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 : 737127 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 : ['2583047'] with mtr_portfolio_ids : ['20514224'] and first list_photo_ids : [] new path : /proc/737127/ 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 , BFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 1 ; length of list_pids : 1 ; length of list_args : 1 time to download the photos : 0.14768218994140625 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Thu Feb 13 17:20:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 6774 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-13 17:20:33.189858: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-13 17:20:33.201800: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-13 17:20:33.203680: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f93ec000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-13 17:20:33.203708: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-13 17:20:33.206948: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-13 17:20:33.361897: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2e4fef60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-13 17:20:33.361973: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-13 17:20:33.363592: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-13 17:20:33.364127: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 17:20:33.367816: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 17:20:33.371389: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-13 17:20:33.372243: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-13 17:20:33.376197: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-13 17:20:33.378291: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-13 17:20:33.386975: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-13 17:20:33.388517: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-13 17:20:33.388631: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 17:20:33.389515: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-13 17:20:33.389533: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-13 17:20:33.389544: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-13 17:20:33.391157: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6081 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-13 17:20:33.845846: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-13 17:20:33.846011: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 17:20:33.846035: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 17:20:33.846052: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-13 17:20:33.846069: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-13 17:20:33.846085: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-13 17:20:33.846100: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-13 17:20:33.846116: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-13 17:20:33.850271: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-13 17:20:33.852707: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-13 17:20:33.852807: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-13 17:20:33.852825: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 17:20:33.852840: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-13 17:20:33.852855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-13 17:20:33.852871: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-13 17:20:33.852888: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-13 17:20:33.852904: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-13 17:20:33.853941: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-13 17:20:33.853991: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-13 17:20:33.854000: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-13 17:20:33.854008: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-13 17:20:33.855146: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6081 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-13 17:20:43.007049: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-13 17:20:43.197578: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-13 17:20:45.115494: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.116131: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.60G (3865470464 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.116705: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.24G (3478923264 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.117206: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3131030784 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.117723: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.62G (2817927680 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.118267: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.36G (2536134912 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.118800: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.12G (2282521344 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.118836: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.119396: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.119417: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.126709: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.126737: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.127286: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.127310: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.133845: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.133870: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.134422: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.134440: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.166704: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.166755: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.167322: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.167350: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.173505: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.173545: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.174314: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.174340: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-13 17:20:45.208789: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.216065: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.218274: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.219058: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.269490: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.270091: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.272988: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.273570: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.304607: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.305268: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.307255: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.307884: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.315873: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.316504: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.318365: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.318993: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.325152: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.325769: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.327493: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.328067: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.358200: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.358875: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.359505: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.360131: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.365420: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.366035: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.393878: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.394492: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.395063: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.395624: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.412807: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.413564: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.414235: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.414839: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.420158: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.420761: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.425576: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.426155: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.438428: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.439056: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.443268: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.443845: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.444483: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.445042: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.446046: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.446614: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.457043: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.457639: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.458296: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.458856: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.459431: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.459996: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.460563: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.461118: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.470441: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.471116: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.477518: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.478121: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.545781: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.546459: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.554725: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.555338: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.573783: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.574408: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.575052: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.575677: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.580021: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.580606: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.581171: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.581732: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.583064: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.583091: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-02-13 17:20:45.593441: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.594063: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.603477: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.604068: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.604649: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.605248: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.605820: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-13 17:20:45.606379: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 1 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: -121.78594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00013971328735351562 nb_pixel_total : 891 time to create 1 rle with old method : 0.001989126205444336 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.40703 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0012445449829101562 length of segment : 14 time for calcul the mask position with numpy : 0.0002589225769042969 nb_pixel_total : 846 time to create 1 rle with old method : 0.0019366741180419922 length of segment : 38 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00032210350036621094 length of segment : 16 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.0005903244018554688 length of segment : 17 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0004923343658447266 length of segment : 22 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0011415481567382812 length of segment : 27 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 795 time to create 1 rle with old method : 0.001787424087524414 length of segment : 33 time for calcul the mask position with numpy : 0.0001270771026611328 nb_pixel_total : 544 time to create 1 rle with old method : 0.0013115406036376953 length of segment : 23 time for calcul the mask position with numpy : 0.0001366138458251953 nb_pixel_total : 1182 time to create 1 rle with old method : 0.0026285648345947266 length of segment : 36 time for calcul the mask position with numpy : 0.00014066696166992188 nb_pixel_total : 548 time to create 1 rle with old method : 0.0012426376342773438 length of segment : 29 time for calcul the mask position with numpy : 0.00013685226440429688 nb_pixel_total : 278 time to create 1 rle with old method : 0.001965045928955078 length of segment : 19 time for calcul the mask position with numpy : 0.00010919570922851562 nb_pixel_total : 699 time to create 1 rle with old method : 0.0016617774963378906 length of segment : 25 time for calcul the mask position with numpy : 0.00013589859008789062 nb_pixel_total : 1687 time to create 1 rle with old method : 0.0037658214569091797 length of segment : 48 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005815029144287109 length of segment : 28 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00044417381286621094 length of segment : 23 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1067 time to create 1 rle with old method : 0.0014793872833251953 length of segment : 45 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0007867813110351562 length of segment : 25 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.0012426376342773438 length of segment : 47 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.00030732154846191406 length of segment : 18 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1058 time to create 1 rle with old method : 0.0014452934265136719 length of segment : 46 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0007116794586181641 length of segment : 27 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0007245540618896484 length of segment : 20 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.0003082752227783203 length of segment : 9 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.21172 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 27 time for calcul the mask position with numpy : 0.00018715858459472656 nb_pixel_total : 2269 time to create 1 rle with old method : 0.0035767555236816406 length of segment : 47 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.00039505958557128906 length of segment : 14 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 1028 time to create 1 rle with old method : 0.0014886856079101562 length of segment : 43 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1063 time to create 1 rle with old method : 0.00151824951171875 length of segment : 36 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.0003590583801269531 length of segment : 16 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00026679039001464844 length of segment : 14 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 637 time to create 1 rle with old method : 0.0008091926574707031 length of segment : 67 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007328987121582031 length of segment : 41 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1455 time to create 1 rle with old method : 0.0020384788513183594 length of segment : 33 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00026035308837890625 length of segment : 11 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1935 time to create 1 rle with old method : 0.0023679733276367188 length of segment : 60 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005548000335693359 length of segment : 29 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006377696990966797 length of segment : 27 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003609657287597656 length of segment : 24 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003247261047363281 length of segment : 15 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00026297569274902344 length of segment : 9 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 1874 time to create 1 rle with old method : 0.0025949478149414062 length of segment : 47 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00016045570373535156 length of segment : 8 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.0009834766387939453 length of segment : 55 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 566 time to create 1 rle with old method : 0.0007970333099365234 length of segment : 40 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003833770751953125 length of segment : 19 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.00036144256591796875 length of segment : 11 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1042 time to create 1 rle with old method : 0.001482248306274414 length of segment : 33 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006911754608154297 length of segment : 25 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00017142295837402344 length of segment : 16 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0007486343383789062 length of segment : 24 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001723766326904297 length of segment : 9 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.99297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 42 time for calcul the mask position with numpy : 0.00014925003051757812 nb_pixel_total : 954 time to create 1 rle with old method : 0.0014531612396240234 length of segment : 31 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 473 time to create 1 rle with old method : 0.0006647109985351562 length of segment : 25 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 607 time to create 1 rle with old method : 0.0008761882781982422 length of segment : 27 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003638267517089844 length of segment : 19 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0004177093505859375 length of segment : 17 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.000362396240234375 length of segment : 22 time for calcul the mask position with numpy : 0.00010776519775390625 nb_pixel_total : 3360 time to create 1 rle with old method : 0.004068613052368164 length of segment : 80 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005619525909423828 length of segment : 21 time for calcul the mask position with numpy : 0.00015044212341308594 nb_pixel_total : 4095 time to create 1 rle with old method : 0.0051555633544921875 length of segment : 66 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 1744 time to create 1 rle with old method : 0.0021352767944335938 length of segment : 51 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 792 time to create 1 rle with old method : 0.0011966228485107422 length of segment : 42 time for calcul the mask position with numpy : 9.870529174804688e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.00043201446533203125 length of segment : 22 time for calcul the mask position with numpy : 0.0001595020294189453 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0014328956604003906 length of segment : 45 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 962 time to create 1 rle with old method : 0.0013751983642578125 length of segment : 23 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 609 time to create 1 rle with old method : 0.0008423328399658203 length of segment : 28 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006318092346191406 length of segment : 24 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005161762237548828 length of segment : 21 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 616 time to create 1 rle with old method : 0.0008373260498046875 length of segment : 23 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00025963783264160156 length of segment : 13 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0003516674041748047 length of segment : 13 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00035500526428222656 length of segment : 17 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007739067077636719 length of segment : 24 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00028204917907714844 length of segment : 20 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00021457672119140625 length of segment : 9 time for calcul the mask position with numpy : 0.00011682510375976562 nb_pixel_total : 535 time to create 1 rle with old method : 0.0008406639099121094 length of segment : 42 time for calcul the mask position with numpy : 0.00020003318786621094 nb_pixel_total : 1878 time to create 1 rle with old method : 0.0023746490478515625 length of segment : 46 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005626678466796875 length of segment : 45 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.000431060791015625 length of segment : 18 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004813671112060547 length of segment : 22 time for calcul the mask position with numpy : 0.00021219253540039062 nb_pixel_total : 2478 time to create 1 rle with old method : 0.003270387649536133 length of segment : 52 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005764961242675781 length of segment : 27 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.00036907196044921875 length of segment : 22 time for calcul the mask position with numpy : 0.00018262863159179688 nb_pixel_total : 1540 time to create 1 rle with old method : 0.002012014389038086 length of segment : 40 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 2580 time to create 1 rle with old method : 0.0032494068145751953 length of segment : 54 time for calcul the mask position with numpy : 0.0001270771026611328 nb_pixel_total : 947 time to create 1 rle with old method : 0.0013089179992675781 length of segment : 31 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 454 time to create 1 rle with old method : 0.0006363391876220703 length of segment : 24 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00018215179443359375 length of segment : 14 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.000133514404296875 length of segment : 10 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0005588531494140625 length of segment : 23 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002560615539550781 length of segment : 28 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 1025 time to create 1 rle with old method : 0.0013298988342285156 length of segment : 61 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0010297298431396484 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: -122.25469 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 0.00010538101196289062 nb_pixel_total : 294 time to create 1 rle with old method : 0.0006306171417236328 length of segment : 23 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 69 time to create 1 rle with old method : 0.00022983551025390625 length of segment : 6 time for calcul the mask position with numpy : 9.465217590332031e-05 