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 : 586718 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 : ['2614741'] with mtr_portfolio_ids : ['20824223'] and first list_photo_ids : [] new path : /proc/586718/ 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 : 0.17781591415405273 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Wed Feb 26 06:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 5289 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-26 06:20:31.113101: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-26 06:20:31.139344: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-26 06:20:31.141835: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f885c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-26 06:20:31.141898: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-26 06:20:31.146521: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-26 06:20:31.420130: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x44048c50 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-26 06:20:31.420178: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-26 06:20:31.421125: 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 2025-02-26 06:20:31.421435: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 06:20:31.423631: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 06:20:31.442144: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 06:20:31.442718: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 06:20:31.475695: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 06:20:31.479119: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 06:20:31.531888: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 06:20:31.533289: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 06:20:31.533710: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 06:20:31.534459: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-26 06:20:31.534478: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-26 06:20:31.534489: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-26 06:20:31.536121: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4827 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. 2025-02-26 06:20:31.812876: 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 2025-02-26 06:20:31.812986: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 06:20:31.813021: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 06:20:31.813047: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 06:20:31.813075: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 06:20:31.813113: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 06:20:31.813143: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 06:20:31.813176: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 06:20:31.814936: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 06:20:31.816204: 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 2025-02-26 06:20:31.816239: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-26 06:20:31.816261: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 06:20:31.816282: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-26 06:20:31.816297: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-26 06:20:31.816311: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-26 06:20:31.816328: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-26 06:20:31.816351: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 06:20:31.817388: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-26 06:20:31.817417: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-26 06:20:31.817426: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-26 06:20:31.817433: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-26 06:20:31.818525: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4827 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 : [] 2025-02-26 06:20:41.504955: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-26 06:20:41.725453: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-26 06:20:43.623738: 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: 17.00000 max: 224.00000 molded_images shape: (1, 640, 640, 3) min: -103.43438 max: 101.12734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.000278472900390625 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.57109 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 680 time to create 1 rle with old method : 0.0008780956268310547 length of segment : 29 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00031113624572753906 length of segment : 12 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.00029587745666503906 length of segment : 14 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.001283407211303711 length of segment : 79 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0009200572967529297 length of segment : 35 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0010998249053955078 length of segment : 29 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.0010960102081298828 length of segment : 133 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0004546642303466797 length of segment : 34 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 2276 time to create 1 rle with old method : 0.003053903579711914 length of segment : 121 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 2970 time to create 1 rle with old method : 0.0035142898559570312 length of segment : 109 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1828 time to create 1 rle with old method : 0.0023806095123291016 length of segment : 62 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0007510185241699219 length of segment : 25 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 2913 time to create 1 rle with old method : 0.0036776065826416016 length of segment : 69 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 1003 time to create 1 rle with old method : 0.0012564659118652344 length of segment : 107 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 428 time to create 1 rle with old method : 0.0005931854248046875 length of segment : 82 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 2697 time to create 1 rle with old method : 0.0031566619873046875 length of segment : 108 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.00041103363037109375 length of segment : 31 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004100799560546875 length of segment : 31 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 3143 time to create 1 rle with old method : 0.0037848949432373047 length of segment : 70 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 659 time to create 1 rle with old method : 0.0008585453033447266 length of segment : 33 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007193088531494141 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.68047 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 : 5.698204040527344e-05 nb_pixel_total : 684 time to create 1 rle with old method : 0.0010673999786376953 length of segment : 20 time for calcul the mask position with numpy : 0.00020551681518554688 nb_pixel_total : 11370 time to create 1 rle with old method : 0.013929605484008789 length of segment : 108 time for calcul the mask position with numpy : 0.00013518333435058594 nb_pixel_total : 4178 time to create 1 rle with old method : 0.005303382873535156 length of segment : 99 time for calcul the mask position with numpy : 0.00010228157043457031 nb_pixel_total : 2666 time to create 1 rle with old method : 0.0035042762756347656 length of segment : 73 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1082 time to create 1 rle with old method : 0.0013713836669921875 length of segment : 60 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 1798 time to create 1 rle with old method : 0.002341747283935547 length of segment : 39 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1941 time to create 1 rle with old method : 0.0025131702423095703 length of segment : 41 time for calcul the mask position with numpy : 0.00010275840759277344 nb_pixel_total : 4022 time to create 1 rle with old method : 0.004687070846557617 length of segment : 108 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003790855407714844 length of segment : 21 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 2435 time to create 1 rle with old method : 0.003045320510864258 length of segment : 76 time for calcul the mask position with numpy : 0.0001246929168701172 nb_pixel_total : 3923 time to create 1 rle with old method : 0.004862546920776367 length of segment : 117 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004832744598388672 length of segment : 32 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 491 time to create 1 rle with old method : 0.0008132457733154297 length of segment : 57 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0008251667022705078 length of segment : 26 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00016808509826660156 length of segment : 8 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.0004382133483886719 length of segment : 19 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 4163 time to create 1 rle with old method : 0.005313873291015625 length of segment : 59 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0005550384521484375 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.78594 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 : 8.702278137207031e-05 nb_pixel_total : 2224 time to create 1 rle with old method : 0.002717256546020508 length of segment : 62 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 3172 time to create 1 rle with old method : 0.003965139389038086 length of segment : 76 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 431 time to create 1 rle with old method : 0.0006170272827148438 length of segment : 23 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00021767616271972656 length of segment : 21 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1397 time to create 1 rle with old method : 0.001697540283203125 length of segment : 78 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0002415180206298828 length of segment : 7 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008828639984130859 length of segment : 75 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1514 time to create 1 rle with old method : 0.0020530223846435547 length of segment : 45 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1060 time to create 1 rle with old method : 0.0015571117401123047 length of segment : 21 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1101 time to create 1 rle with old method : 0.0014925003051757812 length of segment : 37 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.00035572052001953125 length of segment : 14 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0006520748138427734 length of segment : 27 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0004494190216064453 length of segment : 20 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0006694793701171875 length of segment : 25 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 78 time to create 1 rle with old method : 0.00015115737915039062 length of segment : 9 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004596710205078125 length of segment : 24 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 2135 time to create 1 rle with old method : 0.002652883529663086 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: -121.92266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1521 time to create 1 rle with old method : 0.0019347667694091797 length of segment : 30 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 1482 time to create 1 rle with old method : 0.0023980140686035156 length of segment : 49 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 2114 time to create 1 rle with old method : 0.0027494430541992188 length of segment : 41 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00030303001403808594 length of segment : 12 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0003464221954345703 length of segment : 15 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 964 time to create 1 rle with old method : 0.0012929439544677734 length of segment : 36 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005550384521484375 length of segment : 32 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 560 time to create 1 rle with old method : 0.0008227825164794922 length of segment : 22 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.0002524852752685547 length of segment : 10 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.0009398460388183594 length of segment : 26 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0009675025939941406 length of segment : 25 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.0005104541778564453 length of segment : 20 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 51 time to create 1 rle with old method : 0.00015807151794433594 length of segment : 6 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 488 time to create 1 rle with old method : 0.000949859619140625 length of segment : 24 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00029754638671875 length of segment : 14 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 737 time to create 1 rle with old method : 0.0014026165008544922 length of segment : 35 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0003800392150878906 length of segment : 14 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0005407333374023438 length of segment : 17 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 50 time to create 1 rle with old method : 0.0002079010009765625 length of segment : 17 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0009543895721435547 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.19219 max: 150.99453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 466 time to create 1 rle with old method : 0.0006515979766845703 length of segment : 31 time for calcul the mask position with numpy : 0.00021147727966308594 nb_pixel_total : 10640 time to create 1 rle with old method : 0.012490510940551758 length of segment : 149 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 523 time to create 1 rle with old method : 0.0007696151733398438 length of segment : 24 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 960 time to create 1 rle with old method : 0.0012583732604980469 length of segment : 44 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 859 time to create 1 rle with old method : 0.001096963882446289 length of segment : 41 time for calcul the mask position with numpy : 0.00018739700317382812 nb_pixel_total : 9783 time to create 1 rle with old method : 0.012105226516723633 length of segment : 142 Processing 1 images image shape: (400, 160, 3) min: 11.