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 : 1752582 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 : ['2646028'] with mtr_portfolio_ids : ['21129606'] and first list_photo_ids : [] new path : /proc/1752582/ 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 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.279923677444458 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 8 18:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 6284 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-08 18:20:31.307907: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-08 18:20:31.318021: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-08 18:20:31.319922: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f09e0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-08 18:20:31.320002: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-08 18:20:31.323302: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-08 18:20:31.586499: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x161b3e00 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-08 18:20:31.586590: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-08 18:20:31.588136: 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 2025-03-08 18:20:31.588665: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-08 18:20:31.592000: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-08 18:20:31.594849: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-08 18:20:31.595375: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-08 18:20:31.598520: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-08 18:20:31.600192: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-08 18:20:31.605276: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-08 18:20:31.606707: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-08 18:20:31.606805: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-08 18:20:31.607541: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-08 18:20:31.607560: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-08 18:20:31.607569: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-08 18:20:31.608863: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5764 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. 2025-03-08 18:20:31.946424: 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 2025-03-08 18:20:31.946556: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-08 18:20:31.946580: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-08 18:20:31.946602: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-08 18:20:31.946624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-08 18:20:31.946647: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-08 18:20:31.946664: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-08 18:20:31.946684: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-08 18:20:31.948579: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-08 18:20:31.952622: 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 2025-03-08 18:20:31.952706: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-08 18:20:31.952734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-08 18:20:31.952758: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-08 18:20:31.952783: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-08 18:20:31.952807: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-08 18:20:31.952830: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-08 18:20:31.952855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-08 18:20:31.954761: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-08 18:20:31.954814: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-08 18:20:31.954830: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-08 18:20:31.954844: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-08 18:20:31.959289: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5764 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 : [] 2025-03-08 18:20:41.185296: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-08 18:20:41.510720: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-08 18:20:43.002690: 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 2025-03-08 18:20:43.003239: 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 2025-03-08 18:20:43.003732: 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 2025-03-08 18:20:43.004223: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3131030784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-08 18:20:43.004726: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.62G (2817927680 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-08 18:20:43.005227: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.36G (2536134912 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-08 18:20:43.005731: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2282521344 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-08 18:20:43.005761: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.006439: 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 2025-03-08 18:20:43.006458: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.015017: 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 2025-03-08 18:20:43.015074: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.015579: 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 2025-03-08 18:20:43.015599: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.023217: 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 2025-03-08 18:20:43.023271: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.023797: 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 2025-03-08 18:20:43.023815: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.055594: 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 2025-03-08 18:20:43.055655: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.056168: 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 2025-03-08 18:20:43.056185: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.062125: 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 2025-03-08 18:20:43.062182: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.062698: 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 2025-03-08 18:20:43.062715: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-08 18:20:43.096837: 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 2025-03-08 18:20:43.097387: 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 2025-03-08 18:20:43.099256: 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 2025-03-08 18:20:43.099775: 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 2025-03-08 18:20:43.143226: 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 2025-03-08 18:20:43.143766: 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 2025-03-08 18:20:43.145862: 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 2025-03-08 18:20:43.146374: 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 2025-03-08 18:20:43.172279: 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 2025-03-08 18:20:43.172810: 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 2025-03-08 18:20:43.174284: 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 2025-03-08 18:20:43.174791: 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 2025-03-08 18:20:43.180226: 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 2025-03-08 18:20:43.180735: 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 2025-03-08 18:20:43.182358: 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 2025-03-08 18:20:43.182868: 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 2025-03-08 18:20:43.188469: 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 2025-03-08 18:20:43.188978: 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 2025-03-08 18:20:43.190453: 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 2025-03-08 18:20:43.190964: 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 2025-03-08 18:20:43.224183: 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 2025-03-08 18:20:43.224703: 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 2025-03-08 18:20:43.225206: 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 2025-03-08 18:20:43.225713: 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 2025-03-08 18:20:43.229246: 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 2025-03-08 18:20:43.229771: 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 2025-03-08 18:20:43.251726: 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 2025-03-08 18:20:43.252279: 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 2025-03-08 18:20:43.252789: 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 2025-03-08 18:20:43.253301: 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 2025-03-08 18:20:43.268862: 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 2025-03-08 18:20:43.269474: 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 2025-03-08 18:20:43.270028: 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 2025-03-08 18:20:43.270551: 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 2025-03-08 18:20:43.276255: 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 2025-03-08 18:20:43.276910: 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 2025-03-08 18:20:43.283407: 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 2025-03-08 18:20:43.283994: 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 2025-03-08 18:20:43.297512: 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 2025-03-08 18:20:43.298153: 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 2025-03-08 18:20:43.303388: 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 2025-03-08 18:20:43.304007: 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 2025-03-08 18:20:43.304684: 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 2025-03-08 18:20:43.305364: 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 2025-03-08 18:20:43.306538: 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 2025-03-08 18:20:43.307426: 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 2025-03-08 18:20:43.320054: 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 2025-03-08 18:20:43.320909: 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 2025-03-08 18:20:43.321780: 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 2025-03-08 18:20:43.322627: 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 2025-03-08 18:20:43.323457: 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 2025-03-08 18:20:43.324299: 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 2025-03-08 18:20:43.325105: 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 2025-03-08 18:20:43.325896: 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 2025-03-08 18:20:43.337016: 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 2025-03-08 18:20:43.337915: 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 2025-03-08 18:20:43.345704: 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 2025-03-08 18:20:43.346529: 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 2025-03-08 18:20:43.413246: 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 2025-03-08 18:20:43.414276: 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 2025-03-08 18:20:43.423049: 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 2025-03-08 18:20:43.423837: 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 2025-03-08 18:20:43.439647: 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 2025-03-08 18:20:43.440293: 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 2025-03-08 18:20:43.440929: 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 2025-03-08 18:20:43.441549: 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 2025-03-08 18:20:43.445737: 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 2025-03-08 18:20:43.446363: 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 2025-03-08 18:20:43.447043: 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 2025-03-08 18:20:43.447668: 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 2025-03-08 18:20:43.448826: 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 2025-03-08 18:20:43.448845: 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. 