nb_pixel_total : 1335 time to create 1 rle with old method : 0.0026197433471679688 length of segment : 47 time for calcul the mask position with numpy : 0.00029540061950683594 nb_pixel_total : 5374 time to create 1 rle with old method : 0.0102386474609375 length of segment : 81 time for calcul the mask position with numpy : 0.00019311904907226562 nb_pixel_total : 1231 time to create 1 rle with old method : 0.0025794506072998047 length of segment : 29 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 505 time to create 1 rle with old method : 0.0012927055358886719 length of segment : 43 time for calcul the mask position with numpy : 0.00012445449829101562 nb_pixel_total : 466 time to create 1 rle with old method : 0.001104116439819336 length of segment : 27 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0006952285766601562 length of segment : 17 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.000240325927734375 length of segment : 7 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0008301734924316406 length of segment : 13 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0005478858947753906 length of segment : 16 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0009710788726806641 length of segment : 48 time for calcul the mask position with numpy : 0.00011610984802246094 nb_pixel_total : 664 time to create 1 rle with old method : 0.001531839370727539 length of segment : 41 time for calcul the mask position with numpy : 0.00018644332885742188 nb_pixel_total : 5386 time to create 1 rle with old method : 0.006573677062988281 length of segment : 80 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 846 time to create 1 rle with old method : 0.001138925552368164 length of segment : 34 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0005953311920166016 length of segment : 24 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 859 time to create 1 rle with old method : 0.0012068748474121094 length of segment : 57 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.00043511390686035156 length of segment : 23 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0006341934204101562 length of segment : 30 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1042 time to create 1 rle with old method : 0.0015225410461425781 length of segment : 36 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1314 time to create 1 rle with old method : 0.0017647743225097656 length of segment : 42 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 951 time to create 1 rle with old method : 0.0012938976287841797 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: -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 : 7.271766662597656e-05 nb_pixel_total : 1143 time to create 1 rle with old method : 0.0014638900756835938 length of segment : 59 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003733634948730469 length of segment : 26 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00032901763916015625 length of segment : 13 time for calcul the mask position with numpy : 0.0006287097930908203 nb_pixel_total : 34184 time to create 1 rle with old method : 0.03985166549682617 length of segment : 233 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005786418914794922 length of segment : 32 time for calcul the mask position with numpy : 0.0005774497985839844 nb_pixel_total : 32654 time to create 1 rle with old method : 0.03850984573364258 length of segment : 230 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 170.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 59.76016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 1973 time to create 1 rle with old method : 0.003052949905395508 length of segment : 103 time for calcul the mask position with numpy : 0.00016188621520996094 nb_pixel_total : 2698 time to create 1 rle with old method : 0.003580331802368164 length of segment : 99 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.17656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 0.00017309188842773438 nb_pixel_total : 421 time to create 1 rle with old method : 0.0006620883941650391 length of segment : 24 time for calcul the mask position with numpy : 0.00017213821411132812 nb_pixel_total : 1695 time to create 1 rle with old method : 0.0023682117462158203 length of segment : 73 time for calcul the mask position with numpy : 0.00010371208190917969 nb_pixel_total : 951 time to create 1 rle with old method : 0.0012602806091308594 length of segment : 44 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00027871131896972656 length of segment : 15 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0007767677307128906 length of segment : 28 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.0006470680236816406 length of segment : 30 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0015997886657714844 length of segment : 29 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002510547637939453 length of segment : 23 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.0005033016204833984 length of segment : 34 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0005359649658203125 length of segment : 33 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0005791187286376953 length of segment : 21 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003795623779296875 length of segment : 25 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 773 time to create 1 rle with old method : 0.0011029243469238281 length of segment : 59 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 31 time to create 1 rle with old method : 0.00011205673217773438 length of segment : 19 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00041604042053222656 length of segment : 12 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.000545501708984375 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: -117.20391 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 : 7.867813110351562e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005717277526855469 length of segment : 23 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0010137557983398438 length of segment : 26 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0008387565612792969 length of segment : 57 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 745 time to create 1 rle with old method : 0.0010678768157958984 length of segment : 27 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0005908012390136719 length of segment : 28 time for calcul the mask position with numpy : 0.00013113021850585938 nb_pixel_total : 2584 time to create 1 rle with old method : 0.0032510757446289062 length of segment : 63 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.00036787986755371094 length of segment : 39 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0007104873657226562 length of segment : 45 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 544 time to create 1 rle with old method : 0.0007815361022949219 length of segment : 45 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 685 time to create 1 rle with old method : 0.0010254383087158203 length of segment : 58 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0017294883728027344 length of segment : 55 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 1352 time to create 1 rle with old method : 0.0017786026000976562 length of segment : 57 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 870 time to create 1 rle with old method : 0.0012252330780029297 length of segment : 31 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0006580352783203125 length of segment : 43 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0006892681121826172 length of segment : 45 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0014581680297851562 length of segment : 37 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1120 time to create 1 rle with old method : 0.0015180110931396484 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.46953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.00034165382385253906 length of segment : 11 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0009937286376953125 length of segment : 24 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 1591 time to create 1 rle with old method : 0.002159595489501953 length of segment : 60 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 762 time to create 1 rle with old method : 0.0011067390441894531 length of segment : 30 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 704 time to create 1 rle with old method : 0.0009827613830566406 length of segment : 57 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.00042438507080078125 length of segment : 15 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 143 time to create 1 rle with old method : 0.0002143383026123047 length of segment : 24 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002980232238769531 length of segment : 15 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.00044846534729003906 length of segment : 18 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.000431060791015625 length of segment : 29 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.00044083595275878906 length of segment : 28 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006906986236572266 length of segment : 22 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003724098205566406 length of segment : 18 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 51 time to create 1 rle with old method : 0.00010991096496582031 length of segment : 11 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002295970916748047 length of segment : 13 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006043910980224609 length of segment : 38 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.00036787986755371094 length of segment : 22 time for calcul the mask position with numpy : 0.00011730194091796875 nb_pixel_total : 4463 time to create 1 rle with old method : 0.005770683288574219 length of segment : 75 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.0004260540008544922 length of segment : 27 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.0002391338348388672 length of segment : 17 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.00022363662719726562 length of segment : 19 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0015513896942138672 length of segment : 25 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 1721 time to create 1 rle with old method : 0.0021915435791015625 length of segment : 67 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.34844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 149 time to create 1 rle with old method : 0.00028777122497558594 length of segment : 12 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0004754066467285156 length of segment : 21 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.0006573200225830078 length of segment : 26 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0005066394805908203 length of segment : 22 time for calcul the mask position with numpy : 0.0002868175506591797 nb_pixel_total : 1284 time to create 1 rle with old method : 0.0018088817596435547 length of segment : 36 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0007293224334716797 length of segment : 32 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.0012638568878173828 length of segment : 46 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 1784 time to create 1 rle with old method : 0.0024819374084472656 length of segment : 48 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005729198455810547 length of segment : 19 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005536079406738281 length of segment : 34 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 2110 time to create 1 rle with old method : 0.002590656280517578 length of segment : 71 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 986 time to create 1 rle with old method : 0.0012428760528564453 length of segment : 70 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1130 time to create 1 rle with old method : 0.0015523433685302734 length of segment : 53 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.0009598731994628906 length of segment : 51 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 682 time to create 1 rle with old method : 0.0009322166442871094 length of segment : 62 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.00046443939208984375 length of segment : 47 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1220 time to create 1 rle with old method : 0.0016827583312988281 length of segment : 36 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00037598609924316406 length of segment : 41 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1773 time to create 1 rle with old method : 0.002279520034790039 length of segment : 83 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 853 time to create 1 rle with old method : 0.0011515617370605469 length of segment : 61 time for calcul the mask position with numpy : 0.00011348724365234375 nb_pixel_total : 3028 time to create 1 rle with old method : 0.003816843032836914 length of segment : 131 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 481 time to create 1 rle with old method : 0.0006935596466064453 length of segment : 23 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0020613670349121094 length of segment : 108 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.14922 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 72 time for calcul the mask position with numpy : 0.00014066696166992188 nb_pixel_total : 122 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 7 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 266 time to create 1 rle with old method : 0.0004324913024902344 length of segment : 31 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 1295 time to create 1 rle with old method : 0.001725912094116211 length of segment : 44 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005071163177490234 length of segment : 19 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00020623207092285156 length of segment : 8 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.00036644935607910156 length of segment : 11 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 923 time to create 1 rle with old method : 0.001211404800415039 length of segment : 53 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0009617805480957031 length of segment : 34 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 419 time to create 1 rle with old method : 0.0006382465362548828 length of segment : 16 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 964 time to create 1 rle with old method : 0.0013720989227294922 length of segment : 26 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 2100 time to create 1 rle with old method : 0.0030083656311035156 length of segment : 31 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005717277526855469 length of segment : 24 time for calcul the mask position with numpy : 0.0001704692840576172 nb_pixel_total : 2813 time to create 1 rle with old method : 0.0035715103149414062 length of segment : 133 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 1249 time to create 1 rle with old method : 0.0016932487487792969 length of segment : 45 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003657341003417969 length of segment : 22 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0007424354553222656 length of segment : 35 time for calcul the mask position with numpy : 0.00031757354736328125 nb_pixel_total : 1486 time to create 1 rle with old method : 0.0019583702087402344 length of segment : 152 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003979206085205078 length of segment : 24 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0008816719055175781 length of segment : 24 time for calcul the mask position with numpy : 0.0001537799835205078 nb_pixel_total : 2460 time to create 1 rle with old method : 0.00451350212097168 length of segment : 83 time for calcul the mask position with numpy : 0.00010514259338378906 nb_pixel_total : 78 time to create 1 rle with old method : 0.0002715587615966797 length of segment : 16 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0009632110595703125 length of segment : 41 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 22 time to create 1 rle with old method : 8.034706115722656e-05 length of segment : 9 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00018858909606933594 length of segment : 10 time for calcul the mask position with numpy : 8.559226989746094e-05 nb_pixel_total : 1511 time to create 1 rle with old method : 0.0019173622131347656 length of segment : 53 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.00021028518676757812 length of segment : 11 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 2775 time to create 1 rle with old method : 0.004126548767089844 length of segment : 67 time for calcul the mask position with numpy : 0.00015544891357421875 nb_pixel_total : 1150 time to create 1 rle with old method : 0.0017066001892089844 length of segment : 62 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0006647109985351562 length of segment : 44 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0002932548522949219 length of segment : 14 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 855 time to create 1 rle with old method : 0.0014109611511230469 length of segment : 35 time for calcul the mask position with numpy : 0.0004363059997558594 nb_pixel_total : 10394 time to create 1 rle with old method : 0.013170242309570312 length of segment : 138 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 1537 time to create 1 rle with old method : 0.0021979808807373047 length of segment : 67 time for calcul the mask position with numpy : 0.000152587890625 nb_pixel_total : 709 time to create 1 rle with old method : 0.0009961128234863281 length of segment : 60 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003361701965332031 length of segment : 20 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002942085266113281 length of segment : 18 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 922 time to create 1 rle with old method : 0.001318216323852539 length of segment : 35 time for calcul the mask position with numpy : 0.0002722740173339844 nb_pixel_total : 3701 time to create 1 rle with old method : 0.00516819953918457 length of segment : 152 time for calcul the mask position with numpy : 0.00019860267639160156 nb_pixel_total : 812 time to create 1 rle with old method : 0.0014524459838867188 length of segment : 58 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0005872249603271484 length of segment : 32 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0014891624450683594 length of segment : 45 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0007755756378173828 length of segment : 7 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00031113624572753906 length of segment : 15 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0007922649383544922 length of segment : 23 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0004067420959472656 length of segment : 23 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0005331039428710938 length of segment : 36 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0005064010620117188 length of segment : 30 time for calcul the mask position with numpy : 0.00013709068298339844 nb_pixel_total : 1496 time to create 1 rle with old method : 0.002994060516357422 length of segment : 55 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 88 time to create 1 rle with old method : 0.00025343894958496094 length of segment : 24 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.0005235671997070312 length of segment : 23 time for calcul the mask position with numpy : 0.00015997886657714844 nb_pixel_total : 305 time to create 1 rle with old method : 0.0005364418029785156 length of segment : 36 time for calcul the mask position with numpy : 0.00011086463928222656 nb_pixel_total : 2709 time to create 1 rle with old method : 0.003541707992553711 length of segment : 73 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 257 time to create 1 rle with old method : 0.00047588348388671875 length of segment : 54 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 104 time to create 1 rle with old method : 0.00020885467529296875 length of segment : 10 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0004832744598388672 length of segment : 14 length of segment : 0 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0007853507995605469 length of segment : 58 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0004069805145263672 length of segment : 15 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.0001773834228515625 length of segment : 23 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.00043392181396484375 length of segment : 32 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001423358917236328 length of segment : 13 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.00016498565673828125 length of segment : 26 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0007541179656982422 length of segment : 30 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 60 time to create 1 rle with old method : 0.00013256072998046875 length of segment : 9 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.000400543212890625 length of segment : 26 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001990795135498047 length of segment : 10 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002002716064453125 length of segment : 14 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.00030541419982910156 length of segment : 16 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0005512237548828125 length of segment : 31 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 996 time to create 1 rle with old method : 0.0015103816986083984 length of segment : 54 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003325939178466797 length of segment : 38 time for calcul the mask position with numpy : 0.0001239776611328125 nb_pixel_total : 2150 time to create 1 rle with old method : 0.002956867218017578 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: -123.70000 max: 150.98281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0007450580596923828 length of segment : 26 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0011756420135498047 length of segment : 44 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005559921264648438 length of segment : 22 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006604194641113281 length of segment : 52 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 770 time to create 1 rle with old method : 0.0010516643524169922 length of segment : 93 time for calcul the mask position with numpy : 0.0001780986785888672 nb_pixel_total : 1144 time to create 1 rle with old method : 0.0014598369598388672 length of segment : 122 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1364 time to create 1 rle with old method : 0.0017254352569580078 length of segment : 58 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003695487976074219 length of segment : 15 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0006937980651855469 length of segment : 25 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005981922149658203 length of segment : 27 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.0010585784912109375 length of segment : 45 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 2757 time to create 1 rle with old method : 0.0034847259521484375 length of segment : 103 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0007772445678710938 length of segment : 41 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.00040221214294433594 length of segment : 16 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003840923309326172 length of segment : 29 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.0006296634674072266 length of segment : 9 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 409 time to create 1 rle with old method : 0.0006334781646728516 length of segment : 26 time for calcul the mask position with numpy : 0.00029277801513671875 nb_pixel_total : 9524 time to create 1 rle with old method : 0.011470794677734375 length of segment : 313 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.00034308433532714844 length of segment : 19 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 1362 time to create 1 rle with old method : 0.0017209053039550781 length of segment : 59 time for calcul the mask position with numpy : 0.0002834796905517578 nb_pixel_total : 6885 time to create 1 rle with old method : 0.009254693984985352 length of segment : 280 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 254.