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 107.16250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.69219 max: 147.70156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.0002257823944091797 nb_pixel_total : 8385 time to create 1 rle with old method : 0.016919851303100586 length of segment : 163 time for calcul the mask position with numpy : 0.00011658668518066406 nb_pixel_total : 323 time to create 1 rle with old method : 0.0006804466247558594 length of segment : 60 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00041985511779785156 length of segment : 27 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 1755 time to create 1 rle with old method : 0.0031282901763916016 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: -123.00078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 2783 time to create 1 rle with old method : 0.003332853317260742 length of segment : 109 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 1352 time to create 1 rle with old method : 0.001764059066772461 length of segment : 61 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 380 time to create 1 rle with old method : 0.0005061626434326172 length of segment : 29 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1217 time to create 1 rle with old method : 0.0016350746154785156 length of segment : 46 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0009038448333740234 length of segment : 35 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1779 time to create 1 rle with old method : 0.002314329147338867 length of segment : 49 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0009839534759521484 length of segment : 56 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.0015697479248046875 length of segment : 50 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.00046515464782714844 length of segment : 28 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 2373 time to create 1 rle with old method : 0.0029096603393554688 length of segment : 56 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0006809234619140625 length of segment : 28 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0008416175842285156 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.37578 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 32 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 847 time to create 1 rle with old method : 0.0011093616485595703 length of segment : 30 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0006120204925537109 length of segment : 28 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1147 time to create 1 rle with old method : 0.0014867782592773438 length of segment : 43 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.0011479854583740234 length of segment : 32 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 2456 time to create 1 rle with old method : 0.0031464099884033203 length of segment : 58 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1498 time to create 1 rle with old method : 0.0020253658294677734 length of segment : 48 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1507 time to create 1 rle with old method : 0.0019953250885009766 length of segment : 40 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.002026081085205078 length of segment : 41 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 3743 time to create 1 rle with old method : 0.00434112548828125 length of segment : 84 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 2062 time to create 1 rle with old method : 0.0028748512268066406 length of segment : 46 time for calcul the mask position with numpy : 9.560585021972656e-05 nb_pixel_total : 3400 time to create 1 rle with old method : 0.0042264461517333984 length of segment : 132 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1424 time to create 1 rle with old method : 0.0019216537475585938 length of segment : 37 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 3031 time to create 1 rle with old method : 0.0037970542907714844 length of segment : 103 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003228187561035156 length of segment : 16 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1706 time to create 1 rle with old method : 0.0022928714752197266 length of segment : 47 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1739 time to create 1 rle with old method : 0.0022928714752197266 length of segment : 48 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.0002970695495605469 length of segment : 13 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1207 time to create 1 rle with old method : 0.0013904571533203125 length of segment : 66 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 786 time to create 1 rle with old method : 0.0010356903076171875 length of segment : 40 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 619 time to create 1 rle with old method : 0.0008406639099121094 length of segment : 40 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 3153 time to create 1 rle with old method : 0.0037834644317626953 length of segment : 64 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0006268024444580078 length of segment : 23 time for calcul the mask position with numpy : 6.723403930664062e-05 nb_pixel_total : 1381 time to create 1 rle with old method : 0.0019373893737792969 length of segment : 43 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0007350444793701172 length of segment : 28 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 1855 time to create 1 rle with old method : 0.002257108688354492 length of segment : 58 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 3372 time to create 1 rle with old method : 0.004078388214111328 length of segment : 104 time for calcul the mask position with numpy : 0.00012350082397460938 nb_pixel_total : 2917 time to create 1 rle with old method : 0.004853487014770508 length of segment : 67 time for calcul the mask position with numpy : 9.322166442871094e-05 nb_pixel_total : 2507 time to create 1 rle with old method : 0.0033495426177978516 length of segment : 71 time for calcul the mask position with numpy : 7.843971252441406e-05 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0018892288208007812 length of segment : 62 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1486 time to create 1 rle with old method : 0.0018639564514160156 length of segment : 40 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002980232238769531 length of segment : 16 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1006 time to create 1 rle with old method : 0.0012543201446533203 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -106.28203 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 : 0.00014066696166992188 nb_pixel_total : 9690 time to create 1 rle with old method : 0.011499643325805664 length of segment : 121 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0007576942443847656 length of segment : 32 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1086 time to create 1 rle with old method : 0.0014977455139160156 length of segment : 39 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005440711975097656 length of segment : 25 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1616 time to create 1 rle with old method : 0.0028569698333740234 length of segment : 61 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 2107 time to create 1 rle with old method : 0.0028541088104248047 length of segment : 69 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007579326629638672 length of segment : 28 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0007853507995605469 length of segment : 25 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.0003943443298339844 length of segment : 38 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003693103790283203 length of segment : 16 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 434 time to create 1 rle with old method : 0.0005691051483154297 length of segment : 29 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 671 time to create 1 rle with old method : 0.000942230224609375 length of segment : 29 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003685951232910156 length of segment : 16 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1522 time to create 1 rle with old method : 0.0022699832916259766 length of segment : 54 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1542 time to create 1 rle with old method : 0.0019807815551757812 length of segment : 74 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.57109 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 : 6.580352783203125e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0008757114410400391 length of segment : 33 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 2438 time to create 1 rle with old method : 0.0037965774536132812 length of segment : 62 time for calcul the mask position with numpy : 0.0001709461212158203 nb_pixel_total : 6205 time to create 1 rle with old method : 0.009876251220703125 length of segment : 93 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 2790 time to create 1 rle with old method : 0.0034530162811279297 length of segment : 69 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0007843971252441406 length of segment : 30 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 1283 time to create 1 rle with old method : 0.0016908645629882812 length of segment : 44 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 909 time to create 1 rle with old method : 0.0011341571807861328 length of segment : 63 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 716 time to create 1 rle with old method : 0.0009827613830566406 length of segment : 50 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003154277801513672 length of segment : 40 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1051 time to create 1 rle with old method : 0.0013370513916015625 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: -119.18047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.000881195068359375 length of segment : 37 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005402565002441406 length of segment : 23 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 646 time to create 1 rle with old method : 0.0009047985076904297 length of segment : 37 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.0004591941833496094 length of segment : 20 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1552 time to create 1 rle with old method : 0.001995563507080078 length of segment : 99 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1928 time to create 1 rle with old method : 0.0024840831756591797 length of segment : 66 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1323 time to create 1 rle with old method : 0.0018491744995117188 length of segment : 39 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.00038170814514160156 length of segment : 32 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 515 time to create 1 rle with old method : 0.0007071495056152344 length of segment : 34 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00024890899658203125 length of segment : 28 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0004203319549560547 length of segment : 49 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005385875701904297 length of segment : 27 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002644062042236328 length of segment : 22 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1997 time to create 1 rle with old method : 0.002560138702392578 length of segment : 65 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.91250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.00038623809814453125 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.53203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 639 time to create 1 rle with old method : 0.0008747577667236328 length of segment : 92 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0004458427429199219 length of segment : 26 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2002 time to create 1 rle with old method : 0.0025942325592041016 length of segment : 65 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.00020623207092285156 length of segment : 19 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00035762786865234375 length of segment : 42 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0007452964782714844 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.61797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 28 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0006778240203857422 length of segment : 34 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1402 time to create 1 rle with old method : 0.001764059066772461 length of segment : 46 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1224 time to create 1 rle with old method : 0.0019948482513427734 length of segment : 58 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 529 time to create 1 rle with old method : 0.0007066726684570312 length of segment : 37 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0003046989440917969 length of segment : 20 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 2997 time to create 1 rle with old method : 0.0038747787475585938 length of segment : 69 time for calcul the mask position with numpy : 0.00011277198791503906 nb_pixel_total : 4432 time to create 1 rle with old method : 0.005579471588134766 length of segment : 68 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0006067752838134766 length of segment : 15 time for calcul the mask position with numpy : 0.0003376007080078125 nb_pixel_total : 11476 time to create 1 rle with old method : 0.013185739517211914 length of segment : 139 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1121 time to create 1 rle with old method : 0.0014503002166748047 length of segment : 66 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1396 time to create 1 rle with old method : 0.0018076896667480469 length of segment : 61 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.00043964385986328125 length of segment : 15 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0006380081176757812 length of segment : 27 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.00031685829162597656 length of segment : 30 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1012 time to create 1 rle with old method : 0.0013384819030761719 length of segment : 41 time for calcul the mask position with numpy : 0.0001163482666015625 nb_pixel_total : 2555 time to create 1 rle with old method : 0.00325775146484375 length of segment : 71 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003540515899658203 length of segment : 23 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 846 time to create 1 rle with old method : 0.0013871192932128906 length of segment : 41 time for calcul the mask position with numpy : 0.00022482872009277344 nb_pixel_total : 10662 time to create 1 rle with old method : 0.012432575225830078 length of segment : 143 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0005853176116943359 length of segment : 20 time for calcul the mask position with numpy : 0.00010085105895996094 nb_pixel_total : 4207 time to create 1 rle with old method : 0.005351543426513672 length of segment : 69 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0027039051055908203 length of segment : 69 time for calcul the mask position with numpy : 0.000331878662109375 nb_pixel_total : 11393 time to create 1 rle with old method : 0.013733625411987305 length of segment : 181 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 2500 time to create 1 rle with old method : 0.003022909164428711 length of segment : 73 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006623268127441406 length of segment : 24 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.0004601478576660156 length of segment : 21 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 2456 time to create 1 rle with old method : 0.0031003952026367188 length of segment : 76 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 871 time to create 1 rle with old method : 0.0011096000671386719 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.94219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 0.00011944770812988281 nb_pixel_total : 4760 time to create 1 rle with old method : 0.005567789077758789 length of segment : 110 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002963542938232422 length of segment : 12 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 875 time to create 1 rle with old method : 0.0011188983917236328 length of segment : 35 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 884 time to create 1 rle with old method : 0.0011470317840576172 length of segment : 39 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 3821 time to create 1 rle with old method : 0.004900932312011719 length of segment : 59 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 3682 time to create 1 rle with old method : 0.004487514495849609 length of segment : 90 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005884170532226562 length of segment : 25 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 3634 time to create 1 rle with old method : 0.006094455718994141 length of segment : 90 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 828 time to create 1 rle with old method : 0.0015118122100830078 length of segment : 29 time for calcul the mask position with numpy : 0.00014448165893554688 nb_pixel_total : 3586 time to create 1 rle with old method : 0.0062754154205322266 length of segment : 105 time for calcul the mask position with numpy : 0.00017333030700683594 nb_pixel_total : 5136 time to create 1 rle with old method : 0.008617877960205078 length of segment : 111 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0007290840148925781 length of segment : 31 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 2899 time to