2025-03-08 18:20:43.459004: 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 2025-03-08 18:20:43.459545: 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 2025-03-08 18:20:43.468738: 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 2025-03-08 18:20:43.469428: 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 2025-03-08 18:20:43.469964: 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 2025-03-08 18:20:43.470503: 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 2025-03-08 18:20:43.471043: 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 2025-03-08 18:20:43.471557: 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 : 2 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: -119.27031 max: 145.23281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00011181831359863281 nb_pixel_total : 311 time to create 1 rle with old method : 0.0007164478302001953 length of segment : 43 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0014600753784179688 length of segment : 56 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.00668644905090332 length of segment : 34 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00028777122497558594 length of segment : 14 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 727 time to create 1 rle with old method : 0.0015163421630859375 length of segment : 49 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.00015664100646972656 length of segment : 23 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0004858970642089844 length of segment : 49 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0011377334594726562 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.71953 max: 151.08047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009407997131347656 length of segment : 41 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0007643699645996094 length of segment : 38 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00021791458129882812 length of segment : 16 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.00048160552978515625 length of segment : 27 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.000354766845703125 length of segment : 17 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.00103759765625 length of segment : 32 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0006422996520996094 length of segment : 58 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005609989166259766 length of segment : 28 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005450248718261719 length of segment : 42 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1151 time to create 1 rle with old method : 0.0014319419860839844 length of segment : 46 time for calcul the mask position with numpy : 0.00010371208190917969 nb_pixel_total : 927 time to create 1 rle with old method : 0.0011620521545410156 length of segment : 42 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00028634071350097656 length of segment : 27 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00019216537475585938 length of segment : 16 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0005202293395996094 length of segment : 30 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 727 time to create 1 rle with old method : 0.0009188652038574219 length of segment : 47 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.00028324127197265625 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.42266 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 : 6.222724914550781e-05 nb_pixel_total : 1728 time to create 1 rle with old method : 0.002138853073120117 length of segment : 63 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.00020170211791992188 length of segment : 18 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 644 time to create 1 rle with old method : 0.0009374618530273438 length of segment : 24 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1589 time to create 1 rle with old method : 0.0019321441650390625 length of segment : 56 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0008885860443115234 length of segment : 75 time for calcul the mask position with numpy : 0.0002117156982421875 nb_pixel_total : 8009 time to create 1 rle with old method : 0.009887933731079102 length of segment : 117 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.48906 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 : 9.560585021972656e-05 nb_pixel_total : 4764 time to create 1 rle with old method : 0.0058841705322265625 length of segment : 64 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0005571842193603516 length of segment : 25 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005071163177490234 length of segment : 22 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003635883331298828 length of segment : 21 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 703 time to create 1 rle with old method : 0.0008993148803710938 length of segment : 47 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 213.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 86.70156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.0010826587677001953 length of segment : 17 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 1570 time to create 1 rle with old method : 0.0027420520782470703 length of segment : 111 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0008447170257568359 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 173.00000 molded_images shape: (1, 640, 640, 3) min: -101.30156 max: 56.55703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0019142627716064453 nb_pixel_total : 153310 time to create 1 rle with new method : 0.0029218196868896484 length of segment : 400 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.50078 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 : 5.9604644775390625e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.00041556358337402344 length of segment : 11 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1202 time to create 1 rle with old method : 0.0023674964904785156 length of segment : 30 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2183 time to create 1 rle with old method : 0.0031621456146240234 length of segment : 44 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0006377696990966797 length of segment : 25 time for calcul the mask position with numpy : 0.0001971721649169922 nb_pixel_total : 6400 time to create 1 rle with old method : 0.007668495178222656 length of segment : 129 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 1395 time to create 1 rle with old method : 0.0018770694732666016 length of segment : 45 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002732276916503906 length of segment : 15 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002396106719970703 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: -111.20391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00020694732666015625 length of segment : 10 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00020503997802734375 length of segment : 11 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.0002009868621826172 length of segment : 9 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0004966259002685547 length of segment : 29 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 32 time to create 1 rle with old method : 9.560585021972656e-05 length of segment : 5 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0003364086151123047 length of segment : 18 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003037452697753906 length of segment : 21 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 62 time to create 1 rle with old method : 0.0001163482666015625 length of segment : 8 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.00044989585876464844 length of segment : 13 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.00041604042053222656 length of segment : 17 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 692 time to create 1 rle with old method : 0.0008614063262939453 length of segment : 33 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00016498565673828125 length of segment : 14 time for calcul the mask position with numpy : 0.00019073486328125 nb_pixel_total : 8387 time to create 1 rle with old method : 0.010062217712402344 length of segment : 72 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.0006175041198730469 length of segment : 35 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.00011658668518066406 length of segment : 8 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.0009784698486328125 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.89922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 0.0004534721374511719 nb_pixel_total : 29860 time to create 1 rle with old method : 0.034545183181762695 length of segment : 285 time for calcul the mask position with numpy : 0.0001418590545654297 nb_pixel_total : 2800 time to create 1 rle with old method : 0.003504514694213867 length of segment : 63 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 898 time to create 1 rle with old method : 0.001619100570678711 length of segment : 36 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0004413127899169922 length of segment : 12 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 1016 time to create 1 rle with old method : 0.002192258834838867 length of segment : 40 time for calcul the mask position with numpy : 0.00014162063598632812 nb_pixel_total : 2694 time to create 1 rle with old method : 0.005146026611328125 length of segment : 63 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0019783973693847656 length of segment : 52 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.0004642009735107422 length of segment : 21 time for calcul the mask position with numpy : 0.00035643577575683594 nb_pixel_total : 15853 time to create 1 rle with old method : 0.01885509490966797 length of segment : 238 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 729 time to create 1 rle with old method : 0.0009908676147460938 length of segment : 37 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0009071826934814453 length of segment : 28 time for calcul the mask position with numpy : 0.00028514862060546875 nb_pixel_total : 12052 time to create 1 rle with old method : 0.014065027236938477 length of segment : 206 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 202.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 71.11172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0008094310760498047 length of segment : 44 time for calcul the mask position with numpy : 0.00010561943054199219 nb_pixel_total : 2778 time to create 1 rle with old method : 0.0035605430603027344 length of segment : 143 time for calcul the mask position with numpy : 0.0001246929168701172 nb_pixel_total : 2734 time to create 1 rle with old method : 0.003440380096435547 length of segment : 143 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 1265 time to create 1 rle with old method : 0.001596689224243164 length of segment : 69 time for calcul the mask position with numpy : 0.0001990795135498047 nb_pixel_total : 3295 time to create 1 rle with old method : 0.004019737243652344 length of segment : 182 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006432533264160156 length of segment : 33 Processing 1 images image shape: (280, 400, 3) min: 9.00000 max: 174.