005546092987060547 nb_pixel_total : 571 time to create 1 rle with old method : 0.0006971359252929688 time for calcul the mask position with numpy : 0.0056264400482177734 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005228519439697266 time for calcul the mask position with numpy : 0.009492158889770508 nb_pixel_total : 8255 time to create 1 rle with old method : 0.00874471664428711 time for calcul the mask position with numpy : 0.009548187255859375 nb_pixel_total : 809 time to create 1 rle with old method : 0.0008268356323242188 time for calcul the mask position with numpy : 0.009765863418579102 nb_pixel_total : 647 time to create 1 rle with old method : 0.0007503032684326172 time for calcul the mask position with numpy : 0.010282039642333984 nb_pixel_total : 122 time to create 1 rle with old method : 0.0001575946807861328 time for calcul the mask position with numpy : 0.010161161422729492 nb_pixel_total : 14357 time to create 1 rle with old method : 0.015581607818603516 time for calcul the mask position with numpy : 0.009244441986083984 nb_pixel_total : 384 time to create 1 rle with old method : 0.0004227161407470703 time for calcul the mask position with numpy : 0.006241321563720703 nb_pixel_total : 120 time to create 1 rle with old method : 0.0001804828643798828 time for calcul the mask position with numpy : 0.006335020065307617 nb_pixel_total : 1202 time to create 1 rle with old method : 0.001428842544555664 time for calcul the mask position with numpy : 0.006242513656616211 nb_pixel_total : 16818 time to create 1 rle with old method : 0.017818212509155273 time for calcul the mask position with numpy : 0.006151914596557617 nb_pixel_total : 654 time to create 1 rle with old method : 0.0007696151733398438 time for calcul the mask position with numpy : 0.006165742874145508 nb_pixel_total : 1411 time to create 1 rle with old method : 0.0016436576843261719 time for calcul the mask position with numpy : 0.006142854690551758 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002071857452392578 time for calcul the mask position with numpy : 0.006138324737548828 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007915496826171875 time for calcul the mask position with numpy : 0.006095409393310547 nb_pixel_total : 1535 time to create 1 rle with old method : 0.0018968582153320312 time for calcul the mask position with numpy : 0.006072521209716797 nb_pixel_total : 4347 time to create 1 rle with old method : 0.0049288272857666016 time for calcul the mask position with numpy : 0.0059833526611328125 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005681514739990234 time for calcul the mask position with numpy : 0.006108283996582031 nb_pixel_total : 377 time to create 1 rle with old method : 0.0004825592041015625 time for calcul the mask position with numpy : 0.006058692932128906 nb_pixel_total : 1780 time to create 1 rle with old method : 0.0020165443420410156 time for calcul the mask position with numpy : 0.00594329833984375 nb_pixel_total : 1806 time to create 1 rle with old method : 0.002080202102661133 time for calcul the mask position with numpy : 0.0061190128326416016 nb_pixel_total : 394 time to create 1 rle with old method : 0.0004761219024658203 time for calcul the mask position with numpy : 0.005967617034912109 nb_pixel_total : 124 time to create 1 rle with old method : 0.00016450881958007812 time for calcul the mask position with numpy : 0.006036281585693359 nb_pixel_total : 2415 time to create 1 rle with old method : 0.0026617050170898438 time for calcul the mask position with numpy : 0.0059163570404052734 nb_pixel_total : 1908 time to create 1 rle with old method : 0.0020172595977783203 time for calcul the mask position with numpy : 0.00610041618347168 nb_pixel_total : 1363 time to create 1 rle with old method : 0.0014247894287109375 time for calcul the mask position with numpy : 0.006340503692626953 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003085136413574219 time for calcul the mask position with numpy : 0.0059468746185302734 nb_pixel_total : 860 time to create 1 rle with old method : 0.0009953975677490234 time for calcul the mask position with numpy : 0.005783796310424805 nb_pixel_total : 2500 time to create 1 rle with old method : 0.0028083324432373047 time for calcul the mask position with numpy : 0.0058062076568603516 nb_pixel_total : 208 time to create 1 rle with old method : 0.00023746490478515625 time for calcul the mask position with numpy : 0.006015300750732422 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002765655517578125 time for calcul the mask position with numpy : 0.0059278011322021484 nb_pixel_total : 166 time to create 1 rle with old method : 0.00023794174194335938 time for calcul the mask position with numpy : 0.00579071044921875 nb_pixel_total : 1293 time to create 1 rle with old method : 0.0015244483947753906 time for calcul the mask position with numpy : 0.0059413909912109375 nb_pixel_total : 76 time to create 1 rle with old method : 0.00012350082397460938 time for calcul the mask position with numpy : 0.00594329833984375 nb_pixel_total : 699 time to create 1 rle with old method : 0.0009124279022216797 time for calcul the mask position with numpy : 0.0057353973388671875 nb_pixel_total : 1094 time to create 1 rle with old method : 0.001249074935913086 time for calcul the mask position with numpy : 0.005838871002197266 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002512931823730469 time for calcul the mask position with numpy : 0.006015300750732422 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002429485321044922 time for calcul the mask position with numpy : 0.006053924560546875 nb_pixel_total : 149 time to create 1 rle with old method : 0.0002307891845703125 time for calcul the mask position with numpy : 0.005944967269897461 nb_pixel_total : 250 time to create 1 rle with old method : 0.0002980232238769531 time for calcul the mask position with numpy : 0.005961418151855469 nb_pixel_total : 54 time to create 1 rle with old method : 8.320808410644531e-05 time for calcul the mask position with numpy : 0.0059337615966796875 nb_pixel_total : 3611 time to create 1 rle with old method : 0.004130840301513672 time for calcul the mask position with numpy : 0.005913734436035156 nb_pixel_total : 145 time to create 1 rle with old method : 0.00019216537475585938 time for calcul the mask position with numpy : 0.006114959716796875 nb_pixel_total : 129 time to create 1 rle with old method : 0.0001697540283203125 time for calcul the mask position with numpy : 0.005789279937744141 nb_pixel_total : 399 time to create 1 rle with old method : 0.00045013427734375 time for calcul the mask position with numpy : 0.0057926177978515625 nb_pixel_total : 290 time to create 1 rle with old method : 0.00035381317138671875 time for calcul the mask position with numpy : 0.005985260009765625 nb_pixel_total : 145 time to create 1 rle with old method : 0.0001938343048095703 time for calcul the mask position with numpy : 0.005927562713623047 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005545616149902344 time for calcul the mask position with numpy : 0.005870819091796875 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002627372741699219 time for calcul the mask position with numpy : 0.005785703659057617 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001246929168701172 time for calcul the mask position with numpy : 0.005939006805419922 nb_pixel_total : 2727 time to create 1 rle with old method : 0.0031576156616210938 time for calcul the mask position with numpy : 0.005814790725708008 nb_pixel_total : 15 time to create 1 rle with old method : 5.125999450683594e-05 time for calcul the mask position with numpy : 0.005874156951904297 nb_pixel_total : 217 time to create 1 rle with old method : 0.00025773048400878906 time for calcul the mask position with numpy : 0.005914211273193359 nb_pixel_total : 7 time to create 1 rle with old method : 4.124641418457031e-05 time for calcul the mask position with numpy : 0.005880594253540039 nb_pixel_total : 647 time to create 1 rle with old method : 0.0008161067962646484 time for calcul the mask position with numpy : 0.0061969757080078125 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005507469177246094 time for calcul the mask position with numpy : 0.006057024002075195 nb_pixel_total : 1602 time to create 1 rle with old method : 0.001718282699584961 time for calcul the mask position with numpy : 0.006051063537597656 nb_pixel_total : 300 time to create 1 rle with old method : 0.00033593177795410156 time for calcul the mask position with numpy : 0.0060269832611083984 nb_pixel_total : 1607 time to create 1 rle with old method : 0.0017628669738769531 time for calcul the mask position with numpy : 0.005955219268798828 nb_pixel_total : 149 time to create 1 rle with old method : 0.0001823902130126953 time for calcul the mask position with numpy : 0.005919933319091797 nb_pixel_total : 190 time to create 1 rle with old method : 0.00022935867309570312 time for calcul the mask position with numpy : 