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 : 2385694 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 : ['2634593'] with mtr_portfolio_ids : ['21033063'] and first list_photo_ids : [] new path : /proc/2385694/ 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 : 0.31124043464660645 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 Wed Mar 5 00:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3740 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-05 00:20:31.679935: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-05 00:20:31.707151: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-05 00:20:31.708646: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd438000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-05 00:20:31.708666: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-05 00:20:31.711401: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-05 00:20:31.855203: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xf300740 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-05 00:20:31.855248: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-05 00:20:31.855958: 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 2025-03-05 00:20:31.856617: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-05 00:20:31.860290: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-05 00:20:31.862456: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-05 00:20:31.863752: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-05 00:20:31.866051: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-05 00:20:31.867219: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-05 00:20:31.871774: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-05 00:20:31.872821: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-05 00:20:31.872895: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-05 00:20:31.873455: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-05 00:20:31.873470: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-05 00:20:31.873479: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-05 00:20:31.874369: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3286 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. 2025-03-05 00:20:32.159519: 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 2025-03-05 00:20:32.159636: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-05 00:20:32.159652: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-05 00:20:32.159667: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-05 00:20:32.159681: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-05 00:20:32.159695: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-05 00:20:32.159709: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-05 00:20:32.159723: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-05 00:20:32.160551: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-05 00:20:32.161540: 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 2025-03-05 00:20:32.161572: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-05 00:20:32.161588: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-05 00:20:32.161601: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-05 00:20:32.161615: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-05 00:20:32.161629: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-05 00:20:32.161643: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-05 00:20:32.161660: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-05 00:20:32.162472: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-05 00:20:32.162505: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-05 00:20:32.162513: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-05 00:20:32.162520: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-05 00:20:32.163379: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3286 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 : [] 2025-03-05 00:20:41.597562: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-05 00:20:41.914280: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-05 00:20:43.761998: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.763095: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.44G (2619644160 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.764143: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.20G (2357679616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.764195: 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. 2025-03-05 00:20:43.765184: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.765215: 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. 2025-03-05 00:20:43.775266: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.775327: 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. 2025-03-05 00:20:43.776275: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.776308: 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. 2025-03-05 00:20:43.783801: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.783859: 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. 2025-03-05 00:20:43.784618: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.784643: 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. 2025-03-05 00:20:43.826342: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.826425: 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. 2025-03-05 00:20:43.827084: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.827111: 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. 2025-03-05 00:20:43.836371: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.836436: 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. 2025-03-05 00:20:43.837131: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.837158: 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. 2025-03-05 00:20:43.883459: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.884202: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.886709: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.887440: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.932589: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.933687: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.936565: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.937573: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.973097: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.973784: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.975636: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.976279: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.984232: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.984920: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.986799: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.987489: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.995540: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.996224: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.999152: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:43.999783: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.035007: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.035672: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.036280: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.036894: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.041904: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.042573: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.062856: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.063503: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.064098: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.064688: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.079249: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.079884: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.080479: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.081068: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.085479: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.086079: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.092227: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.092878: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.107528: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.108252: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.113260: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.113859: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.114452: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.115051: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.115821: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.116418: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.128400: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.129036: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.129648: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.130236: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.130824: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.131483: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.132083: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.132720: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.150172: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.150814: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.207400: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.208063: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.208681: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.209295: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.218417: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.219070: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.233119: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.233788: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.234464: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.235092: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.240242: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.240871: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.241492: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.242089: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.243254: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.243278: 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. 2025-03-05 00:20:44.255167: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.255790: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.264844: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.265465: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.266065: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.266654: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.267276: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-05 00:20:44.267870: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.71G (2910715904 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: -120.99688 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.0005960464477539062 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.10234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0009610652923583984 length of segment : 26 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1517 time to create 1 rle with old method : 0.0018107891082763672 length of segment : 146 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1795 time to create 1 rle with old method : 0.002439260482788086 length of segment : 35 time for calcul the mask position with numpy : 0.00018024444580078125 nb_pixel_total : 4732 time to create 1 rle with old method : 0.006873607635498047 length of segment : 108 time for calcul the mask position with numpy : 0.0001773834228515625 nb_pixel_total : 4495 time to create 1 rle with old method : 0.005955219268798828 length of segment : 83 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 2206 time to create 1 rle with old method : 0.003226757049560547 length of segment : 44 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 3420 time to create 1 rle with old method : 0.0047931671142578125 length of segment : 64 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.0003418922424316406 length of segment : 13 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 986 time to create 1 rle with old method : 0.0012652873992919922 length of segment : 56 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 2274 time to create 1 rle with old method : 0.0034198760986328125 length of segment : 45 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 3565 time to create 1 rle with old method : 0.004319190979003906 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: -122.62969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 25 time for calcul the mask position with numpy : 0.00013446807861328125 nb_pixel_total : 1640 time to create 1 rle with old method : 0.0022935867309570312 length of segment : 62 time for calcul the mask position with numpy : 9.822845458984375e-05 nb_pixel_total : 1795 time to create 1 rle with old method : 0.0025615692138671875 length of segment : 52 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003485679626464844 length of segment : 28 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 1826 time to create 1 rle with old method : 0.0025916099548339844 length of segment : 45 time for calcul the mask position with numpy : 0.0001277923583984375 nb_pixel_total : 2141 time to create 1 rle with old method : 0.002864837646484375 length of segment : 62 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 670 time to create 1 rle with old method : 0.0009975433349609375 length of segment : 29 time for calcul the mask position with numpy : 0.0002079010009765625 nb_pixel_total : 7478 time to create 1 rle with old method : 0.008925676345825195 length of segment : 106 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 827 time to create 1 rle with old method : 0.001131296157836914 length of segment : 28 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007369518280029297 length of segment : 28 time for calcul the mask position with numpy : 0.0001327991485595703 nb_pixel_total : 2395 time to create 1 rle with old method : 0.003095388412475586 length of segment : 124 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0008056163787841797 length of segment : 21 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0007464885711669922 length of segment : 18 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007717609405517578 length of segment : 20 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1439 time to create 1 rle with old method : 0.0018568038940429688 length of segment : 52 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 1540 time to create 1 rle with old method : 0.002293109893798828 length of segment : 53 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 335 time to create 1 rle with old method : 0.0004956722259521484 length of segment : 23 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 2000 time to create 1 rle with old method : 0.00246429443359375 length of segment : 53 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004820823669433594 length of segment : 22 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0010263919830322266 length of segment : 34 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0006821155548095703 length of segment : 27 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.00048232078552246094 length of segment : 26 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007824897766113281 length of segment : 31 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007834434509277344 length of segment : 22 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0004343986511230469 length of segment : 20 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1057 time to create 1 rle with old method : 0.0014259815216064453 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.01250 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.0017802715301513672 length of segment : 25 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1310 time to create 1 rle with old method : 0.0022759437561035156 length of segment : 59 time for calcul the mask position with numpy : 0.00013256072998046875 nb_pixel_total : 2598 time to create 1 rle with old method : 0.004461765289306641 length of segment : 59 time for calcul the mask position with numpy : 0.00035500526428222656 nb_pixel_total : 7409 time to create 1 rle with old method : 0.012443065643310547 length of segment : 150 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 885 time to create 1 rle with old method : 0.0015950202941894531 length of segment : 46 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 801 time to create 1 rle with old method : 0.0016241073608398438 length of segment : 30 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 1860 time to create 1 rle with old method : 0.0032880306243896484 length of segment : 52 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 925 time to create 1 rle with old method : 0.0017464160919189453 length of segment : 40 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0003306865692138672 length of segment : 12 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0011670589447021484 length of segment : 26 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0007102489471435547 length of segment : 22 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.00043320655822753906 length of segment : 12 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 654 time to create 1 rle with old method : 0.0011370182037353516 length of segment : 58 Processing 1 images image shape: (400, 400, 3) min: 69.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -42.27813 max: 149.50625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0007464885711669922 length of segment : 29 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0007038116455078125 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.45781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.001239776611328125 length of segment : 29 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0006670951843261719 length of segment : 33 Processing 1 images image shape: (400, 160, 3) min: 6.00000 max: 245.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 134.95547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2609 time to create 1 rle with old method : 0.003083467483520508 length of segment : 72 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004246234893798828 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.09063 max: 150.