create 1 rle with old method : 0.00397038459777832 length of segment : 43 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0015854835510253906 length of segment : 33 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 2097 time to create 1 rle with old method : 0.0023865699768066406 length of segment : 71 time for calcul the mask position with numpy : 0.00020051002502441406 nb_pixel_total : 7595 time to create 1 rle with old method : 0.0091705322265625 length of segment : 137 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005719661712646484 length of segment : 24 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1256 time to create 1 rle with old method : 0.0017061233520507812 length of segment : 32 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0009241104125976562 length of segment : 28 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 696 time to create 1 rle with old method : 0.0008928775787353516 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: -112.94219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 31 time for calcul the mask position with numpy : 0.00015044212341308594 nb_pixel_total : 4752 time to create 1 rle with old method : 0.005707502365112305 length of segment : 59 time for calcul the mask position with numpy : 0.00011372566223144531 nb_pixel_total : 1335 time to create 1 rle with old method : 0.0017981529235839844 length of segment : 43 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 680 time to create 1 rle with old method : 0.0008902549743652344 length of segment : 34 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1384 time to create 1 rle with old method : 0.0017840862274169922 length of segment : 49 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0007555484771728516 length of segment : 22 time for calcul the mask position with numpy : 0.00033211708068847656 nb_pixel_total : 7276 time to create 1 rle with old method : 0.009353399276733398 length of segment : 135 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006539821624755859 length of segment : 36 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00040149688720703125 length of segment : 25 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005981922149658203 length of segment : 35 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1312 time to create 1 rle with old method : 0.0016455650329589844 length of segment : 54 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1480 time to create 1 rle with old method : 0.0018792152404785156 length of segment : 49 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0003185272216796875 length of segment : 20 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0008335113525390625 length of segment : 39 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1466 time to create 1 rle with old method : 0.0018575191497802734 length of segment : 36 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 2164 time to create 1 rle with old method : 0.0026390552520751953 length of segment : 46 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.00036716461181640625 length of segment : 25 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 897 time to create 1 rle with old method : 0.0012464523315429688 length of segment : 44 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00027751922607421875 length of segment : 10 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003342628479003906 length of segment : 24 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 2262 time to create 1 rle with old method : 0.0028400421142578125 length of segment : 52 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 1433 time to create 1 rle with old method : 0.0018877983093261719 length of segment : 81 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00018072128295898438 length of segment : 16 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 1183 time to create 1 rle with old method : 0.0016486644744873047 length of segment : 37 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.00027251243591308594 length of segment : 14 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 17 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00039315223693847656 length of segment : 16 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1272 time to create 1 rle with old method : 0.0016622543334960938 length of segment : 55 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003879070281982422 length of segment : 15 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1372 time to create 1 rle with old method : 0.0018336772918701172 length of segment : 44 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.0003063678741455078 length of segment : 19 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 3425 time to create 1 rle with old method : 0.004356861114501953 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 9.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.27422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0006461143493652344 length of segment : 29 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 2901 time to create 1 rle with old method : 0.005797386169433594 length of segment : 56 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 1447 time to create 1 rle with old method : 0.001932382583618164 length of segment : 43 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0005702972412109375 length of segment : 23 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0007500648498535156 length of segment : 17 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1330 time to create 1 rle with old method : 0.0017218589782714844 length of segment : 30 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0003173351287841797 length of segment : 24 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.00030612945556640625 length of segment : 20 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005393028259277344 length of segment : 29 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 1199 time to create 1 rle with old method : 0.0016498565673828125 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.02813 max: 144.29922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 499 time to create 1 rle with old method : 0.0006775856018066406 length of segment : 45 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00038242340087890625 length of segment : 20 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 1039 time to create 1 rle with old method : 0.001344442367553711 length of segment : 71 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 111 time to create 1 rle with old method : 0.0001881122589111328 length of segment : 17 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.0004494190216064453 length of segment : 45 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.00027942657470703125 length of segment : 18 Processing 1 images image shape: (400, 160, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003807544708251953 length of segment : 23 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 53 time to create 1 rle with old method : 0.00010013580322265625 length of segment : 12 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.00035262107849121094 length of segment : 22 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00021910667419433594 length of segment : 30 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1237 time to create 1 rle with old method : 0.0017621517181396484 length of segment : 39 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00029540061950683594 length of segment : 27 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006296634674072266 length of segment : 26 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00012254714965820312 length of segment : 12 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001659393310546875 length of segment : 11 Processing 1 images image shape: (240, 400, 3) min: 6.00000 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 : 9 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.00044035911560058594 length of segment : 36 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.00025844573974609375 length of segment : 21 time for calcul the mask position with numpy : 0.00016999244689941406 nb_pixel_total : 3601 time to create 1 rle with old method : 0.0046234130859375 length of segment : 229 time for calcul the mask position with numpy : 0.000110626220703125 nb_pixel_total : 4014 time to create 1 rle with old method : 0.004957914352416992 length of segment : 145 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0007648468017578125 length of segment : 35 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 454 time to create 1 rle with old method : 0.0006039142608642578 length of segment : 69 time for calcul the mask position with numpy : 0.000156402587890625 nb_pixel_total : 8893 time to create 1 rle with old method : 0.01070713996887207 length of segment : 135 time for calcul the mask position with numpy : 0.00013184547424316406 nb_pixel_total : 6881 time to create 1 rle with old method : 0.00807809829711914 length of segment : 118 time for calcul the mask position with numpy : 0.00012040138244628906 nb_pixel_total : 7162 time to create 1 rle with old method : 0.00842595100402832 length of segment : 127 Processing 1 images image shape: (240, 400, 3) min: 9.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002810955047607422 length of segment : 17 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0004119873046875 length of segment : 23 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 2161 time to create 1 rle with old method : 0.0028319358825683594 length of segment : 46 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 686 time to create 1 rle with old method : 0.00096893310546875 length of segment : 40 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1981 time to create 1 rle with old method : 0.0023221969604492188 length of segment : 91 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 : 13 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.000568389892578125 length of segment : 21 time for calcul the mask position with numpy : 0.00018334388732910156 nb_pixel_total : 11092 time to create 1 rle with old method : 0.01774144172668457 length of segment : 146 time for calcul the mask position with numpy : 0.0002868175506591797 nb_pixel_total : 12152 time to create 1 rle with old method : 0.020059823989868164 length of segment : 105 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.0007052421569824219 length of segment : 14 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0003170967102050781 length of segment : 23 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 2209 time to create 1 rle with old method : 0.002850055694580078 length of segment : 42 time for calcul the mask position with numpy : 0.0001506805419921875 nb_pixel_total : 4245 time to create 1 rle with old method : 0.0056188106536865234 length of segment : 52 time for calcul the mask position with numpy : 0.00010466575622558594 nb_pixel_total : 1698 time to create 1 rle with old method : 0.0023119449615478516 length of segment : 35 time for calcul the mask position with numpy : 0.0001652240753173828 nb_pixel_total : 5160 time to create 1 rle with old method : 0.006418704986572266 length of segment : 146 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.00016641616821289062 length of segment : 9 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1649 time to create 1 rle with old method : 0.002147197723388672 length of segment : 33 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.00038361549377441406 length of segment : 20 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.00044274330139160156 length of segment : 21 Processing 1 images image shape: (240, 400, 3) min: 10.00000 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 : 5.245208740234375e-05 nb_pixel_total : 853 time to create 1 rle with old method : 0.0011332035064697266 length of segment : 48 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0004608631134033203 length of segment : 34 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0007822513580322266 length of segment : 25 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004928112030029297 length of segment : 18 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 2475 time to create 1 rle with old method : 0.0030755996704101562 length of segment : 188 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 1460 time to create 1 rle with old method : 0.0018715858459472656 length of segment : 67 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.00122833251953125 length of segment : 20 time for calcul the mask position with numpy : 0.0001678466796875 nb_pixel_total : 3894 time to create 1 rle with old method : 0.004996061325073242 length of segment : 111 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.000247955322265625 length of segment : 14 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1551 time to create 1 rle with old method : 0.0019354820251464844 length of segment : 74 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.00030517578125 length of segment : 25 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.0002486705780029297 length of segment : 10 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 4906 time to create 1 rle with old method : 0.0059740543365478516 length of segment : 84 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1450 time to create 1 rle with old method : 0.0021452903747558594 length of segment : 37 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1212 time to create 1 rle with old method : 0.0018324851989746094 length of segment : 23 Processing 1 images image shape: (240, 400, 3) min: 9.00000 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 : 20 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0013773441314697266 length of segment : 35 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0007572174072265625 length of segment : 20 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.00038552284240722656 length of segment : 26 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 750 time to create 1 rle with old method : 0.0009734630584716797 length of segment : 46 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1214 time to create 1 rle with old method : 0.0016713142395019531 length of segment : 33 time for calcul the mask position with numpy : 0.0001289844512939453 nb_pixel_total : 7585 time to create 1 rle with old method : 0.009311437606811523 length of segment : 106 time for calcul the mask position with numpy : 0.000125885009765625 nb_pixel_total : 4267 time to create 1 rle with old method : 0.005011320114135742 length of segment : 90 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 1958 time to create 1 rle with old method : 0.0025091171264648438 length of segment : 49 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1442 time to create 1 rle with old method : 0.0019102096557617188 length of segment : 35 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 2212 time to create 1 rle with old method : 0.0028831958770751953 length of segment : 45 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1507 time to create 1 rle with old method : 0.0017974376678466797 length of segment : 64 time for calcul the mask position with numpy : 0.0003600120544433594 nb_pixel_total : 23463 time to create 1 rle with old method : 0.028898000717163086 length of segment : 212 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0008020401000976562 length of segment : 22 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1488 time to create 1 rle with old method : 0.0017962455749511719 length of segment : 66 time for calcul the mask position with numpy : 0.00015354156494140625 nb_pixel_total : 8024 time to create 1 rle with old method : 0.009679794311523438 length of segment : 121 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1370 time to create 1 rle with old method : 0.0018227100372314453 length of segment : 34 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.0006029605865478516 length of segment : 29 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1077 time to create 1 rle with old method : 0.00139617919921875 length of segment : 89 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007851123809814453 length of segment : 24 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1487 time to create 1 rle with old method : 0.002049684524536133 length of segment : 30 Processing 1 images image shape: (240, 400, 3) min: 10.00000 max: 244.