0.00597071647644043 nb_pixel_total : 1861 time to create 1 rle with old method : 0.0020499229431152344 time for calcul the mask position with numpy : 0.006033420562744141 nb_pixel_total : 337 time to create 1 rle with old method : 0.0003590583801269531 time for calcul the mask position with numpy : 0.006119966506958008 nb_pixel_total : 206 time to create 1 rle with old method : 0.00022530555725097656 time for calcul the mask position with numpy : 0.005938529968261719 nb_pixel_total : 217 time to create 1 rle with old method : 0.0002582073211669922 time for calcul the mask position with numpy : 0.005871772766113281 nb_pixel_total : 148 time to create 1 rle with old method : 0.0001735687255859375 time for calcul the mask position with numpy : 0.0058786869049072266 nb_pixel_total : 12 time to create 1 rle with old method : 7.772445678710938e-05 time for calcul the mask position with numpy : 0.00602412223815918 nb_pixel_total : 164 time to create 1 rle with old method : 0.0001857280731201172 time for calcul the mask position with numpy : 0.009473800659179688 nb_pixel_total : 824 time to create 1 rle with old method : 0.001657247543334961 time for calcul the mask position with numpy : 0.009527206420898438 nb_pixel_total : 45 time to create 1 rle with old method : 0.0001227855682373047 time for calcul the mask position with numpy : 0.006237030029296875 nb_pixel_total : 138 time to create 1 rle with old method : 0.0001723766326904297 time for calcul the mask position with numpy : 0.005728006362915039 nb_pixel_total : 297 time to create 1 rle with old method : 0.00033926963806152344 time for calcul the mask position with numpy : 0.0058972835540771484 nb_pixel_total : 270 time to create 1 rle with old method : 0.00034999847412109375 time for calcul the mask position with numpy : 0.005807161331176758 nb_pixel_total : 733 time to create 1 rle with old method : 0.0008873939514160156 time for calcul the mask position with numpy : 0.005845308303833008 nb_pixel_total : 537 time to create 1 rle with old method : 0.0005640983581542969 time for calcul the mask position with numpy : 0.0058596134185791016 nb_pixel_total : 95 time to create 1 rle with old method : 0.00012254714965820312 time for calcul the mask position with numpy : 0.005824565887451172 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002090930938720703 create new chi : 0.9607734680175781 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 : 0.0015652179718017578 batch 1 Loaded 104 chid ids of type : 4230 Number RLEs to save : 11375 TO DO : save crop sub photo not yet done ! save time : 0.6444566249847412 nb_obj : 102 nb_hashtags : 7 time to prepare the origin masks : 1.2304842472076416 time for calcul the mask position with numpy : 0.017762422561645508 nb_pixel_total : 1839318 time to create 1 rle with new method : 0.03326416015625 time for calcul the mask position with numpy : 0.0060307979583740234 nb_pixel_total : 3636 time to create 1 rle with old method : 0.0040585994720458984 time for calcul the mask position with numpy : 0.00577855110168457 nb_pixel_total : 1080 time to create 1 rle with old method : 0.0011937618255615234 time for calcul the mask position with numpy : 0.0056552886962890625 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006029605865478516 time for calcul the mask position with numpy : 0.005603790283203125 nb_pixel_total : 76 time to create 1 rle with old method : 0.00010514259338378906 time for calcul the mask position with numpy : 0.0055539608001708984 nb_pixel_total : 129 time to create 1 rle with old method : 0.00017714500427246094 time for calcul the mask position with numpy : 0.005551576614379883 nb_pixel_total : 826 time to create 1 rle with old method : 0.0008699893951416016 time for calcul the mask position with numpy : 0.00575566291809082 nb_pixel_total : 622 time to create 1 rle with old method : 0.0007534027099609375 time for calcul the mask position with numpy : 0.005806684494018555 nb_pixel_total : 2591 time to create 1 rle with old method : 0.002686023712158203 time for calcul the mask position with numpy : 0.0056345462799072266 nb_pixel_total : 439 time to create 1 rle with old method : 0.0005505084991455078 time for calcul the mask position with numpy : 0.0055658817291259766 nb_pixel_total : 533 time to create 1 rle with old method : 0.000583648681640625 time for calcul the mask position with numpy : 0.005574464797973633 nb_pixel_total : 993 time to create 1 rle with old method : 0.0011134147644042969 time for calcul the mask position with numpy : 0.005501508712768555 nb_pixel_total : 11 time to create 1 rle with old method : 3.504753112792969e-05 time for calcul the mask position with numpy : 0.005527973175048828 nb_pixel_total : 739 time to create 1 rle with old method : 0.0007789134979248047 time for calcul the mask position with numpy : 0.005712032318115234 nb_pixel_total : 180 time to create 1 rle with old method : 0.000209808349609375 time for calcul the mask position with numpy : 0.0055081844329833984 nb_pixel_total : 400 time to create 1 rle with old method : 0.0004684925079345703 time for calcul the mask position with numpy : 0.005483388900756836 nb_pixel_total : 638 time to create 1 rle with old method : 0.0007255077362060547 time for calcul the mask position with numpy : 0.0056340694427490234 nb_pixel_total : 5679 time to create 1 rle with old method : 0.006577491760253906 time for calcul the mask position with numpy : 0.005589485168457031 nb_pixel_total : 9058 time to create 1 rle with old method : 0.010044097900390625 time for calcul the mask position with numpy : 0.00556182861328125 nb_pixel_total : 453 time to create 1 rle with old method : 0.0006225109100341797 time for calcul the mask position with numpy : 0.005665302276611328 nb_pixel_total : 1443 time to create 1 rle with old method : 0.0016696453094482422 time for calcul the mask position with numpy : 0.005544900894165039 nb_pixel_total : 581 time to create 1 rle with old method : 0.0006940364837646484 time for calcul the mask position with numpy : 0.0057408809661865234 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006041526794433594 time for calcul the mask position with numpy : 0.0072553157806396484 nb_pixel_total : 6453 time to create 1 rle with old method : 0.00690007209777832 time for calcul the mask position with numpy : 0.009386777877807617 nb_pixel_total : 757 time to create 1 rle with old method : 0.0009055137634277344 time for calcul the mask position with numpy : 0.00957179069519043 nb_pixel_total : 86 time to create 1 rle with old method : 0.00012540817260742188 time for calcul the mask position with numpy : 0.009610176086425781 nb_pixel_total : 508 time to create 1 rle with old method : 0.0006108283996582031 time for calcul the mask position with numpy : 0.009432077407836914 nb_pixel_total : 138 time to create 1 rle with old method : 0.00018644332885742188 time for calcul the mask position with numpy : 0.009220123291015625 nb_pixel_total : 102 time to create 1 rle with old method : 0.0001373291015625 time for calcul the mask position with numpy : 0.009484529495239258 nb_pixel_total : 1153 time to create 1 rle with old method : 0.0013117790222167969 time for calcul the mask position with numpy : 0.009906768798828125 nb_pixel_total : 337 time to create 1 rle with old method : 0.00037026405334472656 time for calcul the mask position with numpy : 0.009252786636352539 nb_pixel_total : 191 time to create 1 rle with old method : 0.00023627281188964844 time for calcul the mask position with numpy : 0.0092620849609375 nb_pixel_total : 6530 time to create 1 rle with old method : 0.006694316864013672 time for calcul the mask position with numpy : 0.00918889045715332 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002071857452392578 time for calcul the mask position with numpy : 0.009073734283447266 nb_pixel_total : 169 time to create 1 rle with old method : 0.00019073486328125 time for calcul the mask position with numpy : 0.009318113327026367 nb_pixel_total : 536 time to create 1 rle with old method : 0.0006012916564941406 time for calcul the mask position with numpy : 0.009502649307250977 nb_pixel_total : 1436 time to create 1 rle with old method : 0.0016591548919677734 time for calcul the mask position with numpy : 0.009606599807739258 nb_pixel_total : 321 time to create 1 rle with old method : 0.00047898292541503906 time for calcul the mask position with numpy : 0.006067514419555664 nb_pixel_total : 379 time to create 1 rle with old method : 0.0004260540008544922 time for calcul the mask position with numpy : 0.005903482437133789 nb_pixel_total : 2085 time to create 1 rle with old method : 0.0021474361419677734 time for calcul the mask position with numpy : 0.005860567092895508 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004820823669433594 time for calcul the mask position with numpy : 0.005939483642578125 nb_pixel_total : 316 time to create 1 rle with old method : 0.00041985511779785156 time for calcul the mask position with numpy : 0.00590825080871582 nb_pixel_total : 111 time to create 1 rle with old