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 : 401524 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 : ['2608224'] with mtr_portfolio_ids : ['20752076'] and first list_photo_ids : [] new path : /proc/401524/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.6302075386047363 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Sat Feb 22 18:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3175 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-22 18:20:32.763180: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-22 18:20:32.799145: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-22 18:20:32.801633: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fbb74000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-22 18:20:32.801671: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-22 18:20:32.808069: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-22 18:20:33.071250: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1ec9c150 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-22 18:20:33.071316: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-22 18:20:33.072738: 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 2025-02-22 18:20:33.074312: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 18:20:33.112793: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 18:20:33.132601: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-22 18:20:33.137022: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-22 18:20:33.174534: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-22 18:20:33.180040: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-22 18:20:33.243595: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-22 18:20:33.244959: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-22 18:20:33.245637: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 18:20:33.246625: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-22 18:20:33.246646: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-22 18:20:33.246658: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-22 18:20:33.249530: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2723 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. 2025-02-22 18:20:33.792593: 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 2025-02-22 18:20:33.792696: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 18:20:33.792717: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 18:20:33.792734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-22 18:20:33.792751: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-22 18:20:33.792767: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-22 18:20:33.792784: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-22 18:20:33.792800: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-22 18:20:33.793633: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-22 18:20:33.794570: 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 2025-02-22 18:20:33.794611: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-22 18:20:33.794628: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 18:20:33.794644: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-22 18:20:33.794660: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-22 18:20:33.794676: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-22 18:20:33.794691: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-22 18:20:33.794708: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-22 18:20:33.795559: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-22 18:20:33.795592: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-22 18:20:33.795601: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-22 18:20:33.795608: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-22 18:20:33.796487: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2723 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 : [] 2025-02-22 18:20:42.006539: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-22 18:20:42.359816: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-22 18:20:44.400880: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.401421: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.402486: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.402505: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.409741: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.409764: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.410304: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.410319: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.416913: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.416937: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.417484: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.417500: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.448705: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.448756: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.449313: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.449329: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.455290: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.455327: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.455916: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.455932: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-22 18:20:44.490335: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.490927: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.492813: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.493362: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.536698: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.537258: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.542999: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.543637: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.573260: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.576897: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.578460: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.579022: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.591032: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.591648: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.596341: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.596926: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.606192: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.606758: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.608272: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.608851: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.639506: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.640092: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.640635: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.641175: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.645311: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.645863: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.663305: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.663858: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.664395: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.664930: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.678418: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.678977: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.679518: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.680056: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.688358: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.688920: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.693468: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.694013: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.705695: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.706245: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.710287: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.710836: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.711390: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.712106: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.712883: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.713429: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.723927: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.724471: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.725022: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.725557: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.726092: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.726627: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.741334: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.741885: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.799931: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.799982: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-02-22 18:20:44.800582: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.801177: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.808460: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.809084: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.817147: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.817780: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.860774: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.861660: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.862555: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.863425: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.867874: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.868731: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.869640: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.870528: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.873754: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.882585: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.883386: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.896695: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.897840: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.898947: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.900130: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.901393: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-22 18:20:44.905122: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2320367616 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 4 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.64141 max: 148.04141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.000133514404296875 nb_pixel_total : 719 time to create 1 rle with old method : 0.0013859272003173828 length of segment : 35 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 832 time to create 1 rle with old method : 0.001592397689819336 length of segment : 28 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0010645389556884766 length of segment : 30 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 66 time to create 1 rle with old method : 0.00010967254638671875 length of segment : 24 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.0010540485382080078 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: -118.12188 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.00018334388732910156 nb_pixel_total : 550 time to create 1 rle with old method : 0.0008213520050048828 length of segment : 99 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1383 time to create 1 rle with old method : 0.0017538070678710938 length of segment : 34 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1342 time to create 1 rle with old method : 0.0017857551574707031 length of segment : 29 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 43 time to create 1 rle with old method : 8.559226989746094e-05 length of segment : 7 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 2665 time to create 1 rle with old method : 0.003283262252807617 length of segment : 53 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.000164031982421875 length of segment : 20 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 2475 time to create 1 rle with old method : 0.0055539608001708984 length of segment : 46 Processing 1 images image shape: (400, 400, 3) min: 2.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -91.45391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006990432739257812 length of segment : 33 time for calcul the mask position with numpy : 9.942054748535156e-05 nb_pixel_total : 3246 time to create 1 rle with old method : 0.0042421817779541016 length of segment : 55 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 1828 time to create 1 rle with old method : 0.002486705780029297 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: -112.98516 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.00048828125 length of segment : 30 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0007476806640625 length of segment : 22 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 2601 time to create 1 rle with old method : 0.0035736560821533203 length of segment : 54 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 202.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 90.86562 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 577 time to create 1 rle with old method : 0.0008058547973632812 length of segment : 22 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.0002193450927734375 length of segment : 13 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004801750183105469 length of segment : 40 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003807544708251953 length of segment : 39 time for calcul the mask position with numpy : 0.0005435943603515625 nb_pixel_total : 51739 time to create 1 rle with old method : 0.06240987777709961 length of segment : 234 Processing 1 images image shape: (400, 400, 3) min: 21.00000 max: 188.00000 molded_images shape: (1, 640, 640, 3) min: -87.34844 max: 67.59219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013058185577392578 nb_pixel_total : 150228 time to create 1 rle with new method : 0.001984834671020508 length of segment : 395 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.37188 max: 149.00234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 0.00011563301086425781 nb_pixel_total : 2429 time to create 1 rle with old method : 0.004340171813964844 length of segment : 50 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 297 time to create 1 rle with old method : 0.0005986690521240234 length of segment : 13 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0007507801055908203 length of segment : 25 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1085 time to create 1 rle with old method : 0.002037525177001953 length of segment : 32 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0018813610076904297 length of segment : 35 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.0006196498870849609 length of segment : 21 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 851 time to create 1 rle with old method : 0.001580953598022461 length of segment : 33 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 424 time to create 1 rle with old method : 0.0009799003601074219 length of segment : 18 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 1856 time to create 1 rle with old method : 0.00330352783203125 length of segment : 67 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 772 time to create 1 rle with old method : 0.0011136531829833984 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.74688 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 : 7.653236389160156e-05 nb_pixel_total : 622 time to create 1 rle with old method : 0.000896453857421875 length of segment : 31 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005333423614501953 length of segment : 46 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0006854534149169922 length of segment : 37 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.0006678104400634766 length of segment : 24 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.00047969818115234375 length of segment : 15 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0006954669952392578 length of segment : 27 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 561 time to create 1 rle with old method : 0.0008742809295654297 length of segment : 45 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.000362396240234375 length of segment : 11 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 441 time to create 1 rle with old method : 0.0007498264312744141 length of segment : 22 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005655288696289062 length of segment : 35 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1109 time to create 1 rle with old method : 0.001461029052734375 length of segment : 55 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 1267 time to create 1 rle with old method : 0.0016620159149169922 length of segment : 57 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004191398620605469 length of segment : 26 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1197 time to create 1 rle with old method : 0.0018131732940673828 length of segment : 39 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 872 time to create 1 rle with old method : 0.0012314319610595703 length of segment : 40 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 559 time to create 1 rle with old method : 0.0008192062377929688 length of segment : 41 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.0004184246063232422 length of segment : 18 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.0007293224334716797 length of segment : 31 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 13 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002701282501220703 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.92266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 1188 time to create 1 rle with old method : 0.0021827220916748047 length of segment : 39 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 404 time to create 1 rle with old method : 0.0008041858673095703 length of segment : 26 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0006031990051269531 length of segment : 41 time for calcul the mask position with numpy : 8.440017700195312e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0017056465148925781 length of segment : 37 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0020782947540283203 length of segment : 139 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1309 time to create 1 rle with old method : 0.0017154216766357422 length of segment : 42 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 208.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 76.87344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 2658 time to create 1 rle with old method : 0.0032775402069091797 length of segment : 165 time for calcul the mask position with numpy : 0.00011157989501953125 nb_pixel_total : 1975 time to create 1 rle with old method : 0.002627849578857422 length of segment : 148 time for calcul the mask position with numpy : 0.00019478797912597656 nb_pixel_total : 3482 time to create 1 rle with old method : 0.0044057369232177734 length of segment : 180 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 910 time to create 1 rle with old method : 0.0011696815490722656 length of segment : 42 Processing 1 images image shape: (280, 400, 3) min: 17.00000 max: 192.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 71.29531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009527206420898438 nb_pixel_total : 106529 time to create 1 rle with old method : 0.11857485771179199 length of segment : 283 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.31484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 2309 time to create 1 rle with old method : 0.003625154495239258 length of segment : 62 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00038504600524902344 length of segment : 16 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002503395080566406 length of segment : 12 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 350 time to create 1 rle with old method : 0.0005261898040771484 length of segment : 23 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 307 time to create 1 rle with old method : 0.0006976127624511719 length of segment : 24 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00044417381286621094 length of segment : 11 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002486705780029297 length of segment : 12 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 886 time to create 1 rle with old method : 0.0011913776397705078 length of segment : 40 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0006723403930664062 length of segment : 33 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0003402233123779297 length of segment : 20 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 814 time to create 1 rle with old method : 0.0010445117950439453 length of segment : 34 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00017595291137695312 length of segment : 14 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 521 time to create 1 rle with old method : 0.0006973743438720703 length of segment : 29 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.000244140625 length of segment : 13 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00029587745666503906 length of segment : 22 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 519 time to create 1 rle with old method : 0.0007815361022949219 length of segment : 23 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1346 time to create 1 rle with old method : 0.0016982555389404297 length of segment : 68 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.00031948089599609375 length of segment : 23 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1690 time to create 1 rle with old method : 0.0022308826446533203 length of segment : 50 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.0002655982971191406 length of segment : 14 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 404 time to create 1 rle with old method : 0.0005877017974853516 length of segment : 21 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00017571449279785156 length of segment : 14 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.25234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 579 time to create 1 rle with old method : 0.0007565021514892578 length of segment : 33 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 972 time to create 1 rle with old method : 0.001323699951171875 length of segment : 41 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.00048041343688964844 length of segment : 19 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0009126663208007812 length of segment : 27 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 387 time to create 1 rle with old method : 0.0005059242248535156 length of segment : 35 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0004162788391113281 length of segment : 17 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 848 time to create 1 rle with old method : 0.0011281967163085938 length of segment : 28 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 1891 time to create 1 rle with old method : 0.0023169517517089844 length of segment : 50 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00016570091247558594 length of segment : 9 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 812 time to create 1 rle with old method : 0.0011370182037353516 length of segment : 44 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 1592 time to create 1 rle with old method : 0.0020341873168945312 length of segment : 43 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.00026726722717285156 length of segment : 23 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 842 time to create 1 rle with old method : 0.0011849403381347656 length of segment : 28 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0004119873046875 length of segment : 20 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00031757354736328125 