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 129.33828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002799034118652344 length of segment : 16 time for calcul the mask position with numpy : 0.00036978721618652344 nb_pixel_total : 31249 time to create 1 rle with old method : 0.037686824798583984 length of segment : 116 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.0002658367156982422 length of segment : 18 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 997 time to create 1 rle with old method : 0.0012774467468261719 length of segment : 68 time for calcul the mask position with numpy : 0.0001804828643798828 nb_pixel_total : 12917 time to create 1 rle with old method : 0.015694618225097656 length of segment : 117 time for calcul the mask position with numpy : 0.00017976760864257812 nb_pixel_total : 12443 time to create 1 rle with old method : 0.0141754150390625 length of segment : 133 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.0006561279296875 length of segment : 19 Processing 1 images image shape: (240, 160, 3) min: 42.00000 max: 183.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 76.67889 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Detection mask done ! Trying to reset tf kernel 587250 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 187 tf kernel not reseted sub process len(results) : 350 len(list_Values) 350 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 350 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 : 5068 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 350 chid ids of type : 4228 Number RLEs to save : 17215 save missing photos in datou_result : time spend for datou_step_exec : 26.28883194923401 time spend to save output : 1.9325988292694092 total time spend for step 1 : 28.221430778503418 step2:brightness Wed Feb 26 06:20:56 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/1740547228_586718_1339667907_6486cf858f0838cea29def38b31a872e.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 : 0.011172294616699219 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 : 0.015045404434204102 save missing photos in datou_result : time spend for datou_step_exec : 0.45889973640441895 time spend to save output : 0.030535459518432617 total time spend for step 2 : 0.48943519592285156 step3:blur_detection Wed Feb 26 06:20:57 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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/1740547228_586718_1339667907_6486cf858f0838cea29def38b31a872e.jpg resize: (1440, 2560) 1339667907 -7.955845070451469 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 : 0.015901565551757812 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 : 0.013332128524780273 save missing photos in datou_result : time spend for datou_step_exec : 2.3728179931640625 time spend to save output : 0.03335905075073242 total time spend for step 3 : 2.406177043914795 step4:rle_unique_nms_with_priority Wed Feb 26 06:20:59 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 Begin step rle-unique-nms batch 1 Loaded 350 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 347 nb_hashtags : 7 time to prepare the origin masks : 2.1405346393585205 time for calcul the mask position with numpy : 0.48082613945007324 nb_pixel_total : 3187750 time to create 1 rle with new method : 0.4204540252685547 time for calcul the mask position with numpy : 0.014938116073608398 nb_pixel_total : 111 time to create 1 rle with old method : 0.00015354156494140625 time for calcul the mask position with numpy : 0.015378952026367188 nb_pixel_total : 18 time to create 1 rle with old method : 7.200241088867188e-05 time for calcul the mask position with numpy : 0.015011310577392578 nb_pixel_total : 485 time to create 1 rle with old method : 0.0006427764892578125 time for calcul the mask position with numpy : 0.014984846115112305 nb_pixel_total : 51 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.014603853225708008 nb_pixel_total : 79 time to create 1 rle with old method : 0.0001163482666015625 time for calcul the mask position with numpy : 0.01502537727355957 nb_pixel_total : 183 time to create 1 rle with old method : 0.00022745132446289062 time for calcul the mask position with numpy : 0.014598369598388672 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003008842468261719 time for calcul the mask position with numpy : 0.01484823226928711 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006330013275146484 time for calcul the mask position with numpy : 0.014920711517333984 nb_pixel_total : 2114 time to create 1 rle with old method : 0.0024077892303466797 time for calcul the mask position with numpy : 0.01461338996887207 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006158351898193359 time for calcul the mask position with numpy : 0.015052080154418945 nb_pixel_total : 495 time to create 1 rle with old method : 0.0006191730499267578 time for calcul the mask position with numpy : 0.014930963516235352 nb_pixel_total : 173 time to create 1 rle with old method : 0.00024366378784179688 time for calcul the mask position with numpy : 0.015526294708251953 nb_pixel_total : 132 time to create 1 rle with old method : 0.00017905235290527344 time for calcul the mask position with numpy : 0.014913082122802734 nb_pixel_total : 665 time to create 1 rle with old method : 0.0007147789001464844 time for calcul the mask position with numpy : 0.014755964279174805 nb_pixel_total : 1798 time to create 1 rle with old method : 0.002179861068725586 time for calcul the mask position with numpy : 0.014994144439697266 nb_pixel_total : 317 time to create 1 rle with old method : 0.0004017353057861328 time for calcul the mask position with numpy : 0.014920234680175781 nb_pixel_total : 474 time to create 1 rle with old method : 0.0005135536193847656 time for calcul the mask position with numpy : 0.014699697494506836 nb_pixel_total : 140 time to create 1 rle with old method : 0.00017452239990234375 time for calcul the mask position with numpy : 0.014528512954711914 nb_pixel_total : 1482 time to create 1 rle with old method : 0.001680135726928711 time for calcul the mask position with numpy : 0.014765262603759766 nb_pixel_total : 310 time to create 1 rle with old method : 0.0003864765167236328 time for calcul the mask position with numpy : 0.014941215515136719 nb_pixel_total : 78 time to create 1 rle with old method : 0.00010848045349121094 time for calcul the mask position with numpy : 0.01425027847290039 nb_pixel_total : 204 time to create 1 rle with old method : 0.00022363662719726562 time for calcul the mask position with numpy : 0.01470184326171875 nb_pixel_total : 103 time to create 1 rle with old method : 0.0001499652862548828 time for calcul the mask position with numpy : 0.014694690704345703 nb_pixel_total : 865 time to create 1 rle with old method : 0.0009894371032714844 time for calcul the mask position with numpy : 0.014273881912231445 nb_pixel_total : 85 time to create 1 rle with old method : 0.00011324882507324219 time for calcul the mask position with numpy : 0.01464700698852539 nb_pixel_total : 309 time to create 1 rle with old method : 0.00038909912109375 time for calcul the mask position with numpy : 0.014855384826660156 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005483627319335938 time for calcul the mask position with numpy : 0.014876365661621094 nb_pixel_total : 737 time to create 1 rle with old method : 0.0008549690246582031 time for calcul the mask position with numpy : 0.015230655670166016 nb_pixel_total : 463 time to create 1 rle with old method : 0.0005488395690917969 time for calcul the mask position with numpy : 0.01531839370727539 nb_pixel_total : 168 time to create 1 rle with old method : 0.00022172927856445312 time for calcul the mask position with numpy : 0.0161130428314209 nb_pixel_total : 428 time to create 1 rle with old method : 0.0007982254028320312 time for calcul the mask position with numpy : 0.015977144241333008 nb_pixel_total : 680 time to create 1 rle with old method : 0.0009980201721191406 time for calcul the mask position with numpy : 0.015380859375 nb_pixel_total : 1514 time to create 1 rle with old method : 0.001794576644897461 time for calcul the mask position with numpy : 0.014937400817871094 nb_pixel_total : 972 time to create 1 rle with old method : 0.001214742660522461 time for calcul the mask position with numpy : 0.01508021354675293 nb_pixel_total : 1003 time to create 1 rle with old method : 0.0011529922485351562 time for calcul the mask position with numpy : 0.015013933181762695 nb_pixel_total : 220 time to create 1 rle with old method : 0.00029158592224121094 time for calcul the mask position with numpy : 0.014832019805908203 nb_pixel_total : 1607 time to create 1 rle with old method : 0.0024576187133789062 time for calcul the mask position with numpy : 0.014706611633300781 nb_pixel_total : 1941 time to create 1 rle with old method : 0.0022089481353759766 time for calcul the mask position with numpy : 0.01541900634765625 nb_pixel_total : 257 time to create 1 rle with old method : 0.00033354759216308594 time for calcul the mask position with numpy : 0.01468348503112793 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003216266632080078 time for calcul the mask position with numpy : 0.014946937561035156 nb_pixel_total : 2224 time to create 1 rle with old method : 0.00249481201171875 time for calcul the mask position with numpy : 0.014432907104492188 nb_pixel_total : 27 time to create 1 rle with old method : 4.8160552978515625e-05 time for calcul the mask position with numpy : 0.014913320541381836 nb_pixel_total : 2666 time to create 1 rle with old method : 0.0036258697509765625 time for calcul the mask position with numpy : 0.014801263809204102 nb_pixel_total : 10640 time to create 1 rle with old method : 0.01167607307434082 time for calcul the mask position with numpy : 0.015774011611938477 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009462833404541016 time for calcul the mask position with numpy : 0.014752626419067383 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005433559417724609 time for calcul the mask position with numpy : 0.015017509460449219 nb_pixel_total : 560 time to create 1 rle with old method : 0.0006513595581054688 time for calcul the mask position with numpy : 0.014803171157836914 nb_pixel_total : 1082 time to create 1 rle with old method : 0.001607656478881836 time for calcul the mask position with numpy : 0.01606440544128418 nb_pixel_total : 3172 time to create 1 rle with old method : 0.0037317276000976562 time for calcul the mask position with numpy : 0.015378952026367188 nb_pixel_total : 234 time to create 1 rle with old method : 0.00031304359436035156 time for calcul the mask position with numpy : 0.014802217483520508 nb_pixel_total : 11370 time to create 1 rle with old method : 0.013169050216674805 time for calcul the mask position with numpy : 0.01486349105834961 nb_pixel_total : 1060 time to create 1 rle with old method : 0.0012409687042236328 time for calcul the mask position with numpy : 0.014948368072509766 nb_pixel_total : 1521 time to create 1 rle with old method : 0.0017113685607910156 time for calcul the mask position with numpy : 0.014794349670410156 nb_pixel_total : 684 time to create 1 rle with old method : 0.0008046627044677734 time for calcul the mask position with numpy : 0.014459848403930664 nb_pixel_total : 1397 time to create 1 rle with old method : 0.0014882087707519531 time for calcul the mask position with numpy : 0.015008687973022461 nb_pixel_total : 964 time to create 1 rle with old method : 0.0009963512420654297 time for calcul the mask position with numpy : 0.018712282180786133 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003619194030761719 time for calcul the mask position with numpy : 0.014926671981811523 nb_pixel_total : 2913 time to create 1 rle with old method : 0.0032813549041748047 time for calcul the mask position with numpy : 0.015009880065917969 nb_pixel_total : 154 time to create 1 rle with old method : 0.0002257823944091797 time for calcul the mask position with numpy : 0.014709949493408203 nb_pixel_total : 4022 time to create 1 rle with old method : 0.004392385482788086 time for calcul the mask position with numpy : 0.014960527420043945 nb_pixel_total : 2970 time to create 1 rle with old method : 0.0033147335052490234 time for calcul the mask position with numpy : 0.014827728271484375 nb_pixel_total : 33 time to create 1 rle with old method : 6.937980651855469e-05 time for calcul the mask position with numpy : 0.014750003814697266 nb_pixel_total : 50 time to create 1 rle with old method : 8.797645568847656e-05 time for calcul the mask position with numpy : 0.01464700698852539 nb_pixel_total : 659 time to create 1 rle with old method : 0.0007343292236328125 time for calcul the mask position with numpy : 0.014768600463867188 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005128383636474609 time for calcul the mask position with numpy : 0.01521921157836914 nb_pixel_total : 6 time to create 1 rle with old method : 2.8371810913085938e-05 time for calcul the mask position with numpy : 0.014435291290283203 nb_pixel_total : 313 time to create 1 rle with old method : 0.00036263465881347656 time for calcul the mask position with numpy : 0.01451253890991211 nb_pixel_total : 2435 time to create 1 rle with old method : 0.002728700637817383 time for calcul the mask position with numpy : 0.014611244201660156 nb_pixel_total : 4178 time to create 1 rle with old method : 0.004631996154785156 time for calcul the mask position with numpy : 0.015565633773803711 nb_pixel_total : 523 time to create 1 rle with old method : 0.0006222724914550781 time for calcul the mask position with numpy : 0.014900922775268555 nb_pixel_total : 960 time to create 1 rle with old method : 0.0010793209075927734 time for calcul the mask position with numpy : 0.017063140869140625 nb_pixel_total : 2114 time to create 1 rle with old method : 0.002440929412841797 time for calcul the mask position with numpy : 0.01441049575805664 nb_pixel_total : 321 time to create 1 rle with old method : 0.00039267539978027344 time for calcul the mask position with numpy : 0.014873027801513672 nb_pixel_total : 431 time to create 1 rle with old method : 0.0004968643188476562 time for calcul the mask position with numpy : 0.014451980590820312 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004146099090576172 time for calcul the mask position with numpy : 0.014410257339477539 nb_pixel_total : 8 time to create 1 rle with old method : 3.2901763916015625e-05 time for calcul the mask position with numpy : 0.014481782913208008 nb_pixel_total : 3 time to create 1 rle with old method : 1.9073486328125e-05 time for calcul the mask position with numpy : 0.014606714248657227 nb_pixel_total : 1101 time to create 1 rle with old method : 0.0012793540954589844 time for calcul the mask position with numpy : 0.015065431594848633 nb_pixel_total : 186 time to create 1 rle with old method : 0.00023698806762695312 time for calcul the mask position with numpy : 0.01459813117980957 nb_pixel_total : 701 time to create 1 rle with old method : 0.0008153915405273438 time for calcul the mask position with numpy : 0.014881610870361328 nb_pixel_total : 466 time to create 1 rle with old method : 0.0004992485046386719 time for calcul the mask position with numpy : 0.014753580093383789 nb_pixel_total : 488 time to create 1 rle with old method : 0.0005352497100830078 time for calcul the mask position with numpy : 0.014174461364746094 nb_pixel_total : 556 time to create 1 rle with old method : 0.0005843639373779297 time for calcul the mask position with numpy : 0.015913009643554688 nb_pixel_total : 164 time to create 1 rle with old method : 0.0001857280731201172 time for calcul the mask position with numpy : 0.014819860458374023 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005717277526855469 time for calcul the mask position with numpy : 0.015150785446166992 nb_pixel_total : 847 time to create 1 rle with old method : 0.0009624958038330078 time for calcul the mask position with numpy : 0.015023231506347656 nb_pixel_total : 430 time to create 1 rle with old method : 0.0005154609680175781 time for calcul the mask position with numpy : 0.01551508903503418 nb_pixel_total : 59 time to create 1 