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 56.81484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009148120880126953 nb_pixel_total : 106104 time to create 1 rle with old method : 0.16711139678955078 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 128.11953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005128383636474609 length of segment : 21 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0005218982696533203 length of segment : 21 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0008699893951416016 length of segment : 25 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0003840923309326172 length of segment : 15 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0008635520935058594 length of segment : 29 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.00016570091247558594 length of segment : 12 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 3092 time to create 1 rle with old method : 0.0056989192962646484 length of segment : 72 time for calcul the mask position with numpy : 0.00013494491577148438 nb_pixel_total : 2132 time to create 1 rle with old method : 0.0040171146392822266 length of segment : 92 time for calcul the mask position with numpy : 0.00012063980102539062 nb_pixel_total : 785 time to create 1 rle with old method : 0.0014805793762207031 length of segment : 51 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0005702972412109375 length of segment : 29 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1284 time to create 1 rle with old method : 0.0021653175354003906 length of segment : 45 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 1018 time to create 1 rle with old method : 0.001889944076538086 length of segment : 32 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0011525154113769531 length of segment : 24 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 1101 time to create 1 rle with old method : 0.002091646194458008 length of segment : 41 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1411 time to create 1 rle with old method : 0.0017385482788085938 length of segment : 39 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0004773139953613281 length of segment : 17 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 245.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 131.96328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0007240772247314453 length of segment : 20 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0006620883941650391 length of segment : 30 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 800 time to create 1 rle with old method : 0.0014567375183105469 length of segment : 37 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0008537769317626953 length of segment : 28 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00043201446533203125 length of segment : 18 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0006721019744873047 length of segment : 17 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.00039124488830566406 length of segment : 19 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0007152557373046875 length of segment : 27 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.00037789344787597656 length of segment : 14 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0005943775177001953 length of segment : 23 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.000736236572265625 length of segment : 21 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0006532669067382812 length of segment : 17 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: 147.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0012662410736083984 length of segment : 32 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003178119659423828 length of segment : 13 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0005655288696289062 length of segment : 27 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0007073879241943359 length of segment : 33 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 532 time to create 1 rle with old method : 0.0007176399230957031 length of segment : 39 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0009157657623291016 length of segment : 25 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003714561462402344 length of segment : 46 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.001001119613647461 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: 140.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0005812644958496094 nb_pixel_total : 46082 time to create 1 rle with old method : 0.05927252769470215 length of segment : 292 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.61406 max: 145.46328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.00039005279541015625 length of segment : 38 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.00046539306640625 length of segment : 33 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0009722709655761719 length of segment : 51 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00037980079650878906 length of segment : 14 time for calcul the mask position with numpy : 0.0001251697540283203 nb_pixel_total : 97 time to create 1 rle with old method : 0.0002193450927734375 length of segment : 23 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 761 time to create 1 rle with old method : 0.0013680458068847656 length of segment : 60 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.0014431476593017578 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: -122.21563 max: 150.27969 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008814334869384766 length of segment : 38 time for calcul the mask position with numpy : 0.0001304149627685547 nb_pixel_total : 436 time to create 1 rle with old method : 0.000978708267211914 length of segment : 29 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0008413791656494141 length of segment : 42 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 1371 time to create 1 rle with old method : 0.0017924308776855469 length of segment : 67 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0006110668182373047 length of segment : 22 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.000598907470703125 length of segment : 54 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0016605854034423828 length of segment : 67 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0009672641754150391 length of segment : 39 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.00020051002502441406 length of segment : 21 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 751 time to create 1 rle with old method : 0.0010304450988769531 length of segment : 25 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0008513927459716797 length of segment : 24 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1145 time to create 1 rle with old method : 0.001440286636352539 length of segment : 33 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 1007 time to create 1 rle with old method : 0.0016093254089355469 length of segment : 44 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 922 time to create 1 rle with old method : 0.0012178421020507812 length of segment : 40 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0005230903625488281 length of segment : 21 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0013668537139892578 length of segment : 65 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1118 time to create 1 rle with old method : 0.0014302730560302734 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.36406 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 : 0.00010442733764648438 nb_pixel_total : 1640 time to create 1 rle with old method : 0.002621173858642578 length of segment : 55 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0009391307830810547 length of segment : 35 time for calcul the mask position with numpy : 0.00022339820861816406 nb_pixel_total : 7306 time to create 1 rle with old method : 0.00917673110961914 length of segment : 115 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 644 time to create 1 rle with old method : 0.0008113384246826172 length of segment : 73 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1386 time to create 1 rle with old method : 0.0018613338470458984 length of segment : 56 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.00021195411682128906 length of segment : 19 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0007250308990478516 length of segment : 39 time for calcul the mask position with numpy : 0.0004661083221435547 nb_pixel_total : 9219 time to create 1 rle with old method : 0.0127410888671875 length of segment : 164 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1048 time to create 1 rle with old method : 0.0014705657958984375 length of segment : 55 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.85625 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 : 0.00013947486877441406 nb_pixel_total : 4228 time to create 1 rle with old method : 0.0064563751220703125 length of segment : 62 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0007793903350830078 length of segment : 28 time for calcul the mask position with numpy : 0.00014543533325195312 nb_pixel_total : 333 time to create 1 rle with old method : 0.0011751651763916016 length of segment : 21 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0004923343658447266 length of segment : 21 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 856 time to create 1 rle with old method : 0.001331329345703125 length of segment : 58 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.00038433074951171875 length of segment : 21 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 212.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 83.38125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0008325576782226562 length of segment : 17 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1535 time to create 1 rle with old method : 0.0020487308502197266 length of segment : 114 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0016131401062011719 length of segment : 31 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 1688 time to create 1 rle with old method : 0.002168416976928711 length of segment : 97 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0008666515350341797 length of segment : 28 time for calcul the mask position with numpy : 0.0007102489471435547 nb_pixel_total : 57534 time to create 1 rle with old method : 0.08732891082763672 length of segment : 340 Processing 1 images image shape: (400, 400, 3) min: 8.00000 max: 174.00000 molded_images shape: (1, 640, 640, 3) min: -101.18828 max: 56.