length of segment : 15 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.00017547607421875 length of segment : 15 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0007336139678955078 length of segment : 25 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0008366107940673828 length of segment : 27 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1573 time to create 1 rle with old method : 0.0019943714141845703 length of segment : 43 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1078 time to create 1 rle with old method : 0.0014233589172363281 length of segment : 49 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00034737586975097656 length of segment : 21 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00035858154296875 length of segment : 28 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002639293670654297 length of segment : 21 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00014209747314453125 length of segment : 15 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.00030303001403808594 length of segment : 15 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 709 time to create 1 rle with old method : 0.0009634494781494141 length of segment : 33 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.001682281494140625 length of segment : 42 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1604 time to create 1 rle with old method : 0.0020780563354492188 length of segment : 73 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002605915069580078 length of segment : 14 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.74453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005106925964355469 length of segment : 26 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00033354759216308594 length of segment : 21 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.0010859966278076172 length of segment : 28 time for calcul the mask position with numpy : 0.0001800060272216797 nb_pixel_total : 4976 time to create 1 rle with old method : 0.007700204849243164 length of segment : 83 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004229545593261719 length of segment : 24 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 249 time to create 1 rle with old method : 0.0003695487976074219 length of segment : 18 length of segment : 0 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.0008990764617919922 length of segment : 27 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.60000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 18 time to create 1 rle with old method : 5.7220458984375e-05 length of segment : 4 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00021576881408691406 length of segment : 36 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.94609 max: 149.89297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.001039743423461914 length of segment : 33 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 949 time to create 1 rle with old method : 0.001249551773071289 length of segment : 42 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 761 time to create 1 rle with old method : 0.0010237693786621094 length of segment : 39 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.000133514404296875 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: -118.09844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 80 time to create 1 rle with old method : 0.00016880035400390625 length of segment : 17 time for calcul the mask position with numpy : 9.131431579589844e-05 nb_pixel_total : 2516 time to create 1 rle with old method : 0.0030472278594970703 length of segment : 49 time for calcul the mask position with numpy : 0.0002620220184326172 nb_pixel_total : 98 time to create 1 rle with old method : 0.0001690387725830078 length of segment : 25 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 219 time to create 1 rle with old method : 0.00033664703369140625 length of segment : 16 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 2236 time to create 1 rle with old method : 0.00292205810546875 length of segment : 41 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.0002124309539794922 length of segment : 10 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 2552 time to create 1 rle with old method : 0.003353118896484375 length of segment : 42 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 44 time to create 1 rle with old method : 8.845329284667969e-05 length of segment : 7 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -89.42266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00010466575622558594 nb_pixel_total : 4070 time to create 1 rle with old method : 0.005056858062744141 length of segment : 56 time for calcul the mask position with numpy : 0.00011754035949707031 nb_pixel_total : 4794 time to create 1 rle with old method : 0.005964040756225586 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: -110.21563 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0007045269012451172 length of segment : 31 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0010154247283935547 length of segment : 22 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 204.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 88.59609 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0007176399230957031 length of segment : 19 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1449 time to create 1 rle with old method : 0.0018317699432373047 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 23.00000 max: 184.00000 molded_images shape: (1, 640, 640, 3) min: -88.76250 max: 66.18594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013794898986816406 nb_pixel_total : 152879 time to create 1 rle with new method : 0.002034425735473633 length of segment : 401 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.76641 max: 147.90078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 0.0002422332763671875 nb_pixel_total : 534 time to create 1 rle with old method : 0.0011630058288574219 length of segment : 20 time for calcul the mask position with numpy : 0.0001995563507080078 nb_pixel_total : 2328 time to create 1 rle with old method : 0.0037178993225097656 length of segment : 49 time for calcul the mask position with numpy : 0.00015282630920410156 nb_pixel_total : 430 time to create 1 rle with old method : 0.0006356239318847656 length of segment : 23 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 898 time to create 1 rle with old method : 0.0017266273498535156 length of segment : 32 time for calcul the mask position with numpy : 0.0001544952392578125 nb_pixel_total : 341 time to create 1 rle with old method : 0.0007762908935546875 length of segment : 15 time for calcul the mask position with numpy : 0.00016689300537109375 nb_pixel_total : 316 time to create 1 rle with old method : 0.0007698535919189453 length of segment : 21 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.0007698535919189453 length of segment : 26 time for calcul the mask position with numpy : 0.000152587890625 nb_pixel_total : 350 time to create 1 rle with old method : 0.0006315708160400391 length of segment : 25 time for calcul the mask position with numpy : 0.00021982192993164062 nb_pixel_total : 1126 time to create 1 rle with old method : 0.00189971923828125 length of segment : 52 time for calcul the mask position with numpy : 0.00021791458129882812 nb_pixel_total : 890 time to create 1 rle with old method : 0.0018830299377441406 length of segment : 45 time for calcul the mask position with numpy : 0.0002295970916748047 nb_pixel_total : 1021 time to create 1 rle with old method : 0.0018057823181152344 length of segment : 30 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00021004676818847656 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: -112.02031 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 : 5.602836608886719e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.000823974609375 length of segment : 29 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006659030914306641 length of segment : 36 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 885 time to create 1 rle with old method : 0.0012447834014892578 length of segment : 69 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0006268024444580078 length of segment : 28 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0004317760467529297 length of segment : 13 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0006318092346191406 length of segment : 24 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 873 time to create 1 rle with old method : 0.001312255859375 length of segment : 45 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004429817199707031 length of segment : 27 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 964 time to create 1 rle with old method : 0.0012369155883789062 length of segment : 71 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 333 time to create 1 rle with old method : 0.0004940032958984375 length of segment : 21 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 689 time to create 1 rle with old method : 0.0009219646453857422 length of segment : 30 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.00033545494079589844 length of segment : 21 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.001176595687866211 length of segment : 36 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 890 time to create 1 rle with old method : 0.002197742462158203 length of segment : 64 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005731582641601562 length of segment : 30 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0008401870727539062 length of segment : 73 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0014388561248779297 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: -108.82500 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004584789276123047 length of segment : 44 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 1257 time to create 1 rle with old method : 0.001636505126953125 length of segment : 41 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1547 time to create 1 rle with old method : 0.0020012855529785156 length of segment : 129 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1288 time to create 1 rle with old method : 0.0015568733215332031 length of segment : 43 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 812 time to create 1 rle with old method : 0.0010311603546142578 length of segment : 37 time for calcul the mask position with numpy : 0.0003495216369628906 nb_pixel_total : 15862 time to create 1 rle with old method : 0.01906299591064453 length of segment : 211 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 209.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 83.73672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 1684 time to create 1 rle with old method : 0.002401113510131836 length of segment : 146 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 799 time to create 1 rle with old method : 0.0009975433349609375 length of segment : 40 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 2003 time to create 1 rle with old method : 0.002689838409423828 length of segment : 142 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.0011382102966308594 length of segment : 44 Processing 1 images image shape: (280, 400, 3) min: 17.00000 max: 193.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 75.51797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0010876655578613281 nb_pixel_total : 106619 time to create 1 rle with old method : 0.11679744720458984 length of segment : 279 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.80703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 2255 time to create 1 rle with old method : 0.002859354019165039 length of segment : 61 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003783702850341797 length of segment : 17 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00035452842712402344 length of segment : 19 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 536 time to create 1 rle with old method : 0.0007395744323730469 length of segment : 28 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 2725 time to create 1 rle with old method : 0.003500223159790039 length of segment : 65 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 129 time to create 1 rle with old method : 0.0002357959747314453 length of segment : 13 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 934 time to create 1 rle with old method : 0.0011363029479980469 length of segment : 42 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 1293 time to create 1 rle with old method : 0.0017633438110351562 length of segment : 40 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 1361 time to create 1 rle with old method : 0.0016827583312988281 length of segment : 72 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0004432201385498047 length of segment : 30 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.0004894733428955078 length of segment : 22 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.000762939453125 length of segment : 39 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.000591278076171875 length of segment : 23 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.0002570152282714844 length of segment : 16 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 142 time to create 1 rle with old method : 0.00021076202392578125 length of segment : 11 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1526 time to create 1 rle with old method : 0.001959562301635742 length of segment : 43 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 958 time to create 1 rle with old method : 0.0012507438659667969 length of segment : 79 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.0008275508880615234 length of segment : 30 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.00015664100646972656 length of segment : 14 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0005116462707519531 length of segment : 24 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.0002522468566894531 length of segment : 20 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 778 time to create 1 rle with old method : 0.0010592937469482422 length of segment : 47 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 547 time to create 1 rle with old method : 0.0007622241973876953 length of segment : 19 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 1242 time to create 1 rle with old method : 0.0028569698333740234 length of segment : 58 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 979 time to create 1 rle with old method : 0.0016603469848632812 length of segment : 41 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 676 time to create 1 rle with old method : 0.000926971435546875 length of segment : 27 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.000766754150390625 length of segment : 33 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0005548000335693359 length of segment : 37 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004265308380126953 length of segment : 21 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 829 time to create 1 rle with old method : 0.001058340072631836 length of segment : 29 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.00041937828063964844 length of segment : 18 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 153 time to create 1 rle with old method : 0.00020647048950195312 length of segment : 19 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1902 time to create 1 rle with old method : 0.002137422561645508 length of segment : 56 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00018668174743652344 length of segment : 18 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1631 time to create 1 rle with old method : 0.001962423324584961 length of segment : 45 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0002865791320800781 length of segment : 16 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1653 time to create 1 rle with old method : 0.002007007598876953 length of segment : 45 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.00036215782165527344 length of segment : 20 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 171 time to create 1 rle with old method : 0.0002410411834716797 length of segment : 20 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 101 time to create 1 rle with old method : 0.00014138221740722656 length of segment : 15 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 948 time to create 1 rle with old method : 0.0011479854583740234 length of segment : 31 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 585 time to create 1 rle with old method : 0.0006937980651855469 length of segment : 27 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 557 time to create 1 rle with old method : 0.0006923675537109375 length of segment : 26 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.0009403228759765625 length of segment : 34 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 533 time to create 1 rle with old method : 0.0007171630859375 length of segment : 25 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00015616416931152344 length of segment : 8 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1511 time to create 1 rle with old method : 0.0018057823181152344 length of segment : 45 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002181529998779297 length of segment : 12 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.0002181529998779297 length of segment : 15 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.00038504600524902344 length of segment : 22 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.47891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0007305145263671875 length of segment : 27 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.00026702880859375 length of segment : 21 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 4720 time to create 1 rle with old method : 0.005759000778198242 length of segment : 80 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 403 time to create 1 rle with old method : 0.0005578994750976562 length of segment : 24 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005590915679931641 length of segment : 26 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002999305725097656 length of segment : 18 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 38 time to create 1 rle with old method : 8.988380432128906e-05 length of segment : 14 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0003948211669921875 length of segment : 22 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 3371 time to create 1 rle with old method : 0.0038635730743408203 length of segment : 104 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 15 time to create 1 rle with old method : 4.673004150390625e-05 length of segment : 3 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 38 time to create 1 rle with old method : 7.295608520507812e-05 length of segment : 16 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005347728729248047 length of segment : 32 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0005307197570800781 length of segment : 29 time for calcul the mask position with numpy : 0.00039958953857421875 nb_pixel_total : 34841 time to create 1 rle with old method : 0.04028487205505371 length of segment : 208 time for calcul the mask position with numpy : 0.0003960132598876953 nb_pixel_total : 35667 time to create 1 rle with old method : 0.039305925369262695 length of segment : 245 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.95781 max: 150.35000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 863 time to create 1 rle with old method : 0.0010225772857666016 length of segment : 32 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 894 time to create 1 rle with old method : 0.0012059211730957031 length of segment : 37 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00011491775512695312 length of segment : 13 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 872 time to create 1 rle with old method : 0.001171112060546875 length of segment : 33 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.00011968612670898438 length of segment : 27 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 830 time to create 1 rle with old method : 0.0010981559753417969 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.61797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 0.0001277923583984375 nb_pixel_total : 537 time to create 1 rle with old method : 0.0008461475372314453 length of segment : 98 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00012135505676269531 length of segment : 13 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 2729 time to create 1 rle with old method : 0.0037369728088378906 length of segment : 48 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 708 time to create 1 rle with old method : 0.0009052753448486328 length of segment : 35 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 2268 time to create 1 rle with old method : 0.0027382373809814453 length of segment : 51 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001423358917236328 length of segment : 11 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 30 time to create 1 rle with old method : 8.392333984375e-05 length of segment : 6 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006809234619140625 length of segment : 36 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.00028061866760253906 length of segment : 15 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 479 time to create 1 rle with old method : 0.0006849765777587891 length of segment : 31 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 38 time to create 1 rle with old method : 8.58306884765625e-05 length of segment : 8 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 2311 time to create 1 rle with old method : 0.0029287338256835938 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 19.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -81.95781 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 4586 time to create 1 rle with old method : 0.0055768489837646484 length of segment : 49 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2640 time to create 1 rle with old method : 0.0034296512603759766 length of segment : 43 time for calcul the mask position with numpy : 0.00013756752014160156 nb_pixel_total : 5286 time to create 1 rle with old method : 0.006628274917602539 length of segment : 47 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.45391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0006513595581054688 length of segment : 29 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.00040984153747558594 length of segment : 27 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 202.