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0004477500915527344 length of segment : 23 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.00043964385986328125 length of segment : 42 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006897449493408203 length of segment : 33 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00026345252990722656 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.22734 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005667209625244141 length of segment : 30 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.00046443939208984375 length of segment : 32 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00034737586975097656 length of segment : 16 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1728 time to create 1 rle with old method : 0.002590656280517578 length of segment : 38 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1744 time to create 1 rle with old method : 0.00225067138671875 length of segment : 40 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003552436828613281 length of segment : 20 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007374286651611328 length of segment : 58 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0009033679962158203 length of segment : 34 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2519 time to create 1 rle with old method : 0.0031566619873046875 length of segment : 46 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00017023086547851562 length of segment : 7 time for calcul the mask position with numpy : 0.0005004405975341797 nb_pixel_total : 25616 time to create 1 rle with old method : 0.0289304256439209 length of segment : 288 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 1740 time to create 1 rle with old method : 0.002453327178955078 length of segment : 38 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 2144 time to create 1 rle with old method : 0.004282474517822266 length of segment : 66 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0011889934539794922 length of segment : 33 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.00037288665771484375 length of segment : 21 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 2185 time to create 1 rle with old method : 0.0030794143676757812 length of segment : 49 time for calcul the mask position with numpy : 0.0001380443572998047 nb_pixel_total : 2937 time to create 1 rle with old method : 0.005055427551269531 length of segment : 71 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 707 time to create 1 rle with old method : 0.0014240741729736328 length of segment : 43 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.19609 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 30 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1209 time to create 1 rle with old method : 0.0015573501586914062 length of segment : 39 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 11 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0008027553558349609 length of segment : 57 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 655 time to create 1 rle with old method : 0.0008759498596191406 length of segment : 33 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1772 time to create 1 rle with old method : 0.002237558364868164 length of segment : 63 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003001689910888672 length of segment : 15 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0011548995971679688 length of segment : 31 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006580352783203125 length of segment : 21 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003707408905029297 length of segment : 14 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 2040 time to create 1 rle with old method : 0.0024824142456054688 length of segment : 59 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007965564727783203 length of segment : 25 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0007815361022949219 length of segment : 24 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1762 time to create 1 rle with old method : 0.0023801326751708984 length of segment : 34 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00022554397583007812 length of segment : 15 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.001100301742553711 length of segment : 35 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.00020647048950195312 length of segment : 8 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1091 time to create 1 rle with old method : 0.0014352798461914062 length of segment : 54 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.001150369644165039 length of segment : 36 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 769 time to create 1 rle with old method : 0.00107574462890625 length of segment : 30 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0003190040588378906 length of segment : 23 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 98 time to create 1 rle with old method : 0.00016546249389648438 length of segment : 10 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007140636444091797 length of segment : 25 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00031185150146484375 length of segment : 14 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1755 time to create 1 rle with old method : 0.0023725032806396484 length of segment : 34 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004932880401611328 length of segment : 34 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0006687641143798828 length of segment : 36 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1353 time to create 1 rle with old method : 0.0020265579223632812 length of segment : 43 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0004298686981201172 length of segment : 23 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002815723419189453 length of segment : 18 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 638 time to create 1 rle with old method : 0.0008909702301025391 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: -117.33281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.001070261001586914 length of segment : 28 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 738 time to create 1 rle with old method : 0.0010612010955810547 length of segment : 57 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 2423 time to create 1 rle with old method : 0.003209829330444336 length of segment : 48 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 18 time to create 1 rle with old method : 5.14984130859375e-05 length of segment : 10 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.0002772808074951172 length of segment : 15 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1202 time to create 1 rle with old method : 0.001592397689819336 length of segment : 57 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0017061233520507812 length of segment : 35 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0008614063262939453 length of segment : 37 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1133 time to create 1 rle with old method : 0.0015213489532470703 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 86.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -37.70000 max: 149.92812 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.31719 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 : 5.1021575927734375e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.0006232261657714844 length of segment : 26 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0006213188171386719 length of segment : 23 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 640 time to create 1 rle with old method : 0.0012841224670410156 length of segment : 27 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0008337497711181641 length of segment : 34 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.001096963882446289 length of segment : 23 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.86562 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 538 time to create 1 rle with old method : 0.001043558120727539 length of segment : 26 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0006186962127685547 length of segment : 22 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0004086494445800781 length of segment : 19 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.000453948974609375 length of segment : 25 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0006110668182373047 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.55938 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0005903244018554688 length of segment : 24 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 1240 time to create 1 rle with old method : 0.002337217330932617 length of segment : 96 time for calcul the mask position with numpy : 0.00011134147644042969 nb_pixel_total : 863 time to create 1 rle with old method : 0.0016329288482666016 length of segment : 40 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.00046706199645996094 length of segment : 16 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0004887580871582031 length of segment : 20 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0011107921600341797 length of segment : 67 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 2970 time to create 1 rle with old method : 0.005162954330444336 length of segment : 163 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 2112 time to create 1 rle with old method : 0.0037724971771240234 length of segment : 56 time for calcul the mask position with numpy : 0.00019025802612304688 nb_pixel_total : 3146 time to create 1 rle with old method : 0.004054069519042969 length of segment : 127 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 461 time to create 1 rle with old method : 0.0006327629089355469 length of segment : 24 time for calcul the mask position with numpy : 0.00010538101196289062 nb_pixel_total : 1369 time to create 1 rle with old method : 0.004755735397338867 length of segment : 76 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00025582313537597656 length of segment : 15 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008072853088378906 length of segment : 34 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 1204 time to create 1 rle with old method : 0.0016794204711914062 length of segment : 57 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004947185516357422 length of segment : 34 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0013022422790527344 length of segment : 43 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0008752346038818359 length of segment : 30 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0016238689422607422 length of segment : 62 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.0006806850433349609 length of segment : 25 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0009274482727050781 length of segment : 38 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006594657897949219 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.75859 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 28 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0007650852203369141 length of segment : 33 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.0011785030364990234 length of segment : 33 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.00043010711669921875 length of segment : 17 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0005633831024169922 length of segment : 18 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00031638145446777344 length of segment : 17 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 389 time to create 1 rle with old method : 0.0005118846893310547 length of segment : 35 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 985 time to create 1 rle with old method : 0.0013070106506347656 length of segment : 59 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 990 time to create 1 rle with old method : 0.00128173828125 length of segment : 65 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0007314682006835938 length of segment : 39 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.00025391578674316406 length of segment : 21 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0004837512969970703 length of segment : 19 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00016498565673828125 length of segment : 11 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0010759830474853516 length of segment : 27 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0007660388946533203 length of segment : 28 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0006861686706542969 length of segment : 25 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1108 time to create 1 rle with old method : 0.0019240379333496094 length of segment : 39 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00028514862060546875 length of segment : 16 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0011181831359863281 length of segment : 30 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0004467964172363281 length of segment : 25 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0023734569549560547 length of segment : 52 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 858 time to create 1 rle with old method : 0.001470804214477539 length of segment : 39 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1009 time to create 1 rle with old method : 0.001344919204711914 length of segment : 44 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003681182861328125 length of segment : 17 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.000621795654296875 length of segment : 26 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.0009412765502929688 length of segment : 50 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0007522106170654297 length of segment : 39 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 471 time to create 1 rle with old method : 0.0006327629089355469 length of segment : 42 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0007963180541992188 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -99.45391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 592 time to create 1 rle with old method : 0.0013027191162109375 length of segment : 30 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.0013270378112792969 length of segment : 34 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.0003342628479003906 length of segment : 18 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 980 time to create 1 rle with old method : 0.0021126270294189453 length of segment : 33 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.0003495216369628906 length of segment : 19 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0006327629089355469 length of segment : 15 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00029158592224121094 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 88.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -33.74688 max: 125.58047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.17266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 711 time to create 1 rle with old method : 0.0008921623229980469 length of segment : 52 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008432865142822266 length of segment : 45 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.21719 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0004661083221435547 length of segment : 34 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0007865428924560547 length of segment : 35 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 41 time to create 1 rle with old method : 8.988380432128906e-05 length of segment : 6 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.00021767616271972656 length of segment : 24 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 950 time to create 1 rle with old method : 0.0012078285217285156 length of segment : 59 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005176067352294922 length of segment : 33 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0007915496826171875 length of segment : 35 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.0002543926239013672 length of segment : 22 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.74453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00041031837463378906 nb_pixel_total : 24537 time to create 1 rle with old method : 0.030707359313964844 length of segment : 133 time for calcul the mask position with numpy : 0.00012421607971191406 nb_pixel_total : 1457 time to create 1 rle with old method : 0.001905202865600586 length of segment : 40 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.0001964569091796875 length of segment : 6 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 142.61172 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 9 time to create 1 rle with old method : 7.343292236328125e-05 length of segment : 5 time for calcul the mask position with numpy : 0.0009891986846923828 nb_pixel_total : 48094 time to create 1 rle with old method : 0.05766010284423828 length of segment : 208 time for calcul the mask position with numpy : 0.00040411949157714844 nb_pixel_total : 11383 time to create 1 rle with old method : 0.014081478118896484 length of segment : 112 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 155 time to create 1 rle with old method : 0.00029158592224121094 length of segment : 17 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.0006306171417236328 length of segment : 17 Processing 1 images image shape: (240, 400, 3) min: 30.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.17031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0017375946044921875 length of segment : 61 Processing 1 images image shape: (240, 400, 3) min: 105.00000 max: 228.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 118.41641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0003390312194824219 nb_pixel_total : 22379 time to create 1 rle with old method : 0.03692507743835449 length of segment : 153 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0004627704620361328 length of segment : 26 time for calcul the mask position with numpy : 0.0002830028533935547 nb_pixel_total : 17183 time to create 1 rle with old method : 0.019962787628173828 length of segment : 160 Processing 1 images image shape: (240, 160, 3) min: 0.00000 max: 223.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 109.80982 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.83281 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00043654441833496094 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.25078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 729 time to create 1 rle with old method : 0.001107931137084961 length of segment : 26 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 1385 time to create 1 rle with old method : 0.0016641616821289062 length of segment : 121 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1825 time to create 1 rle with old method : 0.0024437904357910156 length of segment : 35 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1068 time to create 1 rle with old method : 0.001527547836303711 length of segment : 63 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00017905235290527344 length of segment : 23 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 2413 time to create 1 rle with old method : 0.0037479400634765625 length of segment : 65 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1770 time to create 1 rle with old method : 0.002342700958251953 length of segment : 93 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 2154 time to create 1 rle with old method : 0.0027811527252197266 length of segment : 44 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.00015091896057128906 length of segment : 16 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005381107330322266 length of segment : 35 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 3520 time to create 1 rle with old method : 0.004287004470825195 length of segment : 61 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0006315708160400391 length of segment : 37 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 904 time to create 1 rle with old method : 0.0011644363403320312 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.45391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 25 time for calcul the mask position with numpy : 0.00015592575073242188 nb_pixel_total : 1862 time to create 1 rle with old method : 0.0034646987915039062 length of segment : 51 time for calcul the mask position with numpy : 0.00015854835510253906 nb_pixel_total : 1623 time to create 1 rle with old method : 0.0032618045806884766 length of segment : 71 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 2046 time to create 1 rle with old method : 0.002516031265258789 length of segment : 64 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1177 time to create 1 rle with old method : 0.0015993118286132812 length of segment : 49 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.00033020973205566406 length of segment : 24 time for calcul the mask position with numpy : 0.00018978118896484375 nb_pixel_total : 5064 time to create 1 rle with old method : 0.006101131439208984 length of segment : 145 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002601146697998047 length of segment : 16 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.00038433074951171875 length of segment : 17 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 3259 time to create 1 rle with old method : 0.004320859909057617 length of segment : 114 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0008335113525390625 length of segment : 35 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 693 time to create 1 rle with old method : 0.0009088516235351562 length of segment : 37 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 762 time to create 1 rle with old method : 0.0010309219360351562 length of segment : 29 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0016326904296875 length of segment : 42 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002262592315673828 length of segment : 40 time for calcul the mask position with numpy : 0.0001571178436279297 nb_pixel_total : 5054 time to create 1 rle with old method : 0.0062639713287353516 length of segment : 146 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 723 time to create 1 rle with old method : 0.0010037422180175781 length of segment : 33 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00020885467529296875 length of segment : 34 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 766 time to create 1 rle with old method : 0.0010380744934082031 length of segment : 75 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.0010161399841308594 length of segment : 33 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 1854 time to create 1 rle with old method : 0.0031142234802246094 length of segment : 47 time for calcul the mask position with numpy : 0.00010323524475097656 nb_pixel_total : 383 time to create 1 rle with old method : 0.0007970333099365234 length of segment : 18 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0005257129669189453 length of segment : 21 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0008742809295654297 length of segment : 19 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0005960464477539062 length of segment : 18 time for calcul the mask position with numpy : 0.00011515617370605469 nb_pixel_total : 2524 time to create 1 rle with old method : 0.0036704540252685547 length of segment : 94 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.10234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 2480 time to create 1 rle with old method : 0.0030405521392822266 length of segment : 72 time for calcul the mask position with numpy : 0.00011777877807617188 nb_pixel_total : 768 time to create 1 rle with old method : 0.0019757747650146484 length of segment : 35 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0005609989166259766 length of segment : 19 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 926 time to create 1 rle with old method : 0.0013427734375 length of segment : 30 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 1745 time to create 1 rle with old method : 0.002308368682861328 length of segment : 42 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.00041937828063964844 length of segment : 19 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.000949859619140625 length of segment : 40 time for calcul the mask position with numpy : 0.00012874603271484375 nb_pixel_total : 3021 time to create 1 rle with old method : 0.0044667720794677734 length of segment : 50 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 712 time to create 1 rle with old method : 0.0009834766387939453 length of segment : 32 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0004329681396484375 length of segment : 38 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 1071 time to create 1 rle with old method : 0.0013358592987060547 length of segment : 69 time for calcul the mask position with numpy : 0.00021338462829589844 nb_pixel_total : 1487 time to create 1 rle with old method : 0.002636432647705078 length of segment : 115 time for calcul the mask position with numpy : 0.00012230873107910156 nb_pixel_total : 2473 time to create 1 rle with old method : 0.003042936325073242 length of segment : 71 Processing 1 images image shape: (400, 400, 3) min: 70.