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 116.65547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 5250 time to create 1 rle with old method : 0.0061779022216796875 length of segment : 192 time for calcul the mask position with numpy : 0.00014472007751464844 nb_pixel_total : 2832 time to create 1 rle with old method : 0.0036063194274902344 length of segment : 114 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006508827209472656 length of segment : 30 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 456 time to create 1 rle with old method : 0.000652313232421875 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: -122.44219 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 : 0.0001926422119140625 nb_pixel_total : 1100 time to create 1 rle with old method : 0.0019867420196533203 length of segment : 60 time for calcul the mask position with numpy : 0.00014066696166992188 nb_pixel_total : 3435 time to create 1 rle with old method : 0.004696846008300781 length of segment : 55 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 1718 time to create 1 rle with old method : 0.002191305160522461 length of segment : 53 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 306 time to create 1 rle with old method : 0.0005624294281005859 length of segment : 35 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 655 time to create 1 rle with old method : 0.0009391307830810547 length of segment : 34 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.0002014636993408203 length of segment : 18 time for calcul the mask position with numpy : 0.00019502639770507812 nb_pixel_total : 6347 time to create 1 rle with old method : 0.007860898971557617 length of segment : 92 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004870891571044922 length of segment : 30 time for calcul the mask position with numpy : 0.0001862049102783203 nb_pixel_total : 4242 time to create 1 rle with old method : 0.006150484085083008 length of segment : 119 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 995 time to create 1 rle with old method : 0.0013480186462402344 length of segment : 42 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1567 time to create 1 rle with old method : 0.0020437240600585938 length of segment : 69 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.00040721893310546875 length of segment : 21 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0004284381866455078 length of segment : 15 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.0005543231964111328 length of segment : 52 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 383 time to create 1 rle with old method : 0.0006177425384521484 length of segment : 30 time for calcul the mask position with numpy : 0.00015807151794433594 nb_pixel_total : 1796 time to create 1 rle with old method : 0.002554178237915039 length of segment : 61 time for calcul the mask position with numpy : 0.00018095970153808594 nb_pixel_total : 4278 time to create 1 rle with old method : 0.005426883697509766 length of segment : 124 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 616 time to create 1 rle with old method : 0.0009105205535888672 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: -120.86797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.00042438507080078125 length of segment : 26 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 1925 time to create 1 rle with old method : 0.0027556419372558594 length of segment : 53 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0009403228759765625 length of segment : 29 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 295 time to create 1 rle with old method : 0.0004067420959472656 length of segment : 27 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002887248992919922 length of segment : 18 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004909038543701172 length of segment : 35 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 590 time to create 1 rle with old method : 0.0008113384246826172 length of segment : 45 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0005185604095458984 length of segment : 17 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0004942417144775391 length of segment : 33 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005996227264404297 length of segment : 35 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 637 time to create 1 rle with old method : 0.0008490085601806641 length of segment : 34 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.0004341602325439453 length of segment : 27 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.0002434253692626953 length of segment : 22 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0004305839538574219 length of segment : 23 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005757808685302734 length of segment : 32 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00046896934509277344 length of segment : 11 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.0003998279571533203 length of segment : 17 time for calcul the mask position with numpy : 0.0001373291015625 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0018529891967773438 length of segment : 82 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007917881011962891 length of segment : 58 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00015234947204589844 length of segment : 13 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0005154609680175781 length of segment : 53 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1021 time to create 1 rle with old method : 0.0014786720275878906 length of segment : 62 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.0007939338684082031 length of segment : 70 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.0002663135528564453 length of segment : 17 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.0002529621124267578 length of segment : 16 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00043487548828125 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.82891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0009431838989257812 length of segment : 17 time for calcul the mask position with numpy : 0.0001010894775390625 nb_pixel_total : 1960 time to create 1 rle with old method : 0.0025463104248046875 length of segment : 54 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1046 time to create 1 rle with old method : 0.0014469623565673828 length of segment : 61 time for calcul the mask position with numpy : 9.34600830078125e-05 nb_pixel_total : 1687 time to create 1 rle with old method : 0.0020911693572998047 length of segment : 60 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 131 time to create 1 rle with old method : 0.00022840499877929688 length of segment : 14 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 520 time to create 1 rle with old method : 0.0007758140563964844 length of segment : 26 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007786750793457031 length of segment : 22 time for calcul the mask position with numpy : 0.00014710426330566406 nb_pixel_total : 1694 time to create 1 rle with old method : 0.0026144981384277344 length of segment : 55 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004932880401611328 length of segment : 29 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0008628368377685547 length of segment : 13 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.00022554397583007812 length of segment : 11 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004603862762451172 length of segment : 20 time for calcul the mask position with numpy : 0.00013327598571777344 nb_pixel_total : 4387 time to create 1 rle with old method : 0.005527496337890625 length of segment : 112 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 1038 time to create 1 rle with old method : 0.0013363361358642578 length of segment : 54 time for calcul the mask position with numpy : 0.00012135505676269531 nb_pixel_total : 1967 time to create 1 rle with old method : 0.002592802047729492 length of segment : 56 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004639625549316406 length of segment : 21 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 1496 time to create 1 rle with old method : 0.002062559127807617 length of segment : 42 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005438327789306641 length of segment : 25 time for calcul the mask position with numpy : 9.655952453613281e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.0002772808074951172 length of segment : 15 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0007481575012207031 length of segment : 25 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 953 time to create 1 rle with old method : 0.0013928413391113281 length of segment : 26 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 1409 time to create 1 rle with old method : 0.0019271373748779297 length of segment : 43 time for calcul the mask position with numpy : 0.00014972686767578125 nb_pixel_total : 539 time to create 1 rle with old method : 0.0011107921600341797 length of segment : 33 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.18047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 35 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 599 time to create 1 rle with old method : 0.0009071826934814453 length of segment : 26 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 2438 time to create 1 rle with old method : 0.003050565719604492 length of segment : 60 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0003600120544433594 length of segment : 11 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 611 time to create 1 rle with old method : 0.0009205341339111328 length of segment : 39 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 240 time to create 1 rle with old method : 0.00036787986755371094 length of segment : 18 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1847 time to create 1 rle with old method : 0.002561330795288086 length of segment : 59 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0005254745483398438 length of segment : 20 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00019025802612304688 length of segment : 12 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.0001652240753173828 length of segment : 10 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 888 time to create 1 rle with old method : 0.0012214183807373047 length of segment : 38 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.00051116943359375 length of segment : 27 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003261566162109375 length of segment : 13 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 585 time to create 1 rle with old method : 0.0008602142333984375 length of segment : 26 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 810 time to create 1 rle with old method : 0.0011358261108398438 length of segment : 43 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0007128715515136719 length of segment : 29 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.00034546852111816406 length of segment : 20 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0006003379821777344 length of segment : 22 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 1027 time to create 1 rle with old method : 0.001375436782836914 length of segment : 70 time for calcul the mask position with numpy : 0.00011396408081054688 nb_pixel_total : 2239 time to create 1 rle with old method : 0.00284576416015625 length of segment : 50 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 573 time to create 1 rle with old method : 0.0008029937744140625 length of segment : 28 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 812 time to create 1 rle with old method : 0.001962900161743164 length of segment : 65 time for calcul the mask position with numpy : 0.00014019012451171875 nb_pixel_total : 3106 time to create 1 rle with old method : 0.004052162170410156 length of segment : 68 time for calcul the mask position with numpy : 0.0001475811004638672 nb_pixel_total : 5120 time to create 1 rle with old method : 0.006291866302490234 length of segment : 69 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0006084442138671875 length of segment : 34 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00020956993103027344 length of segment : 12 time for calcul the mask position with numpy : 0.000102996826171875 nb_pixel_total : 2231 time to create 1 rle with old method : 0.003780841827392578 length of segment : 77 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0002536773681640625 length of segment : 12 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0005218982696533203 length of segment : 15 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0008280277252197266 length of segment : 31 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0009543895721435547 length of segment : 45 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0004792213439941406 length of segment : 13 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0007569789886474609 length of segment : 32 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0005986690521240234 length of segment : 18 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0023336410522460938 length of segment : 41 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.0003848075866699219 length of segment : 11 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 : 27 time for calcul the mask position with numpy : 0.00011467933654785156 nb_pixel_total : 701 time to create 1 rle with old method : 0.0011682510375976562 length of segment : 35 time for calcul the mask position with numpy : 0.0001068115234375 nb_pixel_total : 2079 time to create 1 rle with old method : 0.002721071243286133 length of segment : 64 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 26 time to create 1 rle with old method : 0.00015592575073242188 length of segment : 14 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002803802490234375 length of segment : 17 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007340908050537109 length of segment : 43 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 624 time to create 1 rle with old method : 0.0009710788726806641 length of segment : 32 time for calcul the mask position with numpy : 0.0001678466796875 nb_pixel_total : 145 time to create 1 rle with old method : 0.0003695487976074219 length of segment : 24 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0017366409301757812 length of segment : 68 time for calcul the mask position with numpy : 0.00010728836059570312 nb_pixel_total : 2758 time to create 1 rle with old method : 0.0034971237182617188 length of segment : 69 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 401 time to create 1 rle with old method : 0.0006201267242431641 length of segment : 20 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 2450 time to create 1 rle with old method : 0.003306150436401367 length of segment : 50 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 2374 time to create 1 rle with old method : 0.0033674240112304688 length of segment : 50 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005810260772705078 length of segment : 41 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 953 time to create 1 rle with old method : 0.0013322830200195312 length of segment : 60 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 491 time to create 1 rle with old method : 0.0007412433624267578 length of segment : 49 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 778 time to create 1 rle with old method : 0.0011301040649414062 length of segment : 41 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.00030303001403808594 length of segment : 15 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0008687973022460938 length of segment : 31 time for calcul the mask position with numpy : 0.0007445812225341797 nb_pixel_total : 29903 time to create 1 rle with old method : 0.03873753547668457 length of segment : 459 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 977 time to create 1 rle with old method : 0.0012927055358886719 length of segment : 32 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0003693103790283203 length of segment : 33 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.00054168701171875 length of segment : 22 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0007221698760986328 length of segment : 56 time for calcul the mask position with numpy : 0.00020384788513183594 nb_pixel_total : 2877 time to create 1 rle with old method : 0.0036754608154296875 length of segment : 156 time for calcul the mask position with numpy : 0.00010609626770019531 nb_pixel_total : 260 time to create 1 rle with old method : 0.0004794597625732422 length of segment : 55 time for calcul the mask position with numpy : 0.00014066696166992188 nb_pixel_total : 2354 time to create 1 rle with old method : 0.002995729446411133 length of segment : 50 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003314018249511719 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: -123.70000 max: 150.85391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 4487 time to create 1 rle with old method : 0.005221366882324219 length of segment : 81 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.00037479400634765625 length of segment : 22 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 217.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 95.48125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0004439353942871094 nb_pixel_total : 29823 time to create 1 rle with old method : 0.036939382553100586 length of segment : 579 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 2026 time to create 1 rle with old method : 0.002817869186401367 length of segment : 38 time for calcul the mask position with numpy : 0.0001468658447265625 nb_pixel_total : 6256 time to create 1 rle with old method : 0.008699178695678711 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: 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 : 5.459785461425781e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.0004253387451171875 length of segment : 16 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002753734588623047 length of segment : 17 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0009374618530273438 length of segment : 29 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0004119873046875 length of segment : 12 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 407 time to create 1 rle with old method : 0.0007166862487792969 length of segment : 23 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0009562969207763672 length of segment : 28 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0007085800170898438 length of segment : 21 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 : 8 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.00048160552978515625 length of segment : 18 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0003745555877685547 length of segment : 20 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.00030040740966796875 length of segment : 27 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 2075 time to create 1 rle with old method : 0.0037186145782470703 length of segment : 50 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0011644363403320312 length of segment : 36 time for calcul the mask position with numpy : 0.00010824203491210938 nb_pixel_total : 690 time to create 1 rle with old method : 0.001645803451538086 length of segment : 29 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0008766651153564453 length of segment : 26 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 491 time to create 1 rle with old method : 0.0010967254638671875 length of segment : 27 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 : 10 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00027561187744140625 length of segment : 13 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0016837120056152344 length of segment : 37 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0006406307220458984 length of segment : 24 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 157 time to create 1 rle with old method : 0.00025010108947753906 length of segment : 14 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0005044937133789062 length of segment : 47 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00038695335388183594 length of segment : 16 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005319118499755859 length of segment : 26 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005402565002441406 length of segment : 25 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002727508544921875 length of segment : 18 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 1733 time to create 1 rle with old method : 0.002402782440185547 length of segment : 76 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 : 15 time for calcul the mask position with numpy : 0.00014472007751464844 nb_pixel_total : 983 time to create 1 rle with old method : 0.0024373531341552734 length of segment : 38 time for calcul the mask position with numpy : 0.00015211105346679688 nb_pixel_total : 751 time to create 1 rle with old method : 0.00167083740234375 length of segment : 26 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 1639 time to create 1 rle with old method : 