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 89.44375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 548 time to create 1 rle with old method : 0.0009849071502685547 length of segment : 19 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 1491 time to create 1 rle with old method : 0.0020554065704345703 length of segment : 46 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 1655 time to create 1 rle with old method : 0.0021011829376220703 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 25.00000 max: 190.00000 molded_images shape: (1, 640, 640, 3) min: -89.37188 max: 69.16641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0012934207916259766 nb_pixel_total : 150547 time to create 1 rle with new method : 0.0022602081298828125 length of segment : 396 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.49688 max: 148.35391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 2379 time to create 1 rle with old method : 0.0029549598693847656 length of segment : 50 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0005834102630615234 length of segment : 23 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.00047898292541503906 length of segment : 14 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0007605552673339844 length of segment : 21 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0005483627319335938 length of segment : 28 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007710456848144531 length of segment : 20 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 1025 time to create 1 rle with old method : 0.0012450218200683594 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.39141 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0007469654083251953 length of segment : 29 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1003 time to create 1 rle with old method : 0.0012998580932617188 length of segment : 56 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 572 time to create 1 rle with old method : 0.0008041858673095703 length of segment : 45 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005908012390136719 length of segment : 25 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0004124641418457031 length of segment : 13 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.00029969215393066406 length of segment : 20 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004405975341796875 length of segment : 47 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0003902912139892578 length of segment : 21 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0006320476531982422 length of segment : 21 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 816 time to create 1 rle with old method : 0.0011696815490722656 length of segment : 50 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 878 time to create 1 rle with old method : 0.0011963844299316406 length of segment : 47 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 702 time to create 1 rle with old method : 0.0009644031524658203 length of segment : 30 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 836 time to create 1 rle with old method : 0.001415252685546875 length of segment : 34 time for calcul the mask position with numpy : 8.487701416015625e-05 nb_pixel_total : 942 time to create 1 rle with old method : 0.0016560554504394531 length of segment : 44 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0006048679351806641 length of segment : 30 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 1833 time to create 1 rle with old method : 0.002347230911254883 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: -113.28203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 0.00011229515075683594 nb_pixel_total : 339 time to create 1 rle with old method : 0.0009403228759765625 length of segment : 43 time for calcul the mask position with numpy : 0.0001742839813232422 nb_pixel_total : 1537 time to create 1 rle with old method : 0.003537416458129883 length of segment : 117 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1232 time to create 1 rle with old method : 0.0015146732330322266 length of segment : 41 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008456707000732422 length of segment : 36 time for calcul the mask position with numpy : 0.0004241466522216797 nb_pixel_total : 12062 time to create 1 rle with old method : 0.014191389083862305 length of segment : 269 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 504 time to create 1 rle with old method : 0.0007143020629882812 length of segment : 29 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 203.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 83.30703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 2091 time to create 1 rle with old method : 0.0024611949920654297 length of segment : 158 time for calcul the mask position with numpy : 0.00011086463928222656 nb_pixel_total : 2234 time to create 1 rle with old method : 0.002815723419189453 length of segment : 153 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 932 time to create 1 rle with old method : 0.0012025833129882812 length of segment : 43 time for calcul the mask position with numpy : 8.559226989746094e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0006203651428222656 length of segment : 57 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1464 time to create 1 rle with old method : 0.0017790794372558594 length of segment : 72 time for calcul the mask position with numpy : 0.0002009868621826172 nb_pixel_total : 3601 time to create 1 rle with old method : 0.0041656494140625 length of segment : 186 Processing 1 images image shape: (280, 400, 3) min: 20.00000 max: 194.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 70.67031 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.81875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 2166 time to create 1 rle with old method : 0.0026693344116210938 length of segment : 60 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002601146697998047 length of segment : 16 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.00024080276489257812 length of segment : 13 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.00013184547424316406 length of segment : 11 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 279 time to create 1 rle with old method : 0.0004088878631591797 length of segment : 22 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 275 time to create 1 rle with old method : 0.0004181861877441406 length of segment : 18 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 1334 time to create 1 rle with old method : 0.0017788410186767578 length of segment : 41 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.00022077560424804688 length of segment : 11 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0014002323150634766 length of segment : 46 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002703666687011719 length of segment : 14 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 26 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1362 time to create 1 rle with old method : 0.0017313957214355469 length of segment : 41 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00017380714416503906 length of segment : 14 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003380775451660156 length of segment : 23 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.00021529197692871094 length of segment : 13 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 37 time to create 1 rle with old method : 8.96453857421875e-05 length of segment : 8 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 579 time to create 1 rle with old method : 0.0008180141448974609 length of segment : 44 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 562 time to create 1 rle with old method : 0.0011060237884521484 length of segment : 33 time for calcul the mask position with numpy : 9.036064147949219e-05 nb_pixel_total : 1544 time to create 1 rle with old method : 0.0026023387908935547 length of segment : 54 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 2547 time to create 1 rle with old method : 0.0032761096954345703 length of segment : 62 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 88 time to create 1 rle with old method : 0.00017333030700683594 length of segment : 8 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0005433559417724609 length of segment : 25 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2729 time to create 1 rle with old method : 0.003403902053833008 length of segment : 58 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00014019012451171875 length of segment : 17 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.12734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.00054931640625 length of segment : 37 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 983 time to create 1 rle with old method : 0.0012586116790771484 length of segment : 42 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0004506111145019531 length of segment : 18 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 670 time to create 1 rle with old method : 0.0008826255798339844 length of segment : 26 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0006461143493652344 length of segment : 30 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 829 time to create 1 rle with old method : 0.0010607242584228516 length of segment : 26 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00042319297790527344 length of segment : 18 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002675056457519531 length of segment : 25 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003402233123779297 length of segment : 16 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007431507110595703 length of segment : 25 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 2116 time to create 1 rle with old method : 0.0025861263275146484 length of segment : 53 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1591 time to create 1 rle with old method : 0.0019598007202148438 length of segment : 44 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00037670135498046875 length of segment : 23 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00021386146545410156 length of segment : 12 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 1464 time to create 1 rle with old method : 0.0017480850219726562 length of segment : 41 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007834434509277344 length of segment : 26 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002663135528564453 length of segment : 19 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.00015807151794433594 length of segment : 15 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.001264333724975586 length of segment : 30 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.0003333091735839844 length of segment : 25 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.00019621849060058594 length of segment : 16 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 448 time to create 1 rle with old method : 0.000652313232421875 length of segment : 40 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.00044727325439453125 length of segment : 22 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00021338462829589844 length of segment : 14 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 501 time to create 1 rle with old method : 0.0006513595581054688 length of segment : 38 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 785 time to create 1 rle with old method : 0.0011310577392578125 length of segment : 28 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.48672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0009396076202392578 length of segment : 28 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 191 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 23 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005743503570556641 length of segment : 26 time for calcul the mask position with numpy : 0.00010991096496582031 nb_pixel_total : 4964 time to create 1 rle with old method : 0.006311178207397461 length of segment : 83 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 22 time to create 1 rle with old method : 6.079673767089844e-05 length of segment : 14 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1455 time to create 1 rle with old method : 0.001851797103881836 length of segment : 53 time for calcul the mask position with numpy : 9.274482727050781e-05 nb_pixel_total : 625 time to create 1 rle with old method : 0.0009028911590576172 length of segment : 25 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0005853176116943359 length of segment : 27 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.85000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 15 time to create 1 rle with old method : 5.0067901611328125e-05 length of segment : 3 time for calcul the mask position with numpy : 0.00021338462829589844 nb_pixel_total : 9387 time to create 1 rle with old method : 0.012133121490478516 length of segment : 251 time for calcul the mask position with numpy : 0.0003199577331542969 nb_pixel_total : 9911 time to create 1 rle with old method : 0.01231694221496582 length of segment : 250 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.54766 max: 147.97109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 942 time to create 1 rle with old method : 0.0012469291687011719 length of segment : 34 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 772 time to create 1 rle with old method : 0.0011444091796875 length of segment : 37 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.00011420249938964844 length of segment : 24 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 783 time to create 1 rle with old method : 0.0011970996856689453 length of segment : 35 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.0011703968048095703 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.80547 max: 150.49844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 1370 time to create 1 rle with old method : 0.0031409263610839844 length of segment : 35 time for calcul the mask position with numpy : 0.0003750324249267578 nb_pixel_total : 169 time to create 1 rle with old method : 0.0006663799285888672 length of segment : 65 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001461505889892578 length of segment : 14 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0012221336364746094 length of segment : 25 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0006792545318603516 length of segment : 58 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.0003509521484375 length of segment : 12 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.0007588863372802734 length of segment : 36 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 697 time to create 1 rle with old method : 0.0013222694396972656 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 26.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -81.04375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 2347 time to create 1 rle with old method : 0.003683805465698242 length of segment : 45 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0007996559143066406 length of segment : 17 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0014178752899169922 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.52813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 363 time to create 1 rle with old method : 0.0005977153778076172 length of segment : 31 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002987384796142578 length of segment : 30 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 209.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 91.15859 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.0007748603820800781 length of segment : 17 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1902 time to create 1 rle with old method : 0.0024461746215820312 length of segment : 70 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 357 time to create 1 rle with old method : 0.0005352497100830078 length of segment : 41 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00026035308837890625 length of segment : 13 time for calcul the mask position with numpy : 0.0013227462768554688 nb_pixel_total : 76409 time to create 1 rle with old method : 0.09697842597961426 length of segment : 341 Processing 1 images image shape: (400, 400, 3) min: 20.00000 max: 186.00000 molded_images shape: (1, 640, 640, 3) min: -88.83672 max: 68.20547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0014111995697021484 nb_pixel_total : 152712 time to create 1 rle with new method : 0.0020494461059570312 length of segment : 405 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.73516 max: 148.20937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 2383 time to create 1 rle with old method : 0.0033338069915771484 length of segment : 49 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.000514984130859375 length of segment : 16 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0010802745819091797 length of segment : 37 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.00067138671875 length of segment : 24 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0006034374237060547 length of segment : 13 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0005817413330078125 length of segment : 26 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 1084 time to create 1 rle with old method : 0.0014536380767822266 length of segment : 33 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.00048041343688964844 length of segment : 22 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003781318664550781 length of segment : 17 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003199577331542969 length of segment : 14 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 1193 time to create 1 rle with old method : 0.0018703937530517578 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.05156 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 : 5.793571472167969e-05 nb_pixel_total : 609 time to create 1 rle with old method : 0.0008215904235839844 length of segment : 30 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0007052421569824219 length of segment : 34 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0006389617919921875 length of segment : 25 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.00042438507080078125 length of segment : 12 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1170 time to create 1 rle with old method : 0.0014307498931884766 length of segment : 60 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 700 time to create 1 rle with old method : 0.0010571479797363281 length of segment : 32 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 661 time to create 1 rle with old method : 0.0009813308715820312 length of segment : 43 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.00040459632873535156 length of segment : 45 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.00031185150146484375 length of segment : 21 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 804 time to create 1 rle with old method : 0.0011942386627197266 length of segment : 45 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 703 time to create 1 rle with old method : 0.0009183883666992188 length of segment : 30 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.00057220458984375 length of segment : 30 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 364 time to create 1 rle with old method : 0.0006909370422363281 length of segment : 23 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 973 time to create 1 rle with old method : 0.0012378692626953125 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: -113.28203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.00045490264892578125 length of segment : 42 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 1151 time to create 1 rle with old method : 0.0014193058013916016 length of segment : 39 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 1556 time to create 1 rle with old method : 0.001813650131225586 length of segment : 139 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 1219 time to create 1 rle with old method : 0.0014884471893310547 length of segment : 40 time for calcul the mask position with numpy : 0.00014019012451171875 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0016160011291503906 length of segment : 107 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 211.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 82.56484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00011301040649414062 nb_pixel_total : 3241 time to create 1 rle with old method : 0.0036284923553466797 length of segment : 133 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 3365 time to create 1 rle with old method : 0.0038275718688964844 length of segment : 116 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 911 time to create 1 rle with old method : 0.0010786056518554688 length of segment : 43 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1423 time to create 1 rle with old method : 0.0015802383422851562 length of segment : 74 Processing 1 images image shape: (280, 400, 3) min: 17.