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0015039443969726562 nb_pixel_total : 154311 time to create 1 rle with new method : 0.003281116485595703 length of segment : 408 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.56328 max: 151.08828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0016391277313232422 length of segment : 35 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.00031828880310058594 length of segment : 11 time for calcul the mask position with numpy : 0.0001125335693359375 nb_pixel_total : 2162 time to create 1 rle with old method : 0.002857685089111328 length of segment : 44 time for calcul the mask position with numpy : 0.00022411346435546875 nb_pixel_total : 7455 time to create 1 rle with old method : 0.008810281753540039 length of segment : 101 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0005483627319335938 length of segment : 17 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002777576446533203 length of segment : 14 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 1465 time to create 1 rle with old method : 0.0019109249114990234 length of segment : 45 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00022721290588378906 length of segment : 16 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0007491111755371094 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.26250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00029349327087402344 length of segment : 10 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00021576881408691406 length of segment : 9 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003724098205566406 length of segment : 18 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.0002338886260986328 length of segment : 9 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 63 time to create 1 rle with old method : 0.0001316070556640625 length of segment : 8 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0005154609680175781 length of segment : 28 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002574920654296875 length of segment : 11 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0013828277587890625 length of segment : 31 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004930496215820312 length of segment : 21 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00019121170043945312 length of segment : 16 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00023865699768066406 length of segment : 16 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.00032520294189453125 length of segment : 15 time for calcul the mask position with numpy : 0.00013828277587890625 nb_pixel_total : 6523 time to create 1 rle with old method : 0.008752107620239258 length of segment : 83 time for calcul the mask position with numpy : 0.00014472007751464844 nb_pixel_total : 1816 time to create 1 rle with old method : 0.0027048587799072266 length of segment : 103 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.55938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 716 time to create 1 rle with old method : 0.0010533332824707031 length of segment : 28 time for calcul the mask position with numpy : 0.00043773651123046875 nb_pixel_total : 15962 time to create 1 rle with old method : 0.019718170166015625 length of segment : 317 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 1355 time to create 1 rle with old method : 0.0018029212951660156 length of segment : 48 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.000934600830078125 length of segment : 25 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1121 time to create 1 rle with old method : 0.0013844966888427734 length of segment : 38 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 867 time to create 1 rle with old method : 0.001129150390625 length of segment : 45 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1228 time to create 1 rle with old method : 0.0015172958374023438 length of segment : 43 time for calcul the mask position with numpy : 0.0001533031463623047 nb_pixel_total : 4188 time to create 1 rle with old method : 0.004929780960083008 length of segment : 147 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004954338073730469 length of segment : 21 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2540 time to create 1 rle with old method : 0.003223419189453125 length of segment : 61 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1382 time to create 1 rle with old method : 0.0018055438995361328 length of segment : 47 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.0005257129669189453 length of segment : 21 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1940 time to create 1 rle with old method : 0.0025184154510498047 length of segment : 46 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 2225 time to create 1 rle with old method : 0.0028154850006103516 length of segment : 54 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 69.49453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 714 time to create 1 rle with old method : 0.0009210109710693359 length of segment : 47 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 2002 time to create 1 rle with old method : 0.0026197433471679688 length of segment : 108 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 2007 time to create 1 rle with old method : 0.002584218978881836 length of segment : 102 time for calcul the mask position with numpy : 0.0002307891845703125 nb_pixel_total : 3440 time to create 1 rle with old method : 0.004279136657714844 length of segment : 192 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0007004737854003906 length of segment : 41 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 716 time to create 1 rle with old method : 0.0010275840759277344 length of segment : 32 Processing 1 images image shape: (280, 400, 3) min: 8.00000 max: 172.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 57.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009441375732421875 nb_pixel_total : 105298 time to create 1 rle with old method : 0.1349623203277588 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: 126.99844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.0004849433898925781 length of segment : 22 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0007007122039794922 length of segment : 21 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.00130462646484375 length of segment : 30 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 1172 time to create 1 rle with old method : 0.0028302669525146484 length of segment : 53 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1275 time to create 1 rle with old method : 0.0022127628326416016 length of segment : 41 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 3749 time to create 1 rle with old method : 0.005270957946777344 length of segment : 70 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.00016880035400390625 length of segment : 11 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 1878 time to create 1 rle with old method : 0.002448558807373047 length of segment : 54 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005340576171875 length of segment : 27 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005271434783935547 length of segment : 25 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1376 time to create 1 rle with old method : 0.001959562301635742 length of segment : 40 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0006465911865234375 length of segment : 26 time for calcul the mask position with numpy : 0.0007860660552978516 nb_pixel_total : 45781 time to create 1 rle with old method : 0.05814480781555176 length of segment : 269 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.0005612373352050781 length of segment : 17 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 1519 time to create 1 rle with old method : 0.0018851757049560547 length of segment : 66 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1423 time to create 1 rle with old method : 0.001985311508178711 length of segment : 38 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1400 time to create 1 rle with old method : 0.002108335494995117 length of segment : 46 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 245.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 127.65859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005903244018554688 length of segment : 28 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.0010657310485839844 length of segment : 35 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003464221954345703 length of segment : 20 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.0013222694396972656 length of segment : 39 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005049705505371094 length of segment : 19 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005636215209960938 length of segment : 41 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.0003898143768310547 length of segment : 22 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0004420280456542969 length of segment : 18 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.00027823448181152344 length of segment : 19 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00016808509826660156 length of segment : 10 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005495548248291016 length of segment : 19 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005767345428466797 length of segment : 21 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0002968311309814453 length of segment : 20 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00030922889709472656 length of segment : 18 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005791187286376953 length of segment : 34 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004429817199707031 length of segment : 23 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 990 time to create 1 rle with old method : 0.0012824535369873047 length of segment : 41 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: 146.15859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0006768703460693359 length of segment : 34 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0008027553558349609 length of segment : 44 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.0009169578552246094 length of segment : 24 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008249282836914062 length of segment : 40 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006816387176513672 length of segment : 35 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0008058547973632812 length of segment : 38 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005440711975097656 length of segment : 33 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.000415802001953125 length of segment : 18 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: 138.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0004706382751464844 nb_pixel_total : 44902 time to create 1 rle with old method : 0.05116105079650879 length of segment : 284 Detection mask done ! Trying to reset tf kernel 1753339 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4651 tf kernel not reseted sub process len(results) : 252 len(list_Values) 252 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 252 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 : 5844 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 252 chid ids of type : 4228 Number RLEs to save : 13024 save missing photos in datou_result : time spend for datou_step_exec : 25.542975425720215 time spend to save output : 12.023915767669678 total time spend for step 1 : 37.56689119338989 step2:brightness Sat Mar 8 18:21:06 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 inside step calcul brightness treat image : temp/1741454428_1752582_1341315107_9d3ae8c51b9368755ad62008aae6b0c9.jpg treat image : temp/1741454428_1752582_1341315104_ec0bc0f449f9518684e0cebe27bb703c.