rle with old method : 0.00022554397583007812 time for calcul the mask position with numpy : 0.01775360107421875 nb_pixel_total : 1706 time to create 1 rle with old method : 0.0019297599792480469 time for calcul the mask position with numpy : 0.014966487884521484 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006296634674072266 time for calcul the mask position with numpy : 0.014853477478027344 nb_pixel_total : 3031 time to create 1 rle with old method : 0.0035924911499023438 time for calcul the mask position with numpy : 0.015243053436279297 nb_pixel_total : 496 time to create 1 rle with old method : 0.0006122589111328125 time for calcul the mask position with numpy : 0.015023946762084961 nb_pixel_total : 650 time to create 1 rle with old method : 0.0007672309875488281 time for calcul the mask position with numpy : 0.01587200164794922 nb_pixel_total : 380 time to create 1 rle with old method : 0.0005080699920654297 time for calcul the mask position with numpy : 0.01497197151184082 nb_pixel_total : 1507 time to create 1 rle with old method : 0.001795053482055664 time for calcul the mask position with numpy : 0.014675140380859375 nb_pixel_total : 27 time to create 1 rle with old method : 7.295608520507812e-05 time for calcul the mask position with numpy : 0.014817953109741211 nb_pixel_total : 49 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.014688491821289062 nb_pixel_total : 434 time to create 1 rle with old method : 0.000499725341796875 time for calcul the mask position with numpy : 0.014734983444213867 nb_pixel_total : 3400 time to create 1 rle with old method : 0.003834962844848633 time for calcul the mask position with numpy : 0.014986753463745117 nb_pixel_total : 1263 time to create 1 rle with old method : 0.0017368793487548828 time for calcul the mask position with numpy : 0.01511383056640625 nb_pixel_total : 1147 time to create 1 rle with old method : 0.0013191699981689453 time for calcul the mask position with numpy : 0.015491724014282227 nb_pixel_total : 646 time to create 1 rle with old method : 0.0007970333099365234 time for calcul the mask position with numpy : 0.01498556137084961 nb_pixel_total : 3743 time to create 1 rle with old method : 0.004357814788818359 time for calcul the mask position with numpy : 0.015211820602416992 nb_pixel_total : 571 time to create 1 rle with old method : 0.0006816387176513672 time for calcul the mask position with numpy : 0.015285968780517578 nb_pixel_total : 594 time to create 1 rle with old method : 0.0006511211395263672 time for calcul the mask position with numpy : 0.0148468017578125 nb_pixel_total : 747 time to create 1 rle with old method : 0.0009055137634277344 time for calcul the mask position with numpy : 0.015076398849487305 nb_pixel_total : 2917 time to create 1 rle with old method : 0.003272533416748047 time for calcul the mask position with numpy : 0.014989376068115234 nb_pixel_total : 547 time to create 1 rle with old method : 0.0006844997406005859 time for calcul the mask position with numpy : 0.01447749137878418 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002231597900390625 time for calcul the mask position with numpy : 0.014723539352416992 nb_pixel_total : 1217 time to create 1 rle with old method : 0.001421213150024414 time for calcul the mask position with numpy : 0.014925479888916016 nb_pixel_total : 8385 time to create 1 rle with old method : 0.009276628494262695 time for calcul the mask position with numpy : 0.014996767044067383 nb_pixel_total : 124 time to create 1 rle with old method : 0.00018715858459472656 time for calcul the mask position with numpy : 0.015160560607910156 nb_pixel_total : 780 time to create 1 rle with old method : 0.001413583755493164 time for calcul the mask position with numpy : 0.016731739044189453 nb_pixel_total : 1207 time to create 1 rle with old method : 0.0017278194427490234 time for calcul the mask position with numpy : 0.01584625244140625 nb_pixel_total : 2783 time to create 1 rle with old method : 0.0032951831817626953 time for calcul the mask position with numpy : 0.015324592590332031 nb_pixel_total : 224 time to create 1 rle with old method : 0.0004696846008300781 time for calcul the mask position with numpy : 0.01651763916015625 nb_pixel_total : 71 time to create 1 rle with old method : 0.000141143798828125 time for calcul the mask position with numpy : 0.015106678009033203 nb_pixel_total : 1855 time to create 1 rle with old method : 0.002148151397705078 time for calcul the mask position with numpy : 0.01509857177734375 nb_pixel_total : 1283 time to create 1 rle with old method : 0.001554250717163086 time for calcul the mask position with numpy : 0.015999555587768555 nb_pixel_total : 2438 time to create 1 rle with old method : 0.002769947052001953 time for calcul the mask position with numpy : 0.01547861099243164 nb_pixel_total : 222 time to create 1 rle with old method : 0.00029921531677246094 time for calcul the mask position with numpy : 0.015451192855834961 nb_pixel_total : 1051 time to create 1 rle with old method : 0.0015628337860107422 time for calcul the mask position with numpy : 0.022653579711914062 nb_pixel_total : 2790 time to create 1 rle with old method : 0.004972696304321289 time for calcul the mask position with numpy : 0.019916534423828125 nb_pixel_total : 170 time to create 1 rle with old method : 0.00034499168395996094 time for calcul the mask position with numpy : 0.020017623901367188 nb_pixel_total : 3153 time to create 1 rle with old method : 0.006041526794433594 time for calcul the mask position with numpy : 0.0203859806060791 nb_pixel_total : 670 time to create 1 rle with old method : 0.0015385150909423828 time for calcul the mask position with numpy : 0.021435976028442383 nb_pixel_total : 297 time to create 1 rle with old method : 0.000732421875 time for calcul the mask position with numpy : 0.02526569366455078 nb_pixel_total : 2062 time to create 1 rle with old method : 0.0029125213623046875 time for calcul the mask position with numpy : 0.017744064331054688 nb_pixel_total : 272 time to create 1 rle with old method : 0.00034689903259277344 time for calcul the mask position with numpy : 0.016840457916259766 nb_pixel_total : 1086 time to create 1 rle with old method : 0.0013585090637207031 time for calcul the mask position with numpy : 0.016396284103393555 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005247592926025391 time for calcul the mask position with numpy : 0.019801616668701172 nb_pixel_total : 300 time to create 1 rle with old method : 0.0004734992980957031 time for calcul the mask position with numpy : 0.01697993278503418 nb_pixel_total : 716 time to create 1 rle with old method : 0.0009818077087402344 time for calcul the mask position with numpy : 0.017342805862426758 nb_pixel_total : 451 time to create 1 rle with old method : 0.0006692409515380859 time for calcul the mask position with numpy : 0.01713395118713379 nb_pixel_total : 6205 time to create 1 rle with old method : 0.007292270660400391 time for calcul the mask position with numpy : 0.015283584594726562 nb_pixel_total : 1522 time to create 1 rle with old method : 0.003178834915161133 time for calcul the mask position with numpy : 0.019138336181640625 nb_pixel_total : 111 time to create 1 rle with old method : 0.00018739700317382812 time for calcul the mask position with numpy : 0.015182971954345703 nb_pixel_total : 1928 time to create 1 rle with old method : 0.002203702926635742 time for calcul the mask position with numpy : 0.01682734489440918 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004742145538330078 time for calcul the mask position with numpy : 0.016389846801757812 nb_pixel_total : 1352 time to create 1 rle with old method : 0.0015411376953125 time for calcul the mask position with numpy : 0.01596999168395996 nb_pixel_total : 1779 time to create 1 rle with old method : 0.0020112991333007812 time for calcul the mask position with numpy : 0.014966249465942383 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003104209899902344 time for calcul the mask position with numpy : 0.014862060546875 nb_pixel_total : 2507 time to create 1 rle with old method : 0.002894878387451172 time for calcul the mask position with numpy : 0.014663219451904297 nb_pixel_total : 320 time to create 1 rle with old method : 0.0003631114959716797 time for calcul the mask position with numpy : 0.014630317687988281 nb_pixel_total : 391 time to create 1 rle with old method : 0.0004532337188720703 time for calcul the mask position with numpy : 0.014928579330444336 nb_pixel_total : 2373 time to create 1 rle with old method : 0.002678394317626953 time for calcul the mask position with numpy : 0.015045881271362305 nb_pixel_total : 909 time to create 1 rle with old method : 0.0010695457458496094 time for calcul the mask position with numpy : 0.01622939109802246 nb_pixel_total : 1552 time to create 1 rle with old method : 0.0021212100982666016 time for calcul the mask position with numpy : 0.0159151554107666 nb_pixel_total : 1323 time to create 1 rle with old method : 0.0016069412231445312 time for calcul the mask position with numpy : 0.01562809944152832 nb_pixel_total : 360 time to create 1 rle with old method : 0.0004894733428955078 time for calcul the mask position with numpy : 0.018299102783203125 nb_pixel_total : 1134 time to create 1 rle with old method : 0.0013108253479003906 time for calcul the mask position with numpy : 0.01588726043701172 nb_pixel_total : 1006 time to create 1 rle with old method : 0.0012674331665039062 time for calcul the mask position with numpy : 0.015495061874389648 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006363391876220703 time for calcul the mask position with numpy : 0.015950679779052734 nb_pixel_total : 619 time to create 1 rle with old method : 0.0007717609405517578 time for calcul the mask position with numpy : 0.015189647674560547 nb_pixel_total : 1424 time to create 1 rle with old method : 0.0016903877258300781 time for calcul the mask position with numpy : 0.01595282554626465 nb_pixel_total : 262 time to create 1 rle with old method : 0.00030684471130371094 time for calcul the mask position with numpy : 0.015821218490600586 nb_pixel_total : 9690 time to create 1 rle with old method : 0.011525869369506836 time for calcul the mask position with numpy : 0.016200542449951172 nb_pixel_total : 786 time to create 1 rle with old method : 0.0009291172027587891 time for calcul the mask position with numpy : 0.015529632568359375 nb_pixel_total : 2107 time to create 1 rle with old method : 0.002392292022705078 time for calcul the mask position with numpy : 0.014977455139160156 nb_pixel_total : 661 time to create 1 rle with old method : 0.0009844303131103516 time for calcul the mask position with numpy : 0.014953851699829102 nb_pixel_total : 1498 time to create 1 rle with old method : 0.0017478466033935547 time for calcul the mask position with numpy : 0.017370223999023438 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004127025604248047 time for calcul the mask position with numpy : 0.01710820198059082 nb_pixel_total : 196 time to create 1 rle with old method : 0.000301361083984375 time for calcul the mask position with numpy : 0.01592278480529785 nb_pixel_total : 1616 time to create 1 rle with old method : 0.0019638538360595703 time for calcul the mask position with numpy : 0.014899015426635742 nb_pixel_total : 31 time to create 1 rle with old method : 5.030632019042969e-05 time for calcul the mask position with numpy : 0.015290498733520508 nb_pixel_total : 216 time to create 1 rle with old method : 0.00037169456481933594 time for calcul the mask position with numpy : 0.01711130142211914 nb_pixel_total : 706 time to create 1 rle with old method : 0.0011889934539794922 time for calcul the mask position with numpy : 0.01601719856262207 nb_pixel_total : 2456 time to create 1 rle with old method : 0.0027518272399902344 time for calcul the mask position with numpy : 0.014909982681274414 nb_pixel_total : 236 time to create 1 rle with old method : 0.00029778480529785156 time for calcul the mask position with numpy : 0.014880895614624023 nb_pixel_total : 337 time to create 1 rle with old method : 0.00039768218994140625 time for calcul the mask position with numpy : 0.014915943145751953 nb_pixel_total : 280 time to create 1 rle with old method : 0.000335693359375 time for calcul the mask position with numpy : 0.014923572540283203 nb_pixel_total : 540 time to create 1 rle with old method : 0.000644683837890625 time for calcul the mask position with numpy : 0.014884233474731445 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003361701965332031 time for calcul the mask position with numpy : 0.014961957931518555 nb_pixel_total : 125 time to create 1 rle with old method : 0.00021457672119140625 time for calcul the mask position with numpy : 0.014904499053955078 nb_pixel_total : 2164 time to create 1 rle with old method : 0.0024504661560058594 time for calcul the mask position with numpy : 0.015015602111816406 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001595020294189453 time for calcul the mask position with numpy : 0.015031099319458008 nb_pixel_total : 3682 time to create 1 rle with old method : 0.0042057037353515625 time for calcul the mask position with numpy : 0.014951705932617188 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001659393310546875 time for calcul the mask position with numpy : 0.014923334121704102 nb_pixel_total : 221 time to create 1 rle with old method : 0.00026988983154296875 time for calcul the mask position with numpy : 0.01489710807800293 nb_pixel_total : 1480 time to create 1 rle with old method : 0.0017037391662597656 time for calcul the mask position with numpy : 0.014879465103149414 nb_pixel_total : 336 time to create 1 rle with old method : 0.0003902912139892578 time for calcul the mask position with numpy : 0.015071630477905273 nb_pixel_total : 154 time to create 1 rle with old method : 0.00020813941955566406 time for calcul the mask position with numpy : 0.015146493911743164 nb_pixel_total : 167 time to create 1 rle with old method : 0.00022101402282714844 time for calcul the mask position with numpy : 0.01493978500366211 nb_pixel_total : 1384 time to create 1 rle with old method : 0.0016067028045654297 time for calcul the mask position with numpy : 0.014912128448486328 nb_pixel_total : 499 time to create 1 rle with old method : 0.0005755424499511719 time for calcul the mask position with numpy : 0.015056371688842773 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005705356597900391 time for calcul the mask position with numpy : 0.017226696014404297 nb_pixel_total : 17 time to create 1 rle with old method : 8.034706115722656e-05 time for calcul the mask position with numpy : 0.01510167121887207 nb_pixel_total : 96 time to create 1 rle with old method : 0.0001361370086669922 time for calcul the mask position with numpy : 0.015884876251220703 nb_pixel_total : 231 time to create 1 rle with old method : 0.0002837181091308594 time for calcul the mask position with numpy : 0.015002012252807617 nb_pixel_total : 379 time to create 1 rle with old method : 0.0004544258117675781 time for calcul the mask position with numpy : 0.015127182006835938 nb_pixel_total : 16 time to create 1 rle with old method : 7.748603820800781e-05 time for calcul the mask position with numpy : 0.014935016632080078 nb_pixel_total : 394 time to create 1 rle with old method : 0.0004622936248779297 time for calcul the mask position with numpy : 0.014883041381835938 nb_pixel_total : 53 time to create 1 rle with old method : 6.937980651855469e-05 time for calcul the mask position with numpy : 0.014949560165405273 nb_pixel_total : 4760 time to create 1 rle with old method : 0.005476951599121094 time for calcul the mask position with numpy : 0.016718387603759766 nb_pixel_total : 66 time to create 1 rle with old method : 0.00011181831359863281 time for calcul the mask position with numpy : 0.015029430389404297 nb_pixel_total : 629 time to create 1 rle with old method : 0.0008471012115478516 time for calcul the mask position with numpy : 0.014952659606933594 nb_pixel_total : 70 time to create 1 rle with old method : 0.00012421607971191406 time for calcul the mask position with numpy : 0.01494455337524414 nb_pixel_total : 441 time to create 1 rle with old method : 0.0005180835723876953 time for calcul the mask position with numpy : 0.014909982681274414 nb_pixel_total : 846 