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 71.29531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0008561611175537109 nb_pixel_total : 106154 time to create 1 rle with old method : 0.11581182479858398 length of segment : 279 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.22109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 23 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00027298927307128906 length of segment : 15 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2919 time to create 1 rle with old method : 0.0035512447357177734 length of segment : 51 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.000400543212890625 length of segment : 22 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 1080 time to create 1 rle with old method : 0.001768350601196289 length of segment : 61 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.00020003318786621094 length of segment : 11 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002903938293457031 length of segment : 16 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.0002167224884033203 length of segment : 11 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.000507354736328125 length of segment : 18 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.000331878662109375 length of segment : 19 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.0002465248107910156 length of segment : 13 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1404 time to create 1 rle with old method : 0.0017964839935302734 length of segment : 47 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003490447998046875 length of segment : 20 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1230 time to create 1 rle with old method : 0.0016524791717529297 length of segment : 40 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00016617774963378906 length of segment : 15 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1513 time to create 1 rle with old method : 0.0018682479858398438 length of segment : 44 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 426 time to create 1 rle with old method : 0.0006210803985595703 length of segment : 21 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 52 time to create 1 rle with old method : 0.00010991096496582031 length of segment : 8 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 1039 time to create 1 rle with old method : 0.001310586929321289 length of segment : 36 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.00045990943908691406 length of segment : 39 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.00027060508728027344 length of segment : 22 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00016236305236816406 length of segment : 14 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0006415843963623047 length of segment : 48 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.00029587745666503906 length of segment : 22 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.56484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 26 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 981 time to create 1 rle with old method : 0.0013060569763183594 length of segment : 41 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.0007274150848388672 length of segment : 31 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.000972747802734375 length of segment : 28 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0005695819854736328 length of segment : 37 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.00037026405334472656 length of segment : 21 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1797 time to create 1 rle with old method : 0.0023539066314697266 length of segment : 48 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0006916522979736328 length of segment : 24 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 677 time to create 1 rle with old method : 0.0009663105010986328 length of segment : 43 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003960132598876953 length of segment : 17 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003516674041748047 length of segment : 18 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.00019860267639160156 length of segment : 20 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0009968280792236328 length of segment : 27 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.00030350685119628906 length of segment : 15 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1127 time to create 1 rle with old method : 0.0014576911926269531 length of segment : 40 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 1619 time to create 1 rle with old method : 0.0019643306732177734 length of segment : 45 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1537 time to create 1 rle with old method : 0.0019245147705078125 length of segment : 42 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1330 time to create 1 rle with old method : 0.0017800331115722656 length of segment : 88 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 567 time to create 1 rle with old method : 0.0006718635559082031 length of segment : 27 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.00035643577575683594 length of segment : 16 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 891 time to create 1 rle with old method : 0.0011687278747558594 length of segment : 30 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.0005254745483398438 length of segment : 24 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.0001468658447265625 length of segment : 15 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.00023674964904785156 length of segment : 20 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00026726722717285156 length of segment : 18 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1588 time to create 1 rle with old method : 0.002043008804321289 length of segment : 45 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 22 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.81484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0005695819854736328 length of segment : 25 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.0009310245513916016 length of segment : 84 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 591 time to create 1 rle with old method : 0.0007114410400390625 length of segment : 28 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 619 time to create 1 rle with old method : 0.0008783340454101562 length of segment : 22 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 4616 time to create 1 rle with old method : 0.0054323673248291016 length of segment : 83 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 425 time to create 1 rle with old method : 0.0005869865417480469 length of segment : 26 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00031757354736328125 length of segment : 24 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 25 time to create 1 rle with old method : 6.127357482910156e-05 length of segment : 7 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 20 time to create 1 rle with old method : 5.14984130859375e-05 length of segment : 4 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005497932434082031 length of segment : 36 Detection mask done ! Trying to reset tf kernel 402164 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1982 tf kernel not reseted sub process len(results) : 491 len(list_Values) 491 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 491 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 : 3175 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 491 chid ids of type : 4228 Number RLEs to save : 21176 save missing photos in datou_result : time spend for datou_step_exec : 32.21841049194336 time spend to save output : 2.5174155235290527 total time spend for step 1 : 34.73582601547241 step2:brightness Sat Feb 22 18:21:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1740244827_401524_1339109752_2b6e59d4bc7d68a0b5ab58c89922a241.jpg treat image : temp/1740244827_401524_1339109751_d9b5ffe2c551dbfd1269439ecfa6e9c3.jpg treat image : temp/1740244827_401524_1339109750_921b5fa7bd775031fe170f8cae68bdfb.jpg treat image : temp/1740244827_401524_1339109657_28ef211d0bb239cc8bbd852b285c362c.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 4 time used for this insertion : 0.03555035591125488 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.011860370635986328 save missing photos in datou_result : time spend for datou_step_exec : 1.0683369636535645 time spend to save output : 0.05271649360656738 total time spend for step 2 : 1.1210534572601318 step3:blur_detection Sat Feb 22 18:21:04 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/1740244827_401524_1339109752_2b6e59d4bc7d68a0b5ab58c89922a241.jpg resize: (1080, 1920) 1339109752 -7.218491496063488 treat image : temp/1740244827_401524_1339109751_d9b5ffe2c551dbfd1269439ecfa6e9c3.jpg resize: (1080, 1920) 1339109751 -7.2772406972626795 treat image : temp/1740244827_401524_1339109750_921b5fa7bd775031fe170f8cae68bdfb.jpg resize: (1080, 1920) 1339109750 -7.262344703452727 treat image : temp/1740244827_401524_1339109657_28ef211d0bb239cc8bbd852b285c362c.jpg resize: (1080, 1920) 1339109657 -7.244428432725791 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 4 time used for this insertion : 0.011684417724609375 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.010869503021240234 save missing photos in datou_result : time spend for datou_step_exec : 5.3292553424835205 time spend to save output : 0.027556657791137695 total time spend for step 3 : 5.356812000274658 step4:rle_unique_nms_with_priority Sat Feb 22 18:21:09 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 491 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 124 nb_hashtags : 6 time to prepare the origin masks : 1.1328554153442383 time for calcul the mask position with numpy : 0.11450743675231934 nb_pixel_total : 1684779 time to create 1 rle with new method : 0.0867612361907959 time for calcul the mask position with numpy : 0.008257150650024414 nb_pixel_total : 497 time to create 1 rle with old method : 0.0005955696105957031 time for calcul the mask position with numpy : 0.010949373245239258 nb_pixel_total : 1383 time to create 1 rle with old method : 0.001990079879760742 time for calcul the mask position with numpy : 0.009775400161743164 nb_pixel_total : 104 time to create 1 rle with old method : 0.0001614093780517578 time for calcul the mask position with numpy : 0.008142232894897461 nb_pixel_total : 86 time to create 1 rle with old method : 0.00012683868408203125 time for calcul the mask position with numpy : 0.008228302001953125 nb_pixel_total : 66 time to create 1 rle with old method : 7.939338684082031e-05 time for calcul the mask position with numpy : 0.008085250854492188 nb_pixel_total : 80 time to create 1 rle with old method : 0.00011944770812988281 time for calcul the mask position with numpy : 0.007970333099365234 nb_pixel_total : 719 time to create 1 rle with old method : 0.000820159912109375 time for calcul the mask position with numpy : 0.008188247680664062 nb_pixel_total : 832 time to create 1 rle with old method : 0.0009081363677978516 time for calcul the mask position with numpy : 0.008109807968139648 nb_pixel_total : 34 time to create 1 rle with old method : 6.651878356933594e-05 time for calcul the mask position with numpy : 0.00820779800415039 nb_pixel_total : 43 time to create 1 rle with old method : 5.555152893066406e-05 time for calcul the mask position with numpy : 0.008188247680664062 nb_pixel_total : 2665 time to create 1 rle with old method : 0.0029723644256591797 time for calcul the mask position with numpy : 0.00836181640625 nb_pixel_total : 51739 time to create 1 rle with old method : 0.05397510528564453 time for calcul the mask position with numpy : 0.00776982307434082 nb_pixel_total : 3246 time to create 1 rle with old method : 0.0033011436462402344 time for calcul the mask position with numpy : 0.007531881332397461 nb_pixel_total : 28 time to create 1 rle with old method : 6.67572021484375e-05 time for calcul the mask position with numpy : 0.007956981658935547 nb_pixel_total : 358 time to create 1 rle with old method : 0.00036907196044921875 time for calcul the mask position with numpy : 0.007739543914794922 nb_pixel_total : 550 time to create 1 rle with old method : 0.0005850791931152344 time for calcul the mask position with numpy : 0.007639646530151367 nb_pixel_total : 352 time to create 1 rle with old method : 0.00036072731018066406 time for calcul the mask position with numpy : 0.007513284683227539 nb_pixel_total : 245 time to create 1 rle with old method : 0.0002493858337402344 time for calcul the mask position with numpy : 0.007712841033935547 nb_pixel_total : 1828 time to create 1 rle with old method : 0.0019550323486328125 time for calcul the mask position with numpy : 0.007671356201171875 nb_pixel_total : 437 time to create 1 rle with old method : 0.0004749298095703125 time for calcul the mask position with numpy : 0.007512569427490234 nb_pixel_total : 129 time to create 1 rle with old method : 0.0001399517059326172 time for calcul the mask position with numpy : 0.007477521896362305 nb_pixel_total : 2601 time to create 1 rle with old method : 0.0026891231536865234 time for calcul the mask position with numpy : 0.0074787139892578125 nb_pixel_total : 577 time to create 1 rle with old method : 0.0006103515625 time for calcul the mask position with numpy : 0.008694887161254883 nb_pixel_total : 150228 time to create 1 rle with new method : 0.5395808219909668 time for calcul the mask position with numpy : 0.008041143417358398 nb_pixel_total : 1197 time to create 1 rle with old method : 0.0013816356658935547 time for calcul the mask position with numpy : 0.008103609085083008 nb_pixel_total : 398 time to create 1 rle with old method : 0.0004858970642089844 time for calcul the mask position with numpy : 0.007928848266601562 nb_pixel_total : 708 time to create 1 rle with old method : 0.0008015632629394531 time for calcul the mask position with numpy : 0.008067131042480469 nb_pixel_total : 206 time to create 1 rle with old method : 0.00023055076599121094 time for calcul the mask position with numpy : 0.008310079574584961 nb_pixel_total : 1188 time to create 1 rle with old method : 0.0012412071228027344 time for calcul the mask position with numpy : 0.008462905883789062 nb_pixel_total : 130 time to create 1 rle with old method : 0.00015854835510253906 time for calcul the mask position with numpy : 0.008094310760498047 nb_pixel_total : 404 time to create 1 rle with old method : 0.0005011558532714844 time for calcul the mask position with numpy : 0.008034706115722656 nb_pixel_total : 910 time to create 1 rle with old method : 0.0010716915130615234 time for calcul the mask position with numpy : 0.008191108703613281 nb_pixel_total : 1267 time to create 1 rle with old method : 0.001425027847290039 time for calcul the mask position with numpy : 0.008247852325439453 nb_pixel_total : 324 time to create 1 rle with old method : 0.00037026405334472656 time for calcul the mask position with numpy : 0.008123636245727539 nb_pixel_total : 2658 time to create 1 rle with old method : 0.0030107498168945312 time for calcul the mask position with numpy : 0.00832223892211914 nb_pixel_total : 254 time to create 1 rle with old method : 0.00033283233642578125 time for calcul the mask position with numpy : 0.008031845092773438 nb_pixel_total : 3482 time to create 1 rle with old method : 0.003962516784667969 time for calcul the mask position with numpy : 0.008079290390014648 nb_pixel_total : 398 time to create 1 rle with old method : 0.0004489421844482422 time for calcul the mask position with numpy : 0.008172273635864258 nb_pixel_total : 1600 time to create 1 rle with old method : 0.0017817020416259766 time for calcul the mask position with numpy : 0.00814199447631836 nb_pixel_total : 424 time to create 1 rle with old method : 0.0004749298095703125 time for calcul the mask position with numpy : 0.00807499885559082 nb_pixel_total : 306 time to create 1 rle with old method : 0.00031828880310058594 time for calcul the mask position with numpy : 0.00805354118347168 nb_pixel_total : 1856 time to create 1 rle with old method : 0.002225160598754883 time for calcul the mask position with numpy : 0.008094549179077148 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006020069122314453 time for calcul the mask position with numpy : 0.008119583129882812 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003147125244140625 time for calcul the mask position with numpy : 0.008377552032470703 nb_pixel_total : 2429 time to create 1 rle with old method : 0.0026340484619140625 time for calcul the mask position with numpy : 0.008118391036987305 nb_pixel_total : 385 time to create 1 rle with old method : 0.00040912628173828125 time for calcul the mask position with numpy : 0.008043527603149414 nb_pixel_total : 423 time to create 1 rle with old method : 0.0004513263702392578 time for calcul the mask position with numpy : 0.0077283382415771484 nb_pixel_total : 200 time to create 1 rle with old method : 0.00022149085998535156 time for calcul the mask position with numpy : 0.007831573486328125 nb_pixel_total : 510 time to create 1 rle with old method : 0.000545501708984375 time for calcul the mask position with numpy : 0.00818014144897461 nb_pixel_total : 36 time to create 1 rle with old method : 7.128715515136719e-05 time for calcul the mask position with numpy : 0.008108854293823242 nb_pixel_total : 790 time to create 1 rle with old method : 0.0008480548858642578 time for calcul the mask position with numpy : 0.008201122283935547 nb_pixel_total : 851 time to create 1 rle with old method : 0.0009579658508300781 time for calcul the mask position with numpy : 0.008040428161621094 nb_pixel_total : 1085 time to create 1 rle with old method : 0.0012161731719970703 time for calcul the mask position with numpy : 0.007807016372680664 nb_pixel_total : 1108 time to create 1 rle with old method : 0.0011603832244873047 time for calcul the mask position with numpy : 0.008130311965942383 nb_pixel_total : 297 time to create 1 rle with old method : 0.0003101825714111328 time for calcul the mask position with numpy : 0.007951021194458008 nb_pixel_total : 772 time to create 1 rle with old method : 0.0008873939514160156 time for calcul the mask position with numpy : 0.008034706115722656 nb_pixel_total : 483 time to create 1 rle with old method : 0.0005538463592529297 time for calcul the mask position with numpy : 0.008205413818359375 nb_pixel_total : 304 time to create 1 rle with old method : 0.00034236907958984375 time for calcul the mask position with numpy : 0.007926702499389648 nb_pixel_total : 441 time to create 1 rle with old method : 0.0004756450653076172 time for calcul the mask position with numpy : 0.00792384147644043 nb_pixel_total : 622 time to create 1 rle with old method : 0.0006661415100097656 time for calcul the mask position with numpy : 0.00805044174194336 nb_pixel_total : 1034 time to create 1 rle with old method : 0.0011284351348876953 time for calcul the mask position with numpy : 0.007845163345336914 nb_pixel_total : 415 time to create 1 rle with old method : 0.0004527568817138672 time for calcul the mask position with numpy : 0.008073568344116211 nb_pixel_total : 283 time to create 1 rle with old method : 0.00035119056701660156 time for calcul the mask position with numpy : 0.008265495300292969 nb_pixel_total : 106529 time to create 1 rle with old method : 0.11303520202636719 time for calcul the mask position with numpy : 0.008016347885131836 nb_pixel_total : 142 time to create 1 rle with old method : 0.00015926361083984375 time for calcul the mask position with numpy : 0.008118867874145508 nb_pixel_total : 350 time to create 1 rle with old method : 0.000396728515625 time for calcul the mask position with numpy : 0.008033514022827148 nb_pixel_total : 10 time to create 1 rle with old method : 2.1219253540039062e-05 time for calcul the mask position with numpy : 0.008065462112426758 nb_pixel_total : 110 time to create 1 rle with old method : 0.0001201629638671875 time for calcul the mask position with numpy : 0.008141040802001953 nb_pixel_total : 146 time to create 1 rle with old method : 0.00016379356384277344 time for calcul the mask position with numpy : 0.007844686508178711 nb_pixel_total : 201 time to create 1 rle with old method : 0.00021123886108398438 time for calcul the mask position with numpy : 0.00802469253540039 nb_pixel_total : 1891 time to create 1 rle with old method : 0.0020742416381835938 time for calcul the mask position with numpy : 0.00807046890258789 nb_pixel_total : 1592 time to create 1 rle with old method : 0.0017852783203125 time for calcul the mask position with numpy : 0.0084075927734375 nb_pixel_total : 387 time to create 1 rle with old method : 0.00045490264892578125 time for calcul the mask position with numpy : 0.008246898651123047 nb_pixel_total : 886 time to create 1 rle with old method : 0.0010156631469726562 time for calcul the mask position with numpy : 0.008145809173583984 nb_pixel_total : 132 time to create 1 rle with old method : 0.00016045570373535156 time for calcul the mask position with numpy : 0.008153676986694336 nb_pixel_total : 271 time to create 1 rle with old method : 0.0003173351287841797 time for calcul the mask position with numpy : 0.008196353912353516 nb_pixel_total : 22 time to create 1 rle with old method : 6.151199340820312e-05 time for calcul the mask position with numpy : 0.008334159851074219 nb_pixel_total : 146 time to create 1 rle with old method : 0.0001914501190185547 time for calcul the mask position with numpy : 0.008089303970336914 nb_pixel_total : 521 time to create 1 rle with old method : 0.0005731582641601562 time for calcul the mask position with numpy : 0.008220911026000977 nb_pixel_total : 147 time to create 1 rle with old method : 0.00017714500427246094 time for calcul the mask position with numpy : 0.008136272430419922 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003898143768310547 time for calcul the mask position with numpy : 0.008084535598754883 nb_pixel_total : 222 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.008034944534301758 nb_pixel_total : 6 time to create 1 rle with old method : 1.71661376953125e-05 time for calcul the mask position with numpy : 0.008176088333129883 nb_pixel_total : 545 time to create 1 rle with old method : 0.0005807876586914062 time for calcul the mask position with numpy : 0.008170604705810547 nb_pixel_total : 842 time to create 1 rle with old method : 0.0009386539459228516 time for calcul the mask position with numpy : 0.007787942886352539 nb_pixel_total : 814 time to create 1 rle with old method : 0.0008680820465087891 time for calcul the mask position with numpy : 0.007907867431640625 nb_pixel_total : 972 time to create 1 rle with old method : 0.0010216236114501953 time for calcul the mask position with numpy : 0.007982730865478516 nb_pixel_total : 305 time to create 1 rle with old method : 0.00034880638122558594 time for calcul the mask position with numpy : 0.008060455322265625 nb_pixel_total : 314 time to create 1 rle with old method : 0.0003457069396972656 time for calcul the mask position with numpy : 0.007888317108154297 nb_pixel_total : 130 time to create 1 rle with old method : 0.00014662742614746094 time for calcul the mask position with numpy : 0.007977724075317383 nb_pixel_total : 427 time to create 1 rle with old method : 0.0005240440368652344 time for calcul the mask position with numpy : 0.007751941680908203 nb_pixel_total : 307 time to create 1 rle with old method : 0.0003638267517089844 time for calcul the mask position with numpy : 0.007935285568237305 nb_pixel_total : 1346 time to create 1 rle with old method : 0.0014190673828125 time for calcul the mask position with numpy : 0.00790095329284668 nb_pixel_total : 812 time to create 1 rle with old method : 0.0008835792541503906 time for calcul the mask position with numpy : 0.008114814758300781 nb_pixel_total : 579 time to create 1 rle with old method : 0.0006613731384277344 time for calcul the mask position with numpy : 0.007827281951904297 nb_pixel_total : 234 time to create 1 rle with old method : 0.0002760887145996094 time for calcul the mask position with numpy : 0.008009672164916992 nb_pixel_total : 519 time to create 1 rle with old method : 0.0005662441253662109 time for calcul the mask position with numpy : 0.007786273956298828 nb_pixel_total : 2309 time to create 1 rle with old method : 0.002496004104614258 time for calcul the mask position with numpy : 0.00808405876159668 nb_pixel_total : 404 time to create 1 rle with old method : 0.0004913806915283203 time for calcul the mask position with numpy : 0.008124351501464844 nb_pixel_total : 4976 time to create 1 rle with old method : 0.005498409271240234 time for calcul the mask position with numpy : 0.007897377014160156 nb_pixel_total : 103 time to create 1 rle with old method : 0.00011324882507324219 time for calcul the mask position with numpy : 0.007873058319091797 nb_pixel_total : 152 time to create 1 rle with old method : 0.0001697540283203125 time for calcul the mask position with numpy : 0.008246898651123047 nb_pixel_total : 17 time to create 1 rle with old method : 3.838539123535156e-05 time for calcul the mask position with numpy : 0.007686138153076172 nb_pixel_total : 187 time to create 1 rle with old method : 0.00021147727966308594 time for calcul the mask position with numpy : 0.008022546768188477 nb_pixel_total : 681 time to create 1 rle with old method : 0.0007348060607910156 time for calcul the mask position with numpy : 0.008048534393310547 nb_pixel_total : 432 time to create 1 rle with old method : 0.0004737377166748047 time for calcul the mask position with numpy : 0.007779359817504883 nb_pixel_total : 709 time to create 1 rle with old method : 0.0008356571197509766 time for calcul the mask position with numpy : 0.007921695709228516 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0013699531555175781 time for calcul the mask position with numpy : 0.007943868637084961 nb_pixel_total : 1604 time to create 1 rle with old method : 0.001676321029663086 time for calcul the mask position with numpy : 0.00810551643371582 nb_pixel_total : 382 time to create 1 rle with old method : 0.0004258155822753906 time for calcul the mask position with numpy : 0.008114814758300781 nb_pixel_total : 167 time to create 1 rle with old method : 0.0001850128173828125 time for calcul the mask position with numpy : 0.007915019989013672 nb_pixel_total : 91 time to create 1 rle with old method : 9.894371032714844e-05 time for calcul the mask position with numpy : 0.008009910583496094 nb_pixel_total : 156 time to create 1 rle with old method : 0.00017714500427246094 time for calcul the mask position with numpy : 0.007866621017456055 nb_pixel_total : 273 time to create 1 rle with old method : 0.00028777122497558594 time for calcul the mask position with numpy : 0.008074522018432617 nb_pixel_total : 214 time to create 1 rle with old method : 0.00022792816162109375 time for calcul the mask position with numpy : 0.007735252380371094 nb_pixel_total : 170 time to create 1 rle with old method : 0.00018525123596191406 time for calcul the mask position with numpy : 0.007795810699462891 nb_pixel_total : 848 time to create 1 rle with old method : 0.0008831024169921875 time for calcul the mask position with numpy : 0.007815837860107422 