method : 0.00013709068298339844 time for calcul the mask position with numpy : 0.006005525588989258 nb_pixel_total : 2073 time to create 1 rle with old method : 0.002401590347290039 time for calcul the mask position with numpy : 0.005848884582519531 nb_pixel_total : 9 time to create 1 rle with old method : 4.9114227294921875e-05 time for calcul the mask position with numpy : 0.005974292755126953 nb_pixel_total : 379 time to create 1 rle with old method : 0.0004439353942871094 time for calcul the mask position with numpy : 0.005778789520263672 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0011396408081054688 time for calcul the mask position with numpy : 0.006203174591064453 nb_pixel_total : 105989 time to create 1 rle with old method : 0.10494160652160645 time for calcul the mask position with numpy : 0.005700826644897461 nb_pixel_total : 1667 time to create 1 rle with old method : 0.0018470287322998047 time for calcul the mask position with numpy : 0.0057773590087890625 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002200603485107422 time for calcul the mask position with numpy : 0.005970954895019531 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002524852752685547 time for calcul the mask position with numpy : 0.005698442459106445 nb_pixel_total : 171 time to create 1 rle with old method : 0.00020599365234375 time for calcul the mask position with numpy : 0.005857706069946289 nb_pixel_total : 592 time to create 1 rle with old method : 0.0007045269012451172 time for calcul the mask position with numpy : 0.005849361419677734 nb_pixel_total : 41049 time to create 1 rle with old method : 0.04283428192138672 time for calcul the mask position with numpy : 0.005690097808837891 nb_pixel_total : 46 time to create 1 rle with old method : 7.939338684082031e-05 time for calcul the mask position with numpy : 0.005677700042724609 nb_pixel_total : 470 time to create 1 rle with old method : 0.0005037784576416016 time for calcul the mask position with numpy : 0.00561976432800293 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002739429473876953 time for calcul the mask position with numpy : 0.008613109588623047 nb_pixel_total : 285 time to create 1 rle with old method : 0.00036144256591796875 time for calcul the mask position with numpy : 0.00552821159362793 nb_pixel_total : 1002 time to create 1 rle with old method : 0.001050710678100586 time for calcul the mask position with numpy : 0.005718708038330078 nb_pixel_total : 483 time to create 1 rle with old method : 0.0005671977996826172 time for calcul the mask position with numpy : 0.005939006805419922 nb_pixel_total : 21 time to create 1 rle with old method : 5.7697296142578125e-05 time for calcul the mask position with numpy : 0.005664348602294922 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002512931823730469 time for calcul the mask position with numpy : 0.006003618240356445 nb_pixel_total : 187 time to create 1 rle with old method : 0.00021457672119140625 time for calcul the mask position with numpy : 0.005604267120361328 nb_pixel_total : 118 time to create 1 rle with old method : 0.00018072128295898438 time for calcul the mask position with numpy : 0.005722999572753906 nb_pixel_total : 20 time to create 1 rle with old method : 4.482269287109375e-05 time for calcul the mask position with numpy : 0.0056955814361572266 nb_pixel_total : 238 time to create 1 rle with old method : 0.0002663135528564453 time for calcul the mask position with numpy : 0.005561113357543945 nb_pixel_total : 66 time to create 1 rle with old method : 9.012222290039062e-05 time for calcul the mask position with numpy : 0.005676984786987305 nb_pixel_total : 50 time to create 1 rle with old method : 7.43865966796875e-05 time for calcul the mask position with numpy : 0.005555868148803711 nb_pixel_total : 137 time to create 1 rle with old method : 0.00016021728515625 time for calcul the mask position with numpy : 0.00567317008972168 nb_pixel_total : 144 time to create 1 rle with old method : 0.00018024444580078125 time for calcul the mask position with numpy : 0.0060045719146728516 nb_pixel_total : 6629 time to create 1 rle with old method : 0.006989717483520508 time for calcul the mask position with numpy : 0.005858659744262695 nb_pixel_total : 290 time to create 1 rle with old method : 0.00037598609924316406 time for calcul the mask position with numpy : 0.006213188171386719 nb_pixel_total : 376 time to create 1 rle with old method : 0.0004336833953857422 time for calcul the mask position with numpy : 0.005796194076538086 nb_pixel_total : 154 time to create 1 rle with old method : 0.00019049644470214844 time for calcul the mask position with numpy : 0.005977153778076172 nb_pixel_total : 264 time to create 1 rle with old method : 0.0002949237823486328 time for calcul the mask position with numpy : 0.005839347839355469 nb_pixel_total : 3476 time to create 1 rle with old method : 0.0039196014404296875 time for calcul the mask position with numpy : 0.005884408950805664 nb_pixel_total : 216 time to create 1 rle with old method : 0.0002465248107910156 time for calcul the mask position with numpy : 0.005817890167236328 nb_pixel_total : 940 time to create 1 rle with old method : 0.001697540283203125 time for calcul the mask position with numpy : 0.005922079086303711 nb_pixel_total : 666 time to create 1 rle with old method : 0.0007519721984863281 time for calcul the mask position with numpy : 0.005770683288574219 nb_pixel_total : 212 time to create 1 rle with old method : 0.0002372264862060547 time for calcul the mask position with numpy : 0.00579524040222168 nb_pixel_total : 26 time to create 1 rle with old method : 7.128715515136719e-05 time for calcul the mask position with numpy : 0.005826711654663086 nb_pixel_total : 1519 time to create 1 rle with old method : 0.0017271041870117188 time for calcul the mask position with numpy : 0.005690574645996094 nb_pixel_total : 1506 time to create 1 rle with old method : 0.0016484260559082031 time for calcul the mask position with numpy : 0.005524635314941406 nb_pixel_total : 234 time to create 1 rle with old method : 0.0002574920654296875 time for calcul the mask position with numpy : 0.005522251129150391 nb_pixel_total : 424 time to create 1 rle with old method : 0.0004630088806152344 time for calcul the mask position with numpy : 0.005545377731323242 nb_pixel_total : 15 time to create 1 rle with old method : 4.863739013671875e-05 time for calcul the mask position with numpy : 0.005602121353149414 nb_pixel_total : 54 time to create 1 rle with old method : 9.083747863769531e-05 time for calcul the mask position with numpy : 0.005707979202270508 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003380775451660156 time for calcul the mask position with numpy : 0.005650997161865234 nb_pixel_total : 58 time to create 1 rle with old method : 8.749961853027344e-05 time for calcul the mask position with numpy : 0.0056607723236083984 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003216266632080078 time for calcul the mask position with numpy : 0.005611896514892578 nb_pixel_total : 2040 time to create 1 rle with old method : 0.0021829605102539062 time for calcul the mask position with numpy : 0.005654573440551758 nb_pixel_total : 1209 time to create 1 rle with old method : 0.0013806819915771484 time for calcul the mask position with numpy : 0.0056803226470947266 nb_pixel_total : 213 time to create 1 rle with old method : 0.00024199485778808594 time for calcul the mask position with numpy : 0.005575895309448242 nb_pixel_total : 393 time to create 1 rle with old method : 0.0004611015319824219 time for calcul the mask position with numpy : 0.005574464797973633 nb_pixel_total : 17 time to create 1 rle with old method : 4.673004150390625e-05 time for calcul the mask position with numpy : 0.005544900894165039 nb_pixel_total : 35 time to create 1 rle with old method : 6.246566772460938e-05 time for calcul the mask position with numpy : 0.005565643310546875 nb_pixel_total : 278 time to create 1 rle with old method : 0.0003077983856201172 time for calcul the mask position with numpy : 0.00558161735534668 nb_pixel_total : 640 time to create 1 rle with old method : 0.0007293224334716797 time for calcul the mask position with numpy : 0.00551915168762207 nb_pixel_total : 260 time to create 1 rle with old method : 0.00030040740966796875 time for calcul the mask position with numpy : 0.00574183464050293 nb_pixel_total : 549 time to create 1 rle with old method : 0.0007505416870117188 time for calcul the mask position with numpy : 0.005677223205566406 nb_pixel_total : 487 time to create 1 rle with old method : 0.0005626678466796875 time for calcul the mask position with numpy : 0.0055370330810546875 nb_pixel_total : 112 time to create 1 rle with old method : 0.000133514404296875 time for calcul the mask position with numpy : 0.0056896209716796875 nb_pixel_total : 175 time to create 1 rle with old method : 0.00020360946655273438 create new chi : 0.9403421878814697 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 : 