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -44.18438 max: 140.69766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.000518798828125 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.44219 max: 148.44375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.0002529621124267578 length of segment : 11 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 346 time to create 1 rle with old method : 0.0005033016204833984 length of segment : 30 time for calcul the mask position with numpy : 0.0002262592315673828 nb_pixel_total : 7323 time to create 1 rle with old method : 0.009237289428710938 length of segment : 111 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.0003452301025390625 length of segment : 17 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 653 time to create 1 rle with old method : 0.000990152359008789 length of segment : 35 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0004582405090332031 length of segment : 20 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0009479522705078125 length of segment : 36 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 895 time to create 1 rle with old method : 0.0013780593872070312 length of segment : 40 Processing 1 images image shape: (400, 160, 3) min: 4.00000 max: 251.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.45391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00021576881408691406 nb_pixel_total : 9510 time to create 1 rle with old method : 0.011717557907104492 length of segment : 139 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.23906 max: 150.20937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.00047707557678222656 length of segment : 23 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004687309265136719 length of segment : 38 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.0004074573516845703 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.18047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004315376281738281 length of segment : 28 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 867 time to create 1 rle with old method : 0.0017750263214111328 length of segment : 31 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 714 time to create 1 rle with old method : 0.0009157657623291016 length of segment : 35 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1722 time to create 1 rle with old method : 0.002276182174682617 length of segment : 36 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.0003752708435058594 length of segment : 16 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 3369 time to create 1 rle with old method : 0.004278898239135742 length of segment : 92 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 2469 time to create 1 rle with old method : 0.00301361083984375 length of segment : 92 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004749298095703125 length of segment : 25 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 3760 time to create 1 rle with old method : 0.0047550201416015625 length of segment : 62 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 554 time to create 1 rle with old method : 0.0007386207580566406 length of segment : 54 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0010685920715332031 length of segment : 26 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 2473 time to create 1 rle with old method : 0.0032608509063720703 length of segment : 57 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 2490 time to create 1 rle with old method : 0.0031282901763916016 length of segment : 48 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0015552043914794922 length of segment : 58 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0009305477142333984 length of segment : 32 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0006265640258789062 length of segment : 23 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 824 time to create 1 rle with old method : 0.0010900497436523438 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.39531 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 36 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 1109 time to create 1 rle with old method : 0.001407623291015625 length of segment : 41 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 602 time to create 1 rle with old method : 0.0008103847503662109 length of segment : 27 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1636 time to create 1 rle with old method : 0.002073049545288086 length of segment : 66 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006258487701416016 length of segment : 22 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.00041174888610839844 length of segment : 20 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0004000663757324219 length of segment : 19 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 421 time to create 1 rle with old method : 0.0006344318389892578 length of segment : 20 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004668235778808594 length of segment : 35 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.000354766845703125 length of segment : 20 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 664 time to create 1 rle with old method : 0.0008990764617919922 length of segment : 32 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1124 time to create 1 rle with old method : 0.0014100074768066406 length of segment : 57 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0010263919830322266 length of segment : 20 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 924 time to create 1 rle with old method : 0.001222848892211914 length of segment : 41 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003840923309326172 length of segment : 15 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.00029730796813964844 length of segment : 14 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.001161813735961914 length of segment : 40 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1697 time to create 1 rle with old method : 0.0021200180053710938 length of segment : 37 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004241466522216797 length of segment : 30 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00030684471130371094 length of segment : 20 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 759 time to create 1 rle with old method : 0.0010347366333007812 length of segment : 29 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002880096435546875 length of segment : 12 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.000156402587890625 length of segment : 8 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.00021409988403320312 length of segment : 21 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0007271766662597656 length of segment : 40 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 2150 time to create 1 rle with old method : 0.002662181854248047 length of segment : 58 time for calcul the mask position with numpy : 0.00010967254638671875 nb_pixel_total : 866 time to create 1 rle with old method : 0.0011630058288574219 length of segment : 39 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.00047850608825683594 length of segment : 32 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004837512969970703 length of segment : 23 time for calcul the mask position with numpy : 0.00011205673217773438 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0018818378448486328 length of segment : 46 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002524852752685547 length of segment : 15 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 629 time to create 1 rle with old method : 0.0008242130279541016 length of segment : 37 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001316070556640625 length of segment : 19 time for calcul the mask position with numpy : 0.00010561943054199219 nb_pixel_total : 1064 time to create 1 rle with old method : 0.0013964176177978516 length of segment : 35 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.0002090930938720703 length of segment : 19 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002562999725341797 length of segment : 14 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.00046753883361816406 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.22344 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 : 0.00010991096496582031 nb_pixel_total : 654 time to create 1 rle with old method : 0.0012285709381103516 length of segment : 51 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0003066062927246094 length of segment : 17 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004496574401855469 length of segment : 15 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005984306335449219 length of segment : 27 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0007097721099853516 length of segment : 18 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0004291534423828125 length of segment : 29 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 2379 time to create 1 rle with old method : 0.0028867721557617188 length of segment : 64 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0008771419525146484 length of segment : 33 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 612 time to create 1 rle with old method : 0.0008342266082763672 length of segment : 21 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 372 time to create 1 rle with old method : 0.0005900859832763672 length of segment : 21 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00020432472229003906 length of segment : 12 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004889965057373047 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 88.00000 max: 253.00000 molded_images shape: (1, 640, 640, 3) min: -35.70000 max: 138.95937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.00047659873962402344 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.71953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0007946491241455078 length of segment : 30 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0003948211669921875 length of segment : 23 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0006897449493408203 length of segment : 30 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0008699893951416016 length of segment : 40 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0006239414215087891 length of segment : 23 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1157 time to create 1 rle with old method : 0.0015416145324707031 length of segment : 37 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.00048279762268066406 length of segment : 26 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006263256072998047 length of segment : 29 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1118 time to create 1 rle with old method : 0.0014488697052001953 length of segment : 35 Processing 1 images image shape: (400, 160, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005443096160888672 length of segment : 36 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.00018024444580078125 length of segment : 14 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 732 time to create 1 rle with old method : 0.000978708267211914 length of segment : 38 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003237724304199219 length of segment : 17 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003218650817871094 length of segment : 24 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.00019693374633789062 length of segment : 11 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002892017364501953 length of segment : 22 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00030350685119628906 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.60234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.0004220008850097656 length of segment : 30 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.00037980079650878906 length of segment : 24 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1088 time to create 1 rle with old method : 0.0014753341674804688 length of segment : 75 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 1982 time to create 1 rle with old method : 0.0024008750915527344 length of segment : 59 time for calcul the mask position with numpy : 0.00012731552124023438 nb_pixel_total : 3870 time to create 1 rle with old method : 0.0047321319580078125 length of segment : 168 time for calcul the mask position with numpy : 0.00012493133544921875 nb_pixel_total : 2584 time to create 1 rle with old method : 0.0032494068145751953 length of segment : 152 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 2917 time to create 1 rle with old method : 0.0036008358001708984 length of segment : 98 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.00041747093200683594 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: -121.66484 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005474090576171875 length of segment : 19 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.00043487548828125 length of segment : 32 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1264 time to create 1 rle with old method : 0.0016787052154541016 length of segment : 58 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00027751922607421875 length of segment : 25 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 576 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 38 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1373 time to create 1 rle with old method : 0.0018570423126220703 length of segment : 39 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1774 time to create 1 rle with old method : 0.0022802352905273438 length of segment : 49 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0007305145263671875 length of segment : 20 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00044989585876464844 length of segment : 24 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1612 time to create 1 rle with old method : 0.0020046234130859375 length of segment : 57 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1232 time to create 1 rle with old method : 0.0016145706176757812 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.38750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0009369850158691406 length of segment : 32 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.000400543212890625 length of segment : 16 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1169 time to create 1 rle with old method : 0.0014684200286865234 length of segment : 50 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 544 time to create 1 rle with old method : 0.0007882118225097656 length of segment : 32 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004832744598388672 length of segment : 33 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004811286926269531 length of segment : 25 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00030922889709472656 length of segment : 17 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.000732421875 length of segment : 23 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1373 time to create 1 rle with old method : 0.0017671585083007812 length of segment : 115 time for calcul the mask position with numpy : 0.00011277198791503906 nb_pixel_total : 513 time to create 1 rle with old method : 0.0007970333099365234 length of segment : 40 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 322 time to create 1 rle with old method : 0.0004749298095703125 length of segment : 24 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0006046295166015625 length of segment : 23 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00022935867309570312 length of segment : 14 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0006265640258789062 length of segment : 22 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.00021886825561523438 length of segment : 19 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 2136 time to create 1 rle with old method : 0.002707242965698242 length of segment : 57 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00034332275390625 length of segment : 25 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0004298686981201172 length of segment : 13 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0004611015319824219 length of segment : 27 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00029468536376953125 length of segment : 13 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.0007455348968505859 length of segment : 26 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.0002052783966064453 length of segment : 8 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 2590 time to create 1 rle with old method : 0.004672527313232422 length of segment : 57 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1707 time to create 1 rle with old method : 0.0030679702758789062 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: -102.78203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00038361549377441406 length of segment : 36 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 612 time to create 1 rle with old method : 0.0008435249328613281 length of segment : 30 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 1693 time to create 1 rle with old method : 0.0032193660736083984 length of segment : 37 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005562305450439453 length of segment : 31 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 689 time to create 1 rle with old method : 0.000896453857421875 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 105.