nb_pixel_total : 18 time to create 1 rle with old method : 2.6226043701171875e-05 time for calcul the mask position with numpy : 0.007724761962890625 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002014636993408203 time for calcul the mask position with numpy : 0.007809877395629883 nb_pixel_total : 580 time to create 1 rle with old method : 0.0006177425384521484 time for calcul the mask position with numpy : 0.007851839065551758 nb_pixel_total : 11 time to create 1 rle with old method : 2.7894973754882812e-05 time for calcul the mask position with numpy : 0.008039474487304688 nb_pixel_total : 249 time to create 1 rle with old method : 0.0002677440643310547 time for calcul the mask position with numpy : 0.00802302360534668 nb_pixel_total : 589 time to create 1 rle with old method : 0.000675201416015625 time for calcul the mask position with numpy : 0.00819540023803711 nb_pixel_total : 94 time to create 1 rle with old method : 0.00011515617370605469 create new chi : 2.015984535217285 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 : 0.009906768798828125 batch 1 Loaded 125 chid ids of type : 4230 Number RLEs to save : 10706 TO DO : save crop sub photo not yet done ! save time : 1.5046703815460205 nb_obj : 124 nb_hashtags : 7 time to prepare the origin masks : 2.260887622833252 time for calcul the mask position with numpy : 0.5437073707580566 nb_pixel_total : 1673938 time to create 1 rle with new method : 0.08648347854614258 time for calcul the mask position with numpy : 0.0061779022216796875 nb_pixel_total : 949 time to create 1 rle with old method : 0.0011000633239746094 time for calcul the mask position with numpy : 0.0060901641845703125 nb_pixel_total : 83 time to create 1 rle with old method : 0.00010895729064941406 time for calcul the mask position with numpy : 0.00612330436706543 nb_pixel_total : 80 time to create 1 rle with old method : 0.00011897087097167969 time for calcul the mask position with numpy : 0.006548881530761719 nb_pixel_total : 789 time to create 1 rle with old method : 0.0014400482177734375 time for calcul the mask position with numpy : 0.0072553157806396484 nb_pixel_total : 44 time to create 1 rle with old method : 7.677078247070312e-05 time for calcul the mask position with numpy : 0.006356716156005859 nb_pixel_total : 4070 time to create 1 rle with old method : 0.004707813262939453 time for calcul the mask position with numpy : 0.006524324417114258 nb_pixel_total : 2516 time to create 1 rle with old method : 0.002844572067260742 time for calcul the mask position with numpy : 0.006571292877197266 nb_pixel_total : 6 time to create 1 rle with old method : 5.745887756347656e-05 time for calcul the mask position with numpy : 0.00640416145324707 nb_pixel_total : 128 time to create 1 rle with old method : 0.00016736984252929688 time for calcul the mask position with numpy : 0.0062770843505859375 nb_pixel_total : 219 time to create 1 rle with old method : 0.0002677440643310547 time for calcul the mask position with numpy : 0.006021261215209961 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004420280456542969 time for calcul the mask position with numpy : 0.0059909820556640625 nb_pixel_total : 2236 time to create 1 rle with old method : 0.0023806095123291016 time for calcul the mask position with numpy : 0.006141185760498047 nb_pixel_total : 430 time to create 1 rle with old method : 0.0005803108215332031 time for calcul the mask position with numpy : 0.006615638732910156 nb_pixel_total : 4794 time to create 1 rle with old method : 0.006067514419555664 time for calcul the mask position with numpy : 0.0065402984619140625 nb_pixel_total : 420 time to create 1 rle with old method : 0.00047397613525390625 time for calcul the mask position with numpy : 0.006047487258911133 nb_pixel_total : 98 time to create 1 rle with old method : 0.00012874603271484375 time for calcul the mask position with numpy : 0.0061075687408447266 nb_pixel_total : 1449 time to create 1 rle with old method : 0.002048969268798828 time for calcul the mask position with numpy : 0.0058515071868896484 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006039142608642578 time for calcul the mask position with numpy : 0.0067157745361328125 nb_pixel_total : 152879 time to create 1 rle with new method : 0.6082849502563477 time for calcul the mask position with numpy : 0.006147146224975586 nb_pixel_total : 689 time to create 1 rle with old method : 0.0007574558258056641 time for calcul the mask position with numpy : 0.0058481693267822266 nb_pixel_total : 812 time to create 1 rle with old method : 0.0008778572082519531 time for calcul the mask position with numpy : 0.005787372589111328 nb_pixel_total : 48 time to create 1 rle with old method : 9.131431579589844e-05 time for calcul the mask position with numpy : 0.005673408508300781 nb_pixel_total : 1257 time to create 1 rle with old method : 0.0013725757598876953 time for calcul the mask position with numpy : 0.005635738372802734 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001590251922607422 time for calcul the mask position with numpy : 0.005525827407836914 nb_pixel_total : 799 time to create 1 rle with old method : 0.0008804798126220703 time for calcul the mask position with numpy : 0.005532503128051758 nb_pixel_total : 348 time to create 1 rle with old method : 0.00036716461181640625 time for calcul the mask position with numpy : 0.005829572677612305 nb_pixel_total : 714 time to create 1 rle with old method : 0.0008106231689453125 time for calcul the mask position with numpy : 0.005636692047119141 nb_pixel_total : 1684 time to create 1 rle with old method : 0.0018568038940429688 time for calcul the mask position with numpy : 0.005790233612060547 nb_pixel_total : 15862 time to create 1 rle with old method : 0.01635456085205078 time for calcul the mask position with numpy : 0.00573420524597168 nb_pixel_total : 1547 time to create 1 rle with old method : 0.0016438961029052734 time for calcul the mask position with numpy : 0.0057108402252197266 nb_pixel_total : 350 time to create 1 rle with old method : 0.00041484832763671875 time for calcul the mask position with numpy : 0.006647348403930664 nb_pixel_total : 964 time to create 1 rle with old method : 0.0010824203491210938 time for calcul the mask position with numpy : 0.009475469589233398 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0010704994201660156 time for calcul the mask position with numpy : 0.008759260177612305 nb_pixel_total : 534 time to create 1 rle with old method : 0.0005838871002197266 time for calcul the mask position with numpy : 0.008735895156860352 nb_pixel_total : 337 time to create 1 rle with old method : 0.0003597736358642578 time for calcul the mask position with numpy : 0.009105920791625977 nb_pixel_total : 2328 time to create 1 rle with old method : 0.002385854721069336 time for calcul the mask position with numpy : 0.008998394012451172 nb_pixel_total : 760 time to create 1 rle with old method : 0.0008251667022705078 time for calcul the mask position with numpy : 0.009379148483276367 nb_pixel_total : 224 time to create 1 rle with old method : 0.00031638145446777344 time for calcul the mask position with numpy : 0.009177684783935547 nb_pixel_total : 351 time to create 1 rle with old method : 0.0003981590270996094 time for calcul the mask position with numpy : 0.008747339248657227 nb_pixel_total : 415 time to create 1 rle with old method : 0.0004892349243164062 time for calcul the mask position with numpy : 0.009485960006713867 nb_pixel_total : 885 time to create 1 rle with old method : 0.0009503364562988281 time for calcul the mask position with numpy : 0.009517908096313477 nb_pixel_total : 411 time to create 1 rle with old method : 0.0004515647888183594 time for calcul the mask position with numpy : 0.009112119674682617 nb_pixel_total : 873 time to create 1 rle with old method : 0.0009098052978515625 time for calcul the mask position with numpy : 0.008907794952392578 nb_pixel_total : 1021 time to create 1 rle with old method : 0.0011112689971923828 time for calcul the mask position with numpy : 0.008919715881347656 nb_pixel_total : 898 time to create 1 rle with old method : 0.0009396076202392578 time for calcul the mask position with numpy : 0.008176565170288086 nb_pixel_total : 341 time to create 1 rle with old method : 0.00037789344787597656 time for calcul the mask position with numpy : 0.007462263107299805 nb_pixel_total : 890 time to create 1 rle with old method : 0.0009214878082275391 time for calcul the mask position with numpy : 0.007211208343505859 nb_pixel_total : 489 time to create 1 rle with old method : 0.0005271434783935547 time for calcul the mask position with numpy : 0.00814199447631836 nb_pixel_total : 1120 time to create 1 rle with old method : 0.0011627674102783203 time for calcul the mask position with numpy : 0.008683919906616211 nb_pixel_total : 316 time to create 1 rle with old method : 0.00034928321838378906 time for calcul the mask position with numpy : 0.00887298583984375 nb_pixel_total : 113 time to create 1 rle with old method : 0.00014901161193847656 time for calcul the mask position with numpy : 0.009037494659423828 nb_pixel_total : 333 time to create 1 rle with old method : 0.0003948211669921875 time for calcul the mask position with numpy : 0.009276151657104492 nb_pixel_total : 605 time to create 1 rle with old method : 0.0006434917449951172 time for calcul the mask position with numpy : 0.009020328521728516 nb_pixel_total : 511 time to create 1 rle with old method : 0.0005300045013427734 time for calcul the mask position with numpy : 0.009150028228759766 nb_pixel_total : 430 time to create 1 rle with old method : 0.0004553794860839844 time for calcul the mask position with numpy : 0.008757829666137695 nb_pixel_total : 222 time to create 1 rle with old method : 0.000247955322265625 time for calcul the mask position with numpy : 0.00891876220703125 nb_pixel_total : 433 time to create 1 rle with old method : 0.00046706199645996094 time for calcul the mask position with numpy : 0.008501768112182617 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003135204315185547 time for calcul the mask position with numpy : 0.009344100952148438 nb_pixel_total : 106619 time to create 1 rle with old method : 0.1101219654083252 time for calcul the mask position with numpy : 0.009531974792480469 nb_pixel_total : 536 time to create 1 rle with old method : 0.0006241798400878906 time for calcul the mask position with numpy : 0.00960683822631836 nb_pixel_total : 55 time to create 1 rle with old method : 9.751319885253906e-05 time for calcul the mask position with numpy : 0.009942054748535156 nb_pixel_total : 105 time to create 1 rle with old method : 0.0001773834228515625 time for calcul the mask position with numpy : 0.0068852901458740234 nb_pixel_total : 1631 time to create 1 rle with old method : 0.00185394287109375 time for calcul the mask position with numpy : 0.006215095520019531 nb_pixel_total : 1902 time to create 1 rle with old method : 0.0021734237670898438 time for calcul the mask position with numpy : 0.006259441375732422 nb_pixel_total : 324 time to create 1 rle with old method : 0.000396728515625 time for calcul the mask position with numpy : 0.006122589111328125 nb_pixel_total : 53 time to create 1 rle with old method : 0.00010347366333007812 time for calcul the mask position with numpy : 0.005889415740966797 nb_pixel_total : 112 time to create 1 rle with old method : 0.00017023086547851562 time for calcul the mask position with numpy : 0.0072705745697021484 nb_pixel_total : 402 time to create 1 rle with old method : 0.0007307529449462891 time for calcul the mask position with numpy : 0.006895780563354492 nb_pixel_total : 1361 time to create 1 rle with old method : 0.0015511512756347656 time for calcul the mask position with numpy : 0.010715484619140625 nb_pixel_total : 264 time to create 1 rle with old method : 0.0004119873046875 time for calcul the mask position with numpy : 0.010520219802856445 nb_pixel_total : 279 time to create 1 rle with old method : 0.0003368854522705078 time for calcul the mask position with numpy : 0.010155200958251953 nb_pixel_total : 142 time to create 1 rle with old method : 0.00018215179443359375 time for calcul the mask position with numpy : 0.009706735610961914 nb_pixel_total : 129 time to create 1 rle with old method : 0.00016736984252929688 time for calcul the mask position with numpy : 0.009633302688598633 nb_pixel_total : 12 time to create 1 rle with old method : 3.6716461181640625e-05 time for calcul the mask position with numpy : 0.009352445602416992 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003132820129394531 time for calcul the mask position with numpy : 0.009452104568481445 nb_pixel_total : 38 time to create 1 rle with old method : 6.103515625e-05 time for calcul the mask position with numpy : 0.009549856185913086 nb_pixel_total : 778 time to create 1 rle with old method : 0.0009407997131347656 time for calcul the mask position with numpy : 0.010127544403076172 nb_pixel_total : 125 time to create 1 rle with old method : 0.00016236305236816406 time for calcul the mask position with numpy : 0.007150411605834961 nb_pixel_total : 242 time to create 1 rle with old method : 0.0002620220184326172 time for calcul the mask position with numpy : 0.005815029144287109 nb_pixel_total : 5197 time to create 1 rle with old method : 0.005456686019897461 time for calcul the mask position with numpy : 0.00608062744140625 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006530284881591797 time for calcul the mask position with numpy : 0.00624537467956543 nb_pixel_total : 557 time to create 1 rle with old method : 0.0006444454193115234 time for calcul the mask position with numpy : 0.006360292434692383 nb_pixel_total : 2 time to create 1 rle with old method : 2.3126602172851562e-05 time for calcul the mask position with numpy : 0.005902290344238281 nb_pixel_total : 1526 time to create 1 rle with old method : 0.001744985580444336 time for calcul the mask position with numpy : 0.0060117244720458984 nb_pixel_total : 948 time to create 1 rle with old method : 0.0010159015655517578 time for calcul the mask position with numpy : 0.00592041015625 nb_pixel_total : 2725 time to create 1 rle with old method : 0.0029861927032470703 time for calcul the mask position with numpy : 0.005859375 nb_pixel_total : 979 time to create 1 rle with old method : 0.0010590553283691406 time for calcul the mask position with numpy : 0.006537199020385742 nb_pixel_total : 291 time to create 1 rle with old method : 0.00034046173095703125 time for calcul the mask position with numpy : 0.00623631477355957 nb_pixel_total : 299 time to create 1 rle with old method : 0.00036597251892089844 time for calcul the mask position with numpy : 0.005915403366088867 nb_pixel_total : 147 time to create 1 rle with old method : 0.00017070770263671875 time for calcul the mask position with numpy : 0.007084846496582031 nb_pixel_total : 747 time to create 1 rle with old method : 0.0008561611175537109 time for calcul the mask position with numpy : 0.005822181701660156 nb_pixel_total : 591 time to create 1 rle with old method : 0.0006368160247802734 time for calcul the mask position with numpy : 0.006114959716796875 nb_pixel_total : 34391 time to create 1 rle with old method : 0.036553144454956055 time for calcul the mask position with numpy : 0.00597691535949707 nb_pixel_total : 586 time to create 1 rle with old method : 0.0006310939788818359 time for calcul the mask position with numpy : 0.005830049514770508 nb_pixel_total : 2255 time to create 1 rle with old method : 0.0023889541625976562 time for calcul the mask position with numpy : 0.0057582855224609375 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005173683166503906 time for calcul the mask position with numpy : 0.0063707828521728516 nb_pixel_total : 4720 time to create 1 rle with old method : 0.00581669807434082 time for calcul the mask position with numpy : 0.006283760070800781 nb_pixel_total : 101 time to create 1 rle with old method : 0.00012063980102539062 time for calcul the mask position with numpy : 0.006199836730957031 nb_pixel_total : 958 time to create 1 rle with old method : 0.0011081695556640625 time for calcul the mask position with numpy : 0.006223201751708984 nb_pixel_total : 80 time to create 1 rle with old method : 0.00011277198791503906 time for calcul the mask position with numpy : 0.005897045135498047 nb_pixel_total : 38 time to create 1 rle with old method : 6.699562072753906e-05 time for calcul the mask position with numpy : 0.005896806716918945 nb_pixel_total : 676 time to create 1 rle with old method : 0.0007228851318359375 time for calcul the mask position with numpy : 0.006037712097167969 nb_pixel_total : 1293 time to create 1 rle with old method : 0.0013585090637207031 time for calcul the mask position with numpy : 0.006872415542602539 nb_pixel_total : 1511 time to create 1 rle with old method : 0.0021102428436279297 time for calcul the mask position with numpy : 0.006422996520996094 nb_pixel_total : 167 time to create 1 rle with old method : 0.00020694732666015625 time for calcul the mask position with numpy : 0.006265401840209961 nb_pixel_total : 61 time to create 1 rle with old method : 8.511543273925781e-05 time for calcul the mask position with numpy : 0.00595855712890625 nb_pixel_total : 130 time to create 1 rle with old method : 0.00016951560974121094 time for calcul the mask position with numpy : 0.006136178970336914 nb_pixel_total : 403 time to create 1 rle with old method : 0.0004296302795410156 time for calcul the mask position with numpy : 0.00599360466003418 nb_pixel_total : 176 time to create 1 rle with old method : 0.00022149085998535156 time for calcul the mask position with numpy : 0.006081581115722656 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003490447998046875 time for calcul the mask position with numpy : 0.006590604782104492 nb_pixel_total : 220 time to create 1 rle with old method : 0.0002582073211669922 time for calcul the mask position with numpy : 0.00642085075378418 nb_pixel_total : 51 time to create 1 rle with old method : 8.7738037109375e-05 time for calcul the mask position with numpy : 0.006232738494873047 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005905628204345703 time for calcul the mask position with numpy : 0.0060558319091796875 nb_pixel_total : 171 time to create 1 rle with old method : 0.00021409988403320312 time for calcul the mask position with numpy : 0.006017446517944336 nb_pixel_total : 829 time to create 1 rle with old method : 0.0009658336639404297 time for calcul the mask position with numpy : 0.0060498714447021484 nb_pixel_total : 15 time to create 1 rle with old method : 3.528594970703125e-05 time for calcul the mask position with numpy : 0.005969524383544922 nb_pixel_total : 3371 time to create 1 rle with old method : 0.0036101341247558594 time for calcul the mask position with numpy : 0.0061876773834228516 nb_pixel_total : 543 time to create 1 rle with old method : 0.0006225109100341797 time for calcul the mask position with numpy : 0.00596928596496582 nb_pixel_total : 153 time to create 1 rle with old method : 0.00017976760864257812 time for calcul the mask position with numpy : 0.005975961685180664 nb_pixel_total : 934 time to create 1 rle with old method : 0.0009717941284179688 time for calcul the mask position with numpy : 0.0062525272369384766 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002429485321044922 time for calcul the mask position with numpy : 0.005887508392333984 nb_pixel_total : 585 time to create 1 rle with old method : 0.0006268024444580078 time for calcul the mask position with numpy : 0.0061681270599365234 nb_pixel_total : 547 time to create 1 rle with old method : 0.0006310939788818359 time for calcul the mask position with numpy : 0.008043766021728516 nb_pixel_total : 90 time to create 1 rle with old method : 0.00011110305786132812 create new chi : 2.402393102645874 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 : 0.0016319751739501953 batch 1 Loaded 125 chid ids of type : 4230 Number RLEs to save : 11121 TO DO : save crop sub photo not yet done ! save time : 0.6699035167694092 nb_obj : 123 nb_hashtags : 6 time to prepare the origin masks : 1.4913322925567627 time for calcul the mask position with numpy : 0.02447342872619629 nb_pixel_total : 1814835 time to create 1 rle with new method : 0.06619930267333984 time for calcul the mask position with numpy : 0.009697675704956055 nb_pixel_total : 486 time to create 1 rle with old method : 0.0005502700805664062 time for calcul the mask position with numpy : 0.005615234375 nb_pixel_total : 36 time to create 1 rle with old method : 8.606910705566406e-05 time for calcul the mask position with numpy : 0.005886077880859375 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001914501190185547 time for calcul the mask position with numpy : 0.005624532699584961 nb_pixel_total : 56 time to create 1 rle with old method : 8.96453857421875e-05 time for calcul the mask position with numpy : 0.009444475173950195 nb_pixel_total : 708 time to create 1 rle with old method : 0.0007989406585693359 time for calcul the mask position with numpy : 0.009467601776123047 nb_pixel_total : 894 time to create 1 rle with old method : 0.0009477138519287109 time for calcul the mask position with numpy : 0.009645223617553711 nb_pixel_total : 863 time to create 1 rle with old method : 0.0008969306945800781 time for calcul the mask position with numpy : 0.014401435852050781 nb_pixel_total : 59 time to create 1 rle with old method : 9.584426879882812e-05 time for calcul the mask position with numpy : 0.009588956832885742 nb_pixel_total : 34 time to create 1 rle with old method : 9.036064147949219e-05 time for calcul the mask position with numpy : 0.009282112121582031 nb_pixel_total : 38 time to create 1 rle with old method : 6.198883056640625e-05 time for calcul the mask position with numpy : 0.009590864181518555 nb_pixel_total : 2268 time to create 1 rle with old method : 0.002412080764770508 time for calcul the mask position with numpy : 0.009370565414428711 nb_pixel_total : 101 time to create 1 rle with old method : 0.00017595291137695312 time for calcul the mask position with numpy : 0.00904083251953125 nb_pixel_total : 30 time to create 1 rle with old method : 4.839897155761719e-05 time for calcul the mask position with numpy : 0.007684230804443359 nb_pixel_total : 71 time to create 1 rle with old method : 9.918212890625e-05 time for calcul the mask position with numpy : 0.005442380905151367 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002205371856689453 time for calcul the mask position with numpy : 0.008392810821533203 nb_pixel_total : 85 time to create 1 rle with old method : 0.00010800361633300781 time for calcul the mask position with numpy : 0.009244441986083984 nb_pixel_total : 365 time to create 1 rle with old method : 0.00039267539978027344 time for calcul the mask position with numpy : 0.00917816162109375 nb_pixel_total : 2729 time to create 1 rle with old method : 0.0028047561645507812 time for calcul the mask position with numpy : 0.009299993515014648 nb_pixel_total : 537 time to create 1 rle with old method : 0.0006048679351806641 time for calcul the mask position with numpy : 0.009276866912841797 nb_pixel_total : 2640 time to create 1 rle with old method : 0.0026793479919433594 time for calcul the mask position with numpy : 0.009400606155395508 nb_pixel_total : 949 time to create 1 rle with old method : 0.0011997222900390625 time for calcul the mask position with numpy : 0.00942683219909668 nb_pixel_total : 4586 time to create 1 rle with old method : 0.004673004150390625 time for calcul the mask position with numpy : 0.00580143928527832 nb_pixel_total : 1491 time to create 1 rle with old method : 0.0017116069793701172 time for calcul the mask position with numpy : 0.005931854248046875 nb_pixel_total : 1643 