0.0014028549194335938 batch 1 Loaded 103 chid ids of type : 4230 Number RLEs to save : 10234 TO DO : save crop sub photo not yet done ! save time : 0.6115689277648926 nb_obj : 101 nb_hashtags : 7 time to prepare the origin masks : 1.2990820407867432 time for calcul the mask position with numpy : 0.018280982971191406 nb_pixel_total : 1835129 time to create 1 rle with new method : 0.508486270904541 time for calcul the mask position with numpy : 0.005994081497192383 nb_pixel_total : 817 time to create 1 rle with old method : 0.0009377002716064453 time for calcul the mask position with numpy : 0.005952119827270508 nb_pixel_total : 2705 time to create 1 rle with old method : 0.0031578540802001953 time for calcul the mask position with numpy : 0.005808830261230469 nb_pixel_total : 278 time to create 1 rle with old method : 0.00035119056701660156 time for calcul the mask position with numpy : 0.005975484848022461 nb_pixel_total : 621 time to create 1 rle with old method : 0.0007784366607666016 time for calcul the mask position with numpy : 0.0058078765869140625 nb_pixel_total : 506 time to create 1 rle with old method : 0.0005710124969482422 time for calcul the mask position with numpy : 0.006094217300415039 nb_pixel_total : 69 time to create 1 rle with old method : 9.512901306152344e-05 time for calcul the mask position with numpy : 0.0057752132415771484 nb_pixel_total : 1239 time to create 1 rle with old method : 0.0014641284942626953 time for calcul the mask position with numpy : 0.005715370178222656 nb_pixel_total : 143 time to create 1 rle with old method : 0.00019049644470214844 time for calcul the mask position with numpy : 0.006322622299194336 nb_pixel_total : 43139 time to create 1 rle with old method : 0.04884982109069824 time for calcul the mask position with numpy : 0.005892038345336914 nb_pixel_total : 902 time to create 1 rle with old method : 0.0010373592376708984 time for calcul the mask position with numpy : 0.005864858627319336 nb_pixel_total : 3187 time to create 1 rle with old method : 0.003417491912841797 time for calcul the mask position with numpy : 0.00578618049621582 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001976490020751953 time for calcul the mask position with numpy : 0.005641460418701172 nb_pixel_total : 460 time to create 1 rle with old method : 0.00048661231994628906 time for calcul the mask position with numpy : 0.006335735321044922 nb_pixel_total : 982 time to create 1 rle with old method : 0.0011048316955566406 time for calcul the mask position with numpy : 0.006658077239990234 nb_pixel_total : 107 time to create 1 rle with old method : 0.00028586387634277344 time for calcul the mask position with numpy : 0.006235361099243164 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002143383026123047 time for calcul the mask position with numpy : 0.0059986114501953125 nb_pixel_total : 430 time to create 1 rle with old method : 0.0004687309265136719 time for calcul the mask position with numpy : 0.005959033966064453 nb_pixel_total : 2763 time to create 1 rle with old method : 0.003081798553466797 time for calcul the mask position with numpy : 0.00614166259765625 nb_pixel_total : 1254 time to create 1 rle with old method : 0.0015110969543457031 time for calcul the mask position with numpy : 0.006067514419555664 nb_pixel_total : 861 time to create 1 rle with old method : 0.0009784698486328125 time for calcul the mask position with numpy : 0.005986690521240234 nb_pixel_total : 847 time to create 1 rle with old method : 0.0009770393371582031 time for calcul the mask position with numpy : 0.0058116912841796875 nb_pixel_total : 1561 time to create 1 rle with old method : 0.0016796588897705078 time for calcul the mask position with numpy : 0.005850553512573242 nb_pixel_total : 590 time to create 1 rle with old method : 0.0007576942443847656 time for calcul the mask position with numpy : 0.006003618240356445 nb_pixel_total : 8827 time to create 1 rle with old method : 0.009390592575073242 time for calcul the mask position with numpy : 0.006020307540893555 nb_pixel_total : 1610 time to create 1 rle with old method : 0.0018148422241210938 time for calcul the mask position with numpy : 0.0060808658599853516 nb_pixel_total : 1694 time to create 1 rle with old method : 0.0018758773803710938 time for calcul the mask position with numpy : 0.005997657775878906 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005762577056884766 time for calcul the mask position with numpy : 0.0062329769134521484 nb_pixel_total : 862 time to create 1 rle with old method : 0.0009560585021972656 time for calcul the mask position with numpy : 0.006023406982421875 nb_pixel_total : 3 time to create 1 rle with old method : 2.7418136596679688e-05 time for calcul the mask position with numpy : 0.005851030349731445 nb_pixel_total : 597 time to create 1 rle with old method : 0.0006937980651855469 time for calcul the mask position with numpy : 0.0059320926666259766 nb_pixel_total : 158 time to create 1 rle with old method : 0.00019216537475585938 time for calcul the mask position with numpy : 0.005781650543212891 nb_pixel_total : 13301 time to create 1 rle with old method : 0.014060735702514648 time for calcul the mask position with numpy : 0.005718708038330078 nb_pixel_total : 1119 time to create 1 rle with old method : 0.0011515617370605469 time for calcul the mask position with numpy : 0.005651712417602539 nb_pixel_total : 418 time to create 1 rle with old method : 0.0004711151123046875 time for calcul the mask position with numpy : 0.005820035934448242 nb_pixel_total : 6597 time to create 1 rle with old method : 0.007589817047119141 time for calcul the mask position with numpy : 0.006051063537597656 nb_pixel_total : 181 time to create 1 rle with old method : 0.00022840499877929688 time for calcul the mask position with numpy : 0.006036520004272461 nb_pixel_total : 2485 time to create 1 rle with old method : 0.0029642581939697266 time for calcul the mask position with numpy : 0.006067037582397461 nb_pixel_total : 76 time to create 1 rle with old method : 0.00020956993103027344 time for calcul the mask position with numpy : 0.006111621856689453 nb_pixel_total : 2311 time to create 1 rle with old method : 0.002579212188720703 time for calcul the mask position with numpy : 0.0061740875244140625 nb_pixel_total : 483 time to create 1 rle with old method : 0.0005934238433837891 time for calcul the mask position with numpy : 0.005873441696166992 nb_pixel_total : 1137 time to create 1 rle with old method : 0.0012600421905517578 time for calcul the mask position with numpy : 0.005879402160644531 nb_pixel_total : 289 time to create 1 rle with old method : 0.000392913818359375 time for calcul the mask position with numpy : 0.0058519840240478516 nb_pixel_total : 366 time to create 1 rle with old method : 0.00039696693420410156 time for calcul the mask position with numpy : 0.005932807922363281 nb_pixel_total : 145 time to create 1 rle with old method : 0.0001976490020751953 time for calcul the mask position with numpy : 0.005711555480957031 nb_pixel_total : 1807 time to create 1 rle with old method : 0.0018346309661865234 time for calcul the mask position with numpy : 0.005708932876586914 nb_pixel_total : 564 time to create 1 rle with old method : 0.0005896091461181641 time for calcul the mask position with numpy : 0.005919218063354492 nb_pixel_total : 1016 time to create 1 rle with old method : 0.00102996826171875 time for calcul the mask position with numpy : 0.005862712860107422 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011205673217773438 time for calcul the mask position with numpy : 0.006247043609619141 nb_pixel_total : 105504 time to create 1 rle with old method : 0.10556817054748535 time for calcul the mask position with numpy : 0.005792856216430664 nb_pixel_total : 195 time to create 1 rle with old method : 0.00021839141845703125 time for calcul the mask position with numpy : 0.0056056976318359375 nb_pixel_total : 127 time to create 1 rle with old method : 0.000152587890625 time for calcul the mask position with numpy : 0.0056552886962890625 nb_pixel_total : 1043 time to create 1 rle with old method : 0.0011708736419677734 time for calcul the mask position with numpy : 0.0058596134185791016 nb_pixel_total : 54 time to create 1 rle with old method : 7.748603820800781e-05 time for calcul the mask position with numpy : 0.005708217620849609 nb_pixel_total : 289 time to create 1 rle with old method : 0.00034165382385253906 time for calcul the mask position with numpy : 0.006420612335205078 nb_pixel_total : 193 time to create 1 rle with old method : 0.00024437904357910156 time for calcul the mask position with numpy : 0.005912303924560547 nb_pixel_total : 1065 time to create 1 rle with old method : 0.0011301040649414062 time for calcul the mask position with numpy : 0.0055999755859375 nb_pixel_total : 214 time to create 1 rle with old method : 0.00023651123046875 time for calcul the mask position with numpy : 0.005596160888671875 nb_pixel_total : 421 time to create 1 rle with old method : 