time to create 1 rle with old method : 0.0009846687316894531 time for calcul the mask position with numpy : 0.01714468002319336 nb_pixel_total : 276 time to create 1 rle with old method : 0.00039649009704589844 time for calcul the mask position with numpy : 0.01488184928894043 nb_pixel_total : 179 time to create 1 rle with old method : 0.0002295970916748047 time for calcul the mask position with numpy : 0.014873027801513672 nb_pixel_total : 403 time to create 1 rle with old method : 0.0004734992980957031 time for calcul the mask position with numpy : 0.01490330696105957 nb_pixel_total : 40 time to create 1 rle with old method : 6.0558319091796875e-05 time for calcul the mask position with numpy : 0.014941215515136719 nb_pixel_total : 7276 time to create 1 rle with old method : 0.008478879928588867 time for calcul the mask position with numpy : 0.018141984939575195 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002422332763671875 time for calcul the mask position with numpy : 0.014988183975219727 nb_pixel_total : 26 time to create 1 rle with old method : 6.985664367675781e-05 time for calcul the mask position with numpy : 0.015168905258178711 nb_pixel_total : 188 time to create 1 rle with old method : 0.0003986358642578125 time for calcul the mask position with numpy : 0.016839981079101562 nb_pixel_total : 244 time to create 1 rle with old method : 0.00030159950256347656 time for calcul the mask position with numpy : 0.014899969100952148 nb_pixel_total : 207 time to create 1 rle with old method : 0.0002498626708984375 time for calcul the mask position with numpy : 0.014918804168701172 nb_pixel_total : 2997 time to create 1 rle with old method : 0.0036013126373291016 time for calcul the mask position with numpy : 0.016010284423828125 nb_pixel_total : 519 time to create 1 rle with old method : 0.0005977153778076172 time for calcul the mask position with numpy : 0.014882087707519531 nb_pixel_total : 528 time to create 1 rle with old method : 0.00061798095703125 time for calcul the mask position with numpy : 0.015034675598144531 nb_pixel_total : 256 time to create 1 rle with old method : 0.0003056526184082031 time for calcul the mask position with numpy : 0.01510310173034668 nb_pixel_total : 11 time to create 1 rle with old method : 3.0994415283203125e-05 time for calcul the mask position with numpy : 0.015026330947875977 nb_pixel_total : 261 time to create 1 rle with old method : 0.0003516674041748047 time for calcul the mask position with numpy : 0.014951944351196289 nb_pixel_total : 111 time to create 1 rle with old method : 0.00014781951904296875 time for calcul the mask position with numpy : 0.014999151229858398 nb_pixel_total : 168 time to create 1 rle with old method : 0.00023221969604492188 time for calcul the mask position with numpy : 0.014971733093261719 nb_pixel_total : 1039 time to create 1 rle with old method : 0.0012035369873046875 time for calcul the mask position with numpy : 0.014965057373046875 nb_pixel_total : 174 time to create 1 rle with old method : 0.00021147727966308594 time for calcul the mask position with numpy : 0.01495218276977539 nb_pixel_total : 1396 time to create 1 rle with old method : 0.001596689224243164 time for calcul the mask position with numpy : 0.01737523078918457 nb_pixel_total : 19 time to create 1 rle with old method : 7.891654968261719e-05 time for calcul the mask position with numpy : 0.01524662971496582 nb_pixel_total : 1312 time to create 1 rle with old method : 0.001491546630859375 time for calcul the mask position with numpy : 0.014870405197143555 nb_pixel_total : 1121 time to create 1 rle with old method : 0.001317739486694336 time for calcul the mask position with numpy : 0.015780210494995117 nb_pixel_total : 122 time to create 1 rle with old method : 0.00020599365234375 time for calcul the mask position with numpy : 0.016600847244262695 nb_pixel_total : 310 time to create 1 rle with old method : 0.0003790855407714844 time for calcul the mask position with numpy : 0.014897346496582031 nb_pixel_total : 1224 time to create 1 rle with old method : 0.0014050006866455078 time for calcul the mask position with numpy : 0.014842033386230469 nb_pixel_total : 249 time to create 1 rle with old method : 0.000293731689453125 time for calcul the mask position with numpy : 0.014838933944702148 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005819797515869141 time for calcul the mask position with numpy : 0.01489877700805664 nb_pixel_total : 639 time to create 1 rle with old method : 0.0007853507995605469 time for calcul the mask position with numpy : 0.014811992645263672 nb_pixel_total : 11476 time to create 1 rle with old method : 0.014533758163452148 time for calcul the mask position with numpy : 0.014691829681396484 nb_pixel_total : 449 time to create 1 rle with old method : 0.000530242919921875 time for calcul the mask position with numpy : 0.01490163803100586 nb_pixel_total : 1237 time to create 1 rle with old method : 0.0014579296112060547 time for calcul the mask position with numpy : 0.014960765838623047 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002849102020263672 time for calcul the mask position with numpy : 0.014912605285644531 nb_pixel_total : 2500 time to create 1 rle with old method : 0.002888917922973633 time for calcul the mask position with numpy : 0.014938116073608398 nb_pixel_total : 3586 time to create 1 rle with old method : 0.004137754440307617 time for calcul the mask position with numpy : 0.01594829559326172 nb_pixel_total : 444 time to create 1 rle with old method : 0.0009448528289794922 time for calcul the mask position with numpy : 0.018595457077026367 nb_pixel_total : 1466 time to create 1 rle with old method : 0.002421855926513672 time for calcul the mask position with numpy : 0.01719045639038086 nb_pixel_total : 43 time to create 1 rle with old method : 0.00025177001953125 time for calcul the mask position with numpy : 0.01710963249206543 nb_pixel_total : 2899 time to create 1 rle with old method : 0.004714250564575195 time for calcul the mask position with numpy : 0.017157316207885742 nb_pixel_total : 1433 time to create 1 rle with old method : 0.0016705989837646484 time for calcul the mask position with numpy : 0.014539480209350586 nb_pixel_total : 448 time to create 1 rle with old method : 0.0005092620849609375 time for calcul the mask position with numpy : 0.014325857162475586 nb_pixel_total : 529 time to create 1 rle with old method : 0.0005745887756347656 time for calcul the mask position with numpy : 0.014501094818115234 nb_pixel_total : 441 time to create 1 rle with old method : 0.0004987716674804688 time for calcul the mask position with numpy : 0.014409065246582031 nb_pixel_total : 3425 time to create 1 rle with old method : 0.003726482391357422 time for calcul the mask position with numpy : 0.01442861557006836 nb_pixel_total : 680 time to create 1 rle with old method : 0.0007138252258300781 time for calcul the mask position with numpy : 0.014357566833496094 nb_pixel_total : 193 time to create 1 rle with old method : 0.00023937225341796875 time for calcul the mask position with numpy : 0.01466679573059082 nb_pixel_total : 2096 time to create 1 rle with old method : 0.002336263656616211 time for calcul the mask position with numpy : 0.014899015426635742 nb_pixel_total : 712 time to create 1 rle with old method : 0.0008103847503662109 time for calcul the mask position with numpy : 0.014095306396484375 nb_pixel_total : 2002 time to create 1 rle with old method : 0.002204418182373047 time for calcul the mask position with numpy : 0.015002965927124023 nb_pixel_total : 3745 time to create 1 rle with old method : 0.0041158199310302734 time for calcul the mask position with numpy : 0.014478683471679688 nb_pixel_total : 470 time to create 1 rle with old method : 0.0005555152893066406 time for calcul the mask position with numpy : 0.01439046859741211 nb_pixel_total : 2555 time to create 1 rle with old method : 0.002868175506591797 time for calcul the mask position with numpy : 0.014241695404052734 nb_pixel_total : 31 time to create 1 rle with old method : 6.961822509765625e-05 time for calcul the mask position with numpy : 0.014215707778930664 nb_pixel_total : 161 time to create 1 rle with old method : 0.000209808349609375 time for calcul the mask position with numpy : 0.014448881149291992 nb_pixel_total : 1402 time to create 1 rle with old method : 0.001562356948852539 time for calcul the mask position with numpy : 0.013978719711303711 nb_pixel_total : 1335 time to create 1 rle with old method : 0.0013947486877441406 time for calcul the mask position with numpy : 0.014387369155883789 nb_pixel_total : 884 time to create 1 rle with old method : 0.0009500980377197266 time for calcul the mask position with numpy : 0.014554262161254883 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006256103515625 time for calcul the mask position with numpy : 0.014332056045532227 nb_pixel_total : 44 time to create 1 rle with old method : 7.104873657226562e-05 time for calcul the mask position with numpy : 0.014441251754760742 nb_pixel_total : 198 time to create 1 rle with old method : 0.00023865699768066406 time for calcul the mask position with numpy : 0.014754056930541992 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005309581756591797 time for calcul the mask position with numpy : 0.014554262161254883 nb_pixel_total : 3821 time to create 1 rle with old method : 0.0041310787200927734 time for calcul the mask position with numpy : 0.01434469223022461 nb_pixel_total : 4432 time to create 1 rle with old method : 0.0048220157623291016 time for calcul the mask position with numpy : 0.014858245849609375 nb_pixel_total : 1183 time to create 1 rle with old method : 0.0013651847839355469 time for calcul the mask position with numpy : 0.014834880828857422 nb_pixel_total : 76 time to create 1 rle with old method : 0.0001575946807861328 time for calcul the mask position with numpy : 0.014630794525146484 nb_pixel_total : 263 time to create 1 rle with old method : 0.00031304359436035156 time for calcul the mask position with numpy : 0.014843463897705078 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0017819404602050781 time for calcul the mask position with numpy : 0.014626264572143555 nb_pixel_total : 11352 time to create 1 rle with old method : 0.01234579086303711 time for calcul the mask position with numpy : 0.014802932739257812 nb_pixel_total : 2901 time to create 1 rle with old method : 0.0032029151916503906 time for calcul the mask position with numpy : 0.015032529830932617 nb_pixel_total : 875 time to create 1 rle with old method : 0.001007080078125 time for calcul the mask position with numpy : 0.014481782913208008 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0015189647674560547 time for calcul the mask position with numpy : 0.014735221862792969 nb_pixel_total : 38 time to create 1 rle with old method : 0.00010228157043457031 time for calcul the mask position with numpy : 0.014745235443115234 nb_pixel_total : 334 time to create 1 rle with old method : 0.00039887428283691406 time for calcul the mask position with numpy : 0.014422178268432617 nb_pixel_total : 1447 time to create 1 rle with old method : 0.0016477108001708984 time for calcul the mask position with numpy : 0.014604330062866211 nb_pixel_total : 4752 time to create 1 rle with old method : 0.005236625671386719 time for calcul the mask position with numpy : 0.014558076858520508 nb_pixel_total : 1330 time to create 1 rle with old method : 0.0014595985412597656 time for calcul the mask position with numpy : 0.014341354370117188 nb_pixel_total : 828 time to create 1 rle with old method : 0.0009288787841796875 time for calcul the mask position with numpy : 0.014505386352539062 nb_pixel_total : 897 time to create 1 rle with old method : 0.0010457038879394531 time for calcul the mask position with numpy : 0.014213323593139648 nb_pixel_total : 15 time to create 1 rle with old method : 7.891654968261719e-05 time for calcul the mask position with numpy : 0.014101743698120117 nb_pixel_total : 395 time to create 1 rle with old method : 0.0004220008850097656 time for calcul the mask position with numpy : 0.013805150985717773 nb_pixel_total : 80 time to create 1 rle with old method : 9.298324584960938e-05 time for calcul the mask position with numpy : 0.014263153076171875 nb_pixel_total : 148 time to create 1 rle with old method : 0.0001690387725830078 time for calcul the mask position with numpy : 0.01423025131225586 nb_pixel_total : 2049 time to create 1 rle with old method : 0.002260446548461914 time for calcul the mask position with numpy : 0.014194250106811523 nb_pixel_total : 2209 time to create 1 rle with old method : 0.0023050308227539062 time for calcul the mask position with numpy : 0.014327049255371094 nb_pixel_total : 1442 time to create 1 rle with old method : 0.0015742778778076172 time for calcul the mask position with numpy : 0.01426076889038086 nb_pixel_total : 725 time to create 1 rle with old method : 0.0007755756378173828 time for calcul the mask position with numpy : 0.013947010040283203 nb_pixel_total : 30 time to create 1 rle with old method : 6.127357482910156e-05 time for calcul the mask position with numpy : 0.014455556869506836 nb_pixel_total : 441 time to create 1 rle with old method : 0.0005223751068115234 time for calcul the mask position with numpy : 0.014342308044433594 nb_pixel_total : 31081 time to create 1 rle with old method : 0.032507896423339844 time for calcul the mask position with numpy : 0.014478683471679688 nb_pixel_total : 44 time to create 1 rle with old method : 7.939338684082031e-05 time for calcul the mask position with numpy : 0.014825105667114258 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003070831298828125 time for calcul the mask position with numpy : 0.016468286514282227 nb_pixel_total : 4806 time to create 1 rle with old method : 0.006737232208251953 time for calcul the mask position with numpy : 0.015249013900756836 nb_pixel_total : 153 time to create 1 rle with old method : 0.00019168853759765625 time for calcul the mask position with numpy : 0.01491093635559082 nb_pixel_total : 4267 time to create 1 rle with old method : 0.004746198654174805 time for calcul the mask position with numpy : 0.014857769012451172 nb_pixel_total : 384 time to create 1 rle with old method : 0.00046133995056152344 time for calcul the mask position with numpy : 0.014623880386352539 nb_pixel_total : 879 time to create 1 rle with old method : 0.0010223388671875 time for calcul the mask position with numpy : 0.014812946319580078 nb_pixel_total : 290 time to create 1 rle with old method : 0.0003345012664794922 time for calcul the mask position with numpy : 0.014782428741455078 nb_pixel_total : 3601 time to create 1 rle with old method : 0.004059791564941406 time for calcul the mask position with numpy : 0.014597177505493164 nb_pixel_total : 321 time to create 1 rle with old method : 0.00036263465881347656 time for calcul the mask position with numpy : 0.01481008529663086 nb_pixel_total : 533 time to create 1 rle with old method : 0.0006051063537597656 time for calcul the mask position with numpy : 0.014804363250732422 nb_pixel_total : 445 time to create 1 rle with old method : 0.0005311965942382812 time for calcul the mask position with numpy : 0.01607489585876465 nb_pixel_total : 168 time to create 1 rle with old method : 0.0002009868621826172 time for calcul the mask position with numpy : 0.014207839965820312 nb_pixel_total : 3894 time to create 1 rle with old method : 0.0042667388916015625 time for calcul the mask position with numpy : 0.014850616455078125 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002200603485107422 time for calcul the mask position with numpy : 0.01478123664855957 nb_pixel_total : 11092 time to create 1 rle with old method : 0.012308597564697266 time for calcul the mask position with numpy : 0.014883279800415039 nb_pixel_total : 2212 time to create 1 rle with old method : 0.0024785995483398438 time for calcul the mask position with numpy : 0.014946699142456055 nb_pixel_total : 750 time to create 1 rle with old method : 0.0008497238159179688 time for calcul the mask position with numpy : 0.014958858489990234 nb_pixel_total : 21726 time to create 1 rle with old method : 0.02523064613342285 time for calcul the mask position with numpy : 0.01494288444519043 nb_pixel_total : 150 time to create 1 rle with old method : 