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -18.70000 max: 136.26641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.14141 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 458 time to create 1 rle with old method : 0.0005700588226318359 length of segment : 53 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 233 time to create 1 rle with old method : 0.00034546852111816406 length of segment : 20 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 3596 time to create 1 rle with old method : 0.004533052444458008 length of segment : 100 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005557537078857422 length of segment : 39 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0008132457733154297 length of segment : 35 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1093 time to create 1 rle with old method : 0.0013985633850097656 length of segment : 39 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.0006062984466552734 length of segment : 23 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 720 time to create 1 rle with old method : 0.001432657241821289 length of segment : 32 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0007541179656982422 length of segment : 56 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0006906986236572266 length of segment : 30 time for calcul the mask position with numpy : 0.00010466575622558594 nb_pixel_total : 2728 time to create 1 rle with old method : 0.004662275314331055 length of segment : 96 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0004191398620605469 length of segment : 22 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003790855407714844 length of segment : 29 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 1426 time to create 1 rle with old method : 0.0019121170043945312 length of segment : 106 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.66250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0002551078796386719 nb_pixel_total : 19277 time to create 1 rle with old method : 0.021982669830322266 length of segment : 191 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1549 time to create 1 rle with old method : 0.0018825531005859375 length of segment : 42 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 378 time to create 1 rle with old method : 0.0005905628204345703 length of segment : 52 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.46719 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.0005340576171875 nb_pixel_total : 41241 time to create 1 rle with old method : 0.047593116760253906 length of segment : 338 time for calcul the mask position with numpy : 0.0003006458282470703 nb_pixel_total : 13025 time to create 1 rle with old method : 0.016507387161254883 length of segment : 84 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003647804260253906 length of segment : 24 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00040650367736816406 length of segment : 28 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0006990432739257812 length of segment : 21 Processing 1 images image shape: (240, 400, 3) min: 29.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.83437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.0002646446228027344 length of segment : 11 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0011105537414550781 length of segment : 37 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 462 time to create 1 rle with old method : 0.0009484291076660156 length of segment : 23 Processing 1 images image shape: (240, 400, 3) min: 106.00000 max: 223.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 111.01797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.97500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0004940032958984375 nb_pixel_total : 33550 time to create 1 rle with old method : 0.04654979705810547 length of segment : 139 Processing 1 images image shape: (240, 160, 3) min: 0.00000 max: 231.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 119.48628 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 1306 time to create 1 rle with old method : 0.0017092227935791016 length of segment : 28 Detection mask done ! Trying to reset tf kernel 2386443 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2545 tf kernel not reseted sub process len(results) : 428 len(list_Values) 428 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 428 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 : 3738 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 428 chid ids of type : 4228 Number RLEs to save : 17972 save missing photos in datou_result : time spend for datou_step_exec : 30.33672785758972 time spend to save output : 1.4520952701568604 total time spend for step 1 : 31.788823127746582 step2:brightness Wed Mar 5 00:21:00 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/1741130428_2385694_1340895795_e7fe5e9b5191fe0de5f1bf9266761516.jpg treat image : temp/1741130428_2385694_1340891294_1de2331f62277878e64cbcf485943f37.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 : 0.011915206909179688 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 : 0.01476287841796875 save missing photos in datou_result : time spend for datou_step_exec : 1.1151235103607178 time spend to save output : 0.03151559829711914 total time spend for step 2 : 1.146639108657837 step3:blur_detection Wed Mar 5 00:21:01 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1741130428_2385694_1340895795_e7fe5e9b5191fe0de5f1bf9266761516.jpg resize: (1440, 2560) 1340895795 -7.805488582752435 treat image : temp/1741130428_2385694_1340891294_1de2331f62277878e64cbcf485943f37.jpg resize: (1440, 2560) 1340891294 -7.803453604685461 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 : 0.015237808227539062 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 : 0.014047861099243164 save missing photos in datou_result : time spend for datou_step_exec : 4.294320583343506 time spend to save output : 0.034647226333618164 total time spend for step 3 : 4.328967809677124 step4:rle_unique_nms_with_priority Wed Mar 5 00:21:06 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 428 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 204 nb_hashtags : 6 time to prepare the origin masks : 1.9382827281951904 time for calcul the mask position with numpy : 0.6588211059570312 nb_pixel_total : 3400363 time to create 1 rle with new method : 0.3947432041168213 time for calcul the mask position with numpy : 0.015017509460449219 nb_pixel_total : 654 time to create 1 rle with old method : 0.0007011890411376953 time for calcul the mask position with numpy : 0.01505589485168457 nb_pixel_total : 149 time to create 1 rle with old method : 0.00023627281188964844 time for calcul the mask position with numpy : 0.014798641204833984 nb_pixel_total : 3420 time to create 1 rle with old method : 0.003901243209838867 time for calcul the mask position with numpy : 0.015098333358764648 nb_pixel_total : 2598 time to create 1 rle with old method : 0.0029458999633789062 time for calcul the mask position with numpy : 0.01509237289428711 nb_pixel_total : 567 time to create 1 rle with old method : 0.0008854866027832031 time for calcul the mask position with numpy : 0.015231609344482422 nb_pixel_total : 832 time to create 1 rle with old method : 0.001032114028930664 time for calcul the mask position with numpy : 0.015605926513671875 nb_pixel_total : 7404 time to create 1 rle with old method : 0.009331226348876953 time for calcul the mask position with numpy : 0.015331745147705078 nb_pixel_total : 7478 time to create 1 rle with old method : 0.008817672729492188 time for calcul the mask position with numpy : 0.01518869400024414 nb_pixel_total : 734 time to create 1 rle with old method : 0.0008852481842041016 time for calcul the mask position with numpy : 0.015695571899414062 nb_pixel_total : 1860 time to create 1 rle with old method : 0.0021042823791503906 time for calcul the mask position with numpy : 0.014728784561157227 nb_pixel_total : 678 time to create 1 rle with old method : 0.0007927417755126953 time for calcul the mask position with numpy : 0.015460968017578125 nb_pixel_total : 1826 time to create 1 rle with old method : 0.001991748809814453 time for calcul the mask position with numpy : 0.015007734298706055 nb_pixel_total : 1310 time to create 1 rle with old method : 0.0014889240264892578 time for calcul the mask position with numpy : 0.014739274978637695 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005648136138916016 time for calcul the mask position with numpy : 0.015008211135864258 nb_pixel_total : 153 time to create 1 rle with old method : 0.0001850128173828125 time for calcul the mask position with numpy : 0.014809846878051758 nb_pixel_total : 22 time to create 1 rle with old method : 4.291534423828125e-05 time for calcul the mask position with numpy : 0.014914751052856445 nb_pixel_total : 240 time to create 1 rle with old method : 0.0002808570861816406 time for calcul the mask position with numpy : 0.014931678771972656 nb_pixel_total : 2141 time to create 1 rle with old method : 0.002730131149291992 time for calcul the mask position with numpy : 0.015666484832763672 nb_pixel_total : 22 time to create 1 rle with old method : 7.796287536621094e-05 time for calcul the mask position with numpy : 0.01511526107788086 nb_pixel_total : 335 time to create 1 rle with old method : 0.0004265308380126953 time for calcul the mask position with numpy : 0.015310287475585938 nb_pixel_total : 1517 time to create 1 rle with old method : 0.0022449493408203125 time for calcul the mask position with numpy : 0.016797780990600586 nb_pixel_total : 33 time to create 1 rle with old method : 6.651878356933594e-05 time for calcul the mask position with numpy : 0.01490926742553711 nb_pixel_total : 9 time to create 1 rle with old method : 3.3855438232421875e-05 time for calcul the mask position with numpy : 0.015048027038574219 nb_pixel_total : 547 time to create 1 rle with old method : 0.0006289482116699219 time for calcul the mask position with numpy : 0.015127420425415039 nb_pixel_total : 4732 time to create 1 rle with old method : 0.005793333053588867 time for calcul the mask position with numpy : 0.01495218276977539 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009000301361083984 time for calcul the mask position with numpy : 0.016475915908813477 nb_pixel_total : 233 time to create 1 rle with old method : 0.0002791881561279297 time for calcul the mask position with numpy : 0.015106201171875 nb_pixel_total : 670 time to create 1 rle with old method : 0.0007936954498291016 time for calcul the mask position with numpy : 0.014716625213623047 nb_pixel_total : 551 time to create 1 rle with old method : 0.0006778240203857422 time for calcul the mask position with numpy : 0.01505589485168457 nb_pixel_total : 289 time to create 1 rle with old method : 0.00033402442932128906 time for calcul the mask position with numpy : 0.015306472778320312 nb_pixel_total : 99 time to create 1 rle with old method : 0.00018024444580078125 time for calcul the mask position with numpy : 0.017045974731445312 nb_pixel_total : 2206 time to create 1 rle with old method : 0.003156423568725586 time for calcul the mask position with numpy : 0.015348196029663086 nb_pixel_total : 1795 time to create 1 rle with old method : 0.0020380020141601562 time for calcul the mask position with numpy : 0.015159130096435547 nb_pixel_total : 925 time to create 1 rle with old method : 0.0010564327239990234 time for calcul the mask position with numpy : 0.015113353729248047 nb_pixel_total : 2609 time to create 1 rle with old method : 0.0030355453491210938 time for calcul the mask position with numpy : 0.014715433120727539 nb_pixel_total : 107 time to create 1 rle with old method : 0.00017452239990234375 time for calcul the mask position with numpy : 0.014825582504272461 nb_pixel_total : 1439 time to create 1 rle with old method : 0.001634359359741211 time for calcul the mask position with numpy : 0.015234231948852539 nb_pixel_total : 306 time to create 1 rle with old method : 0.0003807544708251953 time for calcul the mask position with numpy : 0.014988899230957031 nb_pixel_total : 1640 time to create 1 rle with old method : 0.0018835067749023438 time for calcul the mask position with numpy : 0.015048503875732422 nb_pixel_total : 313 time to create 1 rle with old method : 0.0003650188446044922 time for calcul the mask position with numpy : 0.014868497848510742 nb_pixel_total : 1795 time to create 1 rle with old method : 0.0020189285278320312 time for calcul the mask position with numpy : 0.015276908874511719 nb_pixel_total : 13 time to create 1 rle with old method : 0.000110626220703125 time for calcul the mask position with numpy : 0.014869451522827148 nb_pixel_total : 2390 time to create 1 rle with old method : 0.002753019332885742 time for calcul the mask position with numpy : 0.0159761905670166 nb_pixel_total : 13 time to create 1 rle with old method : 6.461143493652344e-05 time for calcul the mask position with numpy : 0.015047788619995117 nb_pixel_total : 530 time to create 1 rle with old method : 0.0006597042083740234 time for calcul the mask position with numpy : 0.01527857780456543 nb_pixel_total : 325 time to create 1 rle with old method : 0.0004863739013671875 time for calcul the mask position with numpy : 0.015135049819946289 nb_pixel_total : 191 time to create 1 rle with old method : 0.00023102760314941406 time for calcul the mask position with numpy : 0.01543736457824707 nb_pixel_total : 4495 time to create 1 rle with old method : 0.005120754241943359 time for calcul the mask position with numpy : 0.01491093635559082 nb_pixel_total : 827 time to create 1 rle with old method : 0.0009753704071044922 time for calcul the mask position with numpy : 0.016379594802856445 nb_pixel_total : 637 time to create 1 rle with old method : 0.0007719993591308594 time for calcul the mask position with numpy : 0.015098810195922852 nb_pixel_total : 986 time to create 1 rle with old method : 0.0011370182037353516 time for calcul the mask position with numpy : 0.014849662780761719 nb_pixel_total : 1057 time to create 1 rle with old method : 0.0012531280517578125 time for calcul the mask position with numpy : 0.015015125274658203 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003364086151123047 time for calcul the mask position with numpy : 0.014990091323852539 nb_pixel_total : 287 time to create 1 rle with old method : 0.0003459453582763672 time for calcul the mask position with numpy : 0.014978885650634766 nb_pixel_total : 801 time to create 1 rle with old method : 0.0009274482727050781 time for calcul the mask position with numpy : 0.014852046966552734 nb_pixel_total : 304 time to create 1 rle with old method : 0.0003654956817626953 time for calcul the mask position with numpy : 0.01488041877746582 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005371570587158203 time for calcul the mask position with numpy : 0.014899969100952148 nb_pixel_total : 213 time to create 1 rle with old method : 0.00027108192443847656 time for calcul the mask position with numpy : 0.01495814323425293 nb_pixel_total : 2185 time to create 1 rle with old method : 0.002498149871826172 time for calcul the mask position with numpy : 0.014922142028808594 nb_pixel_total : 1762 time to create 1 rle with old method : 0.0020914077758789062 time for calcul the mask position with numpy : 0.015119314193725586 nb_pixel_total : 58 time to create 1 rle with old method : 0.0001385211944580078 time for calcul the mask position with numpy : 0.015577077865600586 nb_pixel_total : 692 time to create 1 rle with old method : 0.0008785724639892578 time for calcul the mask position with numpy : 0.017308712005615234 nb_pixel_total : 2937 time to create 1 rle with old method : 0.0035011768341064453 time for calcul the mask position with numpy : 0.015055179595947266 nb_pixel_total : 297 time to create 1 rle with old method : 0.00037479400634765625 time for calcul the mask position with numpy : 0.014941692352294922 nb_pixel_total : 18 time to create 1 rle with old method : 3.1948089599609375e-05 time for calcul the mask position with numpy : 0.015028238296508789 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003437995910644531 time for calcul the mask position with numpy : 0.015157699584960938 nb_pixel_total : 230 time to create 1 rle with old method : 0.000293731689453125 time for calcul the mask position with numpy : 0.015045881271362305 nb_pixel_total : 5 time to create 1 rle with old method : 3.790855407714844e-05 time for calcul the mask position with numpy : 0.015398740768432617 nb_pixel_total : 164 time to create 1 rle with old method : 0.00021648406982421875 time for calcul the mask position with numpy : 0.015146732330322266 nb_pixel_total : 1772 time to create 1 rle with old method : 0.0020699501037597656 time for calcul the mask position with numpy : 0.015128850936889648 nb_pixel_total : 329 time to create 1 rle with old method : 0.0004966259002685547 time for calcul the mask position with numpy : 0.01653885841369629 nb_pixel_total : 239 time to create 1 rle with old method : 0.0002982616424560547 time for calcul the mask position with numpy : 0.015128135681152344 nb_pixel_total : 765 time to create 1 rle with old method : 0.0009222030639648438 time for calcul the mask position with numpy : 0.015124082565307617 nb_pixel_total : 309 time to create 1 rle with old method : 0.00038242340087890625 time for calcul the mask position with numpy : 0.015186309814453125 nb_pixel_total : 337 time to create 1 rle with old method : 0.00041365623474121094 time for calcul the mask position with numpy : 0.01936650276184082 nb_pixel_total : 40 time to create 1 rle with old method : 0.00016999244689941406 time for calcul the mask position with numpy : 0.03107285499572754 nb_pixel_total : 688 time to create 1 rle with old method : 0.004861116409301758 time for calcul the mask position with numpy : 0.022622108459472656 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001418590545654297 time for calcul the mask position with numpy : 0.015521526336669922 nb_pixel_total : 640 time to create 1 rle with old method : 0.0007531642913818359 time for calcul the mask position with numpy : 0.015536785125732422 nb_pixel_total : 1938 time to create 1 rle with old method : 0.0029489994049072266 time for calcul the mask position with numpy : 0.017226696014404297 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001266002655029297 time for calcul the mask position with numpy : 0.015735149383544922 nb_pixel_total : 907 time to create 1 rle with old method : 0.0010495185852050781 time for calcul the mask position with numpy : 0.015653610229492188 nb_pixel_total : 226 time to create 1 rle with old method : 0.000335693359375 time for calcul the mask position with numpy : 0.01591634750366211 nb_pixel_total : 516 time to create 1 rle with old method : 0.0005803108215332031 time for calcul the mask position with numpy : 0.015211820602416992 nb_pixel_total : 113 time to create 1 rle with old method : 0.00014543533325195312 time for calcul the mask position with numpy : 0.015111684799194336 nb_pixel_total : 534 time to create 1 rle with old method : 0.0006396770477294922 time for calcul the mask position with numpy : 0.015167474746704102 nb_pixel_total : 538 time to create 1 rle with old method : 0.0006196498870849609 time for calcul the mask position with numpy : 0.015355587005615234 nb_pixel_total : 25616 time to create 1 rle with old method : 0.028705120086669922 time for calcul the mask position with numpy : 0.015489339828491211 nb_pixel_total : 796 time to create 1 rle with old method : 0.0009367465972900391 time for calcul the mask position with numpy : 0.015125513076782227 nb_pixel_total : 322 time to create 1 rle with old method : 0.0003905296325683594 time for calcul the mask position with numpy : 0.015079259872436523 nb_pixel_total : 321 time to create 1 rle with old method : 0.00037860870361328125 time for calcul the mask position with numpy : 0.01480245590209961 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004215240478515625 time for calcul the mask position with numpy : 0.015596866607666016 nb_pixel_total : 1353 time to create 1 rle with old method : 0.0015392303466796875 time for calcul the mask position with numpy : 0.015180826187133789 nb_pixel_total : 199 time to create 1 rle with old method : 0.00024890899658203125 time for calcul the mask position with numpy : 0.015149593353271484 nb_pixel_total : 1728 time to create 1 rle with old method : 0.002196073532104492 time for calcul the mask position with numpy : 0.015812397003173828 nb_pixel_total : 551 time to create 1 rle with old method : 0.000637054443359375 time for calcul the mask position with numpy : 0.016174793243408203 nb_pixel_total : 291 time to create 1 rle with old method : 0.0006732940673828125 time for calcul the mask position with numpy : 0.017462730407714844 nb_pixel_total : 50 time to create 1 rle with old method : 0.00010561943054199219 time for calcul the mask position with numpy : 0.015455007553100586 nb_pixel_total : 595 time to create 1 rle with old method : 0.0006973743438720703 time for calcul the mask position with numpy : 0.015373468399047852 nb_pixel_total : 2519 time to create 1 rle with old method : 0.0029871463775634766 time for calcul the mask position with numpy : 0.015085220336914062 nb_pixel_total : 176 time to create 1 rle with old method : 0.00021600723266601562 time for calcul the mask position with numpy : 0.015582084655761719 nb_pixel_total : 220 time to create 1 rle with old method : 0.0002772808074951172 time for calcul the mask position with numpy : 0.014973878860473633 nb_pixel_total : 655 time to create 1 rle with old method : 0.0007674694061279297 time for calcul the mask position with numpy : 0.01512455940246582 nb_pixel_total : 838 time to create 1 rle with old method : 0.0010037422180175781 time for calcul the mask position with numpy : 0.015258550643920898 nb_pixel_total : 520 time to create 1 rle with old method : 0.0006163120269775391 time for calcul the mask position with numpy : 0.014971494674682617 nb_pixel_total : 80 time to create 1 rle with old method : 0.00012445449829101562 time for calcul the mask position with numpy : 0.014976263046264648 nb_pixel_total : 514 time to create 1 rle with old method : 0.0006074905395507812 time for calcul the mask position with numpy : 0.014681339263916016 nb_pixel_total : 39 time to create 1 rle with old method : 7.486343383789062e-05 time for calcul the mask position with numpy : 0.01502084732055664 nb_pixel_total : 1202 time to create 1 rle with old method : 0.0014073848724365234 time for calcul the mask position with numpy : 0.015562772750854492 nb_pixel_total : 755 time to create 1 rle with old method : 0.0008847713470458984 time for calcul the mask position with numpy : 0.015226602554321289 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002589225769042969 time for calcul the mask position with numpy : 0.015179872512817383 nb_pixel_total : 1209 time to create 1 rle with old method : 0.0016698837280273438 time for calcul the mask position with numpy : 0.01564311981201172 nb_pixel_total : 340 time to create 1 rle with old method : 0.0003905296325683594 time for calcul the mask position with numpy : 0.015413761138916016 nb_pixel_total : 495 time to create 1 rle with old method : 0.0005707740783691406 time for calcul the mask position with numpy : 0.014876604080200195 nb_pixel_total : 1091 time to create 1 rle with old method : 0.0012652873992919922 time for calcul the mask position with numpy : 0.015144586563110352 nb_pixel_total : 2040 time to create 1 rle with old method : 0.002324819564819336 time for calcul the mask position with numpy : 0.014967679977416992 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002391338348388672 time for calcul the mask position with numpy : 0.014555692672729492 nb_pixel_total : 266 time to create 1 rle with old method : 0.0003123283386230469 time for calcul the mask position with numpy : 0.014827489852905273 nb_pixel_total : 156 time to create 1 rle with old method : 0.00025153160095214844 time for calcul the mask position with numpy : 0.014851808547973633 nb_pixel_total : 738 time to create 1 rle with old method : 0.0008451938629150391 time for calcul the mask position with numpy : 0.014702081680297852 nb_pixel_total : 2423 time to create 1 rle with old method : 0.002831697463989258 time for calcul the mask position with numpy : 0.014889240264892578 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007710456848144531 time for calcul the mask position with numpy : 0.01467132568359375 nb_pixel_total : 1744 time to create 1 rle with old method : 0.0019979476928710938 time for calcul the mask position with numpy : 0.014752864837646484 nb_pixel_total : 253 time to create 1 rle with old method : 0.00029540061950683594 time for calcul the mask position with numpy : 0.01490473747253418 nb_pixel_total : 360 time to create 1 rle with old method : 0.00046443939208984375 time for calcul the mask position with numpy : 0.014890432357788086 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001811981201171875 time for calcul the mask position with numpy : 0.014940023422241211 nb_pixel_total : 81 time to create 1 rle with old method : 0.00012135505676269531 time for calcul the mask position with numpy : 0.014773368835449219 nb_pixel_total : 288 time to create 1 rle with old method : 0.0003337860107421875 time for calcul the mask position with numpy : 0.014877080917358398 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002415180206298828 time for calcul the mask position with numpy : 0.01604747772216797 nb_pixel_total : 704 time to create 1 rle with old method : 0.0010695457458496094 time for calcul the mask position with numpy : 0.016593456268310547 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002613067626953125 time for calcul the mask position with numpy : 0.01505899429321289 nb_pixel_total : 863 time to create 1 rle with old method : 0.0009949207305908203 time for calcul the mask position with numpy : 0.01491546630859375 nb_pixel_total : 61 time to create 1 rle with old method : 8.893013000488281e-05 time for calcul the mask position with numpy : 0.014990806579589844 nb_pixel_total : 167 time to create 1 rle with old method : 0.00020170211791992188 time for calcul the mask position with numpy : 0.015031099319458008 nb_pixel_total : 858 time to create 1 rle with old method : 0.0009710788726806641 time for calcul the mask position with numpy : 0.014694452285766602 nb_pixel_total : 94 time to create 1 rle with old method : 0.00012922286987304688 time for calcul the mask position with numpy : 0.014923095703125 nb_pixel_total : 605 time to create 1 rle with old method : 0.0006990432739257812 time for calcul the mask position with numpy : 0.014828920364379883 nb_pixel_total : 94 time to create 1 rle with old method : 0.00010824203491210938 time for calcul the mask position with numpy : 0.014879465103149414 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002067089080810547 time for calcul the mask position with numpy : 0.014530658721923828 nb_pixel_total : 41 time to create 1 rle with old method : 5.555152893066406e-05 time for calcul the mask position with numpy : 0.014796972274780273 nb_pixel_total : 275 time to create 1 rle with old method : 0.0003249645233154297 time for calcul the mask position with numpy : 0.014915227890014648 nb_pixel_total : 16 time to create 1 rle with old method : 3.790855407714844e-05 time for calcul the mask position with numpy : 0.014906167984008789 nb_pixel_total : 471 time to create 1 rle with old method : 0.0005397796630859375 time for calcul the mask position with numpy : 0.014989376068115234 nb_pixel_total : 395 time to create 1 rle with old method : 0.0004553794860839844 time for calcul the mask position with numpy : 0.01496744155883789 nb_pixel_total : 1009 time to create 1 rle with old method : 0.0011904239654541016 time for calcul the mask position with numpy : 0.014753341674804688 nb_pixel_total : 172 time to create 1 rle with old method : 0.0002086162567138672 time for calcul the mask position with numpy : 0.014816761016845703 nb_pixel_total : 950 time to create 1 rle with old method : 0.0011138916015625 time for calcul the mask position with numpy : 0.014805793762207031 nb_pixel_total : 632 time to create 1 rle with old method : 0.0007162094116210938 time for calcul the mask position with numpy : 0.014925003051757812 nb_pixel_total : 407 time to create 1 rle with old method : 0.0004744529724121094 time for calcul the mask position with numpy : 0.014796257019042969 nb_pixel_total : 980 time to create 1 rle with old method : 0.001123666763305664 time for calcul the mask position with numpy : 0.014900684356689453 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002455711364746094 time for calcul the mask position with numpy : 0.01497793197631836 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003075599670410156 time for calcul the mask position with numpy : 0.014692068099975586 nb_pixel_total : 794 time to create 1 rle with old method : 0.0008919239044189453 time for calcul the mask position with numpy : 0.01495361328125 nb_pixel_total : 297 time to create 1 rle with old method : 0.0007224082946777344 time for calcul the mask position with numpy : 0.014816045761108398 nb_pixel_total : 1222 time to create 1 rle with old method : 0.001405477523803711 time for calcul the mask position with numpy : 0.014794111251831055 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007145404815673828 time for calcul the mask position with numpy : 0.01475071907043457 nb_pixel_total : 16 time to create 1 rle with old method : 3.7670135498046875e-05 time for calcul the mask position with numpy : 0.01421356201171875 nb_pixel_total : 488 time to create 1 rle with old method : 0.0005307197570800781 time for calcul the mask position with numpy : 0.0149688720703125 nb_pixel_total : 108 time to create 1 rle with old method : 0.0001456737518310547 time for calcul the mask position with numpy : 0.014881134033203125 nb_pixel_total : 562 time to create 1 rle with old method : 0.0006558895111083984 time for calcul the mask position with numpy : 0.014748096466064453 nb_pixel_total : 553 time to create 1 rle with old method : 0.0006494522094726562 time for calcul the mask position with numpy : 0.014753341674804688 nb_pixel_total : 243 time to create 1 rle with old method : 0.00028634071350097656 time for calcul the mask position with numpy : 0.014812707901000977 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003581047058105469 time for calcul the mask position with numpy : 0.01482248306274414 nb_pixel_total : 871 time to create 1 rle with old method : 0.0010061264038085938 time for calcul the mask position with numpy : 0.014937400817871094 nb_pixel_total : 144 time to create 1 rle with old method : 0.0002200603485107422 time for calcul the mask position with numpy : 0.014872550964355469 nb_pixel_total : 365 time to create 1 rle with old method : 0.0004324913024902344 time for calcul the mask position with numpy : 0.015544891357421875 nb_pixel_total : 2970 time to create 1 rle with old method : 0.0032830238342285156 time for calcul the mask position with numpy : 0.01730036735534668 nb_pixel_total : 1108 time to create 1 rle with old method : 0.002155303955078125 time for calcul the mask position with numpy : 0.018542051315307617 nb_pixel_total : 832 time to create 1 rle with old method : 0.001087188720703125 time for calcul the mask position with numpy : 0.01470041275024414 nb_pixel_total : 67 time to create 1 rle with old method : 0.00014328956604003906 time for calcul the mask position with numpy : 0.014962434768676758 nb_pixel_total : 1204 time to create 1 rle with old method : 0.001378774642944336 time for calcul the mask position with numpy : 0.014984369277954102 nb_pixel_total : 592 time to create 1 rle with old method : 0.0006692409515380859 time for calcul the mask position with numpy : 0.014889717102050781 nb_pixel_total : 1369 time to create 1 rle with old method : 0.001588582992553711 time for calcul the mask position with numpy : 0.014968633651733398 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006034374237060547 time for calcul the mask position with numpy : 0.014957904815673828 nb_pixel_total : 985 time to create 1 rle with old method : 0.0011830329895019531 time for calcul the mask position with numpy : 0.015044927597045898 nb_pixel_total : 505 time to create 1 rle with old method : 0.0005872249603271484 time for calcul the mask position with numpy : 0.014594554901123047 nb_pixel_total : 105 time to create 1 rle with old method : 0.00016236305236816406 time for calcul the mask position with numpy : 0.01474905014038086 nb_pixel_total : 1317 time to create 1 rle with old method : 0.0015056133270263672 time for calcul the mask position with numpy : 0.014928102493286133 nb_pixel_total : 700 time to create 1 rle with old method : 0.0008101463317871094 time for calcul the mask position with numpy : 0.015195846557617188 nb_pixel_total : 573 time to create 1 rle with old method : 0.000705718994140625 time for calcul the mask position with numpy : 0.015196800231933594 nb_pixel_total : 142 time to create 1 rle with old method : 0.00019407272338867188 time for calcul the mask position with numpy : 0.015901803970336914 nb_pixel_total : 573 time to create 1 rle with old method : 0.0010595321655273438 time for calcul the mask position with numpy : 0.01560831069946289 nb_pixel_total : 125 time to create 1 rle with old method : 0.00018835067749023438 time for calcul the mask position with numpy : 0.01561427116394043 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007226467132568359 time for calcul the mask position with numpy : 0.01525568962097168 nb_pixel_total : 711 time to create 1 rle with old method : 0.0008356571197509766 time for calcul the mask position with numpy : 0.015027284622192383 nb_pixel_total : 596 time to create 1 rle with old method : 0.0007016658782958984 time for calcul the mask position with numpy : 0.014837503433227539 nb_pixel_total : 2112 time to create 1 rle with old method : 0.0024366378784179688 time for calcul the mask position with numpy : 0.015154838562011719 nb_pixel_total : 461 time to create 1 rle with old method : 0.0005469322204589844 time for calcul the mask position with numpy : 0.015538454055786133 nb_pixel_total : 602 time to create 1 rle with old method : 0.0007402896881103516 time for calcul the mask position with numpy : 0.015062570571899414 nb_pixel_total : 990 time to create 1 rle with old method : 0.0010828971862792969 time for calcul the mask position with numpy : 0.015501737594604492 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003261566162109375 time for calcul the mask position with numpy : 0.018293142318725586 nb_pixel_total : 389 time to create 1 rle with old method : 0.0006287097930908203 time for calcul the mask position with numpy : 0.015201807022094727 nb_pixel_total : 214 time to create 1 rle with old method : 0.0002932548522949219 time for calcul the mask position with numpy : 0.01802849769592285 nb_pixel_total : 24537 time to create 1 rle with old method : 0.02727198600769043 time for calcul the mask position with numpy : 0.01638007164001465 nb_pixel_total : 48085 time to create 1 rle with old method : 0.0559086799621582 time for calcul the mask position with numpy : 0.015524864196777344 nb_pixel_total : 194 time to create 1 rle with old method : 0.00026035308837890625 time for calcul the mask position with numpy : 0.016280174255371094 nb_pixel_total : 9 time to create 1 rle with old method : 3.24249267578125e-05 time for calcul the mask position with numpy : 0.015156269073486328 nb_pixel_total : 60 time to create 1 rle with old method : 0.00010728836059570312 time for calcul the mask position with numpy : 0.015603303909301758 nb_pixel_total : 445 time to create 1 rle with old method : 0.0005137920379638672 time for calcul the mask position with numpy : 0.0159757137298584 nb_pixel_total : 1414 time to create 1 rle with old method : 0.0016281604766845703 time for calcul the mask position with numpy : 0.01561427116394043 nb_pixel_total : 155 time to create 1 rle with old method : 0.00020766258239746094 time for calcul the mask position with numpy : 0.015279054641723633 nb_pixel_total : 22379 time to create 1 rle with old method : 0.025327444076538086 time for calcul the mask position with numpy : 0.015806913375854492 nb_pixel_total : 153 time to create 1 rle with old method : 0.0003917217254638672 time for calcul the mask position with numpy : 0.015358924865722656 nb_pixel_total : 11383 time to create 1 rle with old method : 0.012923240661621094 create new chi : 4.558318138122559 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 : 0.011488676071166992 batch 1 Loaded 205 chid ids of type : 4230 Number RLEs to save : 16903 TO DO : save crop sub photo not yet done ! save time : 1.049682378768921 nb_obj : 223 nb_hashtags : 6 time to prepare the origin masks : 6.216341972351074 time for calcul the mask position with numpy : 0.369065523147583 nb_pixel_total : 3397932 time to create 1 rle with new method : 0.31697678565979004 time for calcul the mask position with numpy : 0.019768238067626953 nb_pixel_total : 3520 time to create 1 rle with old method : 0.004110097885131836 time for calcul the mask position with numpy : 0.04553866386413574 nb_pixel_total : 359 time to create 1 rle with old method : 0.00044083595275878906 time for calcul the mask position with numpy : 0.016903162002563477 nb_pixel_total : 729 time to create 1 rle with old method : 0.0008578300476074219 time for calcul the mask position with numpy : 0.016671180725097656 nb_pixel_total : 48 time to create 1 rle with old method : 0.00011968612670898438 time for calcul the mask position with numpy : 0.011828899383544922 nb_pixel_total : 2480 time to create 1 rle with old method : 0.002857208251953125 time for calcul the mask position with numpy : 0.02762150764465332 nb_pixel_total : 100 time to create 1 rle with old method : 0.00024271011352539062 time for calcul the mask position with numpy : 0.04591488838195801 nb_pixel_total : 3259 time to create 1 rle with old method : 0.0046083927154541016 time for calcul the mask position with numpy : 0.03844738006591797 nb_pixel_total : 163 time to create 1 rle with old method : 0.00020933151245117188 time for calcul the mask position with numpy : 0.01208639144897461 nb_pixel_total : 18 time to create 1 rle with old method : 3.8623809814453125e-05 time for calcul the mask position with numpy : 0.011375188827514648 nb_pixel_total : 1487 time to create 1 rle with old method : 0.0017590522766113281 time for calcul the mask position with numpy : 0.011442422866821289 nb_pixel_total : 233 time to create 1 rle with old method : 0.00026035308837890625 time for calcul the mask position with numpy : 0.011299610137939453 nb_pixel_total : 257 time to create 1 rle with old method : 0.00028634071350097656 time for calcul the mask position with numpy : 0.011180877685546875 nb_pixel_total : 3021 time to create 1 rle with old method : 0.003173828125 time for calcul the mask position with numpy : 0.011594295501708984 nb_pixel_total : 391 time to create 1 rle with old method : 0.0004608631134033203 time for calcul the mask position with numpy : 0.017941951751708984 nb_pixel_total : 1385 time to create 1 rle with old method : 0.0016589164733886719 time for calcul the mask position with numpy : 0.03877091407775879 nb_pixel_total : 1770 time to create 1 rle with old method : 0.0030303001403808594 time for calcul the mask position with numpy : 0.044657230377197266 nb_pixel_total : 1071 time to create 1 rle with old method : 0.0013234615325927734 time for calcul the mask position with numpy : 0.019067764282226562 nb_pixel_total : 780 time to create 1 rle with old method : 0.0010251998901367188 time for calcul the mask position with numpy : 0.019931793212890625 nb_pixel_total : 2413 time to create 1 rle with old method : 0.003551959991455078 time for calcul the mask position with numpy : 0.02462911605834961 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0016543865203857422 time for calcul the mask position with numpy : 0.015265464782714844 nb_pixel_total : 53 time to create 1 rle with old method : 0.00013446807861328125 time for calcul the mask position with numpy : 0.029599905014038086 nb_pixel_total : 1177 time to create 1 rle with old method : 0.0015931129455566406 time for calcul the mask position with numpy : 0.031159400939941406 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003814697265625 time for calcul the mask position with numpy : 0.024027347564697266 nb_pixel_total : 140 time to create 1 rle with old method : 0.000213623046875 time for calcul the mask position with numpy : 0.039037227630615234 