0.0004494190216064453 time for calcul the mask position with numpy : 0.005591869354248047 nb_pixel_total : 197 time to create 1 rle with old method : 0.00022292137145996094 time for calcul the mask position with numpy : 0.005705356597900391 nb_pixel_total : 125 time to create 1 rle with old method : 0.0001456737518310547 time for calcul the mask position with numpy : 0.005958080291748047 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003094673156738281 time for calcul the mask position with numpy : 0.005877494812011719 nb_pixel_total : 5 time to create 1 rle with old method : 2.574920654296875e-05 time for calcul the mask position with numpy : 0.006062030792236328 nb_pixel_total : 48 time to create 1 rle with old method : 7.319450378417969e-05 time for calcul the mask position with numpy : 0.005825042724609375 nb_pixel_total : 312 time to create 1 rle with old method : 0.00034308433532714844 time for calcul the mask position with numpy : 0.005663633346557617 nb_pixel_total : 620 time to create 1 rle with old method : 0.0006594657897949219 time for calcul the mask position with numpy : 0.005669355392456055 nb_pixel_total : 141 time to create 1 rle with old method : 0.00016736984252929688 time for calcul the mask position with numpy : 0.005738735198974609 nb_pixel_total : 154 time to create 1 rle with old method : 0.00018930435180664062 time for calcul the mask position with numpy : 0.005715370178222656 nb_pixel_total : 477 time to create 1 rle with old method : 0.0005087852478027344 time for calcul the mask position with numpy : 0.005619525909423828 nb_pixel_total : 2976 time to create 1 rle with old method : 0.0033338069915771484 time for calcul the mask position with numpy : 0.006063938140869141 nb_pixel_total : 975 time to create 1 rle with old method : 0.0010144710540771484 time for calcul the mask position with numpy : 0.0060558319091796875 nb_pixel_total : 211 time to create 1 rle with old method : 0.00023555755615234375 time for calcul the mask position with numpy : 0.0058269500732421875 nb_pixel_total : 127 time to create 1 rle with old method : 0.00020766258239746094 time for calcul the mask position with numpy : 0.00570368766784668 nb_pixel_total : 631 time to create 1 rle with old method : 0.0006630420684814453 time for calcul the mask position with numpy : 0.0057544708251953125 nb_pixel_total : 30 time to create 1 rle with old method : 6.031990051269531e-05 time for calcul the mask position with numpy : 0.005779266357421875 nb_pixel_total : 227 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.005756855010986328 nb_pixel_total : 471 time to create 1 rle with old method : 0.0005011558532714844 time for calcul the mask position with numpy : 0.005799770355224609 nb_pixel_total : 305 time to create 1 rle with old method : 0.0003390312194824219 time for calcul the mask position with numpy : 0.005662679672241211 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002129077911376953 time for calcul the mask position with numpy : 0.0056819915771484375 nb_pixel_total : 536 time to create 1 rle with old method : 0.0006120204925537109 time for calcul the mask position with numpy : 0.0058100223541259766 nb_pixel_total : 988 time to create 1 rle with old method : 0.001062154769897461 time for calcul the mask position with numpy : 0.005589962005615234 nb_pixel_total : 940 time to create 1 rle with old method : 0.0010099411010742188 time for calcul the mask position with numpy : 0.0055255889892578125 nb_pixel_total : 258 time to create 1 rle with old method : 0.00028324127197265625 time for calcul the mask position with numpy : 0.005857944488525391 nb_pixel_total : 288 time to create 1 rle with old method : 0.00035858154296875 time for calcul the mask position with numpy : 0.008955955505371094 nb_pixel_total : 315 time to create 1 rle with old method : 0.0003387928009033203 time for calcul the mask position with numpy : 0.0057756900787353516 nb_pixel_total : 3576 time to create 1 rle with old method : 0.003922224044799805 time for calcul the mask position with numpy : 0.005519390106201172 nb_pixel_total : 192 time to create 1 rle with old method : 0.00021314620971679688 time for calcul the mask position with numpy : 0.005608081817626953 nb_pixel_total : 194 time to create 1 rle with old method : 0.00025534629821777344 time for calcul the mask position with numpy : 0.005921840667724609 nb_pixel_total : 226 time to create 1 rle with old method : 0.0002696514129638672 time for calcul the mask position with numpy : 0.005553483963012695 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002155303955078125 time for calcul the mask position with numpy : 0.009435176849365234 nb_pixel_total : 121 time to create 1 rle with old method : 0.0001583099365234375 time for calcul the mask position with numpy : 0.00955963134765625 nb_pixel_total : 281 time to create 1 rle with old method : 0.00032711029052734375 time for calcul the mask position with numpy : 0.009364843368530273 nb_pixel_total : 296 time to create 1 rle with old method : 0.00035309791564941406 time for calcul the mask position with numpy : 0.009290218353271484 nb_pixel_total : 17 time to create 1 rle with old method : 5.435943603515625e-05 time for calcul the mask position with numpy : 0.009394407272338867 nb_pixel_total : 564 time to create 1 rle with old method : 0.00060272216796875 time for calcul the mask position with numpy : 0.00945425033569336 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005288124084472656 time for calcul the mask position with numpy : 0.009063482284545898 nb_pixel_total : 170 time to create 1 rle with old method : 0.00020360946655273438 time for calcul the mask position with numpy : 0.009305000305175781 nb_pixel_total : 20 time to create 1 rle with old method : 9.632110595703125e-05 time for calcul the mask position with numpy : 0.009382247924804688 nb_pixel_total : 63 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.009518146514892578 nb_pixel_total : 620 time to create 1 rle with old method : 0.0007555484771728516 time for calcul the mask position with numpy : 0.009469032287597656 nb_pixel_total : 81 time to create 1 rle with old method : 0.00010824203491210938 time for calcul the mask position with numpy : 0.009430170059204102 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002067089080810547 create new chi : 1.4303176403045654 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 : 0.0015707015991210938 batch 1 Loaded 102 chid ids of type : 4230 Number RLEs to save : 9809 TO DO : save crop sub photo not yet done ! save time : 4.849263906478882 map_output_result : {1340356292: (0.0, 'Should be the crop_list due to order', 0.0), 1340356289: (0.0, 'Should be the crop_list due to order', 0.0), 1340356288: (0.0, 'Should be the crop_list due to order', 0.0), 1340356287: (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 [1340356292, 1340356289, 1340356288, 1340356287] Looping around the photos to save general results len do output : 4 /1340356292.Didn't retrieve data . /1340356289.Didn't retrieve data . /1340356288.Didn't retrieve data . /1340356287.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, '2626368') ('4234', '20948718', '1340356292', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356289', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356288', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356287', None, None, None, None, None, '2626368') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.01246333122253418 save_final save missing photos in datou_result : time spend for datou_step_exec : 17.43980073928833 time spend to save output : 0.012728691101074219 total time spend for step 4 : 17.452529430389404 step5:crop_condition Sat Mar 1 11:21:23 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 4 ! batch 1 Loaded 418 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 142 About to insert : list_path_to_insert length 142 new photo from crops ! About to upload 142 photos upload in portfolio : 4869462 init cache_photo without model_param we have 142 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740824486_1634302 we have uploaded 142 photos in the portfolio 4869462 time of upload the photos Elapsed time : 49.39095067977905 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 ! map_result returned by crop_photo_return_map_crop : length : 37 About to insert : list_path_to_insert length 37 new photo from crops ! About to upload 37 photos upload in portfolio : 4869462 init cache_photo without model_param we have 37 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740824536_1634302 we have uploaded 37 photos in the portfolio 4869462 time of upload the photos Elapsed time : 8.716100454330444 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 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 ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 new photo from crops ! About to upload 14 photos upload in portfolio : 4869462 init cache_photo without model_param we have 14 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740824545_1634302 we have uploaded 