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 : 2 time used for this insertion : 0.011743545532226562 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.012872695922851562 save missing photos in datou_result : time spend for datou_step_exec : 1.667762279510498 time spend to save output : 0.02880120277404785 total time spend for step 2 : 1.696563482284546 step3:blur_detection Sat Mar 8 18:21:07 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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/1741454428_1752582_1341315107_9d3ae8c51b9368755ad62008aae6b0c9.jpg resize: (1080, 1920) 1341315107 -7.261615270875711 treat image : temp/1741454428_1752582_1341315104_ec0bc0f449f9518684e0cebe27bb703c.jpg resize: (1080, 1920) 1341315104 -7.252917717549553 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 : 2 time used for this insertion : 0.012981176376342773 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.0131988525390625 save missing photos in datou_result : time spend for datou_step_exec : 2.3154988288879395 time spend to save output : 0.030739545822143555 total time spend for step 3 : 2.346238374710083 step4:rle_unique_nms_with_priority Sat Mar 8 18:21:10 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 252 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 119 nb_hashtags : 7 time to prepare the origin masks : 1.2964272499084473 time for calcul the mask position with numpy : 0.09764480590820312 nb_pixel_total : 1630987 time to create 1 rle with new method : 0.17204570770263672 time for calcul the mask position with numpy : 0.008469104766845703 nb_pixel_total : 126 time to create 1 rle with old method : 0.00016498565673828125 time for calcul the mask position with numpy : 0.008522272109985352 nb_pixel_total : 8009 time to create 1 rle with old method : 0.009023666381835938 time for calcul the mask position with numpy : 0.008402347564697266 nb_pixel_total : 666 time to create 1 rle with old method : 0.0007541179656982422 time for calcul the mask position with numpy : 0.008658409118652344 nb_pixel_total : 702 time to create 1 rle with old method : 0.0008151531219482422 time for calcul the mask position with numpy : 0.008437633514404297 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002422332763671875 time for calcul the mask position with numpy : 0.008361101150512695 nb_pixel_total : 705 time to create 1 rle with old method : 0.0008680820465087891 time for calcul the mask position with numpy : 0.008285284042358398 nb_pixel_total : 58 time to create 1 rle with old method : 8.893013000488281e-05 time for calcul the mask position with numpy : 0.008372306823730469 nb_pixel_total : 237 time to create 1 rle with old method : 0.0002868175506591797 time for calcul the mask position with numpy : 0.00831460952758789 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001392364501953125 time for calcul the mask position with numpy : 0.008440017700195312 nb_pixel_total : 135 time to create 1 rle with old method : 0.0001881122589111328 time for calcul the mask position with numpy : 0.009053945541381836 nb_pixel_total : 311 time to create 1 rle with old method : 0.000492095947265625 time for calcul the mask position with numpy : 0.008395195007324219 nb_pixel_total : 432 time to create 1 rle with old method : 0.0004901885986328125 time for calcul the mask position with numpy : 0.008484601974487305 nb_pixel_total : 140 time to create 1 rle with old method : 0.00016951560974121094 time for calcul the mask position with numpy : 0.008207321166992188 nb_pixel_total : 424 time to create 1 rle with old method : 0.0005080699920654297 time for calcul the mask position with numpy : 0.008426189422607422 nb_pixel_total : 250 time to create 1 rle with old method : 0.0003185272216796875 time for calcul the mask position with numpy : 0.008261919021606445 nb_pixel_total : 10 time to create 1 rle with old method : 2.5987625122070312e-05 time for calcul the mask position with numpy : 0.008381366729736328 nb_pixel_total : 411 time to create 1 rle with old method : 0.00047326087951660156 time for calcul the mask position with numpy : 0.008436918258666992 nb_pixel_total : 362 time to create 1 rle with old method : 0.00043201446533203125 time for calcul the mask position with numpy : 0.009219646453857422 nb_pixel_total : 644 time to create 1 rle with old method : 0.0009844303131103516 time for calcul the mask position with numpy : 0.009133577346801758 nb_pixel_total : 1728 time to create 1 rle with old method : 0.001939535140991211 time for calcul the mask position with numpy : 0.008486509323120117 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001468658447265625 time for calcul the mask position with numpy : 0.008512496948242188 nb_pixel_total : 520 time to create 1 rle with old method : 0.0006306171417236328 time for calcul the mask position with numpy : 0.008326292037963867 nb_pixel_total : 1570 time to create 1 rle with old method : 0.0017368793487548828 time for calcul the mask position with numpy : 0.009811162948608398 nb_pixel_total : 610 time to create 1 rle with old method : 0.0007200241088867188 time for calcul the mask position with numpy : 0.00829005241394043 nb_pixel_total : 237 time to create 1 rle with old method : 0.00025200843811035156 time for calcul the mask position with numpy : 0.008236169815063477 nb_pixel_total : 796 time to create 1 rle with old method : 0.000896453857421875 time for calcul the mask position with numpy : 0.008413553237915039 nb_pixel_total : 357 time to create 1 rle with old method : 0.0003864765167236328 time for calcul the mask position with numpy : 0.009001016616821289 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005316734313964844 time for calcul the mask position with numpy : 0.009156465530395508 nb_pixel_total : 690 time to create 1 rle with old method : 0.0007905960083007812 time for calcul the mask position with numpy : 0.008412361145019531 nb_pixel_total : 927 time to create 1 rle with old method : 0.0010569095611572266 time for calcul the mask position with numpy : 0.008383035659790039 nb_pixel_total : 1151 time to create 1 rle with old method : 0.0012946128845214844 time for calcul the mask position with numpy : 0.008122444152832031 nb_pixel_total : 644 time to create 1 rle with old method : 0.0007421970367431641 time for calcul the mask position with numpy : 0.008158206939697266 nb_pixel_total : 416 time to create 1 rle with old method : 0.0004436969757080078 time for calcul the mask position with numpy : 0.008192777633666992 nb_pixel_total : 207 time to create 1 rle with old method : 0.000240325927734375 time for calcul the mask position with numpy : 0.008424043655395508 nb_pixel_total : 1589 time to create 1 rle with old method : 0.001794576644897461 time for calcul the mask position with numpy : 0.008369207382202148 nb_pixel_total : 4764 time to create 1 rle with old method : 0.005415439605712891 time for calcul the mask position with numpy : 0.008379697799682617 nb_pixel_total : 74 time to create 1 rle with old method : 9.894371032714844e-05 time for calcul the mask position with numpy : 0.008405447006225586 nb_pixel_total : 531 time to create 1 rle with old method : 0.0005970001220703125 time for calcul the mask position with numpy : 0.009421825408935547 nb_pixel_total : 153310 time to create 1 rle with new method : 0.12134408950805664 time for calcul the mask position with numpy : 0.008707046508789062 nb_pixel_total : 729 time to create 1 rle with old method : 0.0008997917175292969 time for calcul the mask position with numpy : 0.008508682250976562 nb_pixel_total : 13271 time to create 1 rle with old method : 0.014896154403686523 time for calcul the mask position with numpy : 0.008399486541748047 nb_pixel_total : 692 time to create 1 rle with old method : 0.0007717609405517578 time for calcul the mask position with numpy : 0.008431673049926758 nb_pixel_total : 293 time to create 1 rle with old method : 0.0004565715789794922 time for calcul the mask position with numpy : 0.008287906646728516 nb_pixel_total : 62 time to create 1 rle with old method : 8.058547973632812e-05 time for calcul the mask position with numpy : 0.008360624313354492 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0014851093292236328 time for calcul the mask position with numpy : 0.00867152214050293 nb_pixel_total : 8387 time to create 1 rle with old method : 0.009271860122680664 time for calcul the mask position with numpy : 0.008299112319946289 nb_pixel_total : 1016 time to create 1 rle with old method : 0.0011229515075683594 time for calcul the mask position with numpy : 0.008608579635620117 nb_pixel_total : 2694 time to create 1 rle with old method : 0.003034353256225586 time for calcul the mask position with numpy : 0.008450508117675781 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005578994750976562 time for calcul the mask position with numpy : 0.008474588394165039 nb_pixel_total : 197 time to create 1 rle with old method : 0.00025391578674316406 time for calcul the mask position with numpy : 0.008279561996459961 nb_pixel_total : 6400 time to create 1 rle with old method : 0.007180452346801758 time for calcul the mask position with numpy : 0.008376359939575195 nb_pixel_total : 625 time to create 1 rle with old method : 0.0006585121154785156 time for calcul the mask position with numpy : 0.008363008499145508 nb_pixel_total : 29860 time to create 1 rle with old method : 0.03418397903442383 time for calcul the mask position with numpy : 0.009893178939819336 nb_pixel_total : 362 time to create 1 rle with old method : 0.0004904270172119141 time for calcul the mask position with numpy : 0.010216474533081055 nb_pixel_total : 2778 time to create 1 rle with old method : 0.0033609867095947266 time for calcul the mask position with numpy : 0.008526086807250977 nb_pixel_total : 3295 time to create 1 rle with old method : 0.004286050796508789 time for calcul the mask position with numpy : 0.009159564971923828 nb_pixel_total : 110 time to create 1 rle with old method : 0.000225067138671875 time for calcul the mask position with numpy : 0.009089231491088867 nb_pixel_total : 2800 time to create 1 rle with old method : 0.0035126209259033203 time for calcul the mask position with numpy : 0.008889913558959961 nb_pixel_total : 1395 time to create 1 rle with old method : 0.0016047954559326172 time for calcul the mask position with numpy : 0.009066104888916016 nb_pixel_total : 1202 time to create 1 rle with old method : 0.0015325546264648438 time for calcul the mask position with numpy : 0.01187276840209961 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004420280456542969 time for calcul the mask position with numpy : 0.009663820266723633 nb_pixel_total : 2183 time to create 1 rle with old method : 0.002832174301147461 time for calcul the mask position with numpy : 0.009099960327148438 nb_pixel_total : 454 time to create 1 rle with old method : 0.0006005764007568359 time for calcul the mask position with numpy : 0.00939488410949707 nb_pixel_total : 284 time to create 1 rle with old method : 0.0004439353942871094 time for calcul the mask position with numpy : 0.009525537490844727 nb_pixel_total : 140 time to create 1 rle with old method : 0.0001785755157470703 time for calcul the mask position with numpy : 0.008982181549072266 nb_pixel_total : 1265 time to create 1 rle with old method : 0.0016036033630371094 time for calcul the mask position with numpy : 0.00836324691772461 nb_pixel_total : 662 time to create 1 rle with old method : 0.0007658004760742188 time for calcul the mask position with numpy : 0.008413314819335938 nb_pixel_total : 179 time to create 1 rle with old method : 0.00026535987854003906 time for calcul the mask position with numpy : 0.008476972579956055 nb_pixel_total : 415 time to create 1 rle with old method : 0.0005507469177246094 time for calcul the mask position with numpy : 0.008487939834594727 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005576610565185547 time for calcul the mask position with numpy : 0.008506059646606445 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002090930938720703 time for calcul the mask position with numpy : 0.01029515266418457 nb_pixel_total : 4 time to create 1 rle with old method : 2.7894973754882812e-05 time for calcul the mask position with numpy : 0.008394479751586914 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002002716064453125 time for calcul the mask position with numpy : 0.008420228958129883 nb_pixel_total : 111 time to create 1 rle with old method : 0.00017547607421875 time for calcul the mask position with numpy : 0.00882863998413086 nb_pixel_total : 98 time