nb_pixel_total : 723 time to create 1 rle with old method : 0.0010571479797363281 time for calcul the mask position with numpy : 0.03698921203613281 nb_pixel_total : 926 time to create 1 rle with old method : 0.0011854171752929688 time for calcul the mask position with numpy : 0.022780895233154297 nb_pixel_total : 2154 time to create 1 rle with old method : 0.003178834915161133 time for calcul the mask position with numpy : 0.022323131561279297 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003809928894042969 time for calcul the mask position with numpy : 0.02532029151916504 nb_pixel_total : 766 time to create 1 rle with old method : 0.0011632442474365234 time for calcul the mask position with numpy : 0.027646541595458984 nb_pixel_total : 5064 time to create 1 rle with old method : 0.010318279266357422 time for calcul the mask position with numpy : 0.02641129493713379 nb_pixel_total : 36 time to create 1 rle with old method : 0.00010728836059570312 time for calcul the mask position with numpy : 0.025293588638305664 nb_pixel_total : 7084 time to create 1 rle with old method : 0.008134841918945312 time for calcul the mask position with numpy : 0.0175321102142334 nb_pixel_total : 78 time to create 1 rle with old method : 0.00016570091247558594 time for calcul the mask position with numpy : 0.01776719093322754 nb_pixel_total : 193 time to create 1 rle with old method : 0.00023889541625976562 time for calcul the mask position with numpy : 0.017886638641357422 nb_pixel_total : 1862 time to create 1 rle with old method : 0.0021152496337890625 time for calcul the mask position with numpy : 0.018224477767944336 nb_pixel_total : 712 time to create 1 rle with old method : 0.001220703125 time for calcul the mask position with numpy : 0.01833820343017578 nb_pixel_total : 346 time to create 1 rle with old method : 0.00040602684020996094 time for calcul the mask position with numpy : 0.019225597381591797 nb_pixel_total : 9510 time to create 1 rle with old method : 0.01081395149230957 time for calcul the mask position with numpy : 0.018482446670532227 nb_pixel_total : 1745 time to create 1 rle with old method : 0.002032041549682617 time for calcul the mask position with numpy : 0.01857781410217285 nb_pixel_total : 156 time to create 1 rle with old method : 0.000202178955078125 time for calcul the mask position with numpy : 0.023332595825195312 nb_pixel_total : 693 time to create 1 rle with old method : 0.0008053779602050781 time for calcul the mask position with numpy : 0.02198505401611328 nb_pixel_total : 1623 time to create 1 rle with old method : 0.0018625259399414062 time for calcul the mask position with numpy : 0.017679214477539062 nb_pixel_total : 580 time to create 1 rle with old method : 0.0006396770477294922 time for calcul the mask position with numpy : 0.037726640701293945 nb_pixel_total : 80 time to create 1 rle with old method : 0.00011897087097167969 time for calcul the mask position with numpy : 0.02157735824584961 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003783702850341797 time for calcul the mask position with numpy : 0.024466991424560547 nb_pixel_total : 1825 time to create 1 rle with old method : 0.0021207332611083984 time for calcul the mask position with numpy : 0.018689632415771484 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0014264583587646484 time for calcul the mask position with numpy : 0.01918196678161621 nb_pixel_total : 625 time to create 1 rle with old method : 0.0007302761077880859 time for calcul the mask position with numpy : 0.015175342559814453 nb_pixel_total : 45 time to create 1 rle with old method : 0.00011038780212402344 time for calcul the mask position with numpy : 0.014266014099121094 nb_pixel_total : 383 time to create 1 rle with old method : 0.00047969818115234375 time for calcul the mask position with numpy : 0.016455650329589844 nb_pixel_total : 179 time to create 1 rle with old method : 0.009101390838623047 time for calcul the mask position with numpy : 0.015781879425048828 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005974769592285156 time for calcul the mask position with numpy : 0.014885663986206055 nb_pixel_total : 1854 time to create 1 rle with old method : 0.002148866653442383 time for calcul the mask position with numpy : 0.011826038360595703 nb_pixel_total : 762 time to create 1 rle with old method : 0.0008981227874755859 time for calcul the mask position with numpy : 0.011455059051513672 nb_pixel_total : 223 time to create 1 rle with old method : 0.00025844573974609375 time for calcul the mask position with numpy : 0.010951042175292969 nb_pixel_total : 2046 time to create 1 rle with old method : 0.002349853515625 time for calcul the mask position with numpy : 0.011279821395874023 nb_pixel_total : 768 time to create 1 rle with old method : 0.0009133815765380859 time for calcul the mask position with numpy : 0.01094198226928711 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003440380096435547 time for calcul the mask position with numpy : 0.01052999496459961 nb_pixel_total : 326 time to create 1 rle with old method : 0.0004303455352783203 time for calcul the mask position with numpy : 0.010860204696655273 nb_pixel_total : 597 time to create 1 rle with old method : 0.0007369518280029297 time for calcul the mask position with numpy : 0.011218547821044922 nb_pixel_total : 115 time to create 1 rle with old method : 0.00016570091247558594 time for calcul the mask position with numpy : 0.014350175857543945 nb_pixel_total : 293 time to create 1 rle with old method : 0.0003571510314941406 time for calcul the mask position with numpy : 0.010837554931640625 nb_pixel_total : 244 time to create 1 rle with old method : 0.000278472900390625 time for calcul the mask position with numpy : 0.010761022567749023 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005216598510742188 time for calcul the mask position with numpy : 0.011427640914916992 nb_pixel_total : 701 time to create 1 rle with old method : 0.0008280277252197266 time for calcul the mask position with numpy : 0.01122283935546875 nb_pixel_total : 1697 time to create 1 rle with old method : 0.0019447803497314453 time for calcul the mask position with numpy : 0.012448787689208984 nb_pixel_total : 26 time to create 1 rle with old method : 7.152557373046875e-05 time for calcul the mask position with numpy : 0.012896299362182617 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001881122589111328 time for calcul the mask position with numpy : 0.011134147644042969 nb_pixel_total : 2490 time to create 1 rle with old method : 0.002614736557006836 time for calcul the mask position with numpy : 0.010897636413574219 nb_pixel_total : 3369 time to create 1 rle with old method : 0.0038270950317382812 time for calcul the mask position with numpy : 0.010758638381958008 nb_pixel_total : 241 time to create 1 rle with old method : 0.00029349327087402344 time for calcul the mask position with numpy : 0.010943889617919922 nb_pixel_total : 1157 time to create 1 rle with old method : 0.0013256072998046875 time for calcul the mask position with numpy : 0.01097869873046875 nb_pixel_total : 2372 time to create 1 rle with old method : 0.0026748180389404297 time for calcul the mask position with numpy : 0.011033296585083008 nb_pixel_total : 292 time to create 1 rle with old method : 0.0003502368927001953 time for calcul the mask position with numpy : 0.011233329772949219 nb_pixel_total : 1636 time to create 1 rle with old method : 0.0021581649780273438 time for calcul the mask position with numpy : 0.011317968368530273 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002799034118652344 time for calcul the mask position with numpy : 0.0103912353515625 nb_pixel_total : 7 time to create 1 rle with old method : 3.910064697265625e-05 time for calcul the mask position with numpy : 0.010715007781982422 nb_pixel_total : 180 time to create 1 rle with old method : 0.0002391338348388672 time for calcul the mask position with numpy : 0.011496782302856445 nb_pixel_total : 334 time to create 1 rle with old method : 0.0003857612609863281 time for calcul the mask position with numpy : 0.01123666763305664 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003349781036376953 time for calcul the mask position with numpy : 0.011142730712890625 nb_pixel_total : 106 time to create 1 rle with old method : 0.0001533031463623047 time for calcul the mask position with numpy : 0.011418342590332031 nb_pixel_total : 714 time to create 1 rle with old method : 0.0009989738464355469 time for calcul the mask position with numpy : 0.015262126922607422 nb_pixel_total : 87 time to create 1 rle with old method : 0.00014901161193847656 time for calcul the mask position with numpy : 0.011601686477661133 nb_pixel_total : 392 time to create 1 rle with old method : 0.0004980564117431641 time for calcul the mask position with numpy : 0.010964393615722656 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001494884490966797 time for calcul the mask position with numpy : 0.011269569396972656 nb_pixel_total : 308 time to create 1 rle with old method : 0.0004017353057861328 time for calcul the mask position with numpy : 0.01144719123840332 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002739429473876953 time for calcul the mask position with numpy : 0.010908365249633789 nb_pixel_total : 171 time to create 1 rle with old method : 0.00021958351135253906 time for calcul the mask position with numpy : 0.011173248291015625 nb_pixel_total : 924 time to create 1 rle with old method : 0.0010380744934082031 time for calcul the mask position with numpy : 0.010790109634399414 nb_pixel_total : 249 time to create 1 rle with old method : 0.000308990478515625 time for calcul the mask position with numpy : 0.011175394058227539 nb_pixel_total : 118 time to create 1 rle with old method : 0.00015354156494140625 time for calcul the mask position with numpy : 0.010961532592773438 nb_pixel_total : 348 time to create 1 rle with old method : 0.0003952980041503906 time for calcul the mask position with numpy : 0.011034965515136719 nb_pixel_total : 178 time to create 1 rle with old method : 0.00023102760314941406 time for calcul the mask position with numpy : 0.011003732681274414 nb_pixel_total : 400 time to create 1 rle with old method : 0.0004858970642089844 time for calcul the mask position with numpy : 0.01245880126953125 nb_pixel_total : 554 time to create 1 rle with old method : 0.0006864070892333984 time for calcul the mask position with numpy : 0.01091766357421875 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002694129943847656 time for calcul the mask position with numpy : 0.01236104965209961 nb_pixel_total : 824 time to create 1 rle with old method : 0.0009622573852539062 time for calcul the mask position with numpy : 0.010893821716308594 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004165172576904297 time for calcul the mask position with numpy : 0.010841846466064453 nb_pixel_total : 319 time to create 1 rle with old method : 0.0003840923309326172 time for calcul the mask position with numpy : 0.010843753814697266 nb_pixel_total : 193 time to create 1 rle with old method : 0.00024318695068359375 time for calcul the mask position with numpy : 0.010975837707519531 nb_pixel_total : 1064 time to create 1 rle with old method : 0.0011820793151855469 time for calcul the mask position with numpy : 0.011161327362060547 nb_pixel_total : 88 time to create 1 rle with old method : 0.00011992454528808594 time for calcul the mask position with numpy : 0.011038064956665039 nb_pixel_total : 7 time to create 1 rle with old method : 3.504753112792969e-05 time for calcul the mask position with numpy : 0.010724782943725586 nb_pixel_total : 442 time to create 1 rle with old method : 0.0005381107330322266 time for calcul the mask position with numpy : 0.010985374450683594 nb_pixel_total : 153 time to create 1 rle with old method : 0.00019550323486328125 time for calcul the mask position with numpy : 0.011133193969726562 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004241466522216797 time for calcul the mask position with numpy : 0.011020183563232422 nb_pixel_total : 331 time to create 1 rle with old method : 0.0003998279571533203 time for calcul the mask position with numpy : 0.011456489562988281 nb_pixel_total : 732 time to create 1 rle with old method : 0.0008556842803955078 time for calcul the mask position with numpy : 0.011571884155273438 nb_pixel_total : 867 time to create 1 rle with old method : 0.0010180473327636719 time for calcul the mask position with numpy : 0.01155710220336914 nb_pixel_total : 334 time to create 1 rle with old method : 0.00040435791015625 time for calcul the mask position with numpy : 0.011439800262451172 nb_pixel_total : 602 time to create 1 rle with old method : 0.0007262229919433594 time for calcul the mask position with numpy : 0.011311531066894531 nb_pixel_total : 441 time to create 1 rle with old method : 0.0005240440368652344 time for calcul the mask position with numpy : 0.011523246765136719 nb_pixel_total : 428 time to create 1 rle with old method : 0.0005123615264892578 time for calcul the mask position with numpy : 0.011519193649291992 nb_pixel_total : 489 time to create 1 rle with old method : 0.0005769729614257812 time for calcul the mask position with numpy : 0.011864185333251953 nb_pixel_total : 2473 time to create 1 rle with old method : 0.0028543472290039062 time for calcul the mask position with numpy : 0.010999679565429688 nb_pixel_total : 191 time to create 1 rle with old method : 0.0002446174621582031 time for calcul the mask position with numpy : 0.011467456817626953 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.010792255401611328 nb_pixel_total : 664 time to create 1 rle with old method : 0.0007789134979248047 time for calcul the mask position with numpy : 0.01083230972290039 nb_pixel_total : 759 time to create 1 rle with old method : 0.0009081363677978516 time for calcul the mask position with numpy : 0.01097869873046875 nb_pixel_total : 421 time to create 1 rle with old method : 0.000514984130859375 time for calcul the mask position with numpy : 0.011362075805664062 nb_pixel_total : 483 time to create 1 rle with old method : 0.0005974769592285156 time for calcul the mask position with numpy : 0.010852336883544922 nb_pixel_total : 612 time to create 1 rle with old method : 0.0007128715515136719 time for calcul the mask position with numpy : 0.011040210723876953 nb_pixel_total : 3760 time to create 1 rle with old method : 0.0043163299560546875 time for calcul the mask position with numpy : 0.011013031005859375 nb_pixel_total : 337 time to create 1 rle with old method : 0.000396728515625 time for calcul the mask position with numpy : 0.010880231857299805 nb_pixel_total : 645 time to create 1 rle with old method : 0.0007708072662353516 time for calcul the mask position with numpy : 0.010815143585205078 nb_pixel_total : 242 time to create 1 rle with old method : 0.000293731689453125 time for calcul the mask position with numpy : 0.011143684387207031 nb_pixel_total : 1109 time to create 1 rle with old method : 0.0012645721435546875 time for calcul the mask position with numpy : 0.010825872421264648 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006487369537353516 time for calcul the mask position with numpy : 0.010833263397216797 nb_pixel_total : 372 time to create 1 rle with old method : 0.000446319580078125 time for calcul the mask position with numpy : 0.01074671745300293 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003638267517089844 time for calcul the mask position with numpy : 0.01061701774597168 nb_pixel_total : 866 time to create 1 rle with old method : 0.0010106563568115234 time for calcul the mask position with numpy : 0.01066446304321289 nb_pixel_total : 296 time to create 1 rle with old method : 0.0003521442413330078 time for calcul the mask position with numpy : 0.011016607284545898 nb_pixel_total : 1121 time to create 1 rle with old method : 0.0012927055358886719 time for calcul the mask position with numpy : 0.01126861572265625 nb_pixel_total : 309 time to create 1 rle with old method : 0.0003752708435058594 time for calcul the mask position with numpy : 0.011420249938964844 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004184246063232422 time for calcul the mask position with numpy : 0.011219263076782227 nb_pixel_total : 629 time to create 1 rle with old method : 0.0007402896881103516 time for calcul the mask position with numpy : 0.011294841766357422 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0014553070068359375 time for calcul the mask position with numpy : 0.011456966400146484 nb_pixel_total : 270 time to create 1 rle with old method : 0.00033664703369140625 time for calcul the mask position with numpy : 0.011400938034057617 nb_pixel_total : 2150 time to create 1 rle with old method : 0.0024318695068359375 time for calcul the mask position with numpy : 0.011635541915893555 nb_pixel_total : 2379 time to create 1 rle with old method : 0.0028710365295410156 time for calcul the mask position with numpy : 0.011976957321166992 nb_pixel_total : 710 time to create 1 rle with old method : 0.0008375644683837891 time for calcul the mask position with numpy : 0.011635303497314453 nb_pixel_total : 654 time to create 1 rle with old method : 0.0007770061492919922 time for calcul the mask position with numpy : 0.011804819107055664 nb_pixel_total : 171 time to create 1 rle with old method : 0.00022363662719726562 time for calcul the mask position with numpy : 0.011611461639404297 nb_pixel_total : 639 time to create 1 rle with old method : 0.0007457733154296875 time for calcul the mask position with numpy : 0.012037277221679688 nb_pixel_total : 331 time to create 1 rle with old method : 0.00040149688720703125 time for calcul the mask position with numpy : 0.011436700820922852 nb_pixel_total : 907 time to create 1 rle with old method : 0.0010478496551513672 time for calcul the mask position with numpy : 0.011555194854736328 nb_pixel_total : 1722 time to create 1 rle with old method : 0.001977682113647461 time for calcul the mask position with numpy : 0.010962486267089844 nb_pixel_total : 310 time to create 1 rle with old method : 0.0003848075866699219 time for calcul the mask position with numpy : 0.014859676361083984 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003371238708496094 time for calcul the mask position with numpy : 0.011910438537597656 nb_pixel_total : 115 time to create 1 rle with old method : 0.00023317337036132812 time for calcul the mask position with numpy : 0.012048006057739258 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003705024719238281 time for calcul the mask position with numpy : 0.012509822845458984 nb_pixel_total : 1373 time to create 1 rle with old method : 0.0022940635681152344 time for calcul the mask position with numpy : 0.01279902458190918 nb_pixel_total : 2590 time to create 1 rle with old method : 0.0042133331298828125 time for calcul the mask position with numpy : 0.013162374496459961 nb_pixel_total : 344 time to create 1 rle with old method : 0.0006062984466552734 time for calcul the mask position with numpy : 0.013074636459350586 nb_pixel_total : 1773 time to create 1 rle with old method : 0.002933025360107422 time for calcul the mask position with numpy : 0.011626720428466797 nb_pixel_total : 76 time to create 1 rle with old method : 0.00011134147644042969 time for calcul the mask position with numpy : 0.011946439743041992 nb_pixel_total : 534 time to create 1 rle with old method : 0.0006184577941894531 time for calcul the mask position with numpy : 0.011747360229492188 nb_pixel_total : 116 time to create 1 rle with old method : 0.00016117095947265625 time for calcul the mask position with numpy : 0.012254714965820312 nb_pixel_total : 1426 time to create 1 rle with old method : 0.0017037391662597656 time for calcul the mask position with numpy : 0.011426687240600586 nb_pixel_total : 1693 time to create 1 rle with old method : 0.00197601318359375 time for calcul the mask position with numpy : 0.012498140335083008 nb_pixel_total : 238 time to create 1 rle with old method : 0.0002989768981933594 time for calcul the mask position with numpy : 0.011263608932495117 nb_pixel_total : 393 time to create 1 rle with old method : 0.00046324729919433594 time for calcul the mask position with numpy : 0.011100292205810547 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003457069396972656 time for calcul the mask position with numpy : 0.011636495590209961 nb_pixel_total : 1088 time to create 1 rle with old method : 0.0012581348419189453 time for calcul the mask position with numpy : 0.011047124862670898 nb_pixel_total : 17 time to create 1 rle with old method : 5.8650970458984375e-05 time for calcul the mask position with numpy : 0.01128840446472168 nb_pixel_total : 136 time to create 1 rle with old method : 0.00018930435180664062 time for calcul the mask position with numpy : 0.010995626449584961 nb_pixel_total : 409 time to create 1 rle with old method : 0.00048542022705078125 time for calcul the mask position with numpy : 0.010857820510864258 nb_pixel_total : 371 time to create 1 rle with old method : 0.00044536590576171875 time for calcul the mask position with numpy : 0.013367176055908203 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003979206085205078 time for calcul the mask position with numpy : 0.010892152786254883 nb_pixel_total : 332 time to create 1 rle with old method : 0.00040030479431152344 time for calcul the mask position with numpy : 0.010770797729492188 nb_pixel_total : 268 time to create 1 rle with old method : 0.00033736228942871094 time for calcul the mask position with numpy : 0.010977983474731445 nb_pixel_total : 708 time to create 1 rle with old method : 0.0008194446563720703 time for calcul the mask position with numpy : 0.011541604995727539 nb_pixel_total : 513 time to create 1 rle with old method : 0.0005888938903808594 time for calcul the mask position with numpy : 0.010923147201538086 nb_pixel_total : 322 time to create 1 rle with old method : 0.00039577484130859375 time for calcul the mask position with numpy : 0.010672807693481445 nb_pixel_total : 61 time to create 1 rle with old method : 0.0001404285430908203 time for calcul the mask position with numpy : 0.010845422744750977 nb_pixel_total : 3870 time to create 1 rle with old method : 0.004405498504638672 time for calcul the mask position with numpy : 0.01143956184387207 nb_pixel_total : 264 time to create 1 rle with old method : 0.0003514289855957031 time for calcul the mask position with numpy : 0.011374950408935547 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003077983856201172 time for calcul the mask position with numpy : 0.01137399673461914 nb_pixel_total : 1264 time to create 1 rle with old method : 0.0014758110046386719 time for calcul the mask position with numpy : 0.012042522430419922 nb_pixel_total : 458 time to create 1 rle with old method : 0.0005357265472412109 time for calcul the mask position with numpy : 0.011658430099487305 nb_pixel_total : 20 time to create 1 rle with old method : 8.153915405273438e-05 time for calcul the mask position with numpy : 0.011310815811157227 nb_pixel_total : 612 time to create 1 rle with old method : 0.0007157325744628906 time for calcul the mask position with numpy : 0.01114201545715332 nb_pixel_total : 3596 time to create 1 rle with old method : 0.004064321517944336 time for calcul the mask position with numpy : 0.011308908462524414 nb_pixel_total : 1612 time to create 1 rle with old method : 0.0018601417541503906 time for calcul the mask position with numpy : 0.011204004287719727 nb_pixel_total : 1373 time to create 1 rle with old method : 0.0016491413116455078 time for calcul the mask position with numpy : 0.011333465576171875 nb_pixel_total : 363 time to create 1 rle with old method : 0.0004630088806152344 time for calcul the mask position with numpy : 0.011291265487670898 nb_pixel_total : 2136 time to create 1 rle with old method : 0.0024328231811523438 time for calcul the mask position with numpy : 0.01130986213684082 nb_pixel_total : 382 time to create 1 rle with old method : 0.0004553794860839844 time for calcul the mask position with numpy : 0.011194944381713867 nb_pixel_total : 233 time to create 1 rle with old method : 0.0002923011779785156 time for calcul the mask position with numpy : 0.011330604553222656 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002422332763671875 time for calcul the mask position with numpy : 0.010846376419067383 nb_pixel_total : 544 time to create 1 rle with old method : 0.0006318092346191406 time for calcul the mask position with numpy : 0.011564016342163086 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001430511474609375 time for calcul the mask position with numpy : 0.010992050170898438 nb_pixel_total : 2728 time to create 1 rle with old method : 0.003058195114135742 time for calcul the mask position with numpy : 0.010714292526245117 nb_pixel_total : 138 time to create 1 rle with old method : 0.0001659393310546875 time for calcul the mask position with numpy : 0.010784626007080078 nb_pixel_total : 1093 time to create 1 rle with old method : 0.0011713504791259766 time for calcul the mask position with numpy : 0.011380910873413086 nb_pixel_total : 576 time to create 1 rle with old method : 0.0006694793701171875 time for calcul the mask position with numpy : 0.011027812957763672 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001468658447265625 time for calcul the mask position with numpy : 0.010822534561157227 nb_pixel_total : 689 time to create 1 rle with old method : 0.0007958412170410156 time for calcul the mask position with numpy : 0.010493040084838867 nb_pixel_total : 1982 time to create 1 rle with old method : 0.0021905899047851562 time for calcul the mask position with numpy : 0.010328531265258789 nb_pixel_total : 401 time to create 1 rle with old method : 0.0004775524139404297 time for calcul the mask position with numpy : 0.011332988739013672 nb_pixel_total : 1169 time to create 1 rle with old method : 0.0013806819915771484 time for calcul the mask position with numpy : 0.01057744026184082 nb_pixel_total : 227 time to create 1 rle with old method : 0.00026869773864746094 time for calcul the mask position with numpy : 0.010528326034545898 nb_pixel_total : 328 time to create 1 rle with old method : 0.00039839744567871094 time for calcul the mask position with numpy : 0.010790824890136719 nb_pixel_total : 383 time to create 1 rle with old method : 0.0004699230194091797 time for calcul the mask position with numpy : 0.01475381851196289 nb_pixel_total : 285 time to create 1 rle with old method : 0.0003440380096435547 time for calcul the mask position with numpy : 0.015076637268066406 nb_pixel_total : 301 time to create 1 rle with old method : 0.0003535747528076172 time for calcul the mask position with numpy : 0.015146255493164062 nb_pixel_total : 1707 time to create 1 rle with old method : 0.001943349838256836 time for calcul the mask position with numpy : 0.014958381652832031 nb_pixel_total : 598 time to create 1 rle with old method : 0.0006957054138183594 time for calcul the mask position with numpy : 0.014959096908569336 nb_pixel_total : 316 time to create 1 rle with old method : 0.0003714561462402344 time for calcul the mask position with numpy : 0.015074014663696289 nb_pixel_total : 720 time to create 1 rle with old method : 0.0008399486541748047 time for calcul the mask position with numpy : 0.015330791473388672 nb_pixel_total : 19277 time to create 1 rle with old method : 0.021215438842773438 time for calcul the mask position with numpy : 0.016010046005249023 nb_pixel_total : 41241 time to create 1 rle with old method : 0.045107126235961914 time for calcul the mask position with numpy : 0.014659404754638672 nb_pixel_total : 274 time to create 1 rle with old method : 0.00034689903259277344 time for calcul the mask position with numpy : 0.014968633651733398 nb_pixel_total : 1170 time to create 1 rle with old method : 0.0013206005096435547 time for calcul the mask position with numpy : 0.015218973159790039 nb_pixel_total : 357 time to create 1 rle with old method : 0.0007920265197753906 time for calcul the mask position with numpy : 0.01579594612121582 nb_pixel_total : 220 time to create 1 rle with old method : 0.000263214111328125 time for calcul the mask position with numpy : 0.016469955444335938 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001780986785888672 time for calcul the mask position with numpy : 0.0172271728515625 nb_pixel_total : 591 time to create 1 rle with old method : 0.0009765625 time for calcul the mask position with numpy : 0.017332792282104492 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003211498260498047 time for calcul the mask position with numpy : 0.01733088493347168 nb_pixel_total : 33550 time to create 1 rle with old method : 0.04300522804260254 time for calcul the mask position with numpy : 0.015044450759887695 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005474090576171875 time for calcul the mask position with numpy : 0.015101909637451172 nb_pixel_total : 12833 time to create 1 rle with old method : 0.014404296875 time for calcul the mask position with numpy : 0.014899253845214844 nb_pixel_total : 1306 time to create 1 rle with old method : 0.0014827251434326172 create new chi : 4.268062591552734 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 : 0.0024614334106445312 batch 1 Loaded 224 chid ids of type : 4230 Number RLEs to save : 18771 TO DO : save crop sub photo not yet done ! save time : 1.2843053340911865 map_output_result : {1340895795: (0.0, 'Should be the crop_list due to order', 0.0), 1340891294: (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 [1340895795, 1340891294] Looping around the photos to save general results len do output : 2 /1340895795.Didn't retrieve data . /1340891294.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, '2634593') ('4234', '21033063', '1340895795', None, None, None, None, None, '2634593') ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340891294', None, None, None, None, None, '2634593') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.015932083129882812 save_final save missing photos in datou_result : time spend for datou_step_exec : 20.423251390457153 time spend to save output : 0.016410350799560547 total time spend for step 4 : 20.439661741256714 step5:crop_condition Wed Mar 5 00:21:26 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 429 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 218 About to insert : list_path_to_insert length 218 new photo from crops ! About to upload 218 photos upload in portfolio : 4869462 init cache_photo without model_param we have 218 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741130493_2385694 we have uploaded 218 photos in the portfolio 4869462 time of upload the photos Elapsed time : 54.971500396728516 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 51 About to insert : list_path_to_insert length 51 new photo from crops ! About to upload 51 photos upload in portfolio : 4869462 init cache_photo without model_param we have 51 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741130549_2385694 we have uploaded 51 photos in the portfolio 4869462 time of upload the photos Elapsed time : 12.547731876373291 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 18 About to insert : list_path_to_insert length 18 new photo from crops ! About to upload 18 photos upload in portfolio : 4869462 init cache_photo without model_param we have 18 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741130562_2385694 we have uploaded 18 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.596876859664917 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 ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! About to upload 13 photos upload in portfolio : 4869462 init cache_photo without model_param we have 13 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741130567_2385694 we have uploaded 13 photos in the portfolio 4869462 time of upload the photos Elapsed time : 5.513033151626587 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 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/1741130573_2385694 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.7336878776550293 we have finished the crop for the class : pehd 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 [1340895795, 1340891294] Looping around the photos to save general results len do output : 301 /1340900997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340900998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340900999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901011Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901012Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901016Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901019Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901023Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901027Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901035Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901037Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901223Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901248Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901307Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901315Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340901339Didn'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, '2634593') ('4234', '21033063', '1340895795', None, None, None, None, None, '2634593') ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340891294', None, None, None, None, None, '2634593') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 905 time used for this insertion : 0.11644434928894043 save_final save missing photos in datou_result : time spend for datou_step_exec : 87.50374746322632 time spend to save output : 0.12412858009338379 total time spend for step 5 : 87.6278760433197 step6:thcl Wed Mar 5 00:22:54 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 : 0.01856398582458496 time to convert the images to numpy array : 0.07027769088745117 time to import caffe and check if the image exist : 0.027176618576049805 time to convert the images to numpy array : 0.07555031776428223 time to import caffe and check if the image exist : 0.022329330444335938 time to convert the images to numpy array : 0.08533000946044922 time to import caffe and check if the image exist : 0.025182723999023438 time to convert the images to numpy array : 0.08555340766906738 time to import caffe and check if the image exist : 0.0389559268951416 time to convert the images to numpy array : 0.0710906982421875 time to import caffe and check if the image exist : 0.0214536190032959 time to convert the images to numpy array : 0.08927345275878906 time to import caffe and check if the image exist : 0.025609731674194336 time to convert the images to numpy array : 0.08656668663024902 time to import caffe and check if the image exist : 0.03515934944152832 time to convert the images to numpy array : 0.08032584190368652 time to import caffe and check if the image exist : 0.01546168327331543 time to convert the images to numpy array : 0.1020960807800293 time to import caffe and check if the image exist : 0.034714698791503906 time to convert the images to numpy array : 0.08654046058654785 total time to convert the images to numpy array : 0.49639463424682617 list photo_ids error: [] list photo_ids correct : [1340901311, 1340901312, 1340901313, 1340901314, 1340901315, 1340901316, 1340901317, 1340901318, 1340901324, 1340901325, 1340901326, 1340901327, 1340901328, 1340901329, 1340901330, 1340901331, 1340901332, 1340901333, 1340901334, 1340901335, 1340901336, 1340901339, 1340901124, 1340901125, 1340901126, 1340901127, 1340901128, 1340901129, 1340901130, 1340901132, 1340901133, 1340901134, 1340901135, 1340901136, 1340901137, 1340901138, 1340901139, 1340901140, 1340901141, 1340901142, 1340901143, 1340901144, 1340901145, 1340901146, 1340901147, 1340901148, 1340901149, 1340901150, 1340901151, 1340901152, 1340901153, 1340901154, 1340901155, 1340901156, 1340901157, 1340901158, 1340901159, 1340901160, 1340901161, 1340901162, 1340901163, 1340901164, 1340901165, 1340901166, 1340901167, 1340901168, 1340901169, 1340901170, 1340901171, 1340901172, 1340901173, 1340901174, 1340901175, 1340901176, 1340901177, 1340901178, 1340901179, 1340901180, 1340901181, 1340901182, 1340901183, 1340901184, 1340901185, 1340901186, 1340901030, 1340901031, 1340901032, 1340901033, 1340901034, 1340901035, 1340901036, 1340901037, 1340901038, 1340901039, 1340901040, 1340901041, 1340901042, 1340901043, 1340901044, 1340901045, 1340901046, 1340901047, 1340901048, 1340901049, 1340901050, 1340901051, 1340901052, 1340901053, 1340901054, 1340901055, 1340901056, 1340901057, 1340901058, 1340901059, 1340901060, 1340901228, 1340901243, 1340901244, 1340901245, 1340901246, 1340901247, 1340901248, 1340901249, 1340901251, 1340901252, 1340901253, 1340901254, 1340901255, 1340901256, 1340901257, 1340901258, 1340901259, 1340901260, 1340901261, 1340901262, 1340901263, 1340901264, 1340901265, 1340901266, 1340901267, 1340901269, 1340901270, 1340901271, 1340901272, 1340901273, 1340901274, 1340901187, 1340901188, 1340901189, 1340901190, 1340901191, 1340901192, 1340901193, 1340901194, 1340901196, 1340901199, 1340901202, 1340901203, 1340901204, 1340901206, 1340901207, 1340901208, 1340901209, 1340901211, 1340901212, 1340901213, 1340901214, 1340901215, 1340901216, 1340901217, 1340901218, 1340901220, 1340901222, 1340901223, 1340901224, 1340901225, 1340901227, 1340901275, 1340901277, 1340901278, 1340901279, 1340901280, 1340901281, 1340901282, 1340901283, 1340901284, 1340901285, 1340901286, 1340901287, 1340901288, 1340901289, 1340901290, 1340901291, 1340901292, 1340901293, 1340901294, 1340901295, 1340901296, 1340901301, 1340901302, 1340901303, 1340901304, 1340901305, 1340901306, 1340901307, 1340901308, 1340901309, 1340901310, 1340901061, 1340901062, 1340901063, 1340901064, 1340901065, 1340901066, 1340901067, 1340901068, 1340901069, 1340901070, 1340901071, 1340901072, 1340901073, 1340901074, 1340901075, 1340901076, 1340901077, 1340901078, 1340901079, 1340901080, 1340901081, 1340901082, 1340901083, 1340901084, 1340901085, 1340901086, 1340901087, 1340901088, 1340901089, 1340901090, 1340901091, 1340900997, 1340900998, 1340900999, 1340901000, 1340901001, 1340901002, 1340901003, 1340901004, 1340901005, 1340901006, 1340901007, 1340901008, 1340901009, 1340901010, 1340901011, 1340901012, 1340901013, 1340901014, 1340901015, 1340901016, 1340901017, 1340901018, 1340901019, 1340901020, 1340901021, 1340901022, 1340901023, 1340901024, 1340901025, 1340901027, 1340901029, 1340901092, 1340901093, 1340901094, 1340901095, 1340901096, 1340901097, 1340901098, 1340901099, 1340901100, 1340901101, 1340901102, 1340901103, 1340901104, 1340901105, 1340901107, 1340901108, 1340901109, 1340901110, 1340901111, 1340901112, 1340901113, 1340901114, 1340901115, 1340901116, 1340901117, 1340901118, 1340901119, 1340901120, 1340901121, 1340901122, 1340901123] number of photos to traite : 301 try to delete the photos incorrect in DB tagging for thcl : 3237 To do loadFromThcl(), then load ParamDescType : thcl3237 thcls : [{'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'}] thcl {'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'} Update svm_hashtag_type_desc : 5561 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) To loadFromThcl() : net_5561 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 4180 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_rubbia_refus_2500 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_rubbia_refus_2500 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_rubbia_refus_2500 /data/models_weight/learn_rubbia_refus_2500/caffemodel size_local : 94358479 size in s3 : 94358479 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:16 caffemodel already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:15 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:09:52 mean.npy already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/synset_words.txt size_local : 334 size in s3 : 334 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:10:06 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /home/admin/workarea/install/caffe_cuda8_python3/python/:/home/admin/workarea/install/darknet/:/home/admin/workarea/git/Velours/python:/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python:/home/admin/mtr/.credentials:/home/admin/workarea/install/caffe/python:/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools/:/home/admin/workarea/git/fotonowerpip/:/home/admin/workarea/install/segment-anything:/home/admin//workarea/git/pyfvs/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt caffemodel_filename : /data/models_weight/learn_rubbia_refus_2500/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3961 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 