time to create 1 rle with old method : 0.0019230842590332031 time for calcul the mask position with numpy : 0.005980968475341797 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003466606140136719 time for calcul the mask position with numpy : 0.006018638610839844 nb_pixel_total : 548 time to create 1 rle with old method : 0.0006656646728515625 time for calcul the mask position with numpy : 0.007531404495239258 nb_pixel_total : 150547 time to create 1 rle with new method : 0.5456178188323975 time for calcul the mask position with numpy : 0.009741544723510742 nb_pixel_total : 942 time to create 1 rle with old method : 0.0011508464813232422 time for calcul the mask position with numpy : 0.009759664535522461 nb_pixel_total : 702 time to create 1 rle with old method : 0.0007696151733398438 time for calcul the mask position with numpy : 0.00968623161315918 nb_pixel_total : 665 time to create 1 rle with old method : 0.0006844997406005859 time for calcul the mask position with numpy : 0.009610891342163086 nb_pixel_total : 1232 time to create 1 rle with old method : 0.0016646385192871094 time for calcul the mask position with numpy : 0.009743928909301758 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002288818359375 time for calcul the mask position with numpy : 0.009896039962768555 nb_pixel_total : 932 time to create 1 rle with old method : 0.001071929931640625 time for calcul the mask position with numpy : 0.009159088134765625 nb_pixel_total : 12031 time to create 1 rle with old method : 0.013747215270996094 time for calcul the mask position with numpy : 0.006014108657836914 nb_pixel_total : 339 time to create 1 rle with old method : 0.0003972053527832031 time for calcul the mask position with numpy : 0.005914211273193359 nb_pixel_total : 539 time to create 1 rle with old method : 0.0006623268127441406 time for calcul the mask position with numpy : 0.0061566829681396484 nb_pixel_total : 2091 time to create 1 rle with old method : 0.002457141876220703 time for calcul the mask position with numpy : 0.006071567535400391 nb_pixel_total : 422 time to create 1 rle with old method : 0.0005018711090087891 time for calcul the mask position with numpy : 0.006074666976928711 nb_pixel_total : 3601 time to create 1 rle with old method : 0.004033327102661133 time for calcul the mask position with numpy : 0.005995273590087891 nb_pixel_total : 328 time to create 1 rle with old method : 0.0003876686096191406 time for calcul the mask position with numpy : 0.00592803955078125 nb_pixel_total : 395 time to create 1 rle with old method : 0.000469207763671875 time for calcul the mask position with numpy : 0.006407022476196289 nb_pixel_total : 272 time to create 1 rle with old method : 0.00034737586975097656 time for calcul the mask position with numpy : 0.005959749221801758 nb_pixel_total : 836 time to create 1 rle with old method : 0.00098419189453125 time for calcul the mask position with numpy : 0.006215095520019531 nb_pixel_total : 38 time to create 1 rle with old method : 9.34600830078125e-05 time for calcul the mask position with numpy : 0.00595855712890625 nb_pixel_total : 510 time to create 1 rle with old method : 0.0006175041198730469 time for calcul the mask position with numpy : 0.0061452388763427734 nb_pixel_total : 1537 time to create 1 rle with old method : 0.0016677379608154297 time for calcul the mask position with numpy : 0.005995512008666992 nb_pixel_total : 349 time to create 1 rle with old method : 0.00045180320739746094 time for calcul the mask position with numpy : 0.00600433349609375 nb_pixel_total : 2379 time to create 1 rle with old method : 0.0027022361755371094 time for calcul the mask position with numpy : 0.006153583526611328 nb_pixel_total : 1003 time to create 1 rle with old method : 0.001146078109741211 time for calcul the mask position with numpy : 0.006045341491699219 nb_pixel_total : 878 time to create 1 rle with old method : 0.0010237693786621094 time for calcul the mask position with numpy : 0.0060863494873046875 nb_pixel_total : 5 time to create 1 rle with old method : 6.031990051269531e-05 time for calcul the mask position with numpy : 0.006056547164916992 nb_pixel_total : 1464 time to create 1 rle with old method : 0.0016655921936035156 time for calcul the mask position with numpy : 0.0059888362884521484 nb_pixel_total : 1025 time to create 1 rle with old method : 0.001176595687866211 time for calcul the mask position with numpy : 0.0060422420501708984 nb_pixel_total : 317 time to create 1 rle with old method : 0.0003712177276611328 time for calcul the mask position with numpy : 0.005961179733276367 nb_pixel_total : 572 time to create 1 rle with old method : 0.0006830692291259766 time for calcul the mask position with numpy : 0.005973100662231445 nb_pixel_total : 446 time to create 1 rle with old method : 0.0005457401275634766 time for calcul the mask position with numpy : 0.006079435348510742 nb_pixel_total : 605 time to create 1 rle with old method : 0.0007028579711914062 time for calcul the mask position with numpy : 0.00601959228515625 nb_pixel_total : 1833 time to create 1 rle with old method : 0.0020639896392822266 time for calcul the mask position with numpy : 0.0060007572174072266 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002570152282714844 time for calcul the mask position with numpy : 0.0063533782958984375 nb_pixel_total : 426 time to create 1 rle with old method : 0.0004947185516357422 time for calcul the mask position with numpy : 0.006066322326660156 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005397796630859375 time for calcul the mask position with numpy : 0.0060312747955322266 nb_pixel_total : 265 time to create 1 rle with old method : 0.00033354759216308594 time for calcul the mask position with numpy : 0.006040334701538086 nb_pixel_total : 133 time to create 1 rle with old method : 0.00017714500427246094 time for calcul the mask position with numpy : 0.005898952484130859 nb_pixel_total : 113 time to create 1 rle with old method : 0.00013256072998046875 time for calcul the mask position with numpy : 0.0060427188873291016 nb_pixel_total : 225 time to create 1 rle with old method : 0.00028967857360839844 time for calcul the mask position with numpy : 0.006046295166015625 nb_pixel_total : 159 time to create 1 rle with old method : 0.00020766258239746094 time for calcul the mask position with numpy : 0.006049156188964844 nb_pixel_total : 279 time to create 1 rle with old method : 0.00035262107849121094 time for calcul the mask position with numpy : 0.0058994293212890625 nb_pixel_total : 2116 time to create 1 rle with old method : 0.0023839473724365234 time for calcul the mask position with numpy : 0.0061588287353515625 nb_pixel_total : 229 time to create 1 rle with old method : 0.0002682209014892578 time for calcul the mask position with numpy : 0.006177663803100586 nb_pixel_total : 1591 time to create 1 rle with old method : 0.0018298625946044922 time for calcul the mask position with numpy : 0.010773897171020508 nb_pixel_total : 412 time to create 1 rle with old method : 0.00048351287841796875 time for calcul the mask position with numpy : 0.00612330436706543 nb_pixel_total : 1011 time to create 1 rle with old method : 0.0011708736419677734 time for calcul the mask position with numpy : 0.006145954132080078 nb_pixel_total : 11 time to create 1 rle with old method : 3.695487976074219e-05 time for calcul the mask position with numpy : 0.00610661506652832 nb_pixel_total : 9387 time to create 1 rle with old method : 0.010383129119873047 time for calcul the mask position with numpy : 0.005945682525634766 nb_pixel_total : 301 time to create 1 rle with old method : 0.00035881996154785156 time for calcul the mask position with numpy : 0.0061342716217041016 nb_pixel_total : 135 time to create 1 rle with old method : 0.00017333030700683594 time for calcul the mask position with numpy : 0.005985260009765625 nb_pixel_total : 144 time to create 1 rle with old method : 0.0001895427703857422 time for calcul the mask position with numpy : 0.006148576736450195 nb_pixel_total : 275 time to create 1 rle with old method : 0.00033736228942871094 time for calcul the mask position with numpy : 0.005973100662231445 nb_pixel_total : 256 time to create 1 rle with old method : 0.00031185150146484375 time for calcul the mask position with numpy : 0.006086111068725586 nb_pixel_total : 1280 time to create 1 rle with old method : 0.0015635490417480469 time for calcul the mask position with numpy : 0.006279706954956055 nb_pixel_total : 77 time to create 1 rle with old method : 0.00011086463928222656 time for calcul the mask position with numpy : 0.006037473678588867 nb_pixel_total : 551 time to create 1 rle with old method : 0.0005815029144287109 time for calcul the mask position with numpy : 0.005925655364990234 nb_pixel_total : 562 time to create 1 rle with old method : 0.0006501674652099609 time for calcul the mask position with numpy : 0.005899906158447266 nb_pixel_total : 913 time to create 1 rle with old method : 0.0010519027709960938 time for calcul the mask position with numpy : 0.0059659481048583984 nb_pixel_total : 16 time to create 1 rle with old method : 6.0558319091796875e-05 time for calcul the mask position with numpy : 0.006044626235961914 nb_pixel_total : 2729 time to create 1 rle with old method : 0.0028400421142578125 time for calcul the mask position with numpy : 0.005997896194458008 nb_pixel_total : 68 time to create 1 rle with old method : 0.00010776519775390625 time for calcul the mask position with numpy : 0.005812406539916992 nb_pixel_total : 983 time to create 1 rle with old method : 0.0011303424835205078 time for calcul the mask position with numpy : 0.00603795051574707 nb_pixel_total : 291 time to create 1 rle with old method : 0.00035691261291503906 time for calcul the mask position with numpy : 0.0058803558349609375 nb_pixel_total : 363 time to create 1 rle with old method : 0.0004687309265136719 time for calcul the mask position with numpy : 0.005999565124511719 nb_pixel_total : 140 time to create 1 rle with old method : 0.00018286705017089844 time for calcul the mask position with numpy : 0.006095170974731445 nb_pixel_total : 497 time to create 1 rle with old method : 0.0005888938903808594 time for calcul the mask position with numpy : 0.0060882568359375 nb_pixel_total : 83 time to create 1 rle with old method : 0.00012254714965820312 time for calcul the mask position with numpy : 0.006046772003173828 nb_pixel_total : 1362 time to create 1 rle with old method : 0.0015690326690673828 time for calcul the mask position with numpy : 0.006028413772583008 nb_pixel_total : 535 time to create 1 rle with old method : 0.0006272792816162109 time for calcul the mask position with numpy : 0.006100893020629883 nb_pixel_total : 448 time to create 1 rle with old method : 0.0005321502685546875 time for calcul the mask position with numpy : 0.006003141403198242 nb_pixel_total : 2166 time to create 1 rle with old method : 0.00235748291015625 time for calcul the mask position with numpy : 0.0064144134521484375 nb_pixel_total : 4964 time to create 1 rle with old method : 0.005176544189453125 time for calcul the mask position with numpy : 0.005906105041503906 nb_pixel_total : 105 time to create 1 rle with old method : 0.00014734268188476562 time for calcul the mask position with numpy : 0.005751609802246094 nb_pixel_total : 22 time to create 1 rle with old method : 5.1975250244140625e-05 time for calcul the mask position with numpy : 0.005709648132324219 nb_pixel_total : 228 time to create 1 rle with old method : 0.00026726722717285156 time for calcul the mask position with numpy : 0.005839347839355469 nb_pixel_total : 125 time to create 1 rle with old method : 0.00016570091247558594 time for calcul the mask position with numpy : 0.006295204162597656 nb_pixel_total : 503 time to create 1 rle with old method : 0.0005965232849121094 time for calcul the mask position with numpy : 0.0058536529541015625 nb_pixel_total : 670 time to create 1 rle with old method : 0.00078582763671875 time for calcul the mask position with numpy : 0.006131649017333984 nb_pixel_total : 1334 time to create 1 rle with old method : 0.0015411376953125 time for calcul the mask position with numpy : 0.0059299468994140625 nb_pixel_total : 2547 time to create 1 rle with old method : 0.002742767333984375 time for calcul the mask position with numpy : 0.006041288375854492 nb_pixel_total : 37 time to create 1 rle with old method : 6.699562072753906e-05 time for calcul the mask position with numpy : 0.005782604217529297 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002243518829345703 time for calcul the mask position with numpy : 0.005903720855712891 nb_pixel_total : 187 time to create 1 rle with old method : 0.00023603439331054688 time for calcul the mask position with numpy : 0.0059697628021240234 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005033016204833984 time for calcul the mask position with numpy : 0.005731821060180664 nb_pixel_total : 48 time to create 1 rle with old method : 7.605552673339844e-05 time for calcul the mask position with numpy : 0.005806922912597656 nb_pixel_total : 120 time to create 1 rle with old method : 0.00021004676818847656 time for calcul the mask position with numpy : 0.005923748016357422 nb_pixel_total : 331 time to create 1 rle with old method : 0.0003914833068847656 time for calcul the mask position with numpy : 0.005911350250244141 nb_pixel_total : 191 time to create 1 rle with old method : 0.00023698806762695312 time for calcul the mask position with numpy : 0.005814313888549805 nb_pixel_total : 267 time to create 1 rle with old method : 0.0002942085266113281 time for calcul the mask position with numpy : 0.005959987640380859 nb_pixel_total : 228 time to create 1 rle with old method : 0.0002677440643310547 time for calcul the mask position with numpy : 0.0057086944580078125 nb_pixel_total : 829 time to create 1 rle with old method : 0.0008788108825683594 time for calcul the mask position with numpy : 0.005650758743286133 nb_pixel_total : 15 time to create 1 rle with old method : 3.361701965332031e-05 time for calcul the mask position with numpy : 0.009519338607788086 nb_pixel_total : 625 time to create 1 rle with old method : 0.0006892681121826172 time for calcul the mask position with numpy : 0.005777120590209961 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002257823944091797 time for calcul the mask position with numpy : 0.005948781967163086 nb_pixel_total : 582 time to create 1 rle with old method : 0.0007526874542236328 time for calcul the mask position with numpy : 0.0058116912841796875 nb_pixel_total : 1455 time to create 1 rle with old method : 0.0015702247619628906 time for calcul the mask position with numpy : 0.005859375 nb_pixel_total : 578 time to create 1 rle with old method : 0.0006201267242431641 create new chi : 1.605588674545288 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 : 0.0017209053039550781 batch 1 Loaded 124 chid ids of type : 4230 Number RLEs to save : 10865 TO DO : save crop sub photo not yet done ! save time : 3.834784746170044 nb_obj : 117 nb_hashtags : 6 time to prepare the origin masks : 2.094395637512207 time for calcul the mask position with numpy : 0.03787112236022949 nb_pixel_total : 1667268 time to create 1 rle with new method : 0.10246419906616211 time for calcul the mask position with numpy : 0.010668039321899414 nb_pixel_total : 1370 time to create 1 rle with old method : 0.0014777183532714844 time for calcul the mask position with numpy : 0.006697654724121094 nb_pixel_total : 75918 time to create 1 rle with old method : 0.08135628700256348 time for calcul the mask position with numpy : 0.009725332260131836 nb_pixel_total : 942 time to create 1 rle with old method : 0.0009982585906982422 time for calcul the mask position with numpy : 0.00971674919128418 nb_pixel_total : 42 time to create 1 rle with old method : 0.00010132789611816406 time for calcul the mask position with numpy : 0.00576472282409668 nb_pixel_total : 64 time to create 1 rle with old method : 9.059906005859375e-05 time for calcul the mask position with numpy : 0.005759239196777344 nb_pixel_total : 74 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.005726814270019531 nb_pixel_total : 697 time to create 1 rle with old method : 0.0007529258728027344 time for calcul the mask position with numpy : 0.0057947635650634766 nb_pixel_total : 772 time to create 1 rle with old method : 0.0008609294891357422 time for calcul the mask position with numpy : 0.008696556091308594 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005125999450683594 time for calcul the mask position with numpy : 0.009683370590209961 nb_pixel_total : 63 time to create 1 rle with old method : 0.00010395050048828125 time for calcul the mask position with numpy : 0.009479999542236328 nb_pixel_total : 31 time to create 1 rle with old method : 8.392333984375e-05 time for calcul the mask position with numpy : 0.00963139533996582 nb_pixel_total : 797 time to create 1 rle with old method : 0.0009458065032958984 time for calcul the mask position with numpy : 0.005687236785888672 nb_pixel_total : 20 time to create 1 rle with old method : 4.8160552978515625e-05 time for calcul the mask position with numpy : 0.005699872970581055 nb_pixel_total : 363 time to create 1 rle with old method : 0.00044417381286621094 time for calcul the mask position with numpy : 0.005663871765136719 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002384185791015625 time for calcul the mask position with numpy : 0.0056896209716796875 nb_pixel_total : 357 time to create 1 rle with old method : 0.0004291534423828125 time for calcul the mask position with numpy : 0.005834341049194336 nb_pixel_total : 2347 time to create 1 rle with old method : 0.0026047229766845703 time for calcul the mask position with numpy : 0.00953984260559082 nb_pixel_total : 535 time to create 1 rle with old method : 0.0006084442138671875 time for calcul the mask position with numpy : 0.009726524353027344 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001518726348876953 time for calcul the mask position with numpy : 0.010051488876342773 nb_pixel_total : 156 time to create 1 rle with old method : 0.00020503997802734375 time for calcul the mask position with numpy : 0.009369611740112305 nb_pixel_total : 1895 time to create 1 rle with old method : 0.0020058155059814453 time for calcul the mask position with numpy : 0.007791280746459961 nb_pixel_total : 178 time to create 1 rle with old method : 0.00021648406982421875 time for calcul the mask position with numpy : 0.0055692195892333984 nb_pixel_total : 503 time to create 1 rle with old method : 0.0005586147308349609 time for calcul the mask position with numpy : 0.010702848434448242 nb_pixel_total : 152712 time to create 1 rle with new method : 0.027894020080566406 time for calcul the mask position with numpy : 0.010218143463134766 nb_pixel_total : 703 time to create 1 rle with old method : 0.0008001327514648438 time for calcul the mask position with numpy : 0.010205507278442383 nb_pixel_total : 1001 time to create 1 rle with old method : 0.0012340545654296875 time for calcul the mask position with numpy : 0.011612415313720703 nb_pixel_total : 76 time to create 1 rle with old method : 0.00011324882507324219 time for calcul the mask position with numpy : 0.010319709777832031 nb_pixel_total : 1151 time to create 1 rle with old method : 0.0012683868408203125 time for calcul the mask position with numpy : 0.010486841201782227 nb_pixel_total : 911 time to create 1 rle with old method : 0.0010230541229248047 time for calcul the mask position with numpy : 0.010176420211791992 nb_pixel_total : 337 time to create 1 rle with old method : 0.00039315223693847656 time for calcul the mask position with numpy : 0.010350704193115234 nb_pixel_total : 196 time to create 1 rle with old method : 0.00024056434631347656 time for calcul the mask position with numpy : 0.010003805160522461 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005762577056884766 time for calcul the mask position with numpy : 0.009913444519042969 nb_pixel_total : 3241 time to create 1 rle with old method : 0.003535032272338867 time for calcul the mask position with numpy : 0.010102272033691406 nb_pixel_total : 291 time to create 1 rle with old method : 0.00047898292541503906 time for calcul the mask position with numpy : 0.00586247444152832 nb_pixel_total : 1556 time to create 1 rle with old method : 0.0017888545989990234 time for calcul the mask position with numpy : 0.005892753601074219 nb_pixel_total : 365 time to create 1 rle with old method : 0.0003981590270996094 time for calcul the mask position with numpy : 0.005944252014160156 nb_pixel_total : 700 time to create 1 rle with old method : 0.00083160400390625 time for calcul the mask position with numpy : 0.00598597526550293 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004124641418457031 time for calcul the mask position with numpy : 0.005961418151855469 nb_pixel_total : 344 time to create 1 rle with old method : 0.0004999637603759766 time for calcul the mask position with numpy : 0.006026029586791992 nb_pixel_total : 2383 time to create 1 rle with old method : 0.0027551651000976562 time for calcul the mask position with numpy : 0.005815982818603516 nb_pixel_total : 661 time to create 1 rle with old method : 0.0007340908050537109 time for calcul the mask position with numpy : 0.005789279937744141 nb_pixel_total : 804 time to create 1 rle with old method : 0.0009429454803466797 time for calcul the mask position with numpy : 0.005644559860229492 nb_pixel_total : 1423 time to create 1 rle with old method : 0.0015506744384765625 time for calcul the mask position with numpy : 0.005791425704956055 nb_pixel_total : 1084 time to create 1 rle with old method : 0.0012221336364746094 time for calcul the mask position with numpy : 0.006075143814086914 nb_pixel_total : 821 time to create 1 rle with old method : 0.000965118408203125 time for calcul the mask position with numpy : 0.005976438522338867 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003056526184082031 time for calcul the mask position with numpy : 0.00612950325012207 nb_pixel_total : 312 time to create 1 rle with old method : 0.0003566741943359375 time for calcul the mask position with numpy : 0.006186008453369141 nb_pixel_total : 1170 time to create 1 rle with old method : 0.00135040283203125 time for calcul the mask position with numpy : 0.006077289581298828 nb_pixel_total : 973 time to create 1 rle with old method : 0.0011734962463378906 time for calcul the mask position with numpy : 0.006201744079589844 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006079673767089844 time for calcul the mask position with numpy : 0.006212711334228516 nb_pixel_total : 311 time to create 1 rle with old method : 0.00038123130798339844 time for calcul the mask position with numpy : 0.0060842037200927734 nb_pixel_total : 1191 time to create 1 rle with old method : 0.0013744831085205078 time for calcul the mask position with numpy : 0.005965709686279297 nb_pixel_total : 364 time to create 1 rle with old method : 0.0004496574401855469 time for calcul the mask position with numpy : 0.0057947635650634766 nb_pixel_total : 609 time to create 1 rle with old method : 0.0006463527679443359 time for calcul the mask position with numpy : 0.00592803955078125 nb_pixel_total : 465 time to create 1 rle with old method : 0.0005326271057128906 time for calcul the mask position with numpy : 0.005739688873291016 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002353191375732422 time for calcul the mask position with numpy : 0.005684852600097656 nb_pixel_total : 433 time to create 1 rle with old method : 0.0004975795745849609 time for calcul the mask position with numpy : 0.005639076232910156 nb_pixel_total : 242 time to create 1 rle with old method : 0.00030231475830078125 time for calcul the mask position