14 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.3349809646606445 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 61 About to insert : list_path_to_insert length 61 new photo from crops ! About to upload 61 photos upload in portfolio : 4869462 init cache_photo without model_param we have 61 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740824550_1634302 we have uploaded 61 photos in the portfolio 4869462 time of upload the photos Elapsed time : 16.30394148826599 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 [1340356292, 1340356289, 1340356288, 1340356287] Looping around the photos to save general results len do output : 254 /1340364654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364663Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364667Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364671Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364673Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364674Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364675Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364676Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364677Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364678Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364679Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364680Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364681Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364682Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364683Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364684Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364685Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364686Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364687Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364688Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364689Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364690Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364691Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364693Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364697Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364701Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364709Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340364929Didn'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, '2626368') ('4234', '20948718', '1340356292', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356289', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356288', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356287', None, None, None, None, None, '2626368') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 766 time used for this insertion : 0.04155445098876953 save_final save missing photos in datou_result : time spend for datou_step_exec : 83.05911779403687 time spend to save output : 0.04814958572387695 total time spend for step 5 : 83.10726737976074 step6:thcl Sat Mar 1 11:22:46 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 : 0.011270523071289062 time to convert the images to numpy array : 0.07809686660766602 time to import caffe and check if the image exist : 0.023543119430541992 time to convert the images to numpy array : 0.0683286190032959 time to import caffe and check if the image exist : 0.019310712814331055 time to convert the images to numpy array : 0.07415318489074707 time to import caffe and check if the image exist : 0.02295064926147461 time to convert the images to numpy array : 0.08265066146850586 time to import caffe and check if the image exist : 0.018903732299804688 time to convert the images to numpy array : 0.09066343307495117 time to import caffe and check if the image exist : 0.025942087173461914 time to convert the images to numpy array : 0.08693289756774902 time to import caffe and check if the image exist : 0.020473480224609375 time to convert the images to numpy array : 0.09400439262390137 time to import caffe and check if the image exist : 0.03365159034729004 time to convert the images to numpy array : 0.08108901977539062 time to import caffe and check if the image exist : 0.02792191505432129 time to convert the images to numpy array : 0.0879678726196289 time to import caffe and check if the image exist : 0.025323867797851562 time to convert the images to numpy array : 0.09108209609985352 total time to convert the images to numpy array : 0.4136350154876709 list photo_ids error: [] list photo_ids correct : [1340364654, 1340364655, 1340364657, 1340364658, 1340364659, 1340364660, 1340364661, 1340364662, 1340364663, 1340364664, 1340364665, 1340364666, 1340364667, 1340364668, 1340364669, 1340364670, 1340364671, 1340364672, 1340364673, 1340364674, 1340364675, 1340364676, 1340364677, 1340364678, 1340364679, 1340364680, 1340364734, 1340364735, 1340364736, 1340364737, 1340364738, 1340364739, 1340364740, 1340364741, 1340364742, 1340364743, 1340364744, 1340364745, 1340364746, 1340364747, 1340364748, 1340364750, 1340364751, 1340364752, 1340364753, 1340364754, 1340364755, 1340364756, 1340364757, 1340364758, 1340364759, 1340364760, 1340364910, 1340364911, 1340364912, 1340364913, 1340364914, 1340364915, 1340364916, 1340364917, 1340364918, 1340364919, 1340364920, 1340364921, 1340364922, 1340364923, 1340364924, 1340364925, 1340364926, 1340364927, 1340364928, 1340364929, 1340364681, 1340364682, 1340364683, 1340364684, 1340364685, 1340364686, 1340364687, 1340364688, 1340364689, 1340364690, 1340364691, 1340364692, 1340364693, 1340364694, 1340364695, 1340364696, 1340364697, 1340364698, 1340364699, 1340364700, 1340364701, 1340364702, 1340364703, 1340364704, 1340364705, 1340364706, 1340364707, 1340364708, 1340364709, 1340364710, 1340364711, 1340364712, 1340364713, 1340364714, 1340364715, 1340364716, 1340364717, 1340364718, 1340364719, 1340364720, 1340364721, 1340364722, 1340364723, 1340364724, 1340364725, 1340364727, 1340364728, 1340364729, 1340364730, 1340364731, 1340364732, 1340364733, 1340364761, 1340364762, 1340364763, 1340364764, 1340364765, 1340364766, 1340364767, 1340364768, 1340364769, 1340364770, 1340364771, 1340364772, 1340364773, 1340364774, 1340364775, 1340364776, 1340364777, 1340364778, 1340364779, 1340364780, 1340364781, 1340364782, 1340364783, 1340364784, 1340364785, 1340364786, 1340364848, 1340364849, 1340364850, 1340364851, 1340364852, 1340364853, 1340364854, 1340364855, 1340364856, 1340364857, 1340364858, 1340364868, 1340364869, 1340364870, 1340364871, 1340364872, 1340364873, 1340364874, 1340364875, 1340364876, 1340364877, 1340364878, 1340364879, 1340364880, 1340364881, 1340364882, 1340364883, 1340364884, 1340364885, 1340364886, 1340364887, 1340364888, 1340364889, 1340364890, 1340364891, 1340364892, 1340364893, 1340364894, 1340364895, 1340364896, 1340364897, 1340364898, 1340364899, 1340364900, 1340364901, 1340364902, 1340364903, 1340364904, 1340364905, 1340364906, 1340364908, 1340364909, 1340364787, 1340364788, 1340364789, 1340364790, 1340364791, 1340364792, 1340364793, 1340364794, 1340364795, 1340364796, 1340364797, 1340364798, 1340364803, 1340364804, 1340364805, 1340364806, 1340364807, 1340364809, 1340364810, 1340364811, 1340364812, 1340364813, 1340364814, 1340364815, 1340364816, 1340364817, 1340364818, 1340364819, 1340364820, 1340364821, 1340364822, 1340364823, 1340364824, 1340364826, 1340364827, 1340364828, 1340364829, 1340364830, 1340364831, 1340364832, 1340364833, 1340364834, 1340364835, 1340364836, 1340364837, 1340364838, 1340364839, 1340364840, 1340364841, 1340364845, 1340364846, 1340364847] number of photos to traite : 254 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 : 5304 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 : 5085 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 1.1561288833618164 time used to do the prediction : 0.9941365718841553 save descriptor for thcl : 3237 time to traite the descriptors : 1.409904956817627 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1340364654 To insert : 1340364655 To insert : 1340364657 To insert : 1340364658 To insert : 1340364659 To insert : 1340364660 To insert : 1340364661 To insert : 1340364662 To insert : 1340364663 To insert : 1340364664 To insert : 1340364665 To insert : 1340364666 To insert : 1340364667 To insert : 1340364668 To insert : 1340364669 To insert : 1340364670 To insert : 1340364671 To insert : 1340364672 To insert : 1340364673 To insert : 1340364674 To insert : 1340364675 To insert : 1340364676 To insert : 1340364677 To insert : 1340364678 To insert : 1340364679 To insert : 1340364680 To insert : 1340364734 To insert : 1340364735 To insert : 1340364736 To insert : 1340364737 To insert : 1340364738 To insert : 1340364739 To insert : 1340364740 To insert : 1340364741 To insert : 1340364742 To insert : 1340364743 To insert : 1340364744 To insert : 1340364745 To insert : 1340364746 To insert : 1340364747 To insert : 1340364748 To insert : 1340364750 To insert : 1340364751 To insert : 1340364752 To insert : 1340364753 To insert : 1340364754 To insert : 1340364755 To insert : 1340364756 To insert : 1340364757 To insert : 1340364758 To insert : 1340364759 To insert : 1340364760 To insert : 1340364910 To insert : 1340364911 To insert : 1340364912 To insert : 1340364913 To insert : 1340364914 To insert : 1340364915 To insert : 1340364916 To insert : 1340364917 To insert : 1340364918 To insert : 1340364919 To insert : 1340364920 To insert : 1340364921 To insert : 1340364922 To insert : 1340364923 To insert : 1340364924 To insert : 1340364925 To insert : 1340364926 To insert : 1340364927 To insert : 1340364928 To insert : 1340364929 To insert : 1340364681 To insert : 1340364682 To insert : 1340364683 To insert : 1340364684 To insert : 1340364685 To insert : 1340364686 To insert : 1340364687 To insert : 1340364688 To insert : 1340364689 To insert : 1340364690 To insert : 1340364691 To insert : 1340364692 To insert : 1340364693 To insert : 1340364694 To insert : 1340364695 To insert : 1340364696 To insert : 1340364697 To insert : 1340364698 To insert : 1340364699 To insert : 1340364700 To insert : 1340364701 To insert : 1340364702 To insert : 1340364703 To insert : 1340364704 To insert : 1340364705 To insert : 1340364706 To insert : 1340364707 To insert : 1340364708 To insert : 1340364709 To insert : 1340364710 To insert : 1340364711 To insert : 1340364712 To insert : 1340364713 To insert : 1340364714 To insert : 1340364715 To insert : 1340364716 To insert : 1340364717 To insert : 1340364718 To insert : 1340364719 To insert : 1340364720 To insert : 1340364721 To insert : 1340364722 To insert : 1340364723 To insert : 1340364724 To insert : 1340364725 To insert : 1340364727 To insert : 1340364728 To insert : 1340364729 To insert : 1340364730 To insert : 1340364731 To insert : 1340364732 To insert : 1340364733 To insert : 1340364761 To insert : 1340364762 To insert : 1340364763 To insert : 1340364764 To insert : 1340364765 To insert : 1340364766 To insert : 1340364767 To insert : 1340364768 To insert : 1340364769 To insert : 1340364770 To insert : 1340364771 To insert : 1340364772 To insert : 1340364773 To insert : 1340364774 To insert : 1340364775 To insert : 1340364776 To insert : 1340364777 To insert : 1340364778 To insert : 1340364779 To insert : 1340364780 To insert : 1340364781 To insert : 1340364782 To insert : 1340364783 To insert : 1340364784 To insert : 1340364785 To insert : 1340364786 To insert : 1340364848 To insert : 1340364849 To insert : 1340364850 To insert : 1340364851 To insert : 1340364852 To insert : 1340364853 To insert : 1340364854 To insert : 1340364855 To insert : 1340364856 To insert : 1340364857 To insert : 1340364858 To insert : 1340364868 To insert : 1340364869 To insert : 1340364870 To insert : 1340364871 To insert : 1340364872 To insert : 1340364873 To insert : 1340364874 To insert : 1340364875 To insert : 1340364876 To insert : 1340364877 To insert : 1340364878 To insert : 1340364879 To insert : 1340364880 To insert : 1340364881 To insert : 1340364882 To insert : 1340364883 To insert : 1340364884 To insert : 1340364885 To insert : 1340364886 To insert : 1340364887 To insert : 1340364888 To insert : 1340364889 To insert : 1340364890 To insert : 1340364891 To insert : 1340364892 To insert : 1340364893 To insert : 1340364894 To insert : 1340364895 To insert : 1340364896 To insert : 1340364897 To insert : 1340364898 To insert : 1340364899 To insert : 1340364900 To insert : 1340364901 To insert : 1340364902 To insert : 1340364903 To insert : 1340364904 To insert : 1340364905 To insert : 1340364906 To insert : 1340364908 To insert : 1340364909 To insert : 1340364787 To insert : 1340364788 To insert : 1340364789 To insert : 1340364790 To insert : 1340364791 To insert : 1340364792 To insert : 1340364793 To insert : 1340364794 To insert : 1340364795 To insert : 1340364796 To insert : 1340364797 To insert : 1340364798 To insert : 1340364803 To insert : 1340364804 To insert : 1340364805 To insert : 1340364806 To insert : 1340364807 To insert : 1340364809 To insert : 1340364810 To insert : 1340364811 To insert : 1340364812 To insert : 1340364813 To insert : 1340364814 To insert : 1340364815 To insert : 1340364816 To insert : 1340364817 To insert : 1340364818 To insert : 1340364819 To insert : 1340364820 To insert : 1340364821 To insert : 1340364822 To insert : 1340364823 To insert : 1340364824 To insert : 1340364826 To insert : 1340364827 To insert : 1340364828 To insert : 1340364829 To insert : 1340364830 To insert : 1340364831 To insert : 1340364832 To insert : 1340364833 To insert : 1340364834 To insert : 1340364835 To insert : 1340364836 To insert : 1340364837 To insert : 1340364838 To insert : 1340364839 To insert : 1340364840 To insert : 1340364841 To insert : 1340364845 To insert : 1340364846 To insert : 1340364847 time to insert the descriptors : 53.41938138008118 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 : 388 time used for this insertion : 0.030089378356933594 save missing photos in datou_result : time spend for datou_step_exec : 61.490087270736694 time spend to save output : 0.08156847953796387 total time spend for step 6 : 61.57165575027466 step7:ventilate_hashtags_in_portfolio Sat Mar 1 11:23:48 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 : 20948718 get user id for portfolio 20948718 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`=20948718 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('mal_croppe','flou','Film_plastique','PEHD','carton','papier','Carton','pet_fonce','Papier','Tetrapak','pehd','metal','pet_clair','PET_fonce','environnement','autre','PET_clair','refus')) 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`=20948718 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('mal_croppe','flou','Film_plastique','PEHD','carton','papier','Carton','pet_fonce','Papier','Tetrapak','pehd','metal','pet_clair','PET_fonce','environnement','autre','PET_clair','refus')) 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`=20948718 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('mal_croppe','flou','Film_plastique','PEHD','carton','papier','Carton','pet_fonce','Papier','Tetrapak','pehd','metal','pet_clair','PET_fonce','environnement','autre','PET_clair','refus')) 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`=20948718 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('mal_croppe','flou','Film_plastique','PEHD','carton','papier','Carton','pet_fonce','Papier','Tetrapak','pehd','metal','pet_clair','PET_fonce','environnement','autre','PET_clair','refus')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20948913,20948914,20948915,20948923,20948919,20948921,20948926,20948922,20948924,20948929,20948927,20948928,20948930?tags=mal_croppe,flou,film_plastique,pehd,carton,papier,pet_fonce,tetrapak,metal,pet_clair,environnement,autre,refus&datou_id_consolidate=4235&port_consolidate=20948718 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1340356292, 1340356289, 1340356288, 1340356287] Looping around the photos to save general results len do output : 1 /20948718. 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, '2626368') ('4234', '20948718', '1340356292', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356289', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356288', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356287', None, None, None, None, None, '2626368') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012719869613647461 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.3183934688568115 time spend to save output : 0.012977361679077148 total time spend for step 7 : 2.3313708305358887 step8:final Sat Mar 1 11:23:50 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 : {1340356292: ('0.20216657906345706',), 1340356289: ('0.20216657906345706',), 1340356288: ('0.20216657906345706',), 1340356287: ('0.20216657906345706',)} new output for save of step final : {1340356292: ('0.20216657906345706',), 1340356289: ('0.20216657906345706',), 1340356288: ('0.20216657906345706',), 1340356287: ('0.20216657906345706',)} [1340356292, 1340356289, 1340356288, 1340356287] Looping around the photos to save general results len do output : 4 /1340356292.Didn't retrieve data . /1340356289.Didn't retrieve data . /1340356288.Didn't retrieve data . /1340356287.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, '2626368') ('4234', '20948718', '1340356292', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356289', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356288', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356287', None, None, None, None, None, '2626368') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.012541770935058594 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12810420989990234 time spend to save output : 0.01284027099609375 total time spend for step 8 : 0.1409444808959961 step9:velours_tree Sat Mar 1 11:23:50 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 : 20948913,20948914,20948915,20948923,20948919,20948921,20948926,20948922,20948924,20948929,20948927,20948928,20948930 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=20948913 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=20948914 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=20948915 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=20948923 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=20948919 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=20948921 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=20948926 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=20948922 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=20948924 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=20948929 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=20948927 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=20948928 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=20948930 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 254 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [3 5 2 5 5 2 2 0 2 0 1 5 1 1 5 2 4 2 4 5 1 5 5 5 5 0 5 0 5 5 5 5 1 5 5 5 5 5 4 2 1 5 0 5 3 5 2 2 2 2 0 2 1 5 1 1 1 1 2 4 5 5 1 5 0 2 2 5 5 1 5 5 5 0 5 3 2 2 2 2 1 2 1 5 1 5 1 2 2 0 5 2 5 2 5 5 5 5 2 4 5 3 0 5 2 0 1 5 1 5 1 1 1 5 1 2 2 4 5 5 5 1 2 5 5 0 2 0 0 5 5 5 5 5 5 5 4 4 2 0 5 0 2 0 2 3 4 0 4 1 4 4 0 2 2 3 5 4 5 4 0 4 2 5 4 5 0 4 0 4 0 0 2 3 2 5 4 0 2 0 0 0 2 0 5 0 2 0 2 0 4 2 0 3 4 1 0 1 1 5 2 2 2 2 2 4 2 3 4 1 3 0 1 1 2 2 4 2 2 2 2 4 0 2 2 3 4 1 2 0 1 2 2 2 2 2 1 0 2 2 3 4 1 0 1 1 2 2 2 2 5 4 0 2] Elapsed time: 0.038933515548706055 graph_id used : 80849 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20948913,20948914,20948915,20948923,20948919,20948921,20948926,20948922,20948924,20948929,20948927,20948928,20948930?tags=mal_croppe,flou,film_plastique,pehd,carton,papier,pet_fonce,tetrapak,metal,pet_clair,environnement,autre,refus&datou_id_consolidate=4235&port_consolidate=20948718&tree_id=80849 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1340356292, 1340356289, 1340356288, 1340356287] Looping around the photos to save general results len do output : 1 /20948718Didn'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, '2626368') ('4234', '20948718', '1340356292', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356289', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356288', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356287', None, None, None, None, None, '2626368') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.011665582656860352 save_final save missing photos in datou_result : time spend for datou_step_exec : 15.790133476257324 time spend to save output : 0.011866331100463867 total time spend for step 9 : 15.801999807357788 step10:send_mail_cod Sat Mar 1 11:24:06 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 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_P20948718_01-03-2025_11_24_06.pdf 20948895 imagette209488951740824646 20948896 imagette209488961740824646 20948897 imagette209488971740824646 20948905 imagette209489051740824646 20948901 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209489011740824646 20948903 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209489031740824647 20948908 imagette209489081740824648 20948904 imagette209489041740824648 20948906 imagette209489061740824648 20948911 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209489111740824648 20948910 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette209489101740824649 20948912 imagette209489121740824650 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20948718 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20948913,20948914,20948915,20948923,20948919,20948921,20948926,20948922,20948924,20948929,20948927,20948928,20948930?tags=mal_croppe,flou,film_plastique,pehd,carton,papier,pet_fonce,tetrapak,metal,pet_clair,environnement,autre,refus&datou_id_consolidate=4235&port_consolidate=20948718&tree_id=80849 your option no_mail is active, we will not send the real mail to your client args[1340356292] : ((1340356292, -7.7870928953995335, 492609224), (1340356292, -0.20156459123690346, 496442774), '0.20216657906345706') We are sending mail with results at cod@fotonower.com args[1340356289] : ((1340356289, -7.792525584728253, 492609224), (1340356289, -0.2034538254279421, 496442774), '0.20216657906345706') We are sending mail with results at cod@fotonower.com args[1340356288] : ((1340356288, -7.785146695104479, 492609224), (1340356288, -0.2090806719709093, 496442774), '0.20216657906345706') We are sending mail with results at cod@fotonower.com args[1340356287] : ((1340356287, -7.79264560180095, 492609224), (1340356287, -0.21210402128182812, 496442774), '0.20216657906345706') We are sending mail with results at cod@fotonower.com refus_total : 0.20216657906345706 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=20948718 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_P20948718_01-03-2025_11_24_06.pdf results_Qualipapia_P20948718_01-03-2025_11_24_06.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20948718_01-03-2025_11_24_06.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','20948718','results_Qualipapia_P20948718_01-03-2025_11_24_06.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20948718_01-03-2025_11_24_06.pdf','pdf','','0.17','0.20216657906345706') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1340356292, 1340356289, 1340356288, 1340356287] 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, '2626368') ('4234', '20948718', '1340356292', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356289', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356288', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356287', None, None, None, None, None, '2626368') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.012681961059570312 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.857191324234009 time spend to save output : 0.012952804565429688 total time spend for step 10 : 4.8701441287994385 step11:split_time_score Sat Mar 1 11:24:11 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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'}] (('08', 4),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 01032025 20948718 Nombre de photos uploadées : 4 / 23040 (0%) 01032025 20948718 Nombre de photos taguées (types de déchets): 4 / 4 (100%) 01032025 20948718 Nombre de photos taguées (volume) : 0 / 4 (0%) elapsed_time : load_data_split_time_score 2.86102294921875e-06 elapsed_time : order_list_meta_photo_and_scores 7.62939453125e-06 ???? elapsed_time : fill_and_build_computed_from_old_data 0.00039958953857421875 elapsed_time : insert_dashboard_record_day_entry 0.02339649200439453 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.23892758134565031 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20948539_01-03-2025_10_46_56.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20948539 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`=20948539 AND mptpi.`type`=4230 To do Qualite : 0.24625960389241422 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20948540_01-03-2025_10_34_55.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20948540 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`=20948540 AND mptpi.`type`=4230 To do Qualite : 0.20216657906345706 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20948718_01-03-2025_11_24_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20948718 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`=20948718 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20948719 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20948720 order by id desc limit 1 Qualite : 0.19748340895258557 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20948721_01-03-2025_11_14_34.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20948721 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`=20948721 AND mptpi.`type`=4230 To do Qualite : 0.20384795441780693 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20948722_01-03-2025_11_16_49.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20948722 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`=20948722 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'01032025': {'nb_upload': 4, 'nb_taggue_class': 4, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1340356292, 1340356289, 1340356288, 1340356287] Looping around the photos to save general results len do output : 1 /20948718Didn'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, '2626368') ('4234', '20948718', '1340356292', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356289', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356288', None, None, None, None, None, '2626368') ('4234', None, None, None, None, None, None, None, '2626368') ('4234', '20948718', '1340356287', None, None, None, None, None, '2626368') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012856721878051758 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.0457582473754883 time spend to save output : 0.013128280639648438 total time spend for step 11 : 2.0588865280151367 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 4 set_done_treatment 48.72user 30.41system 3:48.03elapsed 34%CPU (0avgtext+0avgdata 2415624maxresident)k 147328inputs+17256outputs (4601major+2680667minor)pagefaults 0swaps