1.3386201858520508 time used to do the prediction : 1.1686904430389404 save descriptor for thcl : 3237 time to traite the descriptors : 1.6820039749145508 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1340901311 To insert : 1340901312 To insert : 1340901313 To insert : 1340901314 To insert : 1340901315 To insert : 1340901316 To insert : 1340901317 To insert : 1340901318 To insert : 1340901324 To insert : 1340901325 To insert : 1340901326 To insert : 1340901327 To insert : 1340901328 To insert : 1340901329 To insert : 1340901330 To insert : 1340901331 To insert : 1340901332 To insert : 1340901333 To insert : 1340901334 To insert : 1340901335 To insert : 1340901336 To insert : 1340901339 To insert : 1340901124 To insert : 1340901125 To insert : 1340901126 To insert : 1340901127 To insert : 1340901128 To insert : 1340901129 To insert : 1340901130 To insert : 1340901132 To insert : 1340901133 To insert : 1340901134 To insert : 1340901135 To insert : 1340901136 To insert : 1340901137 To insert : 1340901138 To insert : 1340901139 To insert : 1340901140 To insert : 1340901141 To insert : 1340901142 To insert : 1340901143 To insert : 1340901144 To insert : 1340901145 To insert : 1340901146 To insert : 1340901147 To insert : 1340901148 To insert : 1340901149 To insert : 1340901150 To insert : 1340901151 To insert : 1340901152 To insert : 1340901153 To insert : 1340901154 To insert : 1340901155 To insert : 1340901156 To insert : 1340901157 To insert : 1340901158 To insert : 1340901159 To insert : 1340901160 To insert : 1340901161 To insert : 1340901162 To insert : 1340901163 To insert : 1340901164 To insert : 1340901165 To insert : 1340901166 To insert : 1340901167 To insert : 1340901168 To insert : 1340901169 To insert : 1340901170 To insert : 1340901171 To insert : 1340901172 To insert : 1340901173 To insert : 1340901174 To insert : 1340901175 To insert : 1340901176 To insert : 1340901177 To insert : 1340901178 To insert : 1340901179 To insert : 1340901180 To insert : 1340901181 To insert : 1340901182 To insert : 1340901183 To insert : 1340901184 To insert : 1340901185 To insert : 1340901186 To insert : 1340901030 To insert : 1340901031 To insert : 1340901032 To insert : 1340901033 To insert : 1340901034 To insert : 1340901035 To insert : 1340901036 To insert : 1340901037 To insert : 1340901038 To insert : 1340901039 To insert : 1340901040 To insert : 1340901041 To insert : 1340901042 To insert : 1340901043 To insert : 1340901044 To insert : 1340901045 To insert : 1340901046 To insert : 1340901047 To insert : 1340901048 To insert : 1340901049 To insert : 1340901050 To insert : 1340901051 To insert : 1340901052 To insert : 1340901053 To insert : 1340901054 To insert : 1340901055 To insert : 1340901056 To insert : 1340901057 To insert : 1340901058 To insert : 1340901059 To insert : 1340901060 To insert : 1340901228 To insert : 1340901243 To insert : 1340901244 To insert : 1340901245 To insert : 1340901246 To insert : 1340901247 To insert : 1340901248 To insert : 1340901249 To insert : 1340901251 To insert : 1340901252 To insert : 1340901253 To insert : 1340901254 To insert : 1340901255 To insert : 1340901256 To insert : 1340901257 To insert : 1340901258 To insert : 1340901259 To insert : 1340901260 To insert : 1340901261 To insert : 1340901262 To insert : 1340901263 To insert : 1340901264 To insert : 1340901265 To insert : 1340901266 To insert : 1340901267 To insert : 1340901269 To insert : 1340901270 To insert : 1340901271 To insert : 1340901272 To insert : 1340901273 To insert : 1340901274 To insert : 1340901187 To insert : 1340901188 To insert : 1340901189 To insert : 1340901190 To insert : 1340901191 To insert : 1340901192 To insert : 1340901193 To insert : 1340901194 To insert : 1340901196 To insert : 1340901199 To insert : 1340901202 To insert : 1340901203 To insert : 1340901204 To insert : 1340901206 To insert : 1340901207 To insert : 1340901208 To insert : 1340901209 To insert : 1340901211 To insert : 1340901212 To insert : 1340901213 To insert : 1340901214 To insert : 1340901215 To insert : 1340901216 To insert : 1340901217 To insert : 1340901218 To insert : 1340901220 To insert : 1340901222 To insert : 1340901223 To insert : 1340901224 To insert : 1340901225 To insert : 1340901227 To insert : 1340901275 To insert : 1340901277 To insert : 1340901278 To insert : 1340901279 To insert : 1340901280 To insert : 1340901281 To insert : 1340901282 To insert : 1340901283 To insert : 1340901284 To insert : 1340901285 To insert : 1340901286 To insert : 1340901287 To insert : 1340901288 To insert : 1340901289 To insert : 1340901290 To insert : 1340901291 To insert : 1340901292 To insert : 1340901293 To insert : 1340901294 To insert : 1340901295 To insert : 1340901296 To insert : 1340901301 To insert : 1340901302 To insert : 1340901303 To insert : 1340901304 To insert : 1340901305 To insert : 1340901306 To insert : 1340901307 To insert : 1340901308 To insert : 1340901309 To insert : 1340901310 To insert : 1340901061 To insert : 1340901062 To insert : 1340901063 To insert : 1340901064 To insert : 1340901065 To insert : 1340901066 To insert : 1340901067 To insert : 1340901068 To insert : 1340901069 To insert : 1340901070 To insert : 1340901071 To insert : 1340901072 To insert : 1340901073 To insert : 1340901074 To insert : 1340901075 To insert : 1340901076 To insert : 1340901077 To insert : 1340901078 To insert : 1340901079 To insert : 1340901080 To insert : 1340901081 To insert : 1340901082 To insert : 1340901083 To insert : 1340901084 To insert : 1340901085 To insert : 1340901086 To insert : 1340901087 To insert : 1340901088 To insert : 1340901089 To insert : 1340901090 To insert : 1340901091 To insert : 1340900997 To insert : 1340900998 To insert : 1340900999 To insert : 1340901000 To insert : 1340901001 To insert : 1340901002 To insert : 1340901003 To insert : 1340901004 To insert : 1340901005 To insert : 1340901006 To insert : 1340901007 To insert : 1340901008 To insert : 1340901009 To insert : 1340901010 To insert : 1340901011 To insert : 1340901012 To insert : 1340901013 To insert : 1340901014 To insert : 1340901015 To insert : 1340901016 To insert : 1340901017 To insert : 1340901018 To insert : 1340901019 To insert : 1340901020 To insert : 1340901021 To insert : 1340901022 To insert : 1340901023 To insert : 1340901024 To insert : 1340901025 To insert : 1340901027 To insert : 1340901029 To insert : 1340901092 To insert : 1340901093 To insert : 1340901094 To insert : 1340901095 To insert : 1340901096 To insert : 1340901097 To insert : 1340901098 To insert : 1340901099 To insert : 1340901100 To insert : 1340901101 To insert : 1340901102 To insert : 1340901103 To insert : 1340901104 To insert : 1340901105 To insert : 1340901107 To insert : 1340901108 To insert : 1340901109 To insert : 1340901110 To insert : 1340901111 To insert : 1340901112 To insert : 1340901113 To insert : 1340901114 To insert : 1340901115 To insert : 1340901116 To insert : 1340901117 To insert : 1340901118 To insert : 1340901119 To insert : 1340901120 To insert : 1340901121 To insert : 1340901122 To insert : 1340901123 time to insert the descriptors : 62.32018804550171 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos SAVE THCL : begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 435 time used for this insertion : 0.02991175651550293 save missing photos in datou_result : time spend for datou_step_exec : 71.09359383583069 time spend to save output : 0.08229494094848633 total time spend for step 6 : 71.17588877677917 step7:ventilate_hashtags_in_portfolio Wed Mar 5 00:24:05 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure beginning of datou step ventilate_hashtags_in_portfolio : To implement ! Iterating over portfolio : 21033063 get user id for portfolio 21033063 SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21033063 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_clair','pet_clair','autre','flou','refus','carton','PET_fonce','Papier','Film_plastique','Carton','PEHD','papier','pehd','Tetrapak','pet_fonce','metal','mal_croppe','environnement')) AND mptpi.`min_score`=0.6 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21033063 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_clair','pet_clair','autre','flou','refus','carton','PET_fonce','Papier','Film_plastique','Carton','PEHD','papier','pehd','Tetrapak','pet_fonce','metal','mal_croppe','environnement')) AND mptpi.`min_score`=0.6 To do Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21033063 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_clair','pet_clair','autre','flou','refus','carton','PET_fonce','Papier','Film_plastique','Carton','PEHD','papier','pehd','Tetrapak','pet_fonce','metal','mal_croppe','environnement')) AND mptpi.`min_score`=0.6 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21033063 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('PET_clair','pet_clair','autre','flou','refus','carton','PET_fonce','Papier','Film_plastique','Carton','PEHD','papier','pehd','Tetrapak','pet_fonce','metal','mal_croppe','environnement')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/21034288,21034289,21034290,21034291,21034296,21034301,21034298,21034295,21034299,21034300,21034302,21034303,21034304?tags=pet_clair,autre,flou,refus,carton,pet_fonce,papier,film_plastique,pehd,tetrapak,metal,mal_croppe,environnement&datou_id_consolidate=4235&port_consolidate=21033063 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1340895795, 1340891294] Looping around the photos to save general results len do output : 1 /21033063. before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340895795', None, None, None, None, None, '2634593') ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340891294', None, None, None, None, None, '2634593') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.016467571258544922 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.4351046085357666 time spend to save output : 0.01672053337097168 total time spend for step 7 : 2.4518251419067383 step8:final Wed Mar 5 00:24:07 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 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {1340895795: ('0.8156958851020175',), 1340891294: ('0.8156958851020175',)} new output for save of step final : {1340895795: ('0.8156958851020175',), 1340891294: ('0.8156958851020175',)} [1340895795, 1340891294] Looping around the photos to save general results len do output : 2 /1340895795.Didn't retrieve data . /1340891294.Didn't retrieve data . before output type Used above Used above Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340895795', None, None, None, None, None, '2634593') ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340891294', None, None, None, None, None, '2634593') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.012415170669555664 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11536765098571777 time spend to save output : 0.012663602828979492 total time spend for step 8 : 0.12803125381469727 step9:velours_tree Wed Mar 5 00:24:07 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 list_portfolios : 21034288,21034289,21034290,21034291,21034296,21034301,21034298,21034295,21034299,21034300,21034302,21034303,21034304 photo desc type : 5561 - Retrieving photos to tag... query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034288 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034289 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034290 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034291 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034296 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034301 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034298 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034295 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034299 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034300 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034302 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034303 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21034304 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 301 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [1 4 3 4 1 1 1 1 1 0 3 3 4 1 3 5 1 2 1 4 1 4 0 3 2 5 3 1 1 2 1 2 2 3 3 1 3 2 2 0 2 2 1 2 2 1 1 2 1 1 2 2 1 1 2 1 0 5 3 1 2 5 1 5 0 1 1 2 1 0 2 0 1 1 0 0 0 0 4 3 1 1 5 1 1 1 1 1 4 1 1 1 1 0 1 2 1 0 0 1 5 1 1 1 1 1 1 4 3 1 1 1 1 3 3 1 5 1 3 3 3 1 4 3 2 5 0 3 4 3 0 1 2 1 2 1 3 2 1 2 2 0 2 1 2 3 2 1 2 2 1 2 0 1 2 1 1 1 0 1 2 2 2 1 1 0 2 1 1 1 1 3 1 5 1 2 1 1 2 0 1 2 5 0 1 1 0 1 2 2 2 1 2 1 1 5 2 0 1 1 1 1 3 3 1 1 1 2 1 5 1 3 3 1 1 5 1 0 1 4 1 4 3 2 4 2 1 3 3 4 5 2 0 5 0 2 5 1 4 4 1 1 4 1 1 1 4 2 3 1 0 3 2 0 0 4 5 0 5 5 1 1 1 2 1 1 1 1 5 4 0 0 0 2 3 2 4 0 0 2 0 2 3 0 3 4 1 0 4 4 0 4 1 1 0 4 3 4 5 0 2] Elapsed time: 0.05949115753173828 graph_id used : 81484 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/21034288,21034289,21034290,21034291,21034296,21034301,21034298,21034295,21034299,21034300,21034302,21034303,21034304?tags=pet_clair,autre,flou,refus,carton,pet_fonce,papier,film_plastique,pehd,tetrapak,metal,mal_croppe,environnement&datou_id_consolidate=4235&port_consolidate=21033063&tree_id=81484 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1340895795, 1340891294] Looping around the photos to save general results len do output : 1 /21033063Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340895795', None, None, None, None, None, '2634593') ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340891294', None, None, None, None, None, '2634593') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.014899730682373047 save_final save missing photos in datou_result : time spend for datou_step_exec : 19.880831003189087 time spend to save output : 0.015359640121459961 total time spend for step 9 : 19.896190643310547 step10:send_mail_cod Wed Mar 5 00:24:27 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 complete output_args for input 3 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure dans la step send mail cod work_area: /home/admin/workarea/git/Velours/python in order to get the selector url, please entre the license of selector results_Qualipapia_P21033063_05-03-2025_00_24_27.pdf 21034270 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210342701741130667 21034271 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210342711741130668 21034272 imagette210342721741130669 21034273 imagette210342731741130669 21034278 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210342781741130670 21034283 imagette210342831741130670 21034280 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210342801741130670 21034277 imagette210342771741130671 21034281 change filename to text .imagette210342811741130671 21034282 imagette210342821741130672 21034284 imagette210342841741130672 21034285 imagette210342851741130672 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21033063 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21034288,21034289,21034290,21034291,21034296,21034301,21034298,21034295,21034299,21034300,21034302,21034303,21034304?tags=pet_clair,autre,flou,refus,carton,pet_fonce,papier,film_plastique,pehd,tetrapak,metal,mal_croppe,environnement&datou_id_consolidate=4235&port_consolidate=21033063&tree_id=81484 your option no_mail is active, we will not send the real mail to your client args[1340895795] : ((1340895795, -7.805488582752435, 492609224), (1340895795, 0.3907884538613653, 2107752395), '0.8156958851020175') We are sending mail with results at cod@fotonower.com args[1340891294] : ((1340891294, -7.803453604685461, 492609224), (1340891294, 0.42923231357637714, 2107752395), '0.8156958851020175') We are sending mail with results at cod@fotonower.com refus_total : 0.8156958851020175 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21033063 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21033063_05-03-2025_00_24_27.pdf results_Qualipapia_P21033063_05-03-2025_00_24_27.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21033063_05-03-2025_00_24_27.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4234','21033063','results_Qualipapia_P21033063_05-03-2025_00_24_27.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21033063_05-03-2025_00_24_27.pdf','pdf','','0.17','0.8156958851020175') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1340895795, 1340891294] Looping around the photos to save general results len do output : 0 before output type Used above Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340895795', None, None, None, None, None, '2634593') ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340891294', None, None, None, None, None, '2634593') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.03096175193786621 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.24323296546936 time spend to save output : 0.031131982803344727 total time spend for step 10 : 5.274364948272705 step11:split_time_score Wed Mar 5 00:24:33 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3442, 'mtr_user_id': 31, 'name': 'classifieur_2camions_valcor_021122_v1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'deux_camions,camion_droite,camion_gauche,pas_de_camion', 'svm_portfolios_learning': '7659379,7659034,7657685,7657114', 'photo_hashtag_type': 4458, 'photo_desc_type': 5723, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107760533,2107760534,2107760535,2107760536'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('20', 2),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 04032025 21033063 Nombre de photos uploadées : 2 / 23040 (0%) 04032025 21033063 Nombre de photos taguées (types de déchets): 0 / 2 (0%) 04032025 21033063 Nombre de photos taguées (volume) : 0 / 2 (0%) Catched exception ! Connect or reconnect ! elapsed_time : load_data_split_time_score 3.0994415283203125e-06 elapsed_time : order_list_meta_photo_and_scores 1.239776611328125e-05 ?? elapsed_time : fill_and_build_computed_from_old_data 0.0003600120544433594 elapsed_time : insert_dashboard_record_day_entry 0.023735761642456055 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027579 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027580 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027582 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027584 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027586 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027588 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027590 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027592 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027594 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027596 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027598 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027600 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027602 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027604 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027606 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21027608 order by id desc limit 1 Qualite : 0.8223343609958527 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21030443_04-03-2025_23_02_56.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21030443 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21030443 AND mptpi.`type`=4230 To do Qualite : 0.8156958851020175 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21033063_05-03-2025_00_24_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21033063 order by id desc limit 1 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21033063 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'04032025': {'nb_upload': 2, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1340895795, 1340891294] Looping around the photos to save general results len do output : 1 /21033063Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340895795', None, None, None, None, None, '2634593') ('4234', None, None, None, None, None, None, None, '2634593') ('4234', '21033063', '1340891294', None, None, None, None, None, '2634593') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.015363693237304688 save_final save missing photos in datou_result : time spend for datou_step_exec : 13.327524185180664 time spend to save output : 0.015587806701660156 total time spend for step 11 : 13.343111991882324 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 2 set_done_treatment 55.36user 36.56system 4:22.40elapsed 35%CPU (0avgtext+0avgdata 6572908maxresident)k 994232inputs+23032outputs (6587major+4998982minor)pagefaults 0swaps