with numpy : 0.00644683837890625 nb_pixel_total : 106154 time to create 1 rle with old method : 0.11424040794372559 time for calcul the mask position with numpy : 0.006234884262084961 nb_pixel_total : 151 time to create 1 rle with old method : 0.00018167495727539062 time for calcul the mask position with numpy : 0.005861043930053711 nb_pixel_total : 271 time to create 1 rle with old method : 0.0003039836883544922 time for calcul the mask position with numpy : 0.0057277679443359375 nb_pixel_total : 6 time to create 1 rle with old method : 3.075599670410156e-05 time for calcul the mask position with numpy : 0.005611896514892578 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001380443572998047 time for calcul the mask position with numpy : 0.005658864974975586 nb_pixel_total : 186 time to create 1 rle with old method : 0.000217437744140625 time for calcul the mask position with numpy : 0.00597071647644043 nb_pixel_total : 1619 time to create 1 rle with old method : 0.0018663406372070312 time for calcul the mask position with numpy : 0.005894660949707031 nb_pixel_total : 1797 time to create 1 rle with old method : 0.0019257068634033203 time for calcul the mask position with numpy : 0.006048679351806641 nb_pixel_total : 196 time to create 1 rle with old method : 0.00024580955505371094 time for calcul the mask position with numpy : 0.005836009979248047 nb_pixel_total : 1078 time to create 1 rle with old method : 0.0011484622955322266 time for calcul the mask position with numpy : 0.005865812301635742 nb_pixel_total : 412 time to create 1 rle with old method : 0.0004520416259765625 time for calcul the mask position with numpy : 0.006102085113525391 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003330707550048828 time for calcul the mask position with numpy : 0.00594019889831543 nb_pixel_total : 25 time to create 1 rle with old method : 6.0558319091796875e-05 time for calcul the mask position with numpy : 0.005830049514770508 nb_pixel_total : 152 time to create 1 rle with old method : 0.00019741058349609375 time for calcul the mask position with numpy : 0.0059735774993896484 nb_pixel_total : 124 time to create 1 rle with old method : 0.00017499923706054688 time for calcul the mask position with numpy : 0.006091117858886719 nb_pixel_total : 345 time to create 1 rle with old method : 0.0003883838653564453 time for calcul the mask position with numpy : 0.006020307540893555 nb_pixel_total : 223 time to create 1 rle with old method : 0.00027632713317871094 time for calcul the mask position with numpy : 0.006089925765991211 nb_pixel_total : 508 time to create 1 rle with old method : 0.0005593299865722656 time for calcul the mask position with numpy : 0.0061511993408203125 nb_pixel_total : 891 time to create 1 rle with old method : 0.0010137557983398438 time for calcul the mask position with numpy : 0.0059223175048828125 nb_pixel_total : 246 time to create 1 rle with old method : 0.0002949237823486328 time for calcul the mask position with numpy : 0.0059413909912109375 nb_pixel_total : 1039 time to create 1 rle with old method : 0.001108407974243164 time for calcul the mask position with numpy : 0.005827426910400391 nb_pixel_total : 981 time to create 1 rle with old method : 0.0011234283447265625 time for calcul the mask position with numpy : 0.005853414535522461 nb_pixel_total : 215 time to create 1 rle with old method : 0.00026416778564453125 time for calcul the mask position with numpy : 0.0056858062744140625 nb_pixel_total : 453 time to create 1 rle with old method : 0.0005671977996826172 time for calcul the mask position with numpy : 0.0057086944580078125 nb_pixel_total : 1404 time to create 1 rle with old method : 0.001462697982788086 time for calcul the mask position with numpy : 0.005751132965087891 nb_pixel_total : 677 time to create 1 rle with old method : 0.0008058547973632812 time for calcul the mask position with numpy : 0.005759239196777344 nb_pixel_total : 541 time to create 1 rle with old method : 0.000614166259765625 time for calcul the mask position with numpy : 0.005728483200073242 nb_pixel_total : 260 time to create 1 rle with old method : 0.0003349781036376953 time for calcul the mask position with numpy : 0.005680561065673828 nb_pixel_total : 2919 time to create 1 rle with old method : 0.0031585693359375 time for calcul the mask position with numpy : 0.005884408950805664 nb_pixel_total : 426 time to create 1 rle with old method : 0.0004942417144775391 time for calcul the mask position with numpy : 0.005866050720214844 nb_pixel_total : 4616 time to create 1 rle with old method : 0.005129814147949219 time for calcul the mask position with numpy : 0.0058116912841796875 nb_pixel_total : 105 time to create 1 rle with old method : 0.00013566017150878906 time for calcul the mask position with numpy : 0.00580286979675293 nb_pixel_total : 18 time to create 1 rle with old method : 4.57763671875e-05 time for calcul the mask position with numpy : 0.005771636962890625 nb_pixel_total : 189 time to create 1 rle with old method : 0.0002410411834716797 time for calcul the mask position with numpy : 0.005763053894042969 nb_pixel_total : 695 time to create 1 rle with old method : 0.0008592605590820312 time for calcul the mask position with numpy : 0.006134748458862305 nb_pixel_total : 1230 time to create 1 rle with old method : 0.0012831687927246094 time for calcul the mask position with numpy : 0.0058994293212890625 nb_pixel_total : 1588 time to create 1 rle with old method : 0.0016977787017822266 time for calcul the mask position with numpy : 0.01031184196472168 nb_pixel_total : 52 time to create 1 rle with old method : 8.368492126464844e-05 time for calcul the mask position with numpy : 0.0057752132415771484 nb_pixel_total : 1162 time to create 1 rle with old method : 0.0012607574462890625 time for calcul the mask position with numpy : 0.005733489990234375 nb_pixel_total : 170 time to create 1 rle with old method : 0.00019979476928710938 time for calcul the mask position with numpy : 0.005804300308227539 nb_pixel_total : 50 time to create 1 rle with old method : 9.036064147949219e-05 time for calcul the mask position with numpy : 0.006241559982299805 nb_pixel_total : 433 time to create 1 rle with old method : 0.0004928112030029297 time for calcul the mask position with numpy : 0.006439208984375 nb_pixel_total : 374 time to create 1 rle with old method : 0.00043082237243652344 time for calcul the mask position with numpy : 0.0065004825592041016 nb_pixel_total : 25 time to create 1 rle with old method : 5.245208740234375e-05 time for calcul the mask position with numpy : 0.007739543914794922 nb_pixel_total : 237 time to create 1 rle with old method : 0.0004756450653076172 time for calcul the mask position with numpy : 0.007503986358642578 nb_pixel_total : 3 time to create 1 rle with old method : 2.5987625122070312e-05 time for calcul the mask position with numpy : 0.006379604339599609 nb_pixel_total : 277 time to create 1 rle with old method : 0.0003261566162109375 time for calcul the mask position with numpy : 0.006497383117675781 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005543231964111328 time for calcul the mask position with numpy : 0.006168842315673828 nb_pixel_total : 218 time to create 1 rle with old method : 0.00026988983154296875 time for calcul the mask position with numpy : 0.006397724151611328 nb_pixel_total : 161 time to create 1 rle with old method : 0.00020432472229003906 time for calcul the mask position with numpy : 0.0063228607177734375 nb_pixel_total : 821 time to create 1 rle with old method : 0.0009551048278808594 time for calcul the mask position with numpy : 0.006913900375366211 nb_pixel_total : 20 time to create 1 rle with old method : 4.57763671875e-05 time for calcul the mask position with numpy : 0.006439924240112305 nb_pixel_total : 325 time to create 1 rle with old method : 0.000408172607421875 time for calcul the mask position with numpy : 0.006267070770263672 nb_pixel_total : 615 time to create 1 rle with old method : 0.0007615089416503906 time for calcul the mask position with numpy : 0.006329774856567383 nb_pixel_total : 619 time to create 1 rle with old method : 0.0007278919219970703 time for calcul the mask position with numpy : 0.006227254867553711 nb_pixel_total : 591 time to create 1 rle with old method : 0.0006990432739257812 time for calcul the mask position with numpy : 0.005960702896118164 nb_pixel_total : 147 time to create 1 rle with old method : 0.00016927719116210938 time for calcul the mask position with numpy : 0.0060443878173828125 nb_pixel_total : 516 time to create 1 rle with old method : 0.0005805492401123047 time for calcul the mask position with numpy : 0.0060956478118896484 nb_pixel_total : 567 time to create 1 rle with old method : 0.0006375312805175781 create new chi : 1.2463877201080322 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 : 0.0015153884887695312 batch 1 Loaded 118 chid ids of type : 4230 Number RLEs to save : 10476 TO DO : save crop sub photo not yet done ! save time : 0.6000423431396484 map_output_result : {1339109752: (0.0, 'Should be the crop_list due to order', 0.0), 1339109751: (0.0, 'Should be the crop_list due to order', 0.0), 1339109750: (0.0, 'Should be the crop_list due to order', 0.0), 1339109657: (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 [1339109752, 1339109751, 1339109750, 1339109657] Looping around the photos to save general results len do output : 4 /1339109752.Didn't retrieve data . /1339109751.Didn't retrieve data . /1339109750.Didn't retrieve data . /1339109657.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, '2608224') ('4234', '20752076', '1339109752', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109751', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109750', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109657', None, None, None, None, None, '2608224') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.013122320175170898 save_final save missing photos in datou_result : time spend for datou_step_exec : 21.39901113510132 time spend to save output : 0.013489723205566406 total time spend for step 4 : 21.412500858306885 step5:crop_condition Sat Feb 22 18:21:31 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 4 ! batch 1 Loaded 492 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 195 About to insert : list_path_to_insert length 195 new photo from crops ! About to upload 195 photos upload in portfolio : 4869462 init cache_photo without model_param we have 195 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740244894_401524 we have uploaded 195 photos in the portfolio 4869462 time of upload the photos Elapsed time : 60.22270607948303 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 75 About to insert : list_path_to_insert length 75 new photo from crops ! About to upload 75 photos upload in portfolio : 4869462 init cache_photo without model_param we have 75 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740244955_401524 we have uploaded 75 photos in the portfolio 4869462 time of upload the photos Elapsed time : 22.497167587280273 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/1740244977_401524 we have uploaded 3 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9344766139984131 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/1740244979_401524 we have uploaded 14 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.670356035232544 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 53 About to insert : list_path_to_insert length 53 new photo from crops ! About to upload 53 photos upload in portfolio : 4869462 init cache_photo without model_param we have 53 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740244983_401524 we have uploaded 53 photos in the portfolio 4869462 time of upload the photos Elapsed time : 13.677010297775269 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 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/1740244997_401524 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.7420001029968262 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 [1339109752, 1339109751, 1339109750, 1339109657] Looping around the photos to save general results len do output : 341 /1339117042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117065Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117103Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117105Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117106Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117114Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117115Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117116Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117117Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117118Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117119Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117122Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117123Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117136Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117144Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117145Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117146Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117152Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117153Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117155Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117156Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117157Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117158Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117196Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117204Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117216Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117217Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117218Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117219Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117220Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117221Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117222Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117223Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117224Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117226Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117231Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117232Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117248Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117287Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117288Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117289Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117290Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117291Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117292Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117293Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117294Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117295Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117296Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117297Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117298Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117299Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117300Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117301Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117302Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117303Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117304Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117305Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117306Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117307Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117315Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117344Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117345Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117346Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117347Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117348Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117349Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117350Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117351Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117352Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117353Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117354Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117355Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117356Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117357Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117358Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117359Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117360Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117363Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117364Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117365Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117374Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117375Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117376Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117377Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117378Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117379Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117380Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117381Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117382Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117383Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117384Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117385Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117386Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117387Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117388Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117389Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117390Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117391Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1339117392Didn'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, '2608224') ('4234', '20752076', '1339109752', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109751', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109750', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109657', None, None, None, None, None, '2608224') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1027 time used for this insertion : 0.051343679428100586 save_final save missing photos in datou_result : time spend for datou_step_exec : 106.94102501869202 time spend to save output : 0.05916166305541992 total time spend for step 5 : 107.00018668174744 step6:thcl Sat Feb 22 18:23:18 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 : 0.017863035202026367 time to convert the images to numpy array : 0.0847635269165039 time to import caffe and check if the image exist : 0.022017240524291992 time to convert the images to numpy array : 0.0929558277130127 time to import caffe and check if the image exist : 0.03026604652404785 time to convert the images to numpy array : 0.09469223022460938 time to import caffe and check if the image exist : 0.039682626724243164 time to convert the images to numpy array : 0.0965569019317627 time to import caffe and check if the image exist : 0.026888132095336914 time to convert the images to numpy array : 0.10942649841308594 time to import caffe and check if the image exist : 0.030216217041015625 time to convert the images to numpy array : 0.10834050178527832 time to import caffe and check if the image exist : 0.03567957878112793 time to convert the images to numpy array : 0.10577774047851562 time to import caffe and check if the image exist : 0.0437006950378418 time to convert the images to numpy array : 0.10208868980407715 time to import caffe and check if the image exist : 0.030789613723754883 time to convert the images to numpy array : 0.11486268043518066 time to import caffe and check if the image exist : 0.04712104797363281 time to convert the images to numpy array : 0.09912967681884766 total time to convert the images to numpy array : 0.6130244731903076 list photo_ids error: [] list photo_ids correct : [1339117042, 1339117043, 1339117044, 1339117045, 1339117046, 1339117047, 1339117048, 1339117049, 1339117050, 1339117051, 1339117052, 1339117053, 1339117054, 1339117055, 1339117056, 1339117057, 1339117058, 1339117059, 1339117060, 1339117061, 1339117062, 1339117063, 1339117064, 1339117065, 1339117066, 1339117067, 1339117068, 1339117069, 1339117070, 1339117071, 1339117072, 1339117073, 1339117074, 1339117075, 1339117076, 1339117367, 1339117368, 1339117369, 1339117370, 1339117371, 1339117372, 1339117373, 1339117374, 1339117375, 1339117376, 1339117377, 1339117378, 1339117379, 1339117380, 1339117381, 1339117382, 1339117383, 1339117384, 1339117385, 1339117386, 1339117387, 1339117388, 1339117389, 1339117390, 1339117391, 1339117392, 1339117261, 1339117262, 1339117263, 1339117264, 1339117265, 1339117266, 1339117267, 1339117268, 1339117269, 1339117270, 1339117271, 1339117272, 1339117273, 1339117274, 1339117275, 1339117276, 1339117277, 1339117278, 1339117279, 1339117280, 1339117281, 1339117282, 1339117283, 1339117284, 1339117285, 1339117286, 1339117287, 1339117288, 1339117289, 1339117290, 1339117291, 1339117292, 1339117293, 1339117294, 1339117295, 1339117183, 1339117184, 1339117185, 1339117186, 1339117187, 1339117188, 1339117189, 1339117190, 1339117191, 1339117192, 1339117193, 1339117194, 1339117195, 1339117196, 1339117197, 1339117198, 1339117199, 1339117200, 1339117201, 1339117202, 1339117203, 1339117204, 1339117205, 1339117206, 1339117207, 1339117208, 1339117209, 1339117210, 1339117211, 1339117212, 1339117213, 1339117214, 1339117215, 1339117216, 1339117217, 1339117218, 1339117219, 1339117220, 1339117221, 1339117222, 1339117223, 1339117224, 1339117225, 1339117226, 1339117227, 1339117228, 1339117229, 1339117230, 1339117231, 1339117232, 1339117233, 1339117234, 1339117236, 1339117237, 1339117238, 1339117246, 1339117247, 1339117248, 1339117249, 1339117250, 1339117251, 1339117252, 1339117253, 1339117254, 1339117255, 1339117256, 1339117257, 1339117258, 1339117259, 1339117260, 1339117077, 1339117078, 1339117079, 1339117080, 1339117081, 1339117082, 1339117083, 1339117084, 1339117085, 1339117086, 1339117087, 1339117088, 1339117089, 1339117090, 1339117091, 1339117092, 1339117093, 1339117094, 1339117095, 1339117096, 1339117097, 1339117098, 1339117099, 1339117100, 1339117101, 1339117102, 1339117103, 1339117105, 1339117106, 1339117107, 1339117108, 1339117109, 1339117110, 1339117111, 1339117112, 1339117148, 1339117149, 1339117150, 1339117151, 1339117152, 1339117153, 1339117154, 1339117155, 1339117156, 1339117157, 1339117158, 1339117159, 1339117160, 1339117161, 1339117162, 1339117163, 1339117164, 1339117165, 1339117166, 1339117167, 1339117168, 1339117169, 1339117170, 1339117171, 1339117172, 1339117173, 1339117174, 1339117175, 1339117176, 1339117177, 1339117178, 1339117179, 1339117180, 1339117181, 1339117182, 1339117113, 1339117114, 1339117115, 1339117116, 1339117117, 1339117118, 1339117119, 1339117120, 1339117121, 1339117122, 1339117123, 1339117124, 1339117125, 1339117126, 1339117127, 1339117128, 1339117129, 1339117130, 1339117131, 1339117132, 1339117133, 1339117134, 1339117135, 1339117136, 1339117137, 1339117138, 1339117139, 1339117140, 1339117141, 1339117142, 1339117143, 1339117144, 1339117145, 1339117146, 1339117147, 1339117332, 1339117333, 1339117334, 1339117335, 1339117336, 1339117337, 1339117338, 1339117339, 1339117340, 1339117341, 1339117342, 1339117343, 1339117344, 1339117345, 1339117346, 1339117347, 1339117348, 1339117349, 1339117350, 1339117351, 1339117352, 1339117353, 1339117354, 1339117355, 1339117356, 1339117357, 1339117358, 1339117359, 1339117360, 1339117361, 1339117362, 1339117363, 1339117364, 1339117365, 1339117366, 1339117296, 1339117297, 1339117298, 1339117299, 1339117300, 1339117301, 1339117302, 1339117303, 1339117304, 