to create 1 rle with old method : 0.00012803077697753906 time for calcul the mask position with numpy : 0.008445501327514648 nb_pixel_total : 243 time to create 1 rle with old method : 0.00029540061950683594 time for calcul the mask position with numpy : 0.008455991744995117 nb_pixel_total : 157 time to create 1 rle with old method : 0.0001926422119140625 time for calcul the mask position with numpy : 0.008443832397460938 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001518726348876953 time for calcul the mask position with numpy : 0.008374929428100586 nb_pixel_total : 211 time to create 1 rle with old method : 0.00024318695068359375 time for calcul the mask position with numpy : 0.00840449333190918 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002391338348388672 time for calcul the mask position with numpy : 0.008472919464111328 nb_pixel_total : 63 time to create 1 rle with old method : 9.465217590332031e-05 time for calcul the mask position with numpy : 0.009014129638671875 nb_pixel_total : 106104 time to create 1 rle with old method : 0.11734127998352051 time for calcul the mask position with numpy : 0.008533239364624023 nb_pixel_total : 567 time to create 1 rle with old method : 0.0006606578826904297 time for calcul the mask position with numpy : 0.008481740951538086 nb_pixel_total : 314 time to create 1 rle with old method : 0.00039267539978027344 time for calcul the mask position with numpy : 0.008459091186523438 nb_pixel_total : 200 time to create 1 rle with old method : 0.000244140625 time for calcul the mask position with numpy : 0.008440494537353516 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0011811256408691406 time for calcul the mask position with numpy : 0.010144233703613281 nb_pixel_total : 168 time to create 1 rle with old method : 0.00022840499877929688 time for calcul the mask position with numpy : 0.008467674255371094 nb_pixel_total : 95 time to create 1 rle with old method : 0.00012230873107910156 time for calcul the mask position with numpy : 0.008431434631347656 nb_pixel_total : 351 time to create 1 rle with old method : 0.0005052089691162109 time for calcul the mask position with numpy : 0.009772777557373047 nb_pixel_total : 430 time to create 1 rle with old method : 0.00060272216796875 time for calcul the mask position with numpy : 0.008545160293579102 nb_pixel_total : 46082 time to create 1 rle with old method : 0.05186629295349121 time for calcul the mask position with numpy : 0.010276556015014648 nb_pixel_total : 368 time to create 1 rle with old method : 0.00046539306640625 time for calcul the mask position with numpy : 0.00855708122253418 nb_pixel_total : 296 time to create 1 rle with old method : 0.00037026405334472656 time for calcul the mask position with numpy : 0.008600473403930664 nb_pixel_total : 281 time to create 1 rle with old method : 0.00033473968505859375 time for calcul the mask position with numpy : 0.008540630340576172 nb_pixel_total : 639 time to create 1 rle with old method : 0.0007555484771728516 time for calcul the mask position with numpy : 0.008682012557983398 nb_pixel_total : 326 time to create 1 rle with old method : 0.00044345855712890625 time for calcul the mask position with numpy : 0.010280609130859375 nb_pixel_total : 357 time to create 1 rle with old method : 0.0004742145538330078 time for calcul the mask position with numpy : 0.008589744567871094 nb_pixel_total : 3092 time to create 1 rle with old method : 0.003629922866821289 time for calcul the mask position with numpy : 0.008519411087036133 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003075599670410156 time for calcul the mask position with numpy : 0.009248018264770508 nb_pixel_total : 1411 time to create 1 rle with old method : 0.0023202896118164062 time for calcul the mask position with numpy : 0.009699106216430664 nb_pixel_total : 800 time to create 1 rle with old method : 0.0013272762298583984 time for calcul the mask position with numpy : 0.009681940078735352 nb_pixel_total : 2132 time to create 1 rle with old method : 0.0037126541137695312 time for calcul the mask position with numpy : 0.009768009185791016 nb_pixel_total : 190 time to create 1 rle with old method : 0.000339508056640625 time for calcul the mask position with numpy : 0.012866020202636719 nb_pixel_total : 174 time to create 1 rle with old method : 0.0003387928009033203 time for calcul the mask position with numpy : 0.009760379791259766 nb_pixel_total : 486 time to create 1 rle with old method : 0.0008115768432617188 time for calcul the mask position with numpy : 0.009850502014160156 nb_pixel_total : 208 time to create 1 rle with old method : 0.00039458274841308594 time for calcul the mask position with numpy : 0.009695768356323242 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005042552947998047 time for calcul the mask position with numpy : 0.009212017059326172 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005478858947753906 time for calcul the mask position with numpy : 0.008579015731811523 nb_pixel_total : 426 time to create 1 rle with old method : 0.0005230903625488281 time for calcul the mask position with numpy : 0.008672952651977539 nb_pixel_total : 620 time to create 1 rle with old method : 0.0007472038269042969 time for calcul the mask position with numpy : 0.01007080078125 nb_pixel_total : 532 time to create 1 rle with old method : 0.0006420612335205078 time for calcul the mask position with numpy : 0.008512258529663086 nb_pixel_total : 517 time to create 1 rle with old method : 0.0006194114685058594 time for calcul the mask position with numpy : 0.008479595184326172 nb_pixel_total : 785 time to create 1 rle with old method : 0.0009868144989013672 time for calcul the mask position with numpy : 0.008612394332885742 nb_pixel_total : 257 time to create 1 rle with old method : 0.00037384033203125 time for calcul the mask position with numpy : 0.008603096008300781 nb_pixel_total : 1284 time to create 1 rle with old method : 0.0014634132385253906 time for calcul the mask position with numpy : 0.008625268936157227 nb_pixel_total : 7 time to create 1 rle with old method : 5.269050598144531e-05 time for calcul the mask position with numpy : 0.008608102798461914 nb_pixel_total : 331 time to create 1 rle with old method : 0.00042366981506347656 time for calcul the mask position with numpy : 0.008743762969970703 nb_pixel_total : 360 time to create 1 rle with old method : 0.0006098747253417969 time for calcul the mask position with numpy : 0.00851893424987793 nb_pixel_total : 1 time to create 1 rle with old method : 2.2411346435546875e-05 create new chi : 1.7939977645874023 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 : 0.010204315185546875 batch 1 Loaded 120 chid ids of type : 4230 Number RLEs to save : 11953 TO DO : save crop sub photo not yet done ! save time : 13.770709753036499 nb_obj : 132 nb_hashtags : 7 time to prepare the origin masks : 3.47137451171875 time for calcul the mask position with numpy : 0.13602089881896973 nb_pixel_total : 1548302 time to create 1 rle with new method : 0.2762575149536133 time for calcul the mask position with numpy : 0.008275270462036133 nb_pixel_total : 7306 time to create 1 rle with old method : 0.008844137191772461 time for calcul the mask position with numpy : 0.008113861083984375 nb_pixel_total : 9219 time to create 1 rle with old method : 0.013187170028686523 time for calcul the mask position with numpy : 0.008985519409179688 nb_pixel_total : 644 time to create 1 rle with old method : 0.0010640621185302734 time for calcul the mask position with numpy : 0.009307622909545898 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006935596466064453 time for calcul the mask position with numpy : 0.009204387664794922 nb_pixel_total : 57507 time to create 1 rle with old method : 0.08885502815246582 time for calcul the mask position with numpy : 0.007841825485229492 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004031658172607422 time for calcul the mask position with numpy : 0.007242918014526367 nb_pixel_total : 751 time to create 1 rle with old method : 0.0009171962738037109 time for calcul the mask position with numpy : 0.007285118103027344 nb_pixel_total : 199 time to create 1 rle with old method : 0.00028896331787109375 time for calcul the mask position with numpy : 0.008053779602050781 nb_pixel_total : 55 time to create 1 rle with old method : 0.00010800361633300781 time for calcul the mask position with numpy : 0.007881402969360352 nb_pixel_total : 256 time to create 1 rle with old method : 0.000392913818359375 time for calcul the mask position with numpy : 0.007393360137939453 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0015513896942138672 time for calcul the mask position with numpy : 0.00966501235961914 nb_pixel_total : 639 time to create 1 rle with old method : 0.0007867813110351562 time for calcul the mask position with numpy : 0.012241125106811523 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003838539123535156 time for calcul the mask position with numpy : 0.007596015930175781 nb_pixel_total : 18 time to create 1 rle with old method : 5.888938903808594e-05 time for calcul the mask position with numpy : 0.0073699951171875 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005362033843994141 time for calcul the mask position with numpy : 0.007212400436401367 nb_pixel_total : 139 time to create 1 rle with old method : 0.00022840499877929688 time for calcul the mask position with numpy : 0.008793830871582031 nb_pixel_total : 426 time to create 1 rle with old method : 0.0006234645843505859 time for calcul the mask position with numpy : 0.008964776992797852 nb_pixel_total : 361 time to create 1 rle with old method : 0.0006165504455566406 time for calcul the mask position with numpy : 0.009451150894165039 nb_pixel_total : 523 time to create 1 rle with old method : 0.0007004737854003906 time for calcul the mask position with numpy : 0.008764266967773438 nb_pixel_total : 856 time to create 1 rle with old method : 0.0012161731719970703 time for calcul the mask position with numpy : 0.010584115982055664 nb_pixel_total : 604 time to create 1 rle with old method : 0.0008158683776855469 time for calcul the mask position with numpy : 0.010427236557006836 nb_pixel_total : 1640 time to create 1 rle with old method : 0.002228260040283203 time for calcul the mask position with numpy : 0.010384082794189453 nb_pixel_total : 1535 time to create 1 rle with old method : 0.0033211708068847656 time for calcul the mask position with numpy : 0.009629249572753906 nb_pixel_total : 301 time to create 1 rle with old method : 0.0005736351013183594 time for calcul the mask position with numpy : 0.008800506591796875 nb_pixel_total : 314 time to create 1 rle with old method : 0.0006344318389892578 time for calcul the mask position with numpy : 0.009341001510620117 nb_pixel_total : 665 time to create 1 rle with old method : 0.0011475086212158203 time for calcul the mask position with numpy : 0.010019540786743164 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003895759582519531 time for calcul the mask position with numpy : 0.009866714477539062 nb_pixel_total : 376 time to create 1 rle with old method : 0.0006201267242431641 time for calcul the mask position with numpy : 0.008748292922973633 nb_pixel_total : 333 time to create 1 rle with old method : 0.08684253692626953 time for calcul the mask position with numpy : 0.011327981948852539 nb_pixel_total : 1145 time to create 1 rle with old method : 0.0017795562744140625 time for calcul the mask position with numpy : 0.010531902313232422 nb_pixel_total : 1007 time to create 1 rle with old method : 0.0015568733215332031 time for calcul the mask position with numpy : 0.011121988296508789 nb_pixel_total : 1371 time to