0.0029892921447753906 length of segment : 70 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0011837482452392578 length of segment : 33 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 241 time to create 1 rle with old method : 0.00052642822265625 length of segment : 20 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0009255409240722656 length of segment : 42 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1175 time to create 1 rle with old method : 0.0018024444580078125 length of segment : 42 time for calcul the mask position with numpy : 8.7738037109375e-05 nb_pixel_total : 806 time to create 1 rle with old method : 0.0014312267303466797 length of segment : 32 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.0010268688201904297 length of segment : 22 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00024247169494628906 length of segment : 12 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 1092 time to create 1 rle with old method : 0.0020728111267089844 length of segment : 49 time for calcul the mask position with numpy : 0.0002589225769042969 nb_pixel_total : 3099 time to create 1 rle with old method : 0.005780935287475586 length of segment : 100 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.00022554397583007812 length of segment : 9 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0004181861877441406 length of segment : 18 time for calcul the mask position with numpy : 0.00039005279541015625 nb_pixel_total : 4401 time to create 1 rle with old method : 0.008998394012451172 length of segment : 90 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 : 18 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 1318 time to create 1 rle with old method : 0.002332925796508789 length of segment : 62 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0012743473052978516 length of segment : 18 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 1302 time to create 1 rle with old method : 0.0018506050109863281 length of segment : 54 time for calcul the mask position with numpy : 0.0003807544708251953 nb_pixel_total : 9938 time to create 1 rle with old method : 0.01253366470336914 length of segment : 181 time for calcul the mask position with numpy : 0.00030112266540527344 nb_pixel_total : 3992 time to create 1 rle with old method : 0.0061261653900146484 length of segment : 163 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 1409 time to create 1 rle with old method : 0.0018389225006103516 length of segment : 57 time for calcul the mask position with numpy : 0.0001373291015625 nb_pixel_total : 4644 time to create 1 rle with old method : 0.005577564239501953 length of segment : 103 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.00020694732666015625 length of segment : 12 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 4812 time to create 1 rle with old method : 0.006339073181152344 length of segment : 104 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 512 time to create 1 rle with old method : 0.0007343292236328125 length of segment : 87 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.0003437995910644531 length of segment : 14 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 946 time to create 1 rle with old method : 0.002071857452392578 length of segment : 19 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003800392150878906 length of segment : 27 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 37 time to create 1 rle with old method : 0.00012183189392089844 length of segment : 10 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1077 time to create 1 rle with old method : 0.0017275810241699219 length of segment : 32 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0006461143493652344 length of segment : 31 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 561 time to create 1 rle with old method : 0.0008852481842041016 length of segment : 25 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0009691715240478516 length of segment : 29 Processing 1 images image shape: (240, 400, 3) min: 56.00000 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 : 0 Processing 1 images image shape: (240, 160, 3) min: 48.00000 max: 235.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 115.91056 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0008857250213623047 length of segment : 30 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 896 time to create 1 rle with old method : 0.0015957355499267578 length of segment : 66 Detection mask done ! Trying to reset tf kernel 737890 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1804 tf kernel not reseted sub process len(results) : 493 len(list_Values) 493 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 493 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 : 2997 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 493 chid ids of type : 4228 Number RLEs to save : 20464 save missing photos in datou_result : time spend for datou_step_exec : 27.4954833984375 time spend to save output : 1.4781131744384766 total time spend for step 1 : 28.973596572875977 step2:brightness Thu Feb 13 17:20:59 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1739463629_737127_1337395425_0397972abcd96b30fb20a09b0a832a2c.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 : 1 time used for this insertion : 0.01166987419128418 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.011054515838623047 save missing photos in datou_result : time spend for datou_step_exec : 0.5346941947937012 time spend to save output : 0.027315139770507812 total time spend for step 2 : 0.562009334564209 step3:blur_detection Thu Feb 13 17:20:59 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1739463629_737127_1337395425_0397972abcd96b30fb20a09b0a832a2c.jpg resize: (1440, 2560) 1337395425 -8.494529715002352 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 : 1 time used for this insertion : 0.5094418525695801 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.014077901840209961 save missing photos in datou_result : time spend for datou_step_exec : 2.3006467819213867 time spend to save output : 0.5282242298126221 total time spend for step 3 : 2.828871011734009 step4:rle_unique_nms_with_priority Thu Feb 13 17:21:02 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 493 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 490 nb_hashtags : 6 time to prepare the origin masks : 2.145052433013916 time for calcul the mask position with numpy : 0.2974424362182617 nb_pixel_total : 3223763 time to create 1 rle with new method : 0.4278066158294678 time for calcul the mask position with numpy : 0.015154600143432617 nb_pixel_total : 278 time to create 1 rle with old method : 0.00038051605224609375 time for calcul the mask position with numpy : 0.015018224716186523 nb_pixel_total : 69 time to create 1 rle with old method : 0.00011110305786132812 time for calcul the mask position with numpy : 0.01528620719909668 nb_pixel_total : 120 time to create 1 rle with old method : 0.00017762184143066406 time for calcul the mask position with numpy : 0.015224218368530273 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002541542053222656 time for calcul the mask position with numpy : 0.015042543411254883 nb_pixel_total : 2478 time to create 1 rle with old method : 0.00276947021484375 time for calcul the mask position with numpy : 0.015081644058227539 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003120899200439453 time for calcul the mask position with numpy : 0.015564918518066406 nb_pixel_total : 72 time to create 1 rle with old method : 0.0001232624053955078 time for calcul the mask position with numpy : 0.015555143356323242 nb_pixel_total : 1231 time to create 1 rle with old method : 0.0014643669128417969 time for calcul the mask position with numpy : 0.015235424041748047 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003066062927246094 time for calcul the mask position with numpy : 0.015634536743164062 nb_pixel_total : 792 time to create 1 rle with old method : 0.0010001659393310547 time for calcul the mask position with numpy : 0.016263246536254883 nb_pixel_total : 164 time to create 1 rle with old method : 0.00023603439331054688 time for calcul the mask position with numpy : 0.01570415496826172 nb_pixel_total : 504 time to create 1 rle with old method : 0.0006330013275146484 time for calcul the mask position with numpy : 0.015642642974853516 nb_pixel_total : 72 time to create 1 rle with old method : 0.00013375282287597656 time for calcul the mask position with numpy : 0.016707181930541992 nb_pixel_total : 795 time to create 1 rle with old method : 0.0009632110595703125 time for calcul the mask position with numpy : 0.01542973518371582 nb_pixel_total : 119 time to create 1 rle with old method : 0.0001990795135498047 time for calcul the mask position with numpy : 0.015552282333374023 nb_pixel_total : 846 time to create 1 rle with old method : 0.001055002212524414 time for calcul the mask position with numpy : 0.015480756759643555 nb_pixel_total : 107 time to create 1 rle with old method : 0.0002868175506591797 time for calcul the mask position with numpy : 0.015627384185791016 nb_pixel_total : 188 time to create 1 rle with old method : 0.00024080276489257812 time for calcul the mask position with numpy : 0.01771235466003418 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003173351287841797 time for calcul the mask position with numpy : 0.015533447265625 nb_pixel_total : 534 time to create 1 rle with old method : 0.0006799697875976562 time for calcul the mask position with numpy : 0.015552759170532227 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002753734588623047 time for calcul the mask position with numpy : 0.015975475311279297 nb_pixel_total : 66 time to create 1 rle with old method : 0.00010776519775390625 time for calcul the mask position with numpy : 0.01584029197692871 nb_pixel_total : 202 time to create 1 rle with old method : 0.00031375885009765625 time for calcul the mask position with numpy : 0.017787694931030273 nb_pixel_total : 1335 time to create 1 rle with old method : 0.002493143081665039 time for calcul the mask position with numpy : 0.018197059631347656 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005505084991455078 time for calcul the mask position with numpy : 0.017993450164794922 nb_pixel_total : 548 time to create 1 rle with old method : 0.0007801055908203125 time for calcul the mask position with numpy : 0.020078182220458984 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001666545867919922 time for calcul the mask position with numpy : 0.02074742317199707 nb_pixel_total : 1028 time to create 1 rle with old method : 0.0014717578887939453 time for calcul the mask position with numpy : 0.0194852352142334 nb_pixel_total : 1025 time to create 1 rle with old method : 0.001547098159790039 time for calcul the mask position with numpy : 0.01972508430480957 nb_pixel_total : 607 time to create 1 rle with old method : 0.0008633136749267578 time for calcul the mask position with numpy : 0.019304275512695312 nb_pixel_total : 962 time to create 1 rle with old method : 0.0014383792877197266 time for calcul the mask position with numpy : 0.01874852180480957 nb_pixel_total : 954 time to create 1 rle with old method : 0.0015308856964111328 time for calcul the mask position with numpy : 0.019305706024169922 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003120899200439453 time for calcul the mask position with numpy : 0.01587533950805664 nb_pixel_total : 473 time to create 1 rle with old method : 0.0005819797515869141 time for calcul the mask position with numpy : 0.0170748233795166 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005447864532470703 time for calcul the mask position with numpy : 0.017818450927734375 nb_pixel_total : 1042 time to create 1 rle with old method : 0.0013477802276611328 time for calcul the mask position with numpy : 0.015266895294189453 nb_pixel_total : 1063 time to create 1 rle with old method : 0.0012555122375488281 time for calcul the mask position with numpy : 0.01778244972229004 nb_pixel_total : 466 time to create 1 rle with old method : 0.0007050037384033203 time for calcul the mask position with numpy : 0.01641845703125 nb_pixel_total : 207 time to create 1 rle with old method : 0.0003631114959716797 time for calcul the mask position with numpy : 0.017284393310546875 nb_pixel_total : 423 time to create 1 rle with old method : 0.0007183551788330078 time for calcul the mask position with numpy : 0.017798423767089844 nb_pixel_total : 394 time to create 1 rle with old method : 0.0006601810455322266 time for calcul the mask position with numpy : 0.018240690231323242 nb_pixel_total : 175 time to create 1 rle with old method : 0.00037360191345214844 time for calcul the mask position with numpy : 0.018294095993041992 nb_pixel_total : 704 time to create 1 rle with old method : 0.0011785030364990234 time for calcul the mask position with numpy : 0.015952348709106445 nb_pixel_total : 201 time to create 1 rle with old method : 0.000385284423828125 time for calcul the mask position with numpy : 0.017981290817260742 nb_pixel_total : 535 time to create 1 rle with old method : 0.001010894775390625 time for calcul the mask position with numpy : 0.016974210739135742 nb_pixel_total : 74 time to create 1 rle with old method : 0.00011277198791503906 time for calcul the mask position with numpy : 0.01600933074951172 nb_pixel_total : 91 time to create 1 rle with old method : 0.00014138221740722656 time for calcul the mask position with numpy : 0.015503644943237305 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002892017364501953 time for calcul the mask position with numpy : 0.016658544540405273 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0014629364013671875 time for calcul the mask position with numpy : 0.017778873443603516 nb_pixel_total : 891 time to create 1 rle with old method : 0.0011353492736816406 time for calcul the mask position with numpy : 0.01595902442932129 nb_pixel_total : 1744 time to create 1 rle with old method : 0.002070903778076172 time for calcul the mask position with numpy : 0.015499353408813477 nb_pixel_total : 299 time to create 1 rle with old method : 0.0003902912139892578 time for calcul the mask position with numpy : 0.015897750854492188 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002815723419189453 time for calcul the mask position with numpy : 0.015602588653564453 nb_pixel_total : 4095 time to create 1 rle with old method : 0.004784107208251953 time for calcul the mask position with numpy : 0.016790151596069336 nb_pixel_total : 164 time to create 1 rle with old method : 0.00022029876708984375 time for calcul the mask position with numpy : 0.015782594680786133 nb_pixel_total : 664 time to create 1 rle with old method : 0.0010559558868408203 time for calcul the mask position with numpy : 0.01701807975769043 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002052783966064453 time for calcul the mask position with numpy : 0.01804351806640625 nb_pixel_total : 2698 time to create 1 rle with old method : 0.004024505615234375 time for calcul the mask position with numpy : 0.018851280212402344 nb_pixel_total : 5374 time to create 1 rle with old method : 0.006476402282714844 time for calcul the mask position with numpy : 0.015270233154296875 nb_pixel_total : 609 time to create 1 rle with old method : 0.0007710456848144531 time for calcul the mask position with numpy : 0.01504063606262207 nb_pixel_total : 83 time to create 1 rle with old method : 0.0002105236053466797 time for calcul the mask position with numpy : 0.015233755111694336 nb_pixel_total : 90 time to create 1 rle with old method : 0.00034046173095703125 time for calcul the mask position with numpy : 0.017882585525512695 nb_pixel_total : 32925 time to create 1 rle with old method : 0.04231381416320801 time for calcul the mask position with numpy : 0.015291213989257812 nb_pixel_total : 699 time to create 1 rle with old method : 0.0008566379547119141 time for calcul the mask position with numpy : 0.015312671661376953 nb_pixel_total : 104 time to create 1 rle with old method : 0.0001747608184814453 time for calcul the mask position with numpy : 0.017318248748779297 nb_pixel_total : 294 time to create 1 rle with old method : 0.0004119873046875 time for calcul the mask position with numpy : 0.015423774719238281 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003409385681152344 time for calcul the mask position with numpy : 0.015324115753173828 nb_pixel_total : 466 time to create 1 rle with old method : 0.0005948543548583984 time for calcul the mask position with numpy : 0.015400886535644531 nb_pixel_total : 708 time to create 1 rle with old method : 0.0008933544158935547 time for calcul the mask position with numpy : 0.015458106994628906 nb_pixel_total : 755 time to create 1 rle with old method : 0.0009214878082275391 time for calcul the mask position with numpy : 0.01501917839050293 nb_pixel_total : 140 time to create 1 rle with old method : 0.00019502639770507812 time for calcul the mask position with numpy : 0.014954090118408203 nb_pixel_total : 510 time to create 1 rle with old method : 0.0006113052368164062 time for calcul the mask position with numpy : 0.015227794647216797 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001704692840576172 time for calcul the mask position with numpy : 0.014988899230957031 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003504753112792969 time for calcul the mask position with numpy : 0.01505732536315918 nb_pixel_total : 447 time to create 1 rle with old method : 0.000553131103515625 time for calcul the mask position with numpy : 0.015130043029785156 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003063678741455078 time for calcul the mask position with numpy : 0.015372753143310547 nb_pixel_total : 333 time to create 1 rle with old method : 0.00040721893310546875 time for calcul the mask position with numpy : 0.015213489532470703 nb_pixel_total : 1314 time to create 1 rle with old method : 0.0015265941619873047 time for calcul the mask position with numpy : 0.015146255493164062 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002639293670654297 time for calcul the mask position with numpy : 0.01555776596069336 nb_pixel_total : 136 time to create 1 rle with old method : 0.000213623046875 time for calcul the mask position with numpy : 0.01559591293334961 nb_pixel_total : 454 time to create 1 rle with old method : 0.0007171630859375 time for calcul the mask position with numpy : 0.017143726348876953 nb_pixel_total : 361 time to create 1 rle with old method : 0.00047659873962402344 time for calcul the mask position with numpy : 0.01649641990661621 nb_pixel_total : 1182 time to create 1 rle with old method : 0.001988649368286133 time for calcul the mask position with numpy : 0.017589330673217773 nb_pixel_total : 382 time to create 1 rle with old method : 0.0006852149963378906 time for calcul the mask position with numpy : 0.017617464065551758 nb_pixel_total : 2269 time to create 1 rle with old method : 0.0038018226623535156 time for calcul the mask position with numpy : 0.017640352249145508 nb_pixel_total : 392 time to create 1 rle with old method : 0.0006964206695556641 time for calcul the mask position with numpy : 0.016210079193115234 nb_pixel_total : 409 time to create 1 rle with old method : 0.0005102157592773438 time for calcul the mask position with numpy : 0.015415430068969727 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003025531768798828 time for calcul the mask position with numpy : 0.015544652938842773 nb_pixel_total : 1455 time to create 1 rle with old method : 0.0017518997192382812 time for calcul the mask position with numpy : 0.015526056289672852 nb_pixel_total : 466 time to create 1 rle with old method : 0.0005815029144287109 time for calcul the mask position with numpy : 0.015568256378173828 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005097389221191406 time for calcul the mask position with numpy : 0.015489816665649414 nb_pixel_total : 4 time to create 1 rle with old method : 3.3855438232421875e-05 time for calcul the mask position with numpy : 0.015474557876586914 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006973743438720703 time for calcul the mask position with numpy : 0.015795230865478516 nb_pixel_total : 1878 time to create 1 rle with old method : 0.0022225379943847656 time for calcul the mask position with numpy : 0.015804290771484375 nb_pixel_total : 1973 time to create 1 rle with old method : 0.002320528030395508 time for calcul the mask position with numpy : 0.015722036361694336 nb_pixel_total : 1874 time to create 1 rle with old method : 0.002328634262084961 time for calcul the mask position with numpy : 0.017215490341186523 nb_pixel_total : 1540 time to create 1 rle with old method : 0.0024886131286621094 time for calcul the mask position with numpy : 0.018307209014892578 nb_pixel_total : 31 time to create 1 rle with old method : 8.463859558105469e-05 time for calcul the mask position with numpy : 0.01529550552368164 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006158351898193359 time for calcul the mask position with numpy : 0.01528167724609375 nb_pixel_total : 225 time to create 1 rle with old method : 0.0002925395965576172 time for calcul the mask position with numpy : 0.015300989151000977 nb_pixel_total : 1935 time to create 1 rle with old method : 0.002294778823852539 time for calcul the mask position with numpy : 0.017193078994750977 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005545616149902344 time for calcul the mask position with numpy : 0.01642465591430664 nb_pixel_total : 637 time to create 1 rle with old method : 0.0007700920104980469 time for calcul the mask position with numpy : 0.014973640441894531 nb_pixel_total : 3360 time to create 1 rle with old method : 0.0038313865661621094 time for calcul the mask position with numpy : 0.015033960342407227 nb_pixel_total : 1143 time to create 1 rle with old method : 0.001978635787963867 time for calcul the mask position with numpy : 0.01737666130065918 nb_pixel_total : 260 time to create 1 rle with old method : 0.00032973289489746094 time for calcul the mask position with numpy : 0.015184640884399414 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005235671997070312 time for calcul the mask position with numpy : 0.015038251876831055 nb_pixel_total : 616 time to create 1 rle with old method : 0.0007579326629638672 time for calcul the mask position with numpy : 0.015033245086669922 nb_pixel_total : 1687 time to create 1 rle with old method : 0.0020928382873535156 time for calcul the mask position with numpy : 0.015082120895385742 nb_pixel_total : 169 time to create 1 rle with old method : 0.00023818016052246094 time for calcul the mask position with numpy : 0.015123844146728516 nb_pixel_total : 846 time to create 1 rle with old method : 0.0010228157043457031 time for calcul the mask position with numpy : 0.015065193176269531 nb_pixel_total : 859 time to create 1 rle with old method : 0.0010943412780761719 time for calcul the mask position with numpy : 0.015108108520507812 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003230571746826172 time for calcul the mask position with numpy : 0.015227079391479492 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006999969482421875 time for calcul the mask position with numpy : 0.01538538932800293 nb_pixel_total : 1061 time to create 1 rle with old method : 0.0013439655303955078 time for calcul the mask position with numpy : 0.015190362930297852 nb_pixel_total : 36 time to create 1 rle with old method : 9.34600830078125e-05 time for calcul the mask position with numpy : 0.015495538711547852 nb_pixel_total : 945 time to create 1 rle with old method : 0.0011827945709228516 time for calcul the mask position with numpy : 0.017443180084228516 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003371238708496094 time for calcul the mask position with numpy : 0.015499591827392578 nb_pixel_total : 244 time to create 1 rle with old method : 0.00031566619873046875 time for calcul the mask position with numpy : 0.015374898910522461 nb_pixel_total : 544 time to create 1 rle with old method : 0.0006892681121826172 time for calcul the mask position with numpy : 0.01528310775756836 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003147125244140625 time for calcul the mask position with numpy : 0.01745462417602539 nb_pixel_total : 338 time to create 1 rle with old method : 0.0005424022674560547 time for calcul the mask position with numpy : 0.015588045120239258 nb_pixel_total : 187 time to create 1 rle with old method : 0.0003132820129394531 time for calcul the mask position with numpy : 0.015629053115844727 nb_pixel_total : 122 time to create 1 rle with old method : 0.0001780986785888672 time for calcul the mask position with numpy : 0.015397310256958008 nb_pixel_total : 200 time to create 1 rle with old method : 0.0002551078796386719 time for calcul the mask position with numpy : 0.015357017517089844 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004763603210449219 time for calcul the mask position with numpy : 0.01742863655090332 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0017132759094238281 time for calcul the mask position with numpy : 0.0187985897064209 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001583099365234375 time for calcul the mask position with numpy : 0.015322685241699219 nb_pixel_total : 419 time to create 1 rle with old method : 0.0005321502685546875 time for calcul the mask position with numpy : 0.015588760375976562 nb_pixel_total : 922 time to create 1 rle with old method : 0.0011248588562011719 time for calcul the mask position with numpy : 0.015930652618408203 nb_pixel_total : 116 time to create 1 rle with old method : 0.00018310546875 time for calcul the mask position with numpy : 0.015613794326782227 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005214214324951172 time for calcul the mask position with numpy : 0.015324115753173828 nb_pixel_total : 43 time to create 1 rle with old method : 0.00010347366333007812 time for calcul the mask position with numpy : 0.015353202819824219 nb_pixel_total : 923 time to create 1 rle with old method : 0.0010571479797363281 time for calcul the mask position with numpy : 0.01522517204284668 nb_pixel_total : 345 time to create 1 rle with old method : 0.0004525184631347656 time for calcul the mask position with numpy : 0.015581369400024414 nb_pixel_total : 806 time to create 1 rle with old method : 0.0009872913360595703 time for calcul the mask position with numpy : 0.015704870223999023 nb_pixel_total : 704 time to create 1 rle with old method : 0.0008785724639892578 time for calcul the mask position with numpy : 0.015282630920410156 nb_pixel_total : 143 time to create 1 rle with old method : 0.0001926422119140625 time for calcul the mask position with numpy : 0.015224218368530273 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003199577331542969 time for calcul the mask position with numpy : 0.017402172088623047 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003726482391357422 time for calcul the mask position with numpy : 0.01761031150817871 nb_pixel_total : 51 time to create 1 rle with old method : 0.00012803077697753906 time for calcul the mask position with numpy : 0.017450571060180664 nb_pixel_total : 2757 time to create 1 rle with old method : 0.004964113235473633 time for calcul the mask position with numpy : 0.023722171783447266 nb_pixel_total : 421 time to create 1 rle with old method : 0.0007965564727783203 time for calcul the mask position with numpy : 0.01629471778869629 nb_pixel_total : 135 time to create 1 rle with old method : 0.00018715858459472656 time for calcul the mask position with numpy : 0.015807151794433594 nb_pixel_total : 2584 time to create 1 rle with old method : 0.0030624866485595703 time for calcul the mask position with numpy : 0.01621699333190918 nb_pixel_total : 31 time to create 1 rle with old method : 6.961822509765625e-05 time for calcul the mask position with numpy : 0.015673160552978516 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002434253692626953 time for calcul the mask position with numpy : 0.015490531921386719 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001499652862548828 time for calcul the mask position with numpy : 0.015573501586914062 nb_pixel_total : 42 time to create 1 rle with old method : 7.843971252441406e-05 time for calcul the mask position with numpy : 0.017723798751831055 nb_pixel_total : 175 time to create 1 rle with old method : 0.00029349327087402344 time for calcul the mask position with numpy : 0.015549421310424805 nb_pixel_total : 149 time to create 1 rle with old method : 0.00026345252990722656 time for calcul the mask position with numpy : 0.01781630516052246 nb_pixel_total : 1486 time to create 1 rle with old method : 0.0019109249114990234 time for calcul the mask position with numpy : 0.015697717666625977 nb_pixel_total : 11 time to create 1 rle with old method : 9.202957153320312e-05 time for calcul the mask position with numpy : 0.015485048294067383 nb_pixel_total : 387 time to create 1 rle with old method : 0.0005688667297363281 time for calcul the mask position with numpy : 0.015514850616455078 nb_pixel_total : 122 time to create 1 rle with old method : 0.0002071857452392578 time for calcul the mask position with numpy : 0.015850543975830078 nb_pixel_total : 36 time to create 1 rle with old method : 8.940696716308594e-05 time for calcul the mask position with numpy : 0.015591859817504883 nb_pixel_total : 537 time to create 1 rle with old method : 0.0006642341613769531 time for calcul the mask position with numpy : 0.018801450729370117 nb_pixel_total : 71 time to create 1 rle with old method : 0.00011897087097167969 time for calcul the mask position with numpy : 0.0152740478515625 nb_pixel_total : 333 time to create 1 rle with old method : 0.00042724609375 time for calcul the mask position with numpy : 0.015529632568359375 nb_pixel_total : 382 time to create 1 rle with old method : 0.0004799365997314453 time for calcul the mask position with numpy : 0.015695810317993164 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004627704620361328 time for calcul the mask position with numpy : 0.015506505966186523 nb_pixel_total : 214 time to create 1 rle with old method : 0.0002601146697998047 time for calcul the mask position with numpy : 0.015530824661254883 nb_pixel_total : 529 time to create 1 rle with old method : 0.0006394386291503906 time for calcul the mask position with numpy : 0.015563011169433594 nb_pixel_total : 481 time to create 1 rle with old method : 0.0006041526794433594 time for calcul the mask position with numpy : 0.015905141830444336 nb_pixel_total : 367 time to create 1 rle with old method : 0.0007975101470947266 time for calcul the mask position with numpy : 0.016623497009277344 nb_pixel_total : 131 time to create 1 rle with old method : 0.00018739700317382812 time for calcul the mask position with numpy : 0.01562190055847168 nb_pixel_total : 10343 time to create 1 rle with old method : 0.016750335693359375 time for calcul the mask position with numpy : 0.017843961715698242 nb_pixel_total : 964 time to create 1 rle with old method : 0.0017189979553222656 time for calcul the mask position with numpy : 0.017816543579101562 nb_pixel_total : 456 time to create 1 rle with old method : 0.0007891654968261719 time for calcul the mask position with numpy : 0.017626047134399414 nb_pixel_total : 249 time to create 1 rle with old method : 0.0004909038543701172 time for calcul the mask position with numpy : 0.016228199005126953 nb_pixel_total : 1591 time to create 1 rle with old method : 0.001983642578125 time for calcul the mask position with numpy : 0.015579700469970703 nb_pixel_total : 202 time to create 1 rle with old method : 0.00029087066650390625 time for calcul the mask position with numpy : 0.015589237213134766 nb_pixel_total : 152 time to create 1 rle with old method : 0.00021529197692871094 time for calcul the mask position with numpy : 0.015429496765136719 nb_pixel_total : 409 time to create 1 rle with old method : 0.0004978179931640625 time for calcul the mask position with numpy : 0.015581607818603516 nb_pixel_total : 68 time to create 1 rle with old method : 0.00014352798461914062 time for calcul the mask position with numpy : 0.015605449676513672 nb_pixel_total : 221 time to create 1 rle with old method : 0.00027489662170410156 time for calcul the mask position with numpy : 0.015388011932373047 nb_pixel_total : 227 time to create 1 rle with old method : 0.00028777122497558594 time for calcul the mask position with numpy : 0.015291929244995117 nb_pixel_total : 196 time to create 1 rle with old method : 0.00030922889709472656 time for calcul the mask position with numpy : 0.015240669250488281 nb_pixel_total : 1773 time to create 1 rle with old method : 0.0022125244140625 time for calcul the mask position with numpy : 0.015260457992553711 nb_pixel_total : 628 time to create 1 rle with old method : 0.0007739067077636719 time for calcul the mask position with numpy : 0.015231847763061523 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003762245178222656 time for calcul the mask position with numpy : 0.015273094177246094 nb_pixel_total : 58 time to create 1 rle with old method : 0.00010824203491210938 time for calcul the mask position with numpy : 0.015194892883300781 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005724430084228516 time for calcul the mask position with numpy : 0.015203714370727539 nb_pixel_total : 266 time to create 1 rle with old method : 0.0003535747528076172 time for calcul the mask position with numpy : 0.01672959327697754 nb_pixel_total : 82 time to create 1 rle with old method : 0.00013256072998046875 time for calcul the mask position with numpy : 0.015077829360961914 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005321502685546875 time for calcul the mask position with numpy : 0.015789270401000977 nb_pixel_total : 1174 time to create 1 rle with old method : 0.001461029052734375 time for calcul the mask position with numpy : 0.015508890151977539 nb_pixel_total : 685 time to create 1 rle with old method : 0.0008609294891357422 time for calcul the mask position with numpy : 0.017998933792114258 nb_pixel_total : 337 time to create 1 rle with old method : 0.00042700767517089844 time for calcul the mask position with numpy : 0.015329599380493164 nb_pixel_total : 204 time to create 1 rle with old method : 0.0003628730773925781 time for calcul the mask position with numpy : 0.015728235244750977 nb_pixel_total : 1537 time to create 1 rle with old method : 0.001905679702758789 time for calcul the mask position with numpy : 0.015223264694213867 nb_pixel_total : 840 time to create 1 rle with old method : 0.0010018348693847656 time for calcul the mask position with numpy : 0.016787290573120117 nb_pixel_total : 770 time to create 1 rle with old method : 0.0009455680847167969 time for calcul the mask position with numpy : 0.01528477668762207 nb_pixel_total : 1144 time to create 1 rle with old method : 0.001356363296508789 time for calcul the mask position with numpy : 0.01526188850402832 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003523826599121094 time for calcul the mask position with numpy : 0.01687765121459961 nb_pixel_total : 1284 time to create 1 rle with old method : 0.0016720294952392578 time for calcul the mask position with numpy : 0.01792144775390625 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003848075866699219 time for calcul the mask position with numpy : 0.016812801361083984 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004868507385253906 time for calcul the mask position with numpy : 0.01557469367980957 nb_pixel_total : 14 time to create 1 rle with old method : 4.6253204345703125e-05 time for calcul the mask position with numpy : 0.015256643295288086 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005614757537841797 time for calcul the mask position with numpy : 0.015234947204589844 nb_pixel_total : 311 time to create 1 rle with old method : 0.00044918060302734375 time for calcul the mask position with numpy : 0.015265703201293945 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003306865692138672 time for calcul the mask position with numpy : 0.01528620719909668 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004305839538574219 time for calcul the mask position with numpy : 0.016393184661865234 nb_pixel_total : 307 time to create 1 rle with old method : 0.0004608631134033203 time for calcul the mask position with numpy : 0.01651930809020996 nb_pixel_total : 9524 time to create 1 rle with old method : 0.010523796081542969 time for calcul the mask position with numpy : 0.015296697616577148 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003399848937988281 time for calcul the mask position with numpy : 0.015327930450439453 nb_pixel_total : 625 time to create 1 rle with old method : 0.0007464885711669922 time for calcul the mask position with numpy : 0.017072439193725586 nb_pixel_total : 27 time to create 1 rle with old method : 8.654594421386719e-05 time for calcul the mask position with numpy : 0.015439987182617188 nb_pixel_total : 1364 time to create 1 rle with old method : 0.0015914440155029297 time for calcul the mask position with numpy : 0.01529383659362793 nb_pixel_total : 68 time to create 1 rle with old method : 0.00010657310485839844 time for calcul the mask position with numpy : 0.015228986740112305 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006327629089355469 time for calcul the mask position with numpy : 0.015360116958618164 nb_pixel_total : 3701 time to create 1 rle with old method : 0.004139900207519531 time for calcul the mask position with numpy : 0.015321969985961914 nb_pixel_total : 285 time to create 1 rle with old method : 0.00046181678771972656 time for calcul the mask position with numpy : 0.015303611755371094 nb_pixel_total : 2108 time to create 1 rle with old method : 0.002438783645629883 time for calcul the mask position with numpy : 0.015288352966308594 nb_pixel_total : 2775 time to create 1 rle with old method : 0.0031812191009521484 time for calcul the mask position with numpy : 0.017554044723510742 nb_pixel_total : 379 time to create 1 rle with old method : 0.00046896934509277344 time for calcul the mask position with numpy : 0.015329122543334961 nb_pixel_total : 184 time to create 1 rle with old method : 0.0002467632293701172 time for calcul the mask position with numpy : 0.015320777893066406 nb_pixel_total : 1130 time to create 1 rle with old method : 0.0013418197631835938 time for calcul the mask position with numpy : 0.015267372131347656 nb_pixel_total : 250 time to create 1 rle with old method : 0.00034546852111816406 time for calcul the mask position with numpy : 0.015318870544433594 nb_pixel_total : 1352 time to create 1 rle with old method : 0.0016145706176757812 time for calcul the mask position with numpy : 0.015337467193603516 nb_pixel_total : 125 time to create 1 rle with old method : 0.00017261505126953125 time for calcul the mask position with numpy : 0.016178607940673828 nb_pixel_total : 79 time to create 1 rle with old method : 0.00013256072998046875 time for calcul the mask position with numpy : 0.015347957611083984 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004291534423828125 time for calcul the mask position with numpy : 0.015477657318115234 nb_pixel_total : 1295 time to create 1 rle with old method : 0.0015728473663330078 time for calcul the mask position with numpy : 0.015469074249267578 nb_pixel_total : 804 time to create 1 rle with old method : 0.0009715557098388672 time for calcul the mask position with numpy : 0.015416383743286133 nb_pixel_total : 573 time to create 1 rle with old method : 0.0006780624389648438 time for calcul the mask position with numpy : 0.015301942825317383 nb_pixel_total : 745 time to create 1 rle with old method : 0.0009059906005859375 time for calcul the mask position with numpy : 0.01524972915649414 nb_pixel_total : 78 time to create 1 rle with old method : 0.00014925003051757812 time for calcul the mask position with numpy : 0.01752161979675293 nb_pixel_total : 5250 time to create 1 rle with old method : 0.0059566497802734375 time for calcul the mask position with numpy : 0.015206575393676758 nb_pixel_total : 489 time to create 1 rle with old method : 0.0005977153778076172 time for calcul the mask position with numpy : 0.015272855758666992 nb_pixel_total : 80 time to create 1 rle with old method : 0.00015807151794433594 time for calcul the mask position with numpy : 0.015302896499633789 nb_pixel_total : 1784 time to create 1 rle with old method : 0.0020558834075927734 time for calcul the mask position with numpy : 0.01530313491821289 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0012738704681396484 time for calcul the mask position with numpy : 0.015374898910522461 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006380081176757812 time for calcul the mask position with numpy : 0.01532125473022461 nb_pixel_total : 175 time to create 1 rle with old method : 0.0005939006805419922 time for calcul the mask position with numpy : 0.015371322631835938 nb_pixel_total : 986 time to create 1 rle with old method : 0.0015382766723632812 time for calcul the mask position with numpy : 0.015401601791381836 nb_pixel_total : 32 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.015439033508300781 nb_pixel_total : 60 time to create 1 rle with old method : 0.00011110305786132812 time for calcul the mask position with numpy : 0.01531362533569336 nb_pixel_total : 972 time to create 1 rle with old method : 0.0011792182922363281 time for calcul the mask position with numpy : 0.015379905700683594 nb_pixel_total : 682 time to create 1 rle with old method : 0.0008182525634765625 time for calcul the mask position with numpy : 0.01528167724609375 nb_pixel_total : 350 time to create 1 rle with old method : 0.00045037269592285156 time for calcul the mask position with numpy : 0.015453815460205078 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006020069122314453 time for calcul the mask position with numpy : 0.015297651290893555 nb_pixel_total : 204 time to create 1 rle with old method : 0.00028324127197265625 time for calcul the mask position with numpy : 0.015432357788085938 nb_pixel_total : 228 time to create 1 rle with old method : 0.00031113624572753906 time for calcul the mask position with numpy : 0.015369892120361328 nb_pixel_total : 489 time to create 1 rle with old method : 0.0005860328674316406 time for calcul the mask position with numpy : 0.015350580215454102 nb_pixel_total : 212 time to create 1 rle with old method : 0.0002682209014892578 time for calcul the mask position with numpy : 0.01520538330078125 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003120899200439453 time for calcul the mask position with numpy : 0.015259265899658203 nb_pixel_total : 89 time to create 1 rle with old method : 0.00013899803161621094 time for calcul the mask position with numpy : 0.01522970199584961 nb_pixel_total : 2832 time to create 1 rle with old method : 0.0032854080200195312 time for calcul the mask position with numpy : 0.015427589416503906 nb_pixel_total : 466 time to create 1 rle with old method : 0.0005774497985839844 time for calcul the mask position with numpy : 0.01537013053894043 nb_pixel_total : 157 time to create 1 rle with old method : 0.0002117156982421875 time for calcul the mask position with numpy : 0.01784515380859375 nb_pixel_total : 2849 time to create 1 rle with old method : 0.0033731460571289062 time for calcul the mask position with numpy : 0.015565633773803711 nb_pixel_total : 1287 time to create 1 rle with old method : 0.001516580581665039 time for calcul the mask position with numpy : 0.01650214195251465 nb_pixel_total : 96 time to create 1 rle with old method : 0.00014734268188476562 time for calcul the mask position with numpy : 0.017987728118896484 nb_pixel_total : 4463 time to create 1 rle with old method : 0.0050640106201171875 time for calcul the mask position with numpy : 0.01755046844482422 nb_pixel_total : 1695 time to create 1 rle with old method : 0.0029935836791992188 time for calcul the mask position with numpy : 0.016443490982055664 nb_pixel_total : 2813 time to create 1 rle with old method : 0.0033304691314697266 time for calcul the mask position with numpy : 0.015325784683227539 nb_pixel_total : 100 time to create 1 rle with old method : 0.0001380443572998047 time for calcul the mask position with numpy : 0.015226602554321289 nb_pixel_total : 773 time to create 1 rle with old method : 0.0009443759918212891 time for calcul the mask position with numpy : 0.015259504318237305 nb_pixel_total : 6 time to create 1 rle with old method : 3.3855438232421875e-05 time for calcul the mask position with numpy : 0.015295743942260742 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003292560577392578 time for calcul the mask position with numpy : 0.015376806259155273 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002675056457519531 time for calcul the mask position with numpy : 0.01539301872253418 nb_pixel_total : 1216 time to create 1 rle with old method : 0.0014300346374511719 time for calcul the mask position with numpy : 0.015368938446044922 nb_pixel_total : 441 time to create 1 rle with old method : 0.0005443096160888672 time for calcul the mask position with numpy : 0.01540064811706543 nb_pixel_total : 308 time to create 1 rle with old method : 0.000400543212890625 time for calcul the mask position with numpy : 0.015384674072265625 nb_pixel_total : 544 time to create 1 rle with old method : 0.0007197856903076172 time for calcul the mask position with numpy : 0.015332937240600586 nb_pixel_total : 34 time to create 1 rle with old method : 8.320808410644531e-05 time for calcul the mask position with numpy : 0.015418767929077148 nb_pixel_total : 643 time to create 1 rle with old method : 0.0007922649383544922 time for calcul the mask position with numpy : 0.015346527099609375 nb_pixel_total : 88 time to create 1 rle with old method : 0.00014138221740722656 time for calcul the mask position with numpy : 0.016234874725341797 nb_pixel_total : 358 time to create 1 rle with old method : 0.0005626678466796875 time for calcul the mask position with numpy : 0.018364667892456055 nb_pixel_total : 762 time to create 1 rle with old method : 0.0009276866912841797 time for calcul the mask position with numpy : 0.015405654907226562 nb_pixel_total : 7 time to create 1 rle with old method : 4.029273986816406e-05 time for calcul the mask position with numpy : 0.015423059463500977 nb_pixel_total : 661 time to create 1 rle with old method : 0.0008158683776855469 time for calcul the mask position with numpy : 0.016209840774536133 nb_pixel_total : 291 time to create 1 rle with old method : 0.00047469139099121094 time for calcul the mask position with numpy : 0.016818761825561523 nb_pixel_total : 144 time to create 1 rle with old method : 0.000240325927734375 time for calcul the mask position with numpy : 0.015441179275512695 nb_pixel_total : 2460 time to create 1 rle with old method : 0.002899169921875 time for calcul the mask position with numpy : 0.015517473220825195 nb_pixel_total : 219 time to create 1 rle with old method : 0.0003006458282470703 time for calcul the mask position with numpy : 0.015488386154174805 nb_pixel_total : 448 time to create 1 rle with old method : 0.0005970001220703125 time for calcul the mask position with numpy : 0.01780414581298828 nb_pixel_total : 951 time to create 1 rle with old method : 0.0011696815490722656 time for calcul the mask position with numpy : 0.015432596206665039 nb_pixel_total : 870 time to create 1 rle with old method : 0.0010879039764404297 time for calcul the mask position with numpy : 0.01551055908203125 nb_pixel_total : 105 time to create 1 rle with old method : 0.00017142295837402344 time for calcul the mask position with numpy : 0.015500545501708984 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003535747528076172 time for calcul the mask position with numpy : 0.015448331832885742 nb_pixel_total : 157 time to create 1 rle with old method : 0.00021600723266601562 time for calcul the mask position with numpy : 0.01575756072998047 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004754066467285156 time for calcul the mask position with numpy : 0.015578985214233398 nb_pixel_total : 456 time to create 1 rle with old method : 0.0006799697875976562 time for calcul the mask position with numpy : 0.015474557876586914 nb_pixel_total : 270 time to create 1 rle with old method : 0.0003781318664550781 time for calcul the mask position with numpy : 0.015424251556396484 nb_pixel_total : 30 time to create 1 rle with old method : 9.679794311523438e-05 time for calcul the mask position with numpy : 0.015390872955322266 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006220340728759766 time for calcul the mask position with numpy : 0.01717066764831543 nb_pixel_total : 329 time to create 1 rle with old method : 0.00044918060302734375 time for calcul the mask position with numpy : 0.0153961181640625 nb_pixel_total : 2100 time to create 1 rle with old method : 0.002474069595336914 time for calcul the mask position with numpy : 0.015421390533447266 nb_pixel_total : 136 time to create 1 rle with old method : 0.00020360946655273438 time for calcul the mask position with numpy : 0.015401363372802734 nb_pixel_total : 705 time to create 1 rle with old method : 0.0008666515350341797 time for calcul the mask position with numpy : 0.015478849411010742 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004532337188720703 time for calcul the mask position with numpy : 0.015608549118041992 nb_pixel_total : 1068 time to create 1 rle with old method : 0.0018045902252197266 time for calcul the mask position with numpy : 0.017449140548706055 nb_pixel_total : 236 time to create 1 rle with old method : 0.0004146099090576172 time for calcul the mask position with numpy : 0.01757669448852539 nb_pixel_total : 316 time to create 1 rle with old method : 0.0005886554718017578 time for calcul the mask position with numpy : 0.017474889755249023 nb_pixel_total : 87 time to create 1 rle with old method : 0.00017404556274414062 time for calcul the mask position with numpy : 0.017447233200073242 nb_pixel_total : 177 time to create 1 rle with old method : 0.0003407001495361328 time for calcul the mask position with numpy : 0.01642131805419922 nb_pixel_total : 631 time to create 1 rle with old method : 0.0008139610290527344 time for calcul the mask position with numpy : 0.015563011169433594 nb_pixel_total : 26 time to create 1 rle with old method : 8.96453857421875e-05 time for calcul the mask position with numpy : 0.015294075012207031 nb_pixel_total : 1046 time to create 1 rle with old method : 0.0012807846069335938 time for calcul the mask position with numpy : 0.015396833419799805 nb_pixel_total : 311 time to create 1 rle with old method : 0.00041222572326660156 time for calcul the mask position with numpy : 0.01549530029296875 nb_pixel_total : 325 time to create 1 rle with old method : 0.0004742145538330078 time for calcul the mask position with numpy : 0.0157773494720459 nb_pixel_total : 29823 time to create 1 rle with old method : 0.03322243690490723 time for calcul the mask position with numpy : 0.015294551849365234 nb_pixel_total : 120 time to create 1 rle with old method : 0.0001666545867919922 time for calcul the mask position with numpy : 0.015297412872314453 nb_pixel_total : 319 time to create 1 rle with old method : 0.0004448890686035156 time for calcul the mask position with numpy : 0.018580913543701172 nb_pixel_total : 1231 time to create 1 rle with old method : 0.0014803409576416016 time for calcul the mask position with numpy : 0.015174388885498047 nb_pixel_total : 520 time to create 1 rle with old method : 0.0006415843963623047 time for calcul the mask position with numpy : 0.01507568359375 nb_pixel_total : 112 time to create 1 rle with old method : 0.00016307830810546875 time for calcul the mask position with numpy : 0.015064477920532227 nb_pixel_total : 637 time to create 1 rle with old method : 0.0007545948028564453 time for calcul the mask position with numpy : 0.015146017074584961 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001475811004638672 time for calcul the mask position with numpy : 0.01518392562866211 nb_pixel_total : 590 time to create 1 rle with old method : 0.0007691383361816406 time for calcul the mask position with numpy : 0.015224695205688477 nb_pixel_total : 145 time to create 1 rle with old method : 0.0002117156982421875 time for calcul the mask position with numpy : 0.015394210815429688 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006744861602783203 time for calcul the mask position with numpy : 0.015271186828613281 nb_pixel_total : 362 time to create 1 rle with old method : 0.0004801750183105469 time for calcul the mask position with numpy : 0.015352487564086914 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0015912055969238281 time for calcul the mask position with numpy : 0.015602588653564453 nb_pixel_total : 701 time to create 1 rle with old method : 0.0008666515350341797 time for calcul the mask position with numpy : 0.01558232307434082 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003714561462402344 time for calcul the mask position with numpy : 0.01542806625366211 nb_pixel_total : 35 time to create 1 rle with old method : 9.584426879882812e-05 time for calcul the mask position with numpy : 0.015500068664550781 nb_pixel_total : 1100 time to create 1 rle with old method : 0.0013277530670166016 time for calcul the mask position with numpy : 0.015539407730102539 nb_pixel_total : 183 time to create 1 rle with old method : 0.00027751922607421875 time for calcul the mask position with numpy : 0.015443801879882812 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003676414489746094 time for calcul the mask position with numpy : 0.01549530029296875 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003330707550048828 time for calcul the mask position with numpy : 0.015441179275512695 nb_pixel_total : 202 time to create 1 rle with old method : 0.0003249645233154297 time for calcul the mask position with numpy : 0.015546560287475586 nb_pixel_total : 29903 time to create 1 rle with old method : 0.032560110092163086 time for calcul the mask position with numpy : 0.015411615371704102 nb_pixel_total : 314 time to create 1 rle with old method : 0.0003955364227294922 time for calcul the mask position with numpy : 0.015297651290893555 nb_pixel_total : 198 time to create 1 rle with old method : 0.0002727508544921875 time for calcul the mask position with numpy : 0.015278816223144531 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005075931549072266 time for calcul the mask position with numpy : 0.015204429626464844 nb_pixel_total : 240 time to create 1 rle with old method : 0.0003352165222167969 time for calcul the mask position with numpy : 0.01517033576965332 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0016465187072753906 time for calcul the mask position with numpy : 0.015126705169677734 nb_pixel_total : 162 time to create 1 rle with old method : 0.0002372264862060547 time for calcul the mask position with numpy : 0.015268802642822266 nb_pixel_total : 588 time to create 1 rle with old method : 0.0007860660552978516 time for calcul the mask position with numpy : 0.015303373336791992 nb_pixel_total : 1687 time to create 1 rle with old method : 0.0019404888153076172 time for calcul the mask position with numpy : 0.01555323600769043 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004646778106689453 time for calcul the mask position with numpy : 0.017122507095336914 nb_pixel_total : 305 time to create 1 rle with old method : 0.00041937828063964844 time for calcul the mask position with numpy : 0.016641855239868164 nb_pixel_total : 585 time to create 1 rle with old method : 0.0010211467742919922 time for calcul the mask position with numpy : 0.01755046844482422 nb_pixel_total : 411 time to create 1 rle with old method : 0.0007050037384033203 time for calcul the mask position with numpy : 0.017304658889770508 nb_pixel_total : 265 time to create 1 rle with old method : 0.0004923343658447266 time for calcul the mask position with numpy : 0.017302513122558594 nb_pixel_total : 109 time to create 1 rle with old method : 0.00021958351135253906 time for calcul the mask position with numpy : 0.016896724700927734 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006132125854492188 time for calcul the mask position with numpy : 0.015217781066894531 nb_pixel_total : 153 time to create 1 rle with old method : 0.00022029876708984375 time for calcul the mask position with numpy : 0.01527094841003418 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004050731658935547 time for calcul the mask position with numpy : 0.015272855758666992 nb_pixel_total : 26 time to create 1 rle with old method : 8.96453857421875e-05 time for calcul the mask position with numpy : 0.015482425689697266 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006396770477294922 time for calcul the mask position with numpy : 0.01760578155517578 nb_pixel_total : 810 time to create 1 rle with old method : 0.0009739398956298828 time for calcul the mask position with numpy : 0.016487598419189453 nb_pixel_total : 306 time to create 1 rle with old method : 0.0005412101745605469 time for calcul the mask position with numpy : 0.017298460006713867 nb_pixel_total : 274 time to create 1 rle with old method : 0.000370025634765625 time for calcul the mask position with numpy : 0.015346765518188477 nb_pixel_total : 1027 time to create 1 rle with old method : 0.0012493133544921875 time for calcul the mask position with numpy : 0.015419483184814453 nb_pixel_total : 383 time to create 1 rle with old method : 0.0005075931549072266 time for calcul the mask position with numpy : 0.015471935272216797 nb_pixel_total : 615 time to create 1 rle with old method : 0.0007774829864501953 time for calcul the mask position with numpy : 0.015385866165161133 nb_pixel_total : 4487 time to create 1 rle with old method : 0.005255699157714844 time for calcul the mask position with numpy : 0.015390157699584961 nb_pixel_total : 1567 time to create 1 rle with old method : 0.0018901824951171875 time for calcul the mask position with numpy : 0.015519380569458008 nb_pixel_total : 812 time to create 1 rle with old method : 0.0010237693786621094 time for calcul the mask position with numpy : 0.015264749526977539 nb_pixel_total : 172 time to create 1 rle with old method : 0.00022101402282714844 time for calcul the mask position with numpy : 0.016960859298706055 nb_pixel_total : 352 time to create 1 rle with old method : 0.0005586147308349609 time for calcul the mask position with numpy : 0.016255617141723633 nb_pixel_total : 4387 time to create 1 rle with old method : 0.005726814270019531 time for calcul the mask position with numpy : 0.015349388122558594 nb_pixel_total : 3435 time to create 1 rle with old method : 0.003888368606567383 time for calcul the mask position with numpy : 0.01552128791809082 nb_pixel_total : 295 time to create 1 rle with old method : 0.0004100799560546875 time for calcul the mask position with numpy : 0.015409708023071289 nb_pixel_total : 573 time to create 1 rle with old method : 0.0007319450378417969 time for calcul the mask position with numpy : 0.015462875366210938 nb_pixel_total : 953 time to create 1 rle with old method : 0.0011234283447265625 time for calcul the mask position with numpy : 0.015495777130126953 nb_pixel_total : 5120 time to create 1 rle with old method : 0.005833148956298828 time for calcul the mask position with numpy : 0.015312671661376953 nb_pixel_total : 2079 time to create 1 rle with old method : 0.0024640560150146484 time for calcul the mask position with numpy : 0.015575408935546875 nb_pixel_total : 539 time to create 1 rle with old method : 0.0007009506225585938 time for calcul the mask position with numpy : 0.015457391738891602 nb_pixel_total : 263 time to create 1 rle with old method : 0.00036263465881347656 time for calcul the mask position with numpy : 0.015374422073364258 nb_pixel_total : 1409 time to create 1 rle with old method : 0.001703023910522461 time for calcul the mask position with numpy : 0.01577925682067871 nb_pixel_total : 88 time to create 1 rle with old method : 0.00015211105346679688 time for calcul the mask position with numpy : 0.015511751174926758 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006194114685058594 time for calcul the mask position with numpy : 0.015475273132324219 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005125999450683594 time for calcul the mask position with numpy : 0.015605926513671875 nb_pixel_total : 624 time to create 1 rle with old method : 0.0012295246124267578 time for calcul the mask position with numpy : 0.018084287643432617 nb_pixel_total : 293 time to create 1 rle with old method : 0.00046634674072265625 time for calcul the mask position with numpy : 0.01891922950744629 nb_pixel_total : 405 time to create 1 rle with old method : 0.0004925727844238281 time for calcul the mask position with numpy : 0.015839099884033203 nb_pixel_total : 6347 time to create 1 rle with old method : 0.007415294647216797 time for calcul the mask position with numpy : 0.017974853515625 nb_pixel_total : 166 time to create 1 rle with old method : 0.00024890899658203125 time for calcul the mask position with numpy : 0.017234325408935547 nb_pixel_total : 2450 time to create 1 rle with old method : 0.002872943878173828 time for calcul the mask position with numpy : 0.015250205993652344 nb_pixel_total : 995 time to create 1 rle with old method : 0.0011792182922363281 time for calcul the mask position with numpy : 0.015336275100708008 nb_pixel_total : 1329 time to create 1 rle with old method : 0.001592874526977539 time for calcul the mask position with numpy : 0.015311479568481445 nb_pixel_total : 291 time to create 1 rle with old method : 0.00039076805114746094 time for calcul the mask position with numpy : 0.015315055847167969 nb_pixel_total : 401 time to create 1 rle with old method : 0.0005135536193847656 time for calcul the mask position with numpy : 0.015233278274536133 nb_pixel_total : 142 time to create 1 rle with old method : 0.00020885467529296875 time for calcul the mask position with numpy : 0.015170574188232422 nb_pixel_total : 1336 time to create 1 rle with old method : 0.0015919208526611328 time for calcul the mask position with numpy : 0.015229940414428711 nb_pixel_total : 2438 time to create 1 rle with old method : 0.0028438568115234375 time for calcul the mask position with numpy : 0.015309810638427734 nb_pixel_total : 977 time to create 1 rle with old method : 0.001226663589477539 time for calcul the mask position with numpy : 0.015352725982666016 nb_pixel_total : 439 time to create 1 rle with old method : 0.000560760498046875 time for calcul the mask position with numpy : 0.015273094177246094 nb_pixel_total : 1709 time to create 1 rle with old method : 0.0021293163299560547 time for calcul the mask position with numpy : 0.015192985534667969 nb_pixel_total : 460 time to create 1 rle with old method : 0.0006284713745117188 time for calcul the mask position with numpy : 0.01524209976196289 nb_pixel_total : 211 time to create 1 rle with old method : 0.00029277801513671875 time for calcul the mask position with numpy : 0.015414714813232422 nb_pixel_total : 2374 time to create 1 rle with old method : 0.002777576446533203 time for calcul the mask position with numpy : 0.015530586242675781 nb_pixel_total : 63 time to create 1 rle with old method : 0.0002262592315673828 time for calcul the mask position with numpy : 0.015472888946533203 nb_pixel_total : 239 time to create 1 rle with old method : 0.00031948089599609375 time for calcul the mask position with numpy : 0.015472173690795898 nb_pixel_total : 3106 time to create 1 rle with old method : 0.0038535594940185547 time for calcul the mask position with numpy : 0.015392541885375977 nb_pixel_total : 131 time to create 1 rle with old method : 0.000179290771484375 time for calcul the mask position with numpy : 0.015355110168457031 nb_pixel_total : 611 time to create 1 rle with old method : 0.0007500648498535156 time for calcul the mask position with numpy : 0.015357494354248047 nb_pixel_total : 1718 time to create 1 rle with old method : 0.0020139217376708984 time for calcul the mask position with numpy : 0.01535654067993164 nb_pixel_total : 267 time to create 1 rle with old method : 0.0003769397735595703 time for calcul the mask position with numpy : 0.015312433242797852 nb_pixel_total : 655 time to create 1 rle with old method : 0.0008099079132080078 time for calcul the mask position with numpy : 0.015357732772827148 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007379055023193359 time for calcul the mask position with numpy : 0.015611886978149414 nb_pixel_total : 210 time to create 1 rle with old method : 0.00027751922607421875 time for calcul the mask position with numpy : 0.01625847816467285 nb_pixel_total : 181 time to create 1 rle with old method : 0.0003533363342285156 time for calcul the mask position with numpy : 0.015497684478759766 nb_pixel_total : 109 time to create 1 rle with old method : 0.0001533031463623047 time for calcul the mask position with numpy : 0.01560354232788086 nb_pixel_total : 4242 time to create 1 rle with old method : 0.004748821258544922 time for calcul the mask position with numpy : 0.015144586563110352 nb_pixel_total : 475 time to create 1 rle with old method : 0.0005915164947509766 time for calcul the mask position with numpy : 0.015024900436401367 nb_pixel_total : 1796 time to create 1 rle with old method : 0.002950429916381836 time for calcul the mask position with numpy : 0.017222881317138672 nb_pixel_total : 2239 time to create 1 rle with old method : 0.0036008358001708984 time for calcul the mask position with numpy : 0.017331838607788086 nb_pixel_total : 97 time to create 1 rle with old method : 0.0001697540283203125 time for calcul the mask position with numpy : 0.01738762855529785 nb_pixel_total : 122 time to create 1 rle with old method : 0.0002315044403076172 time for calcul the mask position with numpy : 0.017192363739013672 nb_pixel_total : 376 time to create 1 rle with old method : 0.0006034374237060547 time for calcul the mask position with numpy : 0.016684532165527344 nb_pixel_total : 599 time to create 1 rle with old method : 0.0007064342498779297 time for calcul the mask position with numpy : 0.015110254287719727 nb_pixel_total : 352 time to create 1 rle with old method : 0.00043892860412597656 time for calcul the mask position with numpy : 0.015084266662597656 nb_pixel_total : 344 time to create 1 rle with old method : 0.00042557716369628906 time for calcul the mask position with numpy : 0.015107870101928711 nb_pixel_total : 497 time to create 1 rle with old method : 0.0005867481231689453 time for calcul the mask position with numpy : 0.01517939567565918 nb_pixel_total : 2231 time to create 1 rle with old method : 0.0025212764739990234 time for calcul the mask position with numpy : 0.015090465545654297 nb_pixel_total : 1038 time to create 1 rle with old method : 0.001252889633178711 time for calcul the mask position with numpy : 0.015154123306274414 nb_pixel_total : 306 time to create 1 rle with old method : 0.00036597251892089844 time for calcul the mask position with numpy : 0.015035390853881836 nb_pixel_total : 344 time to create 1 rle with old method : 0.00042057037353515625 time for calcul the mask position with numpy : 0.015027523040771484 nb_pixel_total : 278 time to create 1 rle with old method : 0.00037217140197753906 time for calcul the mask position with numpy : 0.015125513076782227 nb_pixel_total : 2758 time to create 1 rle with old method : 0.003454446792602539 time for calcul the mask position with numpy : 0.015139102935791016 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003399848937988281 time for calcul the mask position with numpy : 0.015223503112792969 nb_pixel_total : 204 time to create 1 rle with old method : 0.00028061866760253906 time for calcul the mask position with numpy : 0.015477418899536133 nb_pixel_total : 953 time to create 1 rle with old method : 0.0016498565673828125 time for calcul the mask position with numpy : 0.01562047004699707 nb_pixel_total : 614 time to create 1 rle with old method : 0.0011756420135498047 time for calcul the mask position with numpy : 0.01653003692626953 nb_pixel_total : 1925 time to create 1 rle with old method : 0.0022606849670410156 time for calcul the mask position with numpy : 0.015400409698486328 nb_pixel_total : 856 time to create 1 rle with old method : 0.000995635986328125 time for calcul the mask position with numpy : 0.015593528747558594 nb_pixel_total : 1960 time to create 1 rle with old method : 0.0023212432861328125 time for calcul the mask position with numpy : 0.01530003547668457 nb_pixel_total : 1847 time to create 1 rle with old method : 0.0022149085998535156 time for calcul the mask position with numpy : 0.015570878982543945 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004017353057861328 time for calcul the mask position with numpy : 0.015540599822998047 nb_pixel_total : 260 time to create 1 rle with old method : 0.0004115104675292969 time for calcul the mask position with numpy : 0.016020536422729492 nb_pixel_total : 326 time to create 1 rle with old method : 0.0004391670227050781 time for calcul the mask position with numpy : 0.01607680320739746 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006890296936035156 time for calcul the mask position with numpy : 0.015941619873046875 nb_pixel_total : 504 time to create 1 rle with old method : 0.0006873607635498047 time for calcul the mask position with numpy : 0.01612401008605957 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003867149353027344 time for calcul the mask position with numpy : 0.0167694091796875 nb_pixel_total : 407 time to create 1 rle with old method : 0.0005140304565429688 time for calcul the mask position with numpy : 0.016143083572387695 nb_pixel_total : 226 time to create 1 rle with old method : 0.00032973289489746094 time for calcul the mask position with numpy : 0.01616668701171875 nb_pixel_total : 1318 time to create 1 rle with old method : 0.002459287643432617 time for calcul the mask position with numpy : 0.016802310943603516 nb_pixel_total : 1175 time to create 1 rle with old method : 0.001413106918334961 time for calcul the mask position with numpy : 0.016053199768066406 nb_pixel_total : 512 time to create 1 rle with old method : 0.0008563995361328125 time for calcul the mask position with numpy : 0.015425920486450195 nb_pixel_total : 10 time to create 1 rle with old method : 0.00015044212341308594 time for calcul the mask position with numpy : 0.015221834182739258 nb_pixel_total : 151 time to create 1 rle with old method : 0.00022220611572265625 time for calcul the mask position with numpy : 0.015252828598022461 nb_pixel_total : 1720 time to create 1 rle with old method : 0.002023935317993164 time for calcul the mask position with numpy : 0.015075922012329102 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002148151397705078 time for calcul the mask position with numpy : 0.015006780624389648 nb_pixel_total : 208 time to create 1 rle with old method : 0.00028061866760253906 time for calcul the mask position with numpy : 0.015138864517211914 nb_pixel_total : 211 time to create 1 rle with old method : 0.00028705596923828125 time for calcul the mask position with numpy : 0.015232324600219727 nb_pixel_total : 157 time to create 1 rle with old method : 0.00021839141845703125 time for calcul the mask position with numpy : 0.01568770408630371 nb_pixel_total : 241 time to create 1 rle with old method : 0.0003414154052734375 time for calcul the mask position with numpy : 0.015059947967529297 nb_pixel_total : 503 time to create 1 rle with old method : 0.0006411075592041016 time for calcul the mask position with numpy : 0.015529632568359375 nb_pixel_total : 316 time to create 1 rle with old method : 0.00043082237243652344 time for calcul the mask position with numpy : 0.01525425910949707 nb_pixel_total : 2075 time to create 1 rle with old method : 0.0026292800903320312 time for calcul the mask position with numpy : 0.01525735855102539 nb_pixel_total : 250 time to create 1 rle with old method : 0.0005321502685546875 time for calcul the mask position with numpy : 0.01534414291381836 nb_pixel_total : 751 time to create 1 rle with old method : 0.0009253025054931641 time for calcul the mask position with numpy : 0.016102075576782227 nb_pixel_total : 9938 time to create 1 rle with old method : 0.014042139053344727 time for calcul the mask position with numpy : 0.020381450653076172 nb_pixel_total : 449 time to create 1 rle with old method : 0.0008866786956787109 time for calcul the mask position with numpy : 0.016865015029907227 nb_pixel_total : 88 time to create 1 rle with old method : 0.0001544952392578125 time for calcul the mask position with numpy : 0.015424489974975586 nb_pixel_total : 491 time to create 1 rle with old method : 0.0005984306335449219 time for calcul the mask position with numpy : 0.015617609024047852 nb_pixel_total : 1639 time to create 1 rle with old method : 0.001940011978149414 time for calcul the mask position with numpy : 0.015455007553100586 nb_pixel_total : 174 time to create 1 rle with old method : 0.00025081634521484375 time for calcul the mask position with numpy : 0.015705108642578125 nb_pixel_total : 111 time to create 1 rle with old method : 0.00015997886657714844 time for calcul the mask position with numpy : 0.01549839973449707 nb_pixel_total : 17 time to create 1 rle with old method : 7.653236389160156e-05 time for calcul the mask position with numpy : 0.015447854995727539 nb_pixel_total : 550 time to create 1 rle with old method : 0.0006852149963378906 time for calcul the mask position with numpy : 0.017356395721435547 nb_pixel_total : 1409 time to create 1 rle with old method : 0.0019466876983642578 time for calcul the mask position with numpy : 0.015409469604492188 nb_pixel_total : 625 time to create 1 rle with old method : 0.0008344650268554688 time for calcul the mask position with numpy : 0.015581846237182617 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0015807151794433594 time for calcul the mask position with numpy : 0.015620708465576172 nb_pixel_total : 3033 time to create 1 rle with old method : 0.0036067962646484375 time for calcul the mask position with numpy : 0.01556086540222168 nb_pixel_total : 690 time to create 1 rle with old method : 0.0008978843688964844 time for calcul the mask position with numpy : 0.015591859817504883 nb_pixel_total : 108 time to create 1 rle with old method : 0.00016307830810546875 time for calcul the mask position with numpy : 0.01600027084350586 nb_pixel_total : 542 time to create 1 rle with old method : 0.0007014274597167969 time for calcul the mask position with numpy : 0.015295267105102539 nb_pixel_total : 120 time to create 1 rle with old method : 0.00018525123596191406 time for calcul the mask position with numpy : 0.015337228775024414 nb_pixel_total : 1092 time to create 1 rle with old method : 0.0013229846954345703 time for calcul the mask position with numpy : 0.015437841415405273 nb_pixel_total : 28 time to create 1 rle with old method : 9.059906005859375e-05 time for calcul the mask position with numpy : 0.01544642448425293 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005202293395996094 time for calcul the mask position with numpy : 0.015671253204345703 nb_pixel_total : 210 time to create 1 rle with old method : 0.00027871131896972656 time for calcul the mask position with numpy : 0.016031742095947266 nb_pixel_total : 1733 time to create 1 rle with old method : 0.002510547637939453 time for calcul the mask position with numpy : 0.016131162643432617 nb_pixel_total : 337 time to create 1 rle with old method : 0.000499725341796875 time for calcul the mask position with numpy : 0.015724658966064453 nb_pixel_total : 983 time to create 1 rle with old method : 0.0011734962463378906 time for calcul the mask position with numpy : 0.015698909759521484 nb_pixel_total : 567 time to create 1 rle with old method : 0.0006990432739257812 time for calcul the mask position with numpy : 0.015534162521362305 nb_pixel_total : 149 time to create 1 rle with old method : 0.0002646446228027344 time for calcul the mask position with numpy : 0.015575408935546875 nb_pixel_total : 840 time to create 1 rle with old method : 0.0010128021240234375 time for calcul the mask position with numpy : 0.015491008758544922 nb_pixel_total : 174 time to create 1 rle with old method : 0.00028014183044433594 time for calcul the mask position with numpy : 0.015565156936645508 nb_pixel_total : 806 time to create 1 rle with old method : 0.001010894775390625 time for calcul the mask position with numpy : 0.015262842178344727 nb_pixel_total : 480 time to create 1 rle with old method : 0.0006189346313476562 time for calcul the mask position with numpy : 0.015225648880004883 nb_pixel_total : 1302 time to create 1 rle with old method : 0.0015506744384765625 time for calcul the mask position with numpy : 0.015451192855834961 nb_pixel_total : 4644 time to create 1 rle with old method : 0.0058367252349853516 time for calcul the mask position with numpy : 0.01772904396057129 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003199577331542969 time for calcul the mask position with numpy : 0.015456914901733398 nb_pixel_total : 37 time to create 1 rle with old method : 7.724761962890625e-05 time for calcul the mask position with numpy : 0.015539884567260742 nb_pixel_total : 309 time to create 1 rle with old method : 0.0004673004150390625 time for calcul the mask position with numpy : 0.015513896942138672 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005397796630859375 time for calcul the mask position with numpy : 0.015558004379272461 nb_pixel_total : 1077 time to create 1 rle with old method : 0.0013053417205810547 time for calcul the mask position with numpy : 0.017742156982421875 nb_pixel_total : 558 time to create 1 rle with old method : 0.0007317066192626953 time for calcul the mask position with numpy : 0.015486717224121094 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0014858245849609375 time for calcul the mask position with numpy : 0.015563249588012695 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003464221954345703 time for calcul the mask position with numpy : 0.01513051986694336 nb_pixel_total : 424 time to create 1 rle with old method : 0.0005500316619873047 time for calcul the mask position with numpy : 0.015085220336914062 nb_pixel_total : 134 time to create 1 rle with old method : 0.00018358230590820312 create new chi : 9.155160427093506 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 : 0.018332242965698242 batch 1 Loaded 491 chid ids of type : 4230 Number RLEs to save : 37677 TO DO : save crop sub photo not yet done ! save time : 2.4499220848083496 map_output_result : {1337395425: (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 [1337395425] Looping around the photos to save general results len do output : 1 /1337395425.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, '2583047') ('4234', '20514224', '1337395425', None, None, None, None, None, '2583047') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.013242006301879883 save_final save missing photos in datou_result : time spend for datou_step_exec : 14.129682302474976 time spend to save output : 0.013720273971557617 total time spend for step 4 : 14.143402576446533 step5:crop_condition Thu Feb 13 17:21:16 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 1 ! batch 1 Loaded 491 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 284 About to insert : list_path_to_insert length 284 new photo from crops ! About to upload 284 photos upload in portfolio : 4869462 init cache_photo without model_param we have 284 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739463683_737127 we have uploaded 284 photos in the portfolio 4869462 time of upload the photos Elapsed time : 78.27490282058716 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 69 About to insert : list_path_to_insert length 69 new photo from crops ! About to upload 69 photos upload in portfolio : 4869462 init cache_photo without model_param we have 69 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739463763_737127 we have uploaded 69 photos in the portfolio 4869462 time of upload the photos Elapsed time : 16.851670742034912 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 ! map_result returned by crop_photo_return_map_crop : length : 10 About to insert : list_path_to_insert length 10 new photo from crops ! About to upload 10 photos upload in portfolio : 4869462 init cache_photo without model_param we have 10 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739463780_737127 we have uploaded 10 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.1234889030456543 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 15 About to insert : list_path_to_insert length 15 new photo from crops ! About to upload 15 photos upload in portfolio : 4869462 init cache_photo without model_param we have 15 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1739463784_737127 we have uploaded 15 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.4352452754974365 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1337395425] Looping around the photos to save general results len do output : 378 /1337405720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405731Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405737Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405744Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405774Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405776Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405873Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405874Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405876Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405891Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405895Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405903Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405928Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405929Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405930Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405931Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405932Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405933Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405934Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405935Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405936Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405937Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405938Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405939Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405940Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405942Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405944Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405945Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405946Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405947Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405948Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405949Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405950Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405951Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405952Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405953Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405954Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405955Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405956Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405957Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405958Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405959Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405960Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405961Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405962Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405963Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405964Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405966Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405969Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405973Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405976Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405980Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405983Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405985Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405989Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405992Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405995Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337405999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406000Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406003Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406008Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406013Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406018Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406032Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406034Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406036Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406038Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1337406194Didn'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, '2583047') ('4234', '20514224', '1337395425', None, None, None, None, None, '2583047') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1135 time used for this insertion : 0.13054299354553223 save_final save missing photos in datou_result : time spend for datou_step_exec : 112.70920968055725 time spend to save output : 0.14642834663391113 total time spend for step 5 : 112.85563802719116 step6:thcl Thu Feb 13 17:23:09 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 : 0.031086444854736328 time to convert the images to numpy array : 0.11053824424743652 time to import caffe and check if the image exist : 0.02425408363342285 time to convert the images to numpy array : 0.12788772583007812 time to import caffe and check if the image exist : 0.03046250343322754 time to convert the images to numpy array : 0.12314629554748535 time to import caffe and check if the image exist : 0.033974647521972656 time to convert the images to numpy array : 0.12172484397888184 time to import caffe and check if the image exist : 0.03003215789794922 time to convert the images to numpy array : 0.12881159782409668 time to import caffe and check if the image exist : 0.05726933479309082 time to convert the images to numpy array : 0.10357308387756348 time to import caffe and check if the image exist : 0.04316878318786621 time to convert the images to numpy array : 0.11955094337463379 time to import caffe and check if the image exist : 0.05047488212585449 time to convert the images to numpy array : 0.1164391040802002 time to import caffe and check if the image exist : 0.054704904556274414 time to convert the images to numpy array : 0.11288666725158691 time to import caffe and check if the image exist : 0.042067766189575195 time to convert the images to numpy array : 0.12695074081420898 total time to convert the images to numpy array : 0.6759164333343506 list photo_ids error: [] list photo_ids correct : [1337405720, 1337405721, 1337405722, 1337405723, 1337405724, 1337405725, 1337405726, 1337405727, 1337405728, 1337405729, 1337405731, 1337405732, 1337405733, 1337405734, 1337405735, 1337405736, 1337405737, 1337405738, 1337405739, 1337405740, 1337405741, 1337405742, 1337405743, 1337405744, 1337405745, 1337405746, 1337405747, 1337405748, 1337405750, 1337405752, 1337405755, 1337405757, 1337405759, 1337405761, 1337405763, 1337405766, 1337405768, 1337405770, 1337405934, 1337405935, 1337405936, 1337405937, 1337405938, 1337405939, 1337405940, 1337405942, 1337405944, 1337405945, 1337405946, 1337405947, 1337405948, 1337405949, 1337405950, 1337405951, 1337405952, 1337405953, 1337405954, 1337405955, 1337405956, 1337405957, 1337405958, 1337405959, 1337405960, 1337405961, 1337405962, 1337405963, 1337405964, 1337405965, 1337405966, 1337405967, 1337405968, 1337405969, 1337405970, 1337405971, 1337405972, 1337405973, 1337405855, 1337405856, 1337405857, 1337405858, 1337405859, 1337405861, 1337405862, 1337405863, 1337405864, 1337405865, 1337405866, 1337405867, 1337405868, 1337405870, 1337405871, 1337405872, 1337405873, 1337405874, 1337405875, 1337405876, 1337405877, 1337405878, 1337405879, 1337405880, 1337405881, 1337405882, 1337405883, 1337405884, 1337405885, 1337405886, 1337405887, 1337405888, 1337405889, 1337405890, 1337405891, 1337405892, 1337405893, 1337405894, 1337406156, 1337406157, 1337406158, 1337406159, 1337406160, 1337406161, 1337406162, 1337406163, 1337406164, 1337406165, 1337406166, 1337406169, 1337406170, 1337406171, 1337406172, 1337406173, 1337406174, 1337406175, 1337406176, 1337406177, 1337406178, 1337406180, 1337406181, 1337406182, 1337406183, 1337406184, 1337406185, 1337406186, 1337406187, 1337406188, 1337406189, 1337406190, 1337406191, 1337406192, 1337406193, 1337406194, 1337405772, 1337405774, 1337405776, 1337405778, 1337405780, 1337405782, 1337405783, 1337405784, 1337405785, 1337405786, 1337405787, 1337405788, 1337405789, 1337405790, 1337405791, 1337405792, 1337405793, 1337405794, 1337405795, 1337405796, 1337405797, 1337405798, 1337405799, 1337405800, 1337405801, 1337405802, 1337405803, 1337405804, 1337405805, 1337405806, 1337405807, 1337405808, 1337405809, 1337405810, 1337405811, 1337405812, 1337405813, 1337405814, 1337406118, 1337406119, 1337406120, 1337406121, 1337406122, 1337406123, 1337406124, 1337406125, 1337406126, 1337406127, 1337406128, 1337406129, 1337406130, 1337406131, 1337406132, 1337406133, 1337406134, 1337406135, 1337406136, 1337406137, 1337406138, 1337406139, 1337406140, 1337406141, 1337406142, 1337406143, 1337406144, 1337406145, 1337406146, 1337406147, 1337406148, 1337406149, 1337406150, 1337406151, 1337406152, 1337406153, 1337406154, 1337406155, 1337405895, 1337405896, 1337405897, 1337405898, 1337405899, 1337405900, 1337405901, 1337405902, 1337405903, 1337405904, 1337405905, 1337405906, 1337405907, 1337405908, 1337405909, 1337405910, 1337405911, 1337405912, 1337405913, 1337405914, 1337405915, 1337405917, 1337405918, 1337405919, 1337405920, 1337405921, 1337405922, 1337405923, 1337405924, 1337405925, 1337405926, 1337405927, 1337405928, 1337405929, 1337405930, 1337405931, 1337405932, 1337405933, 1337405815, 1337405816, 1337405817, 1337405818, 1337405819, 1337405820, 1337405821, 1337405822, 1337405823, 1337405824, 1337405825, 1337405826, 1337405827, 1337405829, 1337405830, 1337405831, 1337405832, 1337405833, 1337405834, 1337405835, 1337405836, 1337405837, 1337405838, 1337405839, 1337405840, 1337405841, 1337405842, 1337405843, 1337405844, 1337405845, 1337405847, 1337405848, 1337405849, 1337405850, 1337405851, 1337405852, 1337405853, 1337405854, 1337406026, 1337406028, 1337406030, 1337406032, 1337406034, 1337406036, 1337406038, 1337406040, 1337406043, 1337406045, 1337406047, 1337406049, 1337406051, 1337406053, 1337406055, 1337406057, 1337406059, 1337406061, 1337406096, 1337406098, 1337406099, 1337406100, 1337406101, 1337406102, 1337406103, 1337406104, 1337406105, 1337406106, 1337406107, 1337406109, 1337406110, 1337406111, 1337406112, 1337406113, 1337406114, 1337406115, 1337406116, 1337406117, 1337405974, 1337405976, 1337405977, 1337405979, 1337405980, 1337405982, 1337405983, 1337405984, 1337405985, 1337405986, 1337405987, 1337405989, 1337405990, 1337405991, 1337405992, 1337405993, 1337405994, 1337405995, 1337405996, 1337405997, 1337405998, 1337405999, 1337406000, 1337406001, 1337406002, 1337406003, 1337406004, 1337406005, 1337406006, 1337406007, 1337406008, 1337406009, 1337406010, 1337406013, 1337406018, 1337406020, 1337406022, 1337406024] number of photos to traite : 378 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 : 8269 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 : 8050 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 2.377346992492676 time used to do the prediction : 1.6456689834594727 save descriptor for thcl : 3237 time to traite the descriptors : 2.450136661529541 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1337405720 To insert : 1337405721 To insert : 