1339117305, 1339117306, 1339117307, 1339117308, 1339117310, 1339117311, 1339117312, 1339117313, 1339117314, 1339117315, 1339117316, 1339117317, 1339117318, 1339117319, 1339117320, 1339117321, 1339117322, 1339117323, 1339117324, 1339117325, 1339117326, 1339117327, 1339117328, 1339117329, 1339117330, 1339117331] number of photos to traite : 341 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 : 3175 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 : 2956 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 1.440666675567627 time used to do the prediction : 1.267888069152832 save descriptor for thcl : 3237 time to traite the descriptors : 2.0658557415008545 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1339117042 To insert : 1339117043 To insert : 1339117044 To insert : 1339117045 To insert : 1339117046 To insert : 1339117047 To insert : 1339117048 To insert : 1339117049 To insert : 1339117050 To insert : 1339117051 To insert : 1339117052 To insert : 1339117053 To insert : 1339117054 To insert : 1339117055 To insert : 1339117056 To insert : 1339117057 To insert : 1339117058 To insert : 1339117059 To insert : 1339117060 To insert : 1339117061 To insert : 1339117062 To insert : 1339117063 To insert : 1339117064 To insert : 1339117065 To insert : 1339117066 To insert : 1339117067 To insert : 1339117068 To insert : 1339117069 To insert : 1339117070 To insert : 1339117071 To insert : 1339117072 To insert : 1339117073 To insert : 1339117074 To insert : 1339117075 To insert : 1339117076 To insert : 1339117367 To insert : 1339117368 To insert : 1339117369 To insert : 1339117370 To insert : 1339117371 To insert : 1339117372 To insert : 1339117373 To insert : 1339117374 To insert : 1339117375 To insert : 1339117376 To insert : 1339117377 To insert : 1339117378 To insert : 1339117379 To insert : 1339117380 To insert : 1339117381 To insert : 1339117382 To insert : 1339117383 To insert : 1339117384 To insert : 1339117385 To insert : 1339117386 To insert : 1339117387 To insert : 1339117388 To insert : 1339117389 To insert : 1339117390 To insert : 1339117391 To insert : 1339117392 To insert : 1339117261 To insert : 1339117262 To insert : 1339117263 To insert : 1339117264 To insert : 1339117265 To insert : 1339117266 To insert : 1339117267 To insert : 1339117268 To insert : 1339117269 To insert : 1339117270 To insert : 1339117271 To insert : 1339117272 To insert : 1339117273 To insert : 1339117274 To insert : 1339117275 To insert : 1339117276 To insert : 1339117277 To insert : 1339117278 To insert : 1339117279 To insert : 1339117280 To insert : 1339117281 To insert : 1339117282 To insert : 1339117283 To insert : 1339117284 To insert : 1339117285 To insert : 1339117286 To insert : 1339117287 To insert : 1339117288 To insert : 1339117289 To insert : 1339117290 To insert : 1339117291 To insert : 1339117292 To insert : 1339117293 To insert : 1339117294 To insert : 1339117295 To insert : 1339117183 To insert : 1339117184 To insert : 1339117185 To insert : 1339117186 To insert : 1339117187 To insert : 1339117188 To insert : 1339117189 To insert : 1339117190 To insert : 1339117191 To insert : 1339117192 To insert : 1339117193 To insert : 1339117194 To insert : 1339117195 To insert : 1339117196 To insert : 1339117197 To insert : 1339117198 To insert : 1339117199 To insert : 1339117200 To insert : 1339117201 To insert : 1339117202 To insert : 1339117203 To insert : 1339117204 To insert : 1339117205 To insert : 1339117206 To insert : 1339117207 To insert : 1339117208 To insert : 1339117209 To insert : 1339117210 To insert : 1339117211 To insert : 1339117212 To insert : 1339117213 To insert : 1339117214 To insert : 1339117215 To insert : 1339117216 To insert : 1339117217 To insert : 1339117218 To insert : 1339117219 To insert : 1339117220 To insert : 1339117221 To insert : 1339117222 To insert : 1339117223 To insert : 1339117224 To insert : 1339117225 To insert : 1339117226 To insert : 1339117227 To insert : 1339117228 To insert : 1339117229 To insert : 1339117230 To insert : 1339117231 To insert : 1339117232 To insert : 1339117233 To insert : 1339117234 To insert : 1339117236 To insert : 1339117237 To insert : 1339117238 To insert : 1339117246 To insert : 1339117247 To insert : 1339117248 To insert : 1339117249 To insert : 1339117250 To insert : 1339117251 To insert : 1339117252 To insert : 1339117253 To insert : 1339117254 To insert : 1339117255 To insert : 1339117256 To insert : 1339117257 To insert : 1339117258 To insert : 1339117259 To insert : 1339117260 To insert : 1339117077 To insert : 1339117078 To insert : 1339117079 To insert : 1339117080 To insert : 1339117081 To insert : 1339117082 To insert : 1339117083 To insert : 1339117084 To insert : 1339117085 To insert : 1339117086 To insert : 1339117087 To insert : 1339117088 To insert : 1339117089 To insert : 1339117090 To insert : 1339117091 To insert : 1339117092 To insert : 1339117093 To insert : 1339117094 To insert : 1339117095 To insert : 1339117096 To insert : 1339117097 To insert : 1339117098 To insert : 1339117099 To insert : 1339117100 To insert : 1339117101 To insert : 1339117102 To insert : 1339117103 To insert : 1339117105 To insert : 1339117106 To insert : 1339117107 To insert : 1339117108 To insert : 1339117109 To insert : 1339117110 To insert : 1339117111 To insert : 1339117112 To insert : 1339117148 To insert : 1339117149 To insert : 1339117150 To insert : 1339117151 To insert : 1339117152 To insert : 1339117153 To insert : 1339117154 To insert : 1339117155 To insert : 1339117156 To insert : 1339117157 To insert : 1339117158 To insert : 1339117159 To insert : 1339117160 To insert : 1339117161 To insert : 1339117162 To insert : 1339117163 To insert : 1339117164 To insert : 1339117165 To insert : 1339117166 To insert : 1339117167 To insert : 1339117168 To insert : 1339117169 To insert : 1339117170 To insert : 1339117171 To insert : 1339117172 To insert : 1339117173 To insert : 1339117174 To insert : 1339117175 To insert : 1339117176 To insert : 1339117177 To insert : 1339117178 To insert : 1339117179 To insert : 1339117180 To insert : 1339117181 To insert : 1339117182 To insert : 1339117113 To insert : 1339117114 To insert : 1339117115 To insert : 1339117116 To insert : 1339117117 To insert : 1339117118 To insert : 1339117119 To insert : 1339117120 To insert : 1339117121 To insert : 1339117122 To insert : 1339117123 To insert : 1339117124 To insert : 1339117125 To insert : 1339117126 To insert : 1339117127 To insert : 1339117128 To insert : 1339117129 To insert : 1339117130 To insert : 1339117131 To insert : 1339117132 To insert : 1339117133 To insert : 1339117134 To insert : 1339117135 To insert : 1339117136 To insert : 1339117137 To insert : 1339117138 To insert : 1339117139 To insert : 1339117140 To insert : 1339117141 To insert : 1339117142 To insert : 1339117143 To insert : 1339117144 To insert : 1339117145 To insert : 1339117146 To insert : 1339117147 To insert : 1339117332 To insert : 1339117333 To insert : 1339117334 To insert : 1339117335 To insert : 1339117336 To insert : 1339117337 To insert : 1339117338 To insert : 1339117339 To insert : 1339117340 To insert : 1339117341 To insert : 1339117342 To insert : 1339117343 To insert : 1339117344 To insert : 1339117345 To insert : 1339117346 To insert : 1339117347 To insert : 1339117348 To insert : 1339117349 To insert : 1339117350 To insert : 1339117351 To insert : 1339117352 To insert : 1339117353 To insert : 1339117354 To insert : 1339117355 To insert : 1339117356 To insert : 1339117357 To insert : 1339117358 To insert : 1339117359 To insert : 1339117360 To insert : 1339117361 To insert : 1339117362 To insert : 1339117363 To insert : 1339117364 To insert : 1339117365 To insert : 1339117366 To insert : 1339117296 To insert : 1339117297 To insert : 1339117298 To insert : 1339117299 To insert : 1339117300 To insert : 1339117301 To insert : 1339117302 To insert : 1339117303 To insert : 1339117304 To insert : 1339117305 To insert : 1339117306 To insert : 1339117307 To insert : 1339117308 To insert : 1339117310 To insert : 1339117311 To insert : 1339117312 To insert : 1339117313 To insert : 1339117314 To insert : 1339117315 To insert : 1339117316 To insert : 1339117317 To insert : 1339117318 To insert : 1339117319 To insert : 1339117320 To insert : 1339117321 To insert : 1339117322 To insert : 1339117323 To insert : 1339117324 To insert : 1339117325 To insert : 1339117326 To insert : 1339117327 To insert : 1339117328 To insert : 1339117329 To insert : 1339117330 To insert : 1339117331 time to insert the descriptors : 75.43376016616821 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 : 532 time used for this insertion : 0.04490828514099121 save missing photos in datou_result : time spend for datou_step_exec : 85.09123110771179 time spend to save output : 0.10199284553527832 total time spend for step 6 : 85.19322395324707 step7:ventilate_hashtags_in_portfolio Sat Feb 22 18:24:43 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 : 20752076 get user id for portfolio 20752076 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`=20752076 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','metal','PEHD','pehd','pet_fonce','Papier','refus','PET_fonce','environnement','flou','PET_clair','pet_clair','Tetrapak','papier','mal_croppe','Film_plastique','Carton','carton')) 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`=20752076 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','metal','PEHD','pehd','pet_fonce','Papier','refus','PET_fonce','environnement','flou','PET_clair','pet_clair','Tetrapak','papier','mal_croppe','Film_plastique','Carton','carton')) 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`=20752076 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','metal','PEHD','pehd','pet_fonce','Papier','refus','PET_fonce','environnement','flou','PET_clair','pet_clair','Tetrapak','papier','mal_croppe','Film_plastique','Carton','carton')) 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`=20752076 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('autre','metal','PEHD','pehd','pet_fonce','Papier','refus','PET_fonce','environnement','flou','PET_clair','pet_clair','Tetrapak','papier','mal_croppe','Film_plastique','Carton','carton')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/20752513,20752514,20752516,20752520,20752526,20752519,20752521,20752522,20752524,20752525,20752527,20752528,20752530?tags=autre,metal,pehd,pet_fonce,papier,refus,environnement,flou,pet_clair,tetrapak,mal_croppe,film_plastique,carton&datou_id_consolidate=4235&port_consolidate=20752076 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1339109752, 1339109751, 1339109750, 1339109657] Looping around the photos to save general results len do output : 1 /20752076. 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, '2608224') ('4234', '20752076', '1339109752', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109751', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109750', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109657', None, None, None, None, None, '2608224') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012417793273925781 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.303800582885742 time spend to save output : 0.012764215469360352 total time spend for step 7 : 2.3165647983551025 step8:final Sat Feb 22 18:24:45 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 : {1339109752: ('0.1799043096617032',), 1339109751: ('0.1799043096617032',), 1339109750: ('0.1799043096617032',), 1339109657: ('0.1799043096617032',)} new output for save of step final : {1339109752: ('0.1799043096617032',), 1339109751: ('0.1799043096617032',), 1339109750: ('0.1799043096617032',), 1339109657: ('0.1799043096617032',)} [1339109752, 1339109751, 1339109750, 1339109657] Looping around the photos to save general results len do output : 4 /1339109752.Didn't retrieve data . /1339109751.Didn't retrieve data . /1339109750.Didn't retrieve data . /1339109657.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, '2608224') ('4234', '20752076', '1339109752', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109751', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109750', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109657', None, None, None, None, None, '2608224') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.013087749481201172 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12776994705200195 time spend to save output : 0.013347864151000977 total time spend for step 8 : 0.14111781120300293 step9:velours_tree Sat Feb 22 18:24:45 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 : 20752513,20752514,20752516,20752520,20752526,20752519,20752521,20752522,20752524,20752525,20752527,20752528,20752530 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=20752513 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=20752514 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=20752516 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=20752520 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=20752526 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=20752519 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=20752521 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=20752522 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=20752524 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=20752525 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=20752527 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=20752528 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=20752530 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 341 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [0 4 1 1 3 0 2 1 2 2 2 0 2 1 2 4 1 0 1 0 0 2 2 2 1 0 2 0 2 2 2 5 0 1 0 1 2 0 0 0 2 2 1 2 0 0 5 1 0 0 2 1 4 2 1 5 4 2 1 1 1 2 0 0 2 1 1 2 2 2 2 2 4 1 0 2 0 2 0 2 2 2 2 2 5 0 1 1 0 2 0 0 2 2 1 0 5 1 0 0 2 1 0 5 0 4 3 1 2 3 0 0 2 0 2 2 2 2 4 1 0 2 2 0 2 0 2 2 5 0 0 2 1 0 2 2 0 0 2 2 1 2 0 0 5 0 1 0 5 0 4 0 1 1 2 0 0 2 2 2 0 2 2 4 4 1 1 0 1 2 0 2 0 2 2 0 2 0 1 2 0 0 0 2 2 1 2 2 0 5 0 1 1 4 5 3 3 1 2 2 5 5 1 2 1 0 5 5 5 5 0 2 1 5 2 1 2 0 3 3 2 5 1 1 0 1 1 5 5 2 5 0 2 2 3 3 4 2 5 5 1 2 5 5 2 5 4 1 5 2 0 3 3 4 2 5 5 1 1 2 1 2 1 5 5 5 1 5 0 0 2 1 1 2 2 0 1 2 0 5 0 5 2 0 2 0 5 0 0 2 1 1 0 2 2 0 4 0 0 2 1 0 0 0 2 0 2 2 1 2 0 2 0 2 0 2 1 1 2 2 1 1 0 0 2 2 0 0 0 2 1 1 0 2 0 0 5 2 0 0 1] Elapsed time: 0.06575679779052734 graph_id used : 79812 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/20752513,20752514,20752516,20752520,20752526,20752519,20752521,20752522,20752524,20752525,20752527,20752528,20752530?tags=autre,metal,pehd,pet_fonce,papier,refus,environnement,flou,pet_clair,tetrapak,mal_croppe,film_plastique,carton&datou_id_consolidate=4235&port_consolidate=20752076&tree_id=79812 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1339109752, 1339109751, 1339109750, 1339109657] Looping around the photos to save general results len do output : 1 /20752076Didn'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, '2608224') ('4234', '20752076', '1339109752', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109751', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109750', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109657', None, None, None, None, None, '2608224') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012044906616210938 save_final save missing photos in datou_result : time spend for datou_step_exec : 23.158156871795654 time spend to save output : 0.012372016906738281 total time spend for step 9 : 23.170528888702393 step10:send_mail_cod Sat Feb 22 18:25:08 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 complete output_args for input 3 We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure dans la step send mail cod work_area: /home/admin/workarea/git/Velours/python in order to get the selector url, please entre the license of selector results_Qualipapia_P20752076_22-02-2025_18_25_08.pdf 20752495 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 .imagette207524951740245108 20752496 change filename to text .change filename to text .change filename to text .imagette207524961740245109 20752498 imagette207524981740245110 20752502 change filename to text .imagette207525021740245110 20752508 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 .imagette207525081740245110 20752501 imagette207525011740245111 20752504 imagette207525041740245111 20752506 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 .imagette207525061740245111 20752507 imagette207525071740245112 20752509 imagette207525091740245112 20752510 imagette207525101740245112 20752512 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 .imagette207525121740245112 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=20752076 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/20752513,20752514,20752516,20752520,20752526,20752519,20752521,20752522,20752524,20752525,20752527,20752528,20752530?tags=autre,metal,pehd,pet_fonce,papier,refus,environnement,flou,pet_clair,tetrapak,mal_croppe,film_plastique,carton&datou_id_consolidate=4235&port_consolidate=20752076&tree_id=79812 your option no_mail is active, we will not send the real mail to your client args[1339109752] : ((1339109752, -7.218491496063488, 492609224), (1339109752, -0.5043580315329623, 501862349), '0.1799043096617032') We are sending mail with results at cod@fotonower.com args[1339109751] : ((1339109751, -7.2772406972626795, 492609224), (1339109751, -0.46893975664845106, 496442774), '0.1799043096617032') We are sending mail with results at cod@fotonower.com args[1339109750] : ((1339109750, -7.262344703452727, 492609224), (1339109750, -0.46336619644224825, 496442774), '0.1799043096617032') We are sending mail with results at cod@fotonower.com args[1339109657] : ((1339109657, -7.244428432725791, 492609224), (1339109657, -0.48178935209441653, 501862349), '0.1799043096617032') We are sending mail with results at cod@fotonower.com refus_total : 0.1799043096617032 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=20752076 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_P20752076_22-02-2025_18_25_08.pdf results_Qualipapia_P20752076_22-02-2025_18_25_08.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20752076_22-02-2025_18_25_08.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','20752076','results_Qualipapia_P20752076_22-02-2025_18_25_08.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20752076_22-02-2025_18_25_08.pdf','pdf','','0.17','0.1799043096617032') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1339109752, 1339109751, 1339109750, 1339109657] 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, '2608224') ('4234', '20752076', '1339109752', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109751', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109750', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109657', None, None, None, None, None, '2608224') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.14511919021606445 save_final save missing photos in datou_result : time spend for datou_step_exec : 5.465228319168091 time spend to save output : 0.14534568786621094 total time spend for step 10 : 5.610574007034302 step11:split_time_score Sat Feb 22 18:25:14 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'}] (('16', 4),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 22022025 20752076 Nombre de photos uploadées : 4 / 23040 (0%) 22022025 20752076 Nombre de photos taguées (types de déchets): 4 / 4 (100%) 22022025 20752076 Nombre de photos taguées (volume) : 0 / 4 (0%) elapsed_time : load_data_split_time_score 1.6689300537109375e-06 elapsed_time : order_list_meta_photo_and_scores 5.0067901611328125e-06 ???? elapsed_time : fill_and_build_computed_from_old_data 0.00027489662170410156 elapsed_time : insert_dashboard_record_day_entry 0.29738616943359375 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751418 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751419 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751420 order by id desc limit 1 Qualite : 0.24203530124163292 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20751421_22-02-2025_16_49_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751421 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`=20751421 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751422 order by id desc limit 1 Qualite : 0.24602261582965912 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20751423_22-02-2025_16_32_50.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751423 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`=20751423 AND mptpi.`type`=4230 To do Qualite : 0.24656465611769834 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20751424_22-02-2025_15_41_04.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751424 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`=20751424 AND mptpi.`type`=4230 To do Qualite : 0.25187974909570504 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20751770_22-02-2025_15_47_07.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20751770 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`=20751770 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752072 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752073 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752074 order by id desc limit 1 Qualite : 0.18286152793546565 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20752075_22-02-2025_18_17_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752075 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`=20752075 AND mptpi.`type`=4230 To do Qualite : 0.1799043096617032 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20752076_22-02-2025_18_25_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752076 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`=20752076 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752077 order by id desc limit 1 Qualite : 0.172181096187051 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20752078_22-02-2025_17_47_21.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752078 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`=20752078 AND mptpi.`type`=4230 To do Qualite : 0.18501113863459137 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20752079_22-02-2025_17_32_23.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752079 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`=20752079 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752080 order by id desc limit 1 Qualite : 0.2079524338091509 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P20752081_22-02-2025_17_17_04.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 20752081 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`=20752081 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'22022025': {'nb_upload': 4, 'nb_taggue_class': 4, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1339109752, 1339109751, 1339109750, 1339109657] Looping around the photos to save general results len do output : 1 /20752076Didn'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, '2608224') ('4234', '20752076', '1339109752', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109751', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109750', None, None, None, None, None, '2608224') ('4234', None, None, None, None, None, None, None, '2608224') ('4234', '20752076', '1339109657', None, None, None, None, None, '2608224') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.011817693710327148 save_final save missing photos in datou_result : time spend for datou_step_exec : 7.949704885482788 time spend to save output : 0.01198577880859375 total time spend for step 11 : 7.961690664291382 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 4 set_done_treatment 52.68user 37.34system 4:58.15elapsed 30%CPU (0avgtext+0avgdata 2476348maxresident)k 2936328inputs+20104outputs (10514major+3406543minor)pagefaults 0swaps