create 1 rle with old method : 0.0021865367889404297 time for calcul the mask position with numpy : 0.011658906936645508 nb_pixel_total : 1118 time to create 1 rle with old method : 0.0019032955169677734 time for calcul the mask position with numpy : 0.012227773666381836 nb_pixel_total : 14 time to create 1 rle with old method : 0.00017309188842773438 time for calcul the mask position with numpy : 0.013460874557495117 nb_pixel_total : 678 time to create 1 rle with old method : 0.0011746883392333984 time for calcul the mask position with numpy : 0.011480093002319336 nb_pixel_total : 461 time to create 1 rle with old method : 0.0008037090301513672 time for calcul the mask position with numpy : 0.009467124938964844 nb_pixel_total : 8 time to create 1 rle with old method : 8.034706115722656e-05 time for calcul the mask position with numpy : 0.009660482406616211 nb_pixel_total : 129 time to create 1 rle with old method : 0.00027561187744140625 time for calcul the mask position with numpy : 0.010702133178710938 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0019767284393310547 time for calcul the mask position with numpy : 0.01228952407836914 nb_pixel_total : 1386 time to create 1 rle with old method : 0.002507448196411133 time for calcul the mask position with numpy : 0.011348247528076172 nb_pixel_total : 24 time to create 1 rle with old method : 9.870529174804688e-05 time for calcul the mask position with numpy : 0.014514923095703125 nb_pixel_total : 4228 time to create 1 rle with old method : 0.005963802337646484 time for calcul the mask position with numpy : 0.011219263076782227 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001506805419921875 time for calcul the mask position with numpy : 0.015149116516113281 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003631114959716797 time for calcul the mask position with numpy : 0.014688253402709961 nb_pixel_total : 517 time to create 1 rle with old method : 0.0009951591491699219 time for calcul the mask position with numpy : 0.019628047943115234 nb_pixel_total : 154311 time to create 1 rle with new method : 0.5667834281921387 time for calcul the mask position with numpy : 0.011941671371459961 nb_pixel_total : 867 time to create 1 rle with old method : 0.001062154769897461 time for calcul the mask position with numpy : 0.012764453887939453 nb_pixel_total : 710 time to create 1 rle with old method : 0.0008924007415771484 time for calcul the mask position with numpy : 0.013544082641601562 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002377033233642578 time for calcul the mask position with numpy : 0.010504484176635742 nb_pixel_total : 1228 time to create 1 rle with old method : 0.0013968944549560547 time for calcul the mask position with numpy : 0.011479854583740234 nb_pixel_total : 63 time to create 1 rle with old method : 0.00011038780212402344 time for calcul the mask position with numpy : 0.012265205383300781 nb_pixel_total : 1355 time to create 1 rle with old method : 0.0016093254089355469 time for calcul the mask position with numpy : 0.018236398696899414 nb_pixel_total : 1121 time to create 1 rle with old method : 0.0014386177062988281 time for calcul the mask position with numpy : 0.015574455261230469 nb_pixel_total : 714 time to create 1 rle with old method : 0.0010128021240234375 time for calcul the mask position with numpy : 0.01639413833618164 nb_pixel_total : 6523 time to create 1 rle with old method : 0.008144378662109375 time for calcul the mask position with numpy : 0.013473987579345703 nb_pixel_total : 7455 time to create 1 rle with old method : 0.00835275650024414 time for calcul the mask position with numpy : 0.0142669677734375 nb_pixel_total : 194 time to create 1 rle with old method : 0.00028443336486816406 time for calcul the mask position with numpy : 0.014217615127563477 nb_pixel_total : 716 time to create 1 rle with old method : 0.00096893310546875 time for calcul the mask position with numpy : 0.017999887466430664 nb_pixel_total : 15962 time to create 1 rle with old method : 0.01891613006591797 time for calcul the mask position with numpy : 0.014163017272949219 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006399154663085938 time for calcul the mask position with numpy : 0.014495372772216797 nb_pixel_total : 3440 time to create 1 rle with old method : 0.003908872604370117 time for calcul the mask position with numpy : 0.013483047485351562 nb_pixel_total : 2002 time to create 1 rle with old method : 0.002313375473022461 time for calcul the mask position with numpy : 0.013789653778076172 nb_pixel_total : 220 time to create 1 rle with old method : 0.00035119056701660156 time for calcul the mask position with numpy : 0.013073205947875977 nb_pixel_total : 113 time to create 1 rle with old method : 0.00017690658569335938 time for calcul the mask position with numpy : 0.017025470733642578 nb_pixel_total : 2538 time to create 1 rle with old method : 0.004046440124511719 time for calcul the mask position with numpy : 0.014600038528442383 nb_pixel_total : 352 time to create 1 rle with old method : 0.00043892860412597656 time for calcul the mask position with numpy : 0.011532068252563477 nb_pixel_total : 12 time to create 1 rle with old method : 8.440017700195312e-05 time for calcul the mask position with numpy : 0.011327028274536133 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005514621734619141 time for calcul the mask position with numpy : 0.007019519805908203 nb_pixel_total : 1465 time to create 1 rle with old method : 0.001703500747680664 time for calcul the mask position with numpy : 0.0075418949127197266 nb_pixel_total : 4188 time to create 1 rle with old method : 0.004773855209350586 time for calcul the mask position with numpy : 0.007843494415283203 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0014767646789550781 time for calcul the mask position with numpy : 0.008109331130981445 nb_pixel_total : 8 time to create 1 rle with old method : 6.246566772460938e-05 time for calcul the mask position with numpy : 0.008193254470825195 nb_pixel_total : 356 time to create 1 rle with old method : 0.0004820823669433594 time for calcul the mask position with numpy : 0.008623361587524414 nb_pixel_total : 363 time to create 1 rle with old method : 0.00048089027404785156 time for calcul the mask position with numpy : 0.008687496185302734 nb_pixel_total : 3 time to create 1 rle with old method : 6.318092346191406e-05 time for calcul the mask position with numpy : 0.009313344955444336 nb_pixel_total : 2162 time to create 1 rle with old method : 0.002562999725341797 time for calcul the mask position with numpy : 0.008476018905639648 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003733634948730469 time for calcul the mask position with numpy : 0.009495735168457031 nb_pixel_total : 1816 time to create 1 rle with old method : 0.0025620460510253906 time for calcul the mask position with numpy : 0.00806570053100586 nb_pixel_total : 716 time to create 1 rle with old method : 0.0008435249328613281 time for calcul the mask position with numpy : 0.008536100387573242 nb_pixel_total : 522 time to create 1 rle with old method : 0.0006852149963378906 time for calcul the mask position with numpy : 0.010224580764770508 nb_pixel_total : 161 time to create 1 rle with old method : 0.00033473968505859375 time for calcul the mask position with numpy : 0.00984334945678711 nb_pixel_total : 121 time to create 1 rle with old method : 0.00022459030151367188 time for calcul the mask position with numpy : 0.00921773910522461 nb_pixel_total : 340 time to create 1 rle with old method : 0.00045299530029296875 time for calcul the mask position with numpy : 0.009037494659423828 nb_pixel_total : 124 time to create 1 rle with old method : 0.00019431114196777344 time for calcul the mask position with numpy : 0.00911712646484375 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002486705780029297 time for calcul the mask position with numpy : 0.008439779281616211 nb_pixel_total : 104 time to create 1 rle with old method : 0.00021696090698242188 time for calcul the mask position with numpy : 0.008777141571044922 nb_pixel_total : 157 time to create 1 rle with old method : 0.00022530555725097656 time for calcul the mask position with numpy : 0.007947206497192383 nb_pixel_total : 125 time to create 1 rle with old method : 0.0001857280731201172 time for calcul the mask position with numpy : 0.007852792739868164 nb_pixel_total : 192 time to create 1 rle with old method : 0.00026535987854003906 time for calcul the mask position with numpy : 0.00906682014465332 nb_pixel_total : 105298 time to create 1 rle with old method : 0.12223482131958008 time for calcul the mask position with numpy : 0.009350299835205078 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001709461212158203 time for calcul the mask position with numpy : 0.008308172225952148 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005173683166503906 time for calcul the mask position with numpy : 0.008626222610473633 nb_pixel_total : 36581 time to create 1 rle with old method : 0.04134058952331543 time for calcul the mask position with numpy : 0.009290695190429688 nb_pixel_total : 36 time to create 1 rle with old method : 0.00012946128845214844 time for calcul the mask position with numpy : 0.010509967803955078 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001842975616455078 time for calcul the mask position with numpy : 0.009358644485473633 nb_pixel_total : 378 time to create 1 rle with old method : 0.0004930496215820312 time for calcul the mask position with numpy : 0.010364294052124023 nb_pixel_total : 11 time to create 1 rle with old method : 9.322166442871094e-05 time for calcul the mask position with numpy : 0.010496139526367188 nb_pixel_total : 402 time to create 1 rle with old method : 0.0006160736083984375 time for calcul the mask position with numpy : 0.011105060577392578 nb_pixel_total : 44902 time to create 1 rle with old method : 0.060608863830566406 time for calcul the mask position with numpy : 0.008667945861816406 nb_pixel_total : 382 time to create 1 rle with old method : 0.0004935264587402344 time for calcul the mask position with numpy : 0.008188724517822266 nb_pixel_total : 338 time to create 1 rle with old method : 0.0004622936248779297 time for calcul the mask position with numpy : 0.00920557975769043 nb_pixel_total : 1878 time to create 1 rle with old method : 0.0024099349975585938 time for calcul the mask position with numpy : 0.009671211242675781 nb_pixel_total : 254 time to create 1 rle with old method : 0.0003571510314941406 time for calcul the mask position with numpy : 0.010476112365722656 nb_pixel_total : 280 time to create 1 rle with old method : 0.0004818439483642578 time for calcul the mask position with numpy : 0.01115870475769043 nb_pixel_total : 354 time to create 1 rle with old method : 0.00045609474182128906 time for calcul the mask position with numpy : 0.011160135269165039 nb_pixel_total : 663 time to create 1 rle with old method : 0.000823974609375 time for calcul the mask position with numpy : 0.009617328643798828 nb_pixel_total : 3749 time to create 1 rle with old method : 0.004334688186645508 time for calcul the mask position with numpy : 0.01822948455810547 nb_pixel_total : 244 time to create 1 rle with old method : 0.00032711029052734375 time for calcul the mask position with numpy : 0.010152339935302734 nb_pixel_total : 299 time to create 1 rle with old method : 0.00042057037353515625 time for calcul the mask position with numpy : 0.00971674919128418 nb_pixel_total : 1376 time to create 1 rle with old method : 0.0016186237335205078 time for calcul the mask position with numpy : 0.009596824645996094 nb_pixel_total : 799 time to create 1 rle with old method : 