0.00019049644470214844 time for calcul the mask position with numpy : 0.014825820922851562 nb_pixel_total : 340 time to create 1 rle with old method : 0.0003955364227294922 time for calcul the mask position with numpy : 0.014643430709838867 nb_pixel_total : 1460 time to create 1 rle with old method : 0.0016756057739257812 time for calcul the mask position with numpy : 0.014829635620117188 nb_pixel_total : 462 time to create 1 rle with old method : 0.0005443096160888672 time for calcul the mask position with numpy : 0.014866828918457031 nb_pixel_total : 304 time to create 1 rle with old method : 0.0003631114959716797 time for calcul the mask position with numpy : 0.01485300064086914 nb_pixel_total : 555 time to create 1 rle with old method : 0.00069427490234375 time for calcul the mask position with numpy : 0.014896154403686523 nb_pixel_total : 2475 time to create 1 rle with old method : 0.0028715133666992188 time for calcul the mask position with numpy : 0.014904022216796875 nb_pixel_total : 1450 time to create 1 rle with old method : 0.0017347335815429688 time for calcul the mask position with numpy : 0.014845848083496094 nb_pixel_total : 124 time to create 1 rle with old method : 0.0002608299255371094 time for calcul the mask position with numpy : 0.014912605285644531 nb_pixel_total : 4014 time to create 1 rle with old method : 0.00455021858215332 time for calcul the mask position with numpy : 0.014815330505371094 nb_pixel_total : 8692 time to create 1 rle with old method : 0.009778738021850586 time for calcul the mask position with numpy : 0.015008211135864258 nb_pixel_total : 90 time to create 1 rle with old method : 0.00020837783813476562 time for calcul the mask position with numpy : 0.014968633651733398 nb_pixel_total : 1018 time to create 1 rle with old method : 0.0011591911315917969 time for calcul the mask position with numpy : 0.014943122863769531 nb_pixel_total : 686 time to create 1 rle with old method : 0.0008006095886230469 time for calcul the mask position with numpy : 0.014915704727172852 nb_pixel_total : 330 time to create 1 rle with old method : 0.0003917217254638672 time for calcul the mask position with numpy : 0.014877796173095703 nb_pixel_total : 3912 time to create 1 rle with old method : 0.004434108734130859 time for calcul the mask position with numpy : 0.014923572540283203 nb_pixel_total : 452 time to create 1 rle with old method : 0.0007669925689697266 time for calcul the mask position with numpy : 0.014920949935913086 nb_pixel_total : 3 time to create 1 rle with old method : 2.7179718017578125e-05 time for calcul the mask position with numpy : 0.014881372451782227 nb_pixel_total : 1551 time to create 1 rle with old method : 0.0018382072448730469 time for calcul the mask position with numpy : 0.014907121658325195 nb_pixel_total : 5160 time to create 1 rle with old method : 0.005979776382446289 time for calcul the mask position with numpy : 0.014970779418945312 nb_pixel_total : 12917 time to create 1 rle with old method : 0.014777183532714844 time for calcul the mask position with numpy : 0.014991521835327148 nb_pixel_total : 61 time to create 1 rle with old method : 0.00017213821411132812 time for calcul the mask position with numpy : 0.015004158020019531 nb_pixel_total : 536 time to create 1 rle with old method : 0.0006508827209472656 time for calcul the mask position with numpy : 0.015039443969726562 nb_pixel_total : 12152 time to create 1 rle with old method : 0.013469457626342773 time for calcul the mask position with numpy : 0.014933109283447266 nb_pixel_total : 7339 time to create 1 rle with old method : 0.008186101913452148 time for calcul the mask position with numpy : 0.015038251876831055 nb_pixel_total : 1981 time to create 1 rle with old method : 0.0022804737091064453 time for calcul the mask position with numpy : 0.014855623245239258 nb_pixel_total : 896 time to create 1 rle with old method : 0.0010340213775634766 time for calcul the mask position with numpy : 0.015578269958496094 nb_pixel_total : 284 time to create 1 rle with old method : 0.0005662441253662109 time for calcul the mask position with numpy : 0.018536090850830078 nb_pixel_total : 1507 time to create 1 rle with old method : 0.0016908645629882812 time for calcul the mask position with numpy : 0.014908313751220703 nb_pixel_total : 122 time to create 1 rle with old method : 0.00016355514526367188 time for calcul the mask position with numpy : 0.014890432357788086 nb_pixel_total : 1958 time to create 1 rle with old method : 0.002187967300415039 time for calcul the mask position with numpy : 0.015132427215576172 nb_pixel_total : 853 time to create 1 rle with old method : 0.0009827613830566406 time for calcul the mask position with numpy : 0.015028953552246094 nb_pixel_total : 2161 time to create 1 rle with old method : 0.002457857131958008 time for calcul the mask position with numpy : 0.014936685562133789 nb_pixel_total : 58 time to create 1 rle with old method : 0.00013780593872070312 time for calcul the mask position with numpy : 0.014865636825561523 nb_pixel_total : 1698 time to create 1 rle with old method : 0.0019626617431640625 time for calcul the mask position with numpy : 0.014854907989501953 nb_pixel_total : 1214 time to create 1 rle with old method : 0.0014247894287109375 time for calcul the mask position with numpy : 0.014868736267089844 nb_pixel_total : 234 time to create 1 rle with old method : 0.00027298927307128906 time for calcul the mask position with numpy : 0.01491999626159668 nb_pixel_total : 6 time to create 1 rle with old method : 1.33514404296875e-05 time for calcul the mask position with numpy : 0.014876365661621094 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002372264862060547 create new chi : 6.815111875534058 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 : 0.01466512680053711 batch 1 Loaded 348 chid ids of type : 4230 Number RLEs to save : 31366 TO DO : save crop sub photo not yet done ! save time : 3.118194103240967 map_output_result : {1339667907: (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 [1339667907] Looping around the photos to save general results len do output : 1 /1339667907.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, '2614741') ('4234', '20824223', '1339667907', None, None, None, None, None, '2614741') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.014600992202758789 save_final save missing photos in datou_result : time spend for datou_step_exec : 12.377274751663208 time spend to save output : 0.014898300170898438 total time spend for step 4 : 12.392173051834106 step5:crop_condition Wed Feb 26 06:21:11 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 348 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 ! map_result returned by crop_photo_return_map_crop : length : 173 About to insert : list_path_to_insert length 173 new photo from crops ! About to upload 173 photos upload in portfolio : 4869462 init cache_photo without model_param we have 173 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740547276_586718 we have uploaded 173 photos in the portfolio 4869462 time of upload the photos Elapsed time : 46.700536251068115 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 51 About to insert : list_path_to_insert length 51 new photo from crops ! About to upload 51 photos upload in portfolio : 4869462 init cache_photo without model_param we have 51 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740547324_586718 we have uploaded 51 photos in the portfolio 4869462 time of upload the photos Elapsed time : 14.677858352661133 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 4869462 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740547338_586718 we have uploaded 3 photos in the portfolio 4869462 time of upload the photos Elapsed time : 1.2873382568359375 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 14 About to insert : list_path_to_insert length 14 new photo from crops ! About to upload 14 photos upload in portfolio : 4869462 init cache_photo without model_param we have 14 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740547340_586718 we have uploaded 14 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.390428304672241 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! About to upload 13 photos upload in portfolio : 4869462 init cache_photo without model_param we have 13 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740547345_586718 we have uploaded 13 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.7218897342681885 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740547349_586718 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.6174657344818115 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740547350_586718 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9603612422943115 we have finished the crop for the class : pet_fonce delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1339667907] Looping around the photos to save general results len do output : 257 /1339675126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675219Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675221Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675223Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675226Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675231Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675232Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675239Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675240Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675241Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675242Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675248Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675297Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675307Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675315Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339675389Didn'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, '2614741') ('4234', '20824223', '1339667907', None, None, None, None, None, '2614741') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 772 time used for this insertion : 0.9189174175262451 save_final save missing photos in datou_result : time spend for datou_step_exec : 79.26219344139099 time spend to save output : 0.926626443862915 total time spend for step 5 : 80.1888198852539 step6:thcl Wed Feb 26 06:22:32 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 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 : 0.020104408264160156 time to convert the images to numpy array : 0.06840777397155762 time to import caffe and check if the image exist : 0.022361040115356445 time to convert the images to numpy array : 0.07241368293762207 time to import caffe and check if the image exist : 0.014923334121704102 time to convert the images to numpy array : 0.09275627136230469 time to import caffe and check if the image exist : 0.024621009826660156 time to convert the images to numpy array : 0.08625411987304688 time to import caffe and check if the image exist : 0.021120309829711914 time to convert the images to numpy array : 0.09128642082214355 time to import caffe and check if the image exist : 0.02059173583984375 time to convert the images to numpy array : 0.09175372123718262 time to import caffe and check if the image exist : 0.028794288635253906 time to convert the images to numpy array : 0.08310604095458984 time to import caffe and check if the image exist : 0.02893209457397461 time to convert the images to numpy array : 0.08562469482421875 time to import caffe and check if the image exist : 0.026792287826538086 time to convert the images to numpy array : 0.08735394477844238 time to import caffe and check if the image exist : 0.03328824043273926 time to convert the images to numpy array : 0.0841529369354248 total time to convert the images to numpy array : 0.35869669914245605 list photo_ids error: [] list photo_ids correct : [1339675234, 1339675235, 1339675236, 1339675237, 1339675238, 1339675239, 1339675240, 1339675241, 1339675242, 1339675243, 1339675244, 1339675245, 1339675246, 1339675247, 1339675248, 1339675249, 1339675250, 1339675251, 1339675252, 1339675253, 1339675255, 1339675256, 1339675257, 1339675258, 1339675259, 1339675260, 1339675365, 1339675366, 1339675367, 1339675368, 1339675369, 1339675370, 1339675371, 1339675373, 1339675374, 1339675375, 1339675376, 1339675377, 1339675378, 1339675379, 1339675380, 1339675381, 1339675382, 1339675383, 1339675384, 1339675385, 1339675386, 1339675388, 1339675389, 1339675181, 1339675182, 1339675183, 1339675184, 1339675185, 1339675186, 1339675187, 1339675188, 1339675189, 1339675190, 1339675191, 1339675192, 1339675193, 1339675194, 1339675195, 1339675196, 1339675197, 1339675198, 1339675199, 1339675200, 1339675201, 1339675202, 1339675203, 1339675204, 1339675205, 1339675206, 1339675153, 1339675154, 1339675155, 1339675156, 1339675157, 1339675158, 1339675159, 1339675160, 1339675161, 1339675162, 1339675163, 1339675164, 1339675166, 1339675167, 1339675169, 1339675170, 1339675171, 1339675172, 1339675173, 1339675174, 1339675175, 1339675176, 1339675177, 1339675178, 1339675179, 1339675180, 1339675126, 1339675127, 1339675128, 1339675129, 1339675130, 1339675131, 1339675132, 1339675133, 1339675134, 1339675135, 1339675137, 1339675138, 1339675139, 1339675140, 1339675141, 1339675142, 1339675143, 1339675144, 1339675145, 1339675146, 1339675147, 1339675148, 1339675149, 1339675150, 1339675151, 1339675152, 1339675287, 1339675288, 1339675289, 1339675290, 1339675291, 1339675292, 1339675293, 1339675294, 1339675295, 1339675296, 1339675297, 1339675298, 1339675299, 1339675300, 1339675301, 1339675302, 1339675303, 1339675304, 1339675305, 1339675306, 1339675307, 1339675308, 1339675309, 1339675310, 1339675311, 1339675312, 1339675339, 1339675340, 1339675341, 1339675342, 1339675343, 1339675344, 1339675345, 1339675346, 1339675347, 1339675348, 1339675349, 1339675350, 1339675351, 1339675352, 1339675353, 1339675354, 1339675355, 1339675356, 1339675357, 1339675358, 1339675359, 1339675360, 1339675361, 1339675362, 1339675363, 1339675364, 1339675207, 1339675209, 1339675210, 1339675211, 1339675212, 1339675213, 1339675214, 1339675215, 1339675216, 1339675217, 1339675218, 1339675219, 1339675220, 1339675221, 1339675222, 1339675223, 1339675224, 1339675225, 1339675226, 1339675227, 1339675228, 1339675229, 1339675230, 1339675231, 1339675232, 1339675233, 1339675313, 1339675314, 1339675315, 1339675316, 1339675317, 1339675318, 1339675319, 1339675320, 1339675321, 1339675322, 1339675323, 1339675324, 1339675325, 1339675326, 1339675327, 1339675328, 1339675329, 1339675330, 1339675331, 1339675332, 1339675333, 1339675334, 1339675335, 1339675336, 1339675337, 1339675338, 1339675261, 1339675262, 1339675263, 1339675264, 1339675265, 1339675266, 1339675267, 1339675268, 1339675269, 1339675270, 1339675271, 1339675272, 1339675273, 1339675274, 1339675275, 1339675276, 1339675277, 1339675278, 1339675279, 1339675280, 1339675281, 1339675282, 1339675283, 1339675284, 1339675285, 1339675286] number of photos to traite : 257 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 : 5510 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 : 5291 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 1.213301420211792 time used to do the prediction : 0.906757116317749 save descriptor for thcl : 3237 time to traite the descriptors : 1.5084357261657715 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1339675234 To insert : 1339675235 To insert : 1339675236 To insert : 1339675237 To insert : 1339675238 To insert : 1339675239 To insert : 1339675240 To insert : 1339675241 To insert : 1339675242 To insert : 1339675243 To insert : 1339675244 To insert : 1339675245 To insert : 1339675246 To insert : 1339675247 To insert : 1339675248 To insert : 1339675249 To insert : 1339675250 To insert : 1339675251 To insert : 1339675252 To insert : 1339675253 To insert : 1339675255 To insert : 1339675256 To insert : 1339675257 To insert : 1339675258 To insert : 1339675259 To insert : 1339675260 To insert : 1339675365 To insert : 1339675366 To insert : 1339675367 To insert : 1339675368 To insert : 1339675369 To insert : 1339675370 To insert : 1339675371 To insert : 1339675373 To insert : 1339675374 To insert : 1339675375 To insert : 1339675376 To insert : 1339675377 To insert : 1339675378 To insert : 1339675379 To insert : 1339675380 To insert : 1339675381 To insert : 1339675382 To insert : 1339675383 To insert : 1339675384 To insert : 1339675385 