python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 20 -a ' -a 3318 ' -s datou_3318 -M 0 -S 0 -U 95,95,120 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 : 2827629 load datou : 3318 # 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 ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 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 : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( 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 ? [ (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 ? 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 ? 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 ? 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 ? 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)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load pdts add pdt : 5275 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 : 3318, datou_cur_ids : ['2746490'] with mtr_portfolio_ids : ['22302317'] and first list_photo_ids : [] new path : /proc/2827629/ 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 ! 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 7928 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 8092 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 8092 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7933 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 7935 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 7934 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 7934 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! WARNING : number of outputs for step 13649 velours_tree is not consistent : 2 used against 1 in the step definition ! Step 9283 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 : type of output 1 of step 7935 doesn't seem to be define in the database( WARNING : type of input 3 of step 7934 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 1 of step 7935 doesn't seem to be define in the database( WARNING : output 1 of step 7933 have datatype=7 whereas input 1 of step 7935 have datatype=None WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 2 of step 8092 doesn't seem to be define in the database( WARNING : type of output 3 of step 8092 doesn't seem to be define in the database( WARNING : type of input 1 of step 7933 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10917 doesn't seem to be define in the database( WARNING : type of output 2 of step 7928 doesn't seem to be define in the database( WARNING : type of input 1 of step 10918 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 7935 have datatype=10 whereas input 3 of step 10916 have datatype=6 WARNING : output 0 of step 7935 have datatype=10 whereas input 0 of step 13649 have datatype=18 WARNING : type of output 1 of step 13649 doesn't seem to be define in the database( WARNING : type of input 5 of step 10916 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, crop_condition, rle_unique_nms_with_priority, ventilate_hashtags_in_portfolio, final, blur_detection, brightness, velours_tree, send_mail_cod, split_time_score over limit max, limiting to limit_max 40 list_input_json : [] origin We have 1 , BFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 11 ; length of list_pids : 11 ; length of list_args : 11 time to download the photos : 1.7893009185791016 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 : 10 step1:mask_detect Sat Apr 12 00:10:32 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 : 3418 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-04-12 00:10:35.366146: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-04-12 00:10:35.395157: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-04-12 00:10:35.397378: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fbcd4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-04-12 00:10:35.397441: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-04-12 00:10:35.401841: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-04-12 00:10:35.563359: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x35b05f20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-04-12 00:10:35.563443: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-04-12 00:10:35.564726: 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 2025-04-12 00:10:35.565272: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-12 00:10:35.568718: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-12 00:10:35.572002: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-12 00:10:35.572578: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-12 00:10:35.576080: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-12 00:10:35.577270: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-12 00:10:35.582303: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-12 00:10:35.583637: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-12 00:10:35.583740: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-12 00:10:35.584360: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-12 00:10:35.584380: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-12 00:10:35.584390: I tensorflow/core/coUsing 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 : [] 2025-04-12 00:10:41.547967: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 51380224 exceeds 10% of free system memory. 2025-04-12 00:10:48.332835: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-12 00:10:48.744596: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-12 00:10:50.950168: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.40G (2575171584 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 00:10:50.950746: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.16G (2317654272 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 00:10:50.950776: 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. 2025-04-12 00:10:50.951346: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.40G (2575171584 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 00:10:50.951364: 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. 2025-04-12 00:10:50.958320: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.40G (2575171584 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 00:10:50.958342: 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. 2025-04-12 00:10:50.958876: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.40G (2575171584 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 00:10:50.958892: 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. 2025-04-12 00:10:50.965398: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.40G (2575171584 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 00:10:50.965421: 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. 2025-04-12 00:10:50.965954: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.40G (2575171584 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 00:10:50.965969: 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 ilocal 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 : 11 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 42 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 86 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 41 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 46 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 57 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 63 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 46 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 61 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 99 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 66 NEW PHOTO Processing 1 images image shape: (2160, 3264, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 3264.00000 nb d'objets trouves : 55 Detection mask done ! Trying to reset tf kernel 2828701 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2310 tf kernel not reseted sub process len(results) : 11 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 11 len(list_Values) 0 process is alive 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 : 3503 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2847 Catched exception ! Connect or reconnect ! 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 ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] time for calcul the mask position with numpy : 0.5131478309631348 nb_pixel_total : 405603 time to create 1 rle with new method : 0.029595136642456055 length of segment : 855 time for calcul the mask position with numpy : 0.30939388275146484 nb_pixel_total : 246339 time to create 1 rle with new method : 0.013641834259033203 length of segment : 525 time for calcul the mask position with numpy : 0.06454038619995117 nb_pixel_total : 23912 time to create 1 rle with old method : 0.03210330009460449 length of segment : 165 time for calcul the mask position with numpy : 0.14739060401916504 nb_pixel_total : 91405 time to create 1 rle with old method : 0.1077578067779541 length of segment : 354 time for calcul the mask position with numpy : 0.04934835433959961 nb_pixel_total : 21265 time to create 1 rle with old method : 0.031728267669677734 length of segment : 147 time for calcul the mask position with numpy : 0.04950737953186035 nb_pixel_total : 25915 time to create 1 rle with old method : 0.03433084487915039 length of segment : 160 time for calcul the mask position with numpy : 0.047652482986450195 nb_pixel_total : 16465 time to create 1 rle with old method : 0.02256941795349121 length of segment : 172 time for calcul the mask position with numpy : 0.10213637351989746 nb_pixel_total : 81060 time to create 1 rle with old method : 0.10013484954833984 length of segment : 340 time for calcul the mask position with numpy : 0.047890424728393555 nb_pixel_total : 16741 time to create 1 