1337405722 To insert : 1337405723 To insert : 1337405724 To insert : 1337405725 To insert : 1337405726 To insert : 1337405727 To insert : 1337405728 To insert : 1337405729 To insert : 1337405731 To insert : 1337405732 To insert : 1337405733 To insert : 1337405734 To insert : 1337405735 To insert : 1337405736 To insert : 1337405737 To insert : 1337405738 To insert : 1337405739 To insert : 1337405740 To insert : 1337405741 To insert : 1337405742 To insert : 1337405743 To insert : 1337405744 To insert : 1337405745 To insert : 1337405746 To insert : 1337405747 To insert : 1337405748 To insert : 1337405750 To insert : 1337405752 To insert : 1337405755 To insert : 1337405757 To insert : 1337405759 To insert : 1337405761 To insert : 1337405763 To insert : 1337405766 To insert : 1337405768 To insert : 1337405770 To insert : 1337405934 To insert : 1337405935 To insert : 1337405936 To insert : 1337405937 To insert : 1337405938 To insert : 1337405939 To insert : 1337405940 To insert : 1337405942 To insert : 1337405944 To insert : 1337405945 To insert : 1337405946 To insert : 1337405947 To insert : 1337405948 To insert : 1337405949 To insert : 1337405950 To insert : 1337405951 To insert : 1337405952 To insert : 1337405953 To insert : 1337405954 To insert : 1337405955 To insert : 1337405956 To insert : 1337405957 To insert : 1337405958 To insert : 1337405959 To insert : 1337405960 To insert : 1337405961 To insert : 1337405962 To insert : 1337405963 To insert : 1337405964 To insert : 1337405965 To insert : 1337405966 To insert : 1337405967 To insert : 1337405968 To insert : 1337405969 To insert : 1337405970 To insert : 1337405971 To insert : 1337405972 To insert : 1337405973 To insert : 1337405855 To insert : 1337405856 To insert : 1337405857 To insert : 1337405858 To insert : 1337405859 To insert : 1337405861 To insert : 1337405862 To insert : 1337405863 To insert : 1337405864 To insert : 1337405865 To insert : 1337405866 To insert : 1337405867 To insert : 1337405868 To insert : 1337405870 To insert : 1337405871 To insert : 1337405872 To insert : 1337405873 To insert : 1337405874 To insert : 1337405875 To insert : 1337405876 To insert : 1337405877 To insert : 1337405878 To insert : 1337405879 To insert : 1337405880 To insert : 1337405881 To insert : 1337405882 To insert : 1337405883 To insert : 1337405884 To insert : 1337405885 To insert : 1337405886 To insert : 1337405887 To insert : 1337405888 To insert : 1337405889 To insert : 1337405890 To insert : 1337405891 To insert : 1337405892 To insert : 1337405893 To insert : 1337405894 To insert : 1337406156 To insert : 1337406157 To insert : 1337406158 To insert : 1337406159 To insert : 1337406160 To insert : 1337406161 To insert : 1337406162 To insert : 1337406163 To insert : 1337406164 To insert : 1337406165 To insert : 1337406166 To insert : 1337406169 To insert : 1337406170 To insert : 1337406171 To insert : 1337406172 To insert : 1337406173 To insert : 1337406174 To insert : 1337406175 To insert : 1337406176 To insert : 1337406177 To insert : 1337406178 To insert : 1337406180 To insert : 1337406181 To insert : 1337406182 To insert : 1337406183 To insert : 1337406184 To insert : 1337406185 To insert : 1337406186 To insert : 1337406187 To insert : 1337406188 To insert : 1337406189 To insert : 1337406190 To insert : 1337406191 To insert : 1337406192 To insert : 1337406193 To insert : 1337406194 To insert : 1337405772 To insert : 1337405774 To insert : 1337405776 To insert : 1337405778 To insert : 1337405780 To insert : 1337405782 To insert : 1337405783 To insert : 1337405784 To insert : 1337405785 To insert : 1337405786 To insert : 1337405787 To insert : 1337405788 To insert : 1337405789 To insert : 1337405790 To insert : 1337405791 To insert : 1337405792 To insert : 1337405793 To insert : 1337405794 To insert : 1337405795 To insert : 1337405796 To insert : 1337405797 To insert : 1337405798 To insert : 1337405799 To insert : 1337405800 To insert : 1337405801 To insert : 1337405802 To insert : 1337405803 To insert : 1337405804 To insert : 1337405805 To insert : 1337405806 To insert : 1337405807 To insert : 1337405808 To insert : 1337405809 To insert : 1337405810 To insert : 1337405811 To insert : 1337405812 To insert : 1337405813 To insert : 1337405814 To insert : 1337406118 To insert : 1337406119 To insert : 1337406120 To insert : 1337406121 To insert : 1337406122 To insert : 1337406123 To insert : 1337406124 To insert : 1337406125 To insert : 1337406126 To insert : 1337406127 To insert : 1337406128 To insert : 1337406129 To insert : 1337406130 To insert : 1337406131 To insert : 1337406132 To insert : 1337406133 To insert : 1337406134 To insert : 1337406135 To insert : 1337406136 To insert : 1337406137 To insert : 1337406138 To insert : 1337406139 To insert : 1337406140 To insert : 1337406141 To insert : 1337406142 To insert : 1337406143 To insert : 1337406144 To insert : 1337406145 To insert : 1337406146 To insert : 1337406147 To insert : 1337406148 To insert : 1337406149 To insert : 1337406150 To insert : 1337406151 To insert : 1337406152 To insert : 1337406153 To insert : 1337406154 To insert : 1337406155 To insert : 1337405895 To insert : 1337405896 To insert : 1337405897 To insert : 1337405898 To insert : 1337405899 To insert : 1337405900 To insert : 1337405901 To insert : 1337405902 To insert : 1337405903 To insert : 1337405904 To insert : 1337405905 To insert : 1337405906 To insert : 1337405907 To insert : 1337405908 To insert : 1337405909 To insert : 1337405910 To insert : 1337405911 To insert : 1337405912 To insert : 1337405913 To insert : 1337405914 To insert : 1337405915 To insert : 1337405917 To insert : 1337405918 To insert : 1337405919 To insert : 1337405920 To insert : 1337405921 To insert : 1337405922 To insert : 1337405923 To insert : 1337405924 To insert : 1337405925 To insert : 1337405926 To insert : 1337405927 To insert : 1337405928 To insert : 1337405929 To insert : 1337405930 To insert : 1337405931 To insert : 1337405932 To insert : 1337405933 To insert : 1337405815 To insert : 1337405816 To insert : 1337405817 To insert : 1337405818 To insert : 1337405819 To insert : 1337405820 To insert : 1337405821 To insert : 1337405822 To insert : 1337405823 To insert : 1337405824 To insert : 1337405825 To insert : 1337405826 To insert : 1337405827 To insert : 1337405829 To insert : 1337405830 To insert : 1337405831 To insert : 1337405832 To insert : 1337405833 To insert : 1337405834 To insert : 1337405835 To insert : 1337405836 To insert : 1337405837 To insert : 1337405838 To insert : 1337405839 To insert : 1337405840 To insert : 1337405841 To insert : 1337405842 To insert : 1337405843 To insert : 1337405844 To insert : 1337405845 To insert : 1337405847 To insert : 1337405848 To insert : 1337405849 To insert : 1337405850 To insert : 1337405851 To insert : 1337405852 To insert : 1337405853 To insert : 1337405854 To insert : 1337406026 To insert : 1337406028 To insert : 1337406030 To insert : 1337406032 To insert : 1337406034 To insert : 1337406036 To insert : 1337406038 To insert : 1337406040 To insert : 1337406043 To insert : 1337406045 To insert : 1337406047 To insert : 1337406049 To insert : 1337406051 To insert : 1337406053 To insert : 1337406055 To insert : 1337406057 To insert : 1337406059 To insert : 1337406061 To insert : 1337406096 To insert : 1337406098 To insert : 1337406099 To insert : 1337406100 To insert : 1337406101 To insert : 1337406102 To insert : 1337406103 To insert : 1337406104 To insert : 1337406105 To insert : 1337406106 To insert : 1337406107 To insert : 1337406109 To insert : 1337406110 To insert : 1337406111 To insert : 1337406112 To insert : 1337406113 To insert : 1337406114 To insert : 1337406115 To insert : 1337406116 To insert : 1337406117 To insert : 1337405974 To insert : 1337405976 To insert : 1337405977 To insert : 1337405979 To insert : 1337405980 To insert : 1337405982 To insert : 1337405983 To insert : 1337405984 To insert : 1337405985 To insert : 1337405986 To insert : 1337405987 To insert : 1337405989 To insert : 1337405990 To insert : 1337405991 To insert : 1337405992 To insert : 1337405993 To insert : 1337405994 To insert : 1337405995 To insert : 1337405996 To insert : 1337405997 To insert : 1337405998 To insert : 1337405999 To insert : 1337406000 To insert : 1337406001 To insert : 1337406002 To insert : 1337406003 To insert : 1337406004 To insert : 1337406005 To insert : 1337406006 To insert : 1337406007 To insert : 1337406008 To insert : 1337406009 To insert : 1337406010 To insert : 1337406013 To insert : 1337406018 To insert : 1337406020 To insert : 1337406022 To insert : 1337406024 time to insert the descriptors : 69.86591625213623 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 : 563 time used for this insertion : 0.04369401931762695 save missing photos in datou_result : time spend for datou_step_exec : 82.58332681655884 time spend to save output : 0.10087013244628906 total time spend for step 6 : 82.68419694900513 step7:ventilate_hashtags_in_portfolio Thu Feb 13 17:24:32 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 20514224 get user id for portfolio 20514224 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`=20514224 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','Carton','PET_fonce','refus','mal_croppe','Papier','papier','PEHD','pehd','Film_plastique','metal','pet_fonce','PET_clair','carton','pet_clair','Tetrapak','environnement','autre')) 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`=20514224 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','Carton','PET_fonce','refus','mal_croppe','Papier','papier','PEHD','pehd','Film_plastique','metal','pet_fonce','PET_clair','carton','pet_clair','Tetrapak','environnement','autre')) 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`=20514224 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','Carton','PET_fonce','refus','mal_croppe','Papier','papier','PEHD','pehd','Film_plastique','metal','pet_fonce','PET_clair','carton','pet_clair','Tetrapak','environnement','autre')) 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`=20514224 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','Carton','PET_fonce','refus','mal_croppe','Papier','papier','PEHD','pehd','Film_plastique','metal','pet_fonce','PET_clair','carton','pet_clair','Tetrapak','environnement','autre')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20515174,20515187,20515185,20515177,20515178,20515180,20515182,20515183,20515184,20515188,20515189,20515190,20515191?tags=flou,carton,pet_fonce,refus,mal_croppe,papier,pehd,film_plastique,metal,pet_clair,tetrapak,environnement,autre&datou_id_consolidate=4235&port_consolidate=20514224 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1337395425] Looping around the photos to save general results len do output : 1 /20514224. 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, '2583047') ('4234', '20514224', '1337395425', None, None, None, None, None, '2583047') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.012546539306640625 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.5607194900512695 time spend to save output : 0.012822866439819336 total time spend for step 7 : 2.573542356491089 step8:final Thu Feb 13 17:24:34 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 : {1337395425: ('0.7070669784657713',)} new output for save of step final : {1337395425: ('0.7070669784657713',)} [1337395425] Looping around the photos to save general results len do output : 1 /1337395425.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, '2583047') ('4234', '20514224', '1337395425', None, None, None, None, None, '2583047') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.010673284530639648 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11016416549682617 time spend to save output : 0.010910987854003906 total time spend for step 8 : 0.12107515335083008 step9:velours_tree Thu Feb 13 17:24:34 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 : 20515174,20515187,20515185,20515177,20515178,20515180,20515182,20515183,20515184,20515188,20515189,20515190,20515191 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=20515174 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=20515187 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=20515185 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=20515177 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=20515178 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=20515180 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=20515182 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=20515183 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=20515184 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=20515188 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=20515189 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=20515190 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=20515191 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 378 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [1 4 1 5 1 5 0 5 3 1 3 3 5 3 2 0 1 3 1 2 2 1 1 1 1 1 1 5 1 5 0 4 5 1 2 3 3 5 2 5 3 3 2 2 1 0 3 2 2 2 1 1 2 1 2 5 5 0 1 1 1 1 4 3 3 5 2 1 5 5 3 0 4 1 4 1 0 1 2 1 1 4 4 2 1 4 1 1 1 3 1 1 3 2 4 1 3 0 1 2 3 4 3 1 3 2 4 2 3 1 1 1 0 1 1 1 1 3 1 3 4 4 0 4 0 0 1 0 3 4 1 1 2 2 1 5 1 0 3 1 1 3 1 0 1 1 1 1 3 1 3 3 0 0 0 1 3 1 0 0 4 1 5 5 0 2 2 2 3 4 1 4 0 4 4 2 4 4 1 1 0 1 1 1 3 5 4 0 0 0 4 1 3 1 1 0 1 0 5 5 5 3 5 3 0 1 3 4 3 0 2 1 1 1 3 3 4 0 3 1 4 0 4 4 1 1 1 0 2 0 3 0 5 5 0 3 4 4 5 5 0 5 1 1 4 4 2 1 4 5 1 0 2 4 1 2 1 4 1 3 2 0 1 2 1 0 1 1 0 1 1 5 1 2 5 5 4 3 5 5 2 4 4 2 2 3 5 0 3 1 2 1 2 4 5 2 3 1 0 1 3 2 4 4 2 3 5 3 4 3 0 3 5 1 4 4 1 0 5 2 3 1 0 0 3 1 0 1 0 4 2 3 3 2 2 0 3 3 0 4 3 4 5 2 4 4 2 4 4 1 3 1 4 1 0 0 0 0 4 4 3 2 5 4 5 5 3 2 2 0 2 4 2 4 4 3 4 4] Elapsed time: 0.1696300506591797 graph_id used : 78400 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20515174,20515187,20515185,20515177,20515178,20515180,20515182,20515183,20515184,20515188,20515189,20515190,20515191?tags=flou,carton,pet_fonce,refus,mal_croppe,papier,pehd,film_plastique,metal,pet_clair,tetrapak,environnement,autre&datou_id_consolidate=4235&port_consolidate=20514224&tree_id=78400 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1337395425] Looping around the photos to save general results len do output : 1 /20514224Didn'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, '2583047') ('4234', '20514224', '1337395425', None, None, None, None, None, '2583047') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.01373147964477539 save_final save missing photos in datou_result : time spend for datou_step_exec : 24.672687292099 time spend to save output : 0.15808796882629395 total time spend for step 9 : 24.830775260925293 step10:send_mail_cod Thu Feb 13 17:24:59 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 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_P20514224_13-02-2025_17_24_59.pdf 20515156 imagette205151561739463899 20515169 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 .imagette205151691739463899 20515167 imagette205151671739463900 20515159 imagette205151591739463900 20515160 imagette205151601739463900 20515162 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 .imagette205151621739463900 20515164 imagette205151641739463901 20515165 imagette205151651739463901 20515166 imagette205151661739463901 20515170 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 .imagette205151701739463901 20515171 imagette205151711739463901 20515173 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 .imagette205151731739463902 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20514224 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20515174,20515187,20515185,20515177,20515178,20515180,20515182,20515183,20515184,20515188,20515189,20515190,20515191?tags=flou,carton,pet_fonce,refus,mal_croppe,papier,pehd,film_plastique,metal,pet_clair,tetrapak,environnement,autre&datou_id_consolidate=4235&port_consolidate=20514224&tree_id=78400 your option no_mail is active, we will not send the real mail to your client args[1337395425] : ((1337395425, -8.494529715002352, 492609224), (1337395425, 0.18136722286957108, 2107752395), '0.7070669784657713') apple ((1337395425, -8.494529715002352, 492609224), (1337395425, 0.18136722286957108, 2107752395), '0.7070669784657713') We are sending mail with results at cod@fotonower.com refus_total : 0.7070669784657713 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=20514224 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_P20514224_13-02-2025_17_24_59.pdf results_Qualipapia_P20514224_13-02-2025_17_24_59.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20514224_13-02-2025_17_24_59.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','20514224','results_Qualipapia_P20514224_13-02-2025_17_24_59.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20514224_13-02-2025_17_24_59.pdf','pdf','','0.14','0.7070669784657713') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1337395425] 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, '2583047') ('4234', '20514224', '1337395425', None, None, None, None, None, '2583047') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.011963129043579102 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.181449890136719 time spend to save output : 0.012124300003051758 total time spend for step 10 : 4.1935741901397705 step11:split_time_score Thu Feb 13 17:25:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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', 1),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 13022025 20514224 Nombre de photos uploadées : 1 / 23040 (0%) 13022025 20514224 Nombre de photos taguées (types de déchets): 0 / 1 (0%) 13022025 20514224 Nombre de photos taguées (volume) : 0 / 1 (0%) elapsed_time : load_data_split_time_score 3.337860107421875e-06 elapsed_time : order_list_meta_photo_and_scores 8.821487426757812e-06 ? elapsed_time : fill_and_build_computed_from_old_data 0.0002276897430419922 elapsed_time : insert_dashboard_record_day_entry 0.023328542709350586 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.7320862458592583 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20494576_13-02-2025_02_24_56.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20494576 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`=20494576 AND mptpi.`type`=4230 To do Qualite : 0.7264310720241793 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20494579_13-02-2025_02_06_48.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20494579 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`=20494579 AND mptpi.`type`=4230 To do Qualite : 0.7299822365685799 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20495174_13-02-2025_03_00_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20495174 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`=20495174 AND mptpi.`type`=4230 To do Qualite : 0.7655406163139977 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20496027_13-02-2025_04_00_13.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20496027 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`=20496027 AND mptpi.`type`=4230 To do Qualite : 0.7600945025030146 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20496534_13-02-2025_05_18_30.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20496534 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`=20496534 AND mptpi.`type`=4230 To do Qualite : 0.7453883550976724 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20497999_13-02-2025_06_18_19.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20497999 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`=20497999 AND mptpi.`type`=4230 To do Qualite : 0.7391335757459001 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20499944_13-02-2025_08_37_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20499944 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`=20499944 AND mptpi.`type`=4230 To do Qualite : 0.7557882263951448 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20501972_13-02-2025_08_23_48.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20501972 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`=20501972 AND mptpi.`type`=4230 To do Qualite : 0.8595146223211381 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20504047_13-02-2025_09_19_43.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20504047 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`=20504047 AND mptpi.`type`=4230 To do Qualite : 0.5262765621769832 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20505052_13-02-2025_10_19_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20505052 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`=20505052 AND mptpi.`type`=4230 To do Qualite : 0.6061830645564577 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20505905_13-02-2025_11_27_48.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20505905 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`=20505905 AND mptpi.`type`=4230 To do Qualite : 0.6861959961273805 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20506480_13-02-2025_12_28_51.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20506480 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`=20506480 AND mptpi.`type`=4230 To do Qualite : 0.5882571610473123 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20506898_13-02-2025_13_38_15.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20506898 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`=20506898 AND mptpi.`type`=4230 To do Qualite : 0.7235509862464906 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20507272_13-02-2025_14_23_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20507272 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`=20507272 AND mptpi.`type`=4230 To do Qualite : 0.6651247030685383 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20509327_13-02-2025_15_27_58.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20509327 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`=20509327 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20511672 order by id desc limit 1 Qualite : 0.7070669784657713 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20514224_13-02-2025_17_24_59.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20514224 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`=20514224 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'13022025': {'nb_upload': 1, '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 [1337395425] Looping around the photos to save general results len do output : 1 /20514224Didn'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, '2583047') ('4234', '20514224', '1337395425', None, None, None, None, None, '2583047') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.012745380401611328 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.9252004623413086 time spend to save output : 0.01313924789428711 total time spend for step 11 : 1.9383397102355957 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 1 set_done_treatment 54.22user 30.02system 4:41.23elapsed 29%CPU (0avgtext+0avgdata 2361624maxresident)k 1424008inputs+22280outputs (16979major+4950131minor)pagefaults 0swaps