To insert : 1339675386 To insert : 1339675388 To insert : 1339675389 To insert : 1339675181 To insert : 1339675182 To insert : 1339675183 To insert : 1339675184 To insert : 1339675185 To insert : 1339675186 To insert : 1339675187 To insert : 1339675188 To insert : 1339675189 To insert : 1339675190 To insert : 1339675191 To insert : 1339675192 To insert : 1339675193 To insert : 1339675194 To insert : 1339675195 To insert : 1339675196 To insert : 1339675197 To insert : 1339675198 To insert : 1339675199 To insert : 1339675200 To insert : 1339675201 To insert : 1339675202 To insert : 1339675203 To insert : 1339675204 To insert : 1339675205 To insert : 1339675206 To insert : 1339675153 To insert : 1339675154 To insert : 1339675155 To insert : 1339675156 To insert : 1339675157 To insert : 1339675158 To insert : 1339675159 To insert : 1339675160 To insert : 1339675161 To insert : 1339675162 To insert : 1339675163 To insert : 1339675164 To insert : 1339675166 To insert : 1339675167 To insert : 1339675169 To insert : 1339675170 To insert : 1339675171 To insert : 1339675172 To insert : 1339675173 To insert : 1339675174 To insert : 1339675175 To insert : 1339675176 To insert : 1339675177 To insert : 1339675178 To insert : 1339675179 To insert : 1339675180 To insert : 1339675126 To insert : 1339675127 To insert : 1339675128 To insert : 1339675129 To insert : 1339675130 To insert : 1339675131 To insert : 1339675132 To insert : 1339675133 To insert : 1339675134 To insert : 1339675135 To insert : 1339675137 To insert : 1339675138 To insert : 1339675139 To insert : 1339675140 To insert : 1339675141 To insert : 1339675142 To insert : 1339675143 To insert : 1339675144 To insert : 1339675145 To insert : 1339675146 To insert : 1339675147 To insert : 1339675148 To insert : 1339675149 To insert : 1339675150 To insert : 1339675151 To insert : 1339675152 To insert : 1339675287 To insert : 1339675288 To insert : 1339675289 To insert : 1339675290 To insert : 1339675291 To insert : 1339675292 To insert : 1339675293 To insert : 1339675294 To insert : 1339675295 To insert : 1339675296 To insert : 1339675297 To insert : 1339675298 To insert : 1339675299 To insert : 1339675300 To insert : 1339675301 To insert : 1339675302 To insert : 1339675303 To insert : 1339675304 To insert : 1339675305 To insert : 1339675306 To insert : 1339675307 To insert : 1339675308 To insert : 1339675309 To insert : 1339675310 To insert : 1339675311 To insert : 1339675312 To insert : 1339675339 To insert : 1339675340 To insert : 1339675341 To insert : 1339675342 To insert : 1339675343 To insert : 1339675344 To insert : 1339675345 To insert : 1339675346 To insert : 1339675347 To insert : 1339675348 To insert : 1339675349 To insert : 1339675350 To insert : 1339675351 To insert : 1339675352 To insert : 1339675353 To insert : 1339675354 To insert : 1339675355 To insert : 1339675356 To insert : 1339675357 To insert : 1339675358 To insert : 1339675359 To insert : 1339675360 To insert : 1339675361 To insert : 1339675362 To insert : 1339675363 To insert : 1339675364 To insert : 1339675207 To insert : 1339675209 To insert : 1339675210 To insert : 1339675211 To insert : 1339675212 To insert : 1339675213 To insert : 1339675214 To insert : 1339675215 To insert : 1339675216 To insert : 1339675217 To insert : 1339675218 To insert : 1339675219 To insert : 1339675220 To insert : 1339675221 To insert : 1339675222 To insert : 1339675223 To insert : 1339675224 To insert : 1339675225 To insert : 1339675226 To insert : 1339675227 To insert : 1339675228 To insert : 1339675229 To insert : 1339675230 To insert : 1339675231 To insert : 1339675232 To insert : 1339675233 To insert : 1339675313 To insert : 1339675314 To insert : 1339675315 To insert : 1339675316 To insert : 1339675317 To insert : 1339675318 To insert : 1339675319 To insert : 1339675320 To insert : 1339675321 To insert : 1339675322 To insert : 1339675323 To insert : 1339675324 To insert : 1339675325 To insert : 1339675326 To insert : 1339675327 To insert : 1339675328 To insert : 1339675329 To insert : 1339675330 To insert : 1339675331 To insert : 1339675332 To insert : 1339675333 To insert : 1339675334 To insert : 1339675335 To insert : 1339675336 To insert : 1339675337 To insert : 1339675338 To insert : 1339675261 To insert : 1339675262 To insert : 1339675263 To insert : 1339675264 To insert : 1339675265 To insert : 1339675266 To insert : 1339675267 To insert : 1339675268 To insert : 1339675269 To insert : 1339675270 To insert : 1339675271 To insert : 1339675272 To insert : 1339675273 To insert : 1339675274 To insert : 1339675275 To insert : 1339675276 To insert : 1339675277 To insert : 1339675278 To insert : 1339675279 To insert : 1339675280 To insert : 1339675281 To insert : 1339675282 To insert : 1339675283 To insert : 1339675284 To insert : 1339675285 To insert : 1339675286 time to insert the descriptors : 56.235692262649536 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 : 397 time used for this insertion : 0.02715921401977539 save missing photos in datou_result : time spend for datou_step_exec : 64.3231589794159 time spend to save output : 0.07597875595092773 total time spend for step 6 : 64.39913773536682 step7:ventilate_hashtags_in_portfolio Wed Feb 26 06:23:36 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 : 20824223 get user id for portfolio 20824223 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`=20824223 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','metal','mal_croppe','PEHD','carton','autre','Film_plastique','pet_clair','pehd','flou','pet_fonce','environnement','refus','Papier','papier','PET_clair','PET_fonce','Tetrapak')) 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`=20824223 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','metal','mal_croppe','PEHD','carton','autre','Film_plastique','pet_clair','pehd','flou','pet_fonce','environnement','refus','Papier','papier','PET_clair','PET_fonce','Tetrapak')) 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`=20824223 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','metal','mal_croppe','PEHD','carton','autre','Film_plastique','pet_clair','pehd','flou','pet_fonce','environnement','refus','Papier','papier','PET_clair','PET_fonce','Tetrapak')) 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`=20824223 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','metal','mal_croppe','PEHD','carton','autre','Film_plastique','pet_clair','pehd','flou','pet_fonce','environnement','refus','Papier','papier','PET_clair','PET_fonce','Tetrapak')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20825212,20825209,20825210,20825216,20825213,20825214,20825223,20825217,20825224,20825219,20825220,20825222,20825225?tags=carton,metal,mal_croppe,pehd,autre,film_plastique,pet_clair,flou,pet_fonce,environnement,refus,papier,tetrapak&datou_id_consolidate=4235&port_consolidate=20824223 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1339667907] Looping around the photos to save general results len do output : 1 /20824223. 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, '2614741') ('4234', '20824223', '1339667907', None, None, None, None, None, '2614741') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.01324319839477539 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.7440412044525146 time spend to save output : 0.013485193252563477 total time spend for step 7 : 3.757526397705078 step8:final Wed Feb 26 06:23:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : {1339667907: ('0.6942148724334576',)} new output for save of step final : {1339667907: ('0.6942148724334576',)} [1339667907] Looping around the photos to save general results len do output : 1 /1339667907.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, '2614741') ('4234', '20824223', '1339667907', None, None, None, None, None, '2614741') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.013452529907226562 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11505365371704102 time spend to save output : 0.013648748397827148 total time spend for step 8 : 0.12870240211486816 step9:velours_tree Wed Feb 26 06:23:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure list_portfolios : 20825212,20825209,20825210,20825216,20825213,20825214,20825223,20825217,20825224,20825219,20825220,20825222,20825225 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=20825212 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=20825209 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=20825210 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=20825216 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=20825213 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=20825214 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=20825223 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=20825217 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=20825224 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=20825219 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=20825220 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=20825222 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=20825225 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 257 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [2 5 4 2 0 5 1 5 5 3 2 5 0 5 2 5 4 2 4 4 2 5 2 2 4 4 2 4 4 1 3 3 0 0 2 3 1 0 3 1 4 2 0 1 0 2 1 0 0 1 4 0 0 1 1 1 2 4 1 2 1 5 2 1 1 1 0 0 1 1 1 4 3 0 2 1 2 1 1 2 0 1 0 1 5 1 5 5 1 3 3 3 3 4 2 0 0 0 2 0 2 3 2 0 2 0 3 0 3 2 2 0 2 3 2 2 2 2 1 3 3 0 1 1 1 1 0 0 3 3 3 0 2 3 5 0 4 2 3 1 5 3 0 2 3 0 2 2 2 4 3 2 1 5 0 4 5 0 3 3 2 3 5 3 3 3 3 2 3 3 3 3 3 3 5 5 0 2 5 3 3 0 0 0 1 5 1 2 1 0 1 0 3 1 2 2 1 2 2 0 1 3 3 3 0 3 2 2 5 2 3 3 0 3 2 5 2 2 3 2 2 0 0 3 1 5 0 1 2 0 4 1 4 0 1 3 3 3 4 0 0 0 2 5 3 0 4 1 0 0 4 2 2 2 2 4 0] Elapsed time: 0.0502166748046875 graph_id used : 80329 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20825212,20825209,20825210,20825216,20825213,20825214,20825223,20825217,20825224,20825219,20825220,20825222,20825225?tags=carton,metal,mal_croppe,pehd,autre,film_plastique,pet_clair,flou,pet_fonce,environnement,refus,papier,tetrapak&datou_id_consolidate=4235&port_consolidate=20824223&tree_id=80329 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1339667907] Looping around the photos to save general results len do output : 1 /20824223Didn'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, '2614741') ('4234', '20824223', '1339667907', None, None, None, None, None, '2614741') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.015006303787231445 save_final save missing photos in datou_result : time spend for datou_step_exec : 21.154706954956055 time spend to save output : 0.01542043685913086 total time spend for step 9 : 21.170127391815186 step10:send_mail_cod Wed Feb 26 06:24:01 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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_P20824223_26-02-2025_06_24_01.pdf 20825193 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 .imagette208251931740547441 20825190 change filename to text .change filename to text .change filename to text .imagette208251901740547442 20825191 imagette208251911740547442 20825197 change filename to text .imagette208251971740547442 20825194 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 .imagette208251941740547442 20825195 imagette208251951740547443 20825204 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 .imagette208252041740547443 20825198 imagette208251981740547444 20825205 change filename to text .change filename to text .imagette208252051740547444 20825201 imagette208252011740547444 20825203 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 .imagette208252031740547444 20825206 imagette208252061740547445 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20824223 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20825212,20825209,20825210,20825216,20825213,20825214,20825223,20825217,20825224,20825219,20825220,20825222,20825225?tags=carton,metal,mal_croppe,pehd,autre,film_plastique,pet_clair,flou,pet_fonce,environnement,refus,papier,tetrapak&datou_id_consolidate=4235&port_consolidate=20824223&tree_id=80329 your option no_mail is active, we will not send the real mail to your client args[1339667907] : ((1339667907, -7.955845070451469, 492609224), (1339667907, 0.22041772633133883, 2107752395), '0.6942148724334576') We are sending mail with results at cod@fotonower.com refus_total : 0.6942148724334576 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=20824223 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_P20824223_26-02-2025_06_24_01.pdf results_Qualipapia_P20824223_26-02-2025_06_24_01.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20824223_26-02-2025_06_24_01.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','20824223','results_Qualipapia_P20824223_26-02-2025_06_24_01.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20824223_26-02-2025_06_24_01.pdf','pdf','','0.15','0.6942148724334576') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1339667907] 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, '2614741') ('4234', '20824223', '1339667907', None, None, None, None, None, '2614741') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.011735916137695312 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.8028082847595215 time spend to save output : 0.011854887008666992 total time spend for step 10 : 4.8146631717681885 step11:split_time_score Wed Feb 26 06:24:06 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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 {} 26022025 20824223 Nombre de photos uploadées : 1 / 23040 (0%) 26022025 20824223 Nombre de photos taguées (types de déchets): 0 / 1 (0%) 26022025 20824223 Nombre de photos taguées (volume) : 0 / 1 (0%) elapsed_time : load_data_split_time_score 1.6689300537109375e-06 elapsed_time : order_list_meta_photo_and_scores 5.7220458984375e-06 ? elapsed_time : fill_and_build_computed_from_old_data 0.00014400482177734375 elapsed_time : insert_dashboard_record_day_entry 0.06409311294555664 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 : 0.6276294534906435 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20821360_26-02-2025_02_03_48.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20821360 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`=20821360 AND mptpi.`type`=4230 To do Qualite : 0.6441905892874558 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20821362_26-02-2025_02_40_50.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20821362 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`=20821362 AND mptpi.`type`=4230 To do Qualite : 0.6758532286835381 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20821883_26-02-2025_03_03_19.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20821883 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`=20821883 AND mptpi.`type`=4230 To do Qualite : 0.6491338101896319 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20822430_26-02-2025_05_39_26.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20822430 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`=20822430 AND mptpi.`type`=4230 To do Qualite : 0.6794979168726529 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20822795_26-02-2025_05_06_35.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20822795 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`=20822795 AND mptpi.`type`=4230 To do Qualite : 0.6942148724334576 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20824223_26-02-2025_06_24_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20824223 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`=20824223 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'26022025': {'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 [1339667907] Looping around the photos to save general results len do output : 1 /20824223Didn'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, '2614741') ('4234', '20824223', '1339667907', None, None, None, None, None, '2614741') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.015464544296264648 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.7260251045227051 time spend to save output : 0.015628814697265625 total time spend for step 11 : 0.7416539192199707 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 41.95user 25.61system 3:42.57elapsed 30%CPU (0avgtext+0avgdata 2484384maxresident)k 1748472inputs+18752outputs (4980major+3870782minor)pagefaults 0swaps