0.0009443759918212891 time for calcul the mask position with numpy : 0.009501218795776367 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007951259613037109 time for calcul the mask position with numpy : 0.009563684463500977 nb_pixel_total : 15 time to create 1 rle with old method : 0.00010609626770019531 time for calcul the mask position with numpy : 0.014137029647827148 nb_pixel_total : 193 time to create 1 rle with old method : 0.00045943260192871094 time for calcul the mask position with numpy : 0.009692192077636719 nb_pixel_total : 484 time to create 1 rle with old method : 0.0006048679351806641 time for calcul the mask position with numpy : 0.009154796600341797 nb_pixel_total : 220 time to create 1 rle with old method : 0.0002982616424560547 time for calcul the mask position with numpy : 0.008687257766723633 nb_pixel_total : 81 time to create 1 rle with old method : 0.0001499652862548828 time for calcul the mask position with numpy : 0.008621692657470703 nb_pixel_total : 412 time to create 1 rle with old method : 0.0004918575286865234 time for calcul the mask position with numpy : 0.00842905044555664 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008451938629150391 time for calcul the mask position with numpy : 0.009349822998046875 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005011558532714844 time for calcul the mask position with numpy : 0.008288860321044922 nb_pixel_total : 620 time to create 1 rle with old method : 0.0007076263427734375 time for calcul the mask position with numpy : 0.008565902709960938 nb_pixel_total : 1172 time to create 1 rle with old method : 0.0012853145599365234 time for calcul the mask position with numpy : 0.008786678314208984 nb_pixel_total : 614 time to create 1 rle with old method : 0.0007662773132324219 time for calcul the mask position with numpy : 0.008607149124145508 nb_pixel_total : 507 time to create 1 rle with old method : 0.0005648136138916016 time for calcul the mask position with numpy : 0.008429527282714844 nb_pixel_total : 56 time to create 1 rle with old method : 0.00010061264038085938 time for calcul the mask position with numpy : 0.008998870849609375 nb_pixel_total : 1275 time to create 1 rle with old method : 0.001379251480102539 time for calcul the mask position with numpy : 0.00837397575378418 nb_pixel_total : 315 time to create 1 rle with old method : 0.0003533363342285156 time for calcul the mask position with numpy : 0.008283615112304688 nb_pixel_total : 368 time to create 1 rle with old method : 0.00045037269592285156 time for calcul the mask position with numpy : 0.00854802131652832 nb_pixel_total : 1022 time to create 1 rle with old method : 0.0011723041534423828 time for calcul the mask position with numpy : 0.008777618408203125 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005609989166259766 time for calcul the mask position with numpy : 0.009508371353149414 nb_pixel_total : 36 time to create 1 rle with old method : 9.942054748535156e-05 time for calcul the mask position with numpy : 0.008771419525146484 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005114078521728516 create new chi : 2.9317822456359863 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 : 0.0029680728912353516 Catched exception ! Connect or reconnect ! batch 1 Loaded 133 chid ids of type : 4230 Number RLEs to save : 13837 TO DO : save crop sub photo not yet done ! save time : 19.688108921051025 map_output_result : {1341315107: (0.0, 'Should be the crop_list due to order', 0.0), 1341315104: (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 [1341315107, 1341315104] Looping around the photos to save general results len do output : 2 /1341315107.Didn't retrieve data . /1341315104.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, '2646028') ('4234', '21129606', '1341315107', None, None, None, None, None, '2646028') ('4234', None, None, None, None, None, None, None, '2646028') ('4234', '21129606', '1341315104', None, None, None, None, None, '2646028') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.0157928466796875 save_final save missing photos in datou_result : time spend for datou_step_exec : 47.440300703048706 time spend to save output : 0.026664257049560547 total time spend for step 4 : 47.46696496009827 step5:crop_condition Sat Mar 8 18:21:57 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 : 2 ! batch 1 Loaded 253 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 ! map_result returned by crop_photo_return_map_crop : length : 84 About to insert : list_path_to_insert length 84 new photo from crops ! About to upload 84 photos upload in portfolio : 4869462 init cache_photo without model_param we have 84 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741454523_1752582 we have uploaded 84 photos in the portfolio 4869462 time of upload the photos Elapsed time : 20.760684490203857 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 ! map_result returned by crop_photo_return_map_crop : length : 30 About to insert : list_path_to_insert length 30 new photo from crops ! About to upload 30 photos upload in portfolio : 4869462 init cache_photo without model_param we have 30 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741454544_1752582 we have uploaded 30 photos in the portfolio 4869462 time of upload the photos Elapsed time : 7.959472894668579 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741454552_1752582 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.44881176948547363 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 16 About to insert : list_path_to_insert length 16 new photo from crops ! About to upload 16 photos upload in portfolio : 4869462 init cache_photo without model_param we have 16 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741454553_1752582 we have uploaded 16 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.683925628662109 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 ! map_result returned by crop_photo_return_map_crop : length : 41 About to insert : list_path_to_insert length 41 new photo from crops ! About to upload 41 photos upload in portfolio : 4869462 init cache_photo without model_param we have 41 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741454558_1752582 we have uploaded 41 photos in the portfolio 4869462 time of upload the photos Elapsed time : 12.407480955123901 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 [1341315107, 1341315104] Looping around the photos to save general results len do output : 172 /1341950757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950767Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950771Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950773Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950775Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950777Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1341950987Didn'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, '2646028') ('4234', '21129606', '1341315107', None, None, None, None, None, '2646028') ('4234', None, None, None, None, None, None, None, '2646028') ('4234', '21129606', '1341315104', None, None, None, None, None, '2646028') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 518 time used for this insertion : 0.03788590431213379 save_final save missing photos in datou_result : time spend for datou_step_exec : 60.80890417098999 time spend to save output : 0.04306983947753906 total time spend for step 5 : 60.85197401046753 step6:thcl Sat Mar 8 18:22:58 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 0.009786844253540039 time to convert the images to numpy array : 0.025086402893066406 time to import caffe and check if the image exist : 0.01665019989013672 time to convert the images to numpy array : 0.04702115058898926 time to import caffe and check if the image exist : 0.010793685913085938 time to convert the images to numpy array : 0.05649256706237793 time to import caffe and check if the image exist : 0.019623279571533203 time to convert the images to numpy array : 0.04919290542602539 time to import caffe and check if the image exist : 0.021228790283203125 time to convert the images to numpy array : 0.048619985580444336 time to import caffe and check if the image exist : 0.015662193298339844 time to convert the images to numpy array : 0.05485057830810547 time to import caffe and check if the image exist : 0.016078472137451172 time to convert the images to numpy array : 0.05692887306213379 time to import caffe and check if the image exist : 0.015172958374023438 time to convert the images to numpy array : 0.05856752395629883 time to import caffe and check if the image exist : 0.03100109100341797 time to convert the images to numpy array : 0.045449018478393555 time to import caffe and check if the image exist : 0.025407791137695312 time to convert the images to numpy array : 0.05019211769104004 total time to convert the images to numpy array : 0.4578232765197754 list photo_ids error: [] list photo_ids correct : [1341950977, 1341950979, 1341950980, 1341950981, 1341950982, 1341950983, 1341950984, 1341950985, 1341950986, 1341950987, 1341950896, 1341950897, 1341950898, 1341950899, 1341950900, 1341950945, 1341950946, 1341950947, 1341950948, 1341950949, 1341950950, 1341950951, 1341950952, 1341950953, 1341950954, 1341950955, 1341950956, 1341950957, 1341950855, 1341950856, 1341950857, 1341950858, 1341950859, 1341950860, 1341950861, 1341950862, 1341950863, 1341950864, 1341950865, 1341950866, 1341950867, 1341950868, 1341950869, 1341950870, 1341950871, 1341950872, 1341950776, 1341950777, 1341950778, 1341950779, 1341950780, 1341950781, 1341950782, 1341950783, 1341950784, 1341950785, 1341950786, 1341950787, 1341950788, 1341950789, 1341950790, 1341950791, 1341950792, 1341950793, 1341950795, 1341950796, 1341950797, 1341950799, 1341950800, 1341950801, 1341950802, 1341950803, 1341950804, 1341950805, 1341950807, 1341950808, 1341950809, 1341950810, 1341950811, 1341950812, 1341950813, 1341950814, 1341950873, 1341950874, 1341950875, 1341950877, 1341950879, 1341950880, 1341950882, 1341950884, 1341950885, 1341950886, 1341950887, 1341950888, 1341950889, 1341950890, 1341950891, 1341950893, 1341950894, 1341950895, 1341950757, 1341950758, 1341950759, 1341950761, 1341950762, 1341950763, 1341950764, 1341950765, 1341950766, 1341950767, 1341950768, 1341950769, 1341950770, 1341950771, 1341950772, 1341950773, 1341950774, 1341950775, 1341950815, 1341950816, 1341950817, 1341950818, 1341950819, 1341950820, 1341950821, 1341950822, 1341950823, 1341950824, 1341950825, 1341950826, 1341950827, 1341950828, 1341950829, 1341950830, 1341950831, 1341950832, 1341950833, 1341950834, 1341950835, 1341950836, 1341950837, 1341950838, 1341950839, 1341950840, 1341950841, 1341950842, 1341950843, 1341950844, 1341950848, 1341950850, 1341950851, 1341950852, 1341950853, 1341950854, 1341950958, 1341950959, 1341950960, 1341950961, 1341950962, 1341950964, 1341950965, 1341950966, 1341950967, 1341950968, 1341950969, 1341950970, 1341950971, 1341950972, 1341950973, 1341950974, 1341950975, 1341950976] number of photos to traite : 172 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 havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 88 wait 20 seconds l 3637 free memory gpu now : 88 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 havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 334 wait 20 seconds WARNING: Logging before InitGoogleLogging() is written to STDERR F0308 18:23:46.103942 1752582 syncedmem.cpp:71] Check failed: error == cudaSuccess (2 vs. 0) out of memory *** Check failure stack trace: *** Command terminated by signal 6 34.50user 26.98system 3:22.96elapsed 30%CPU (0avgtext+0avgdata 2431332maxresident)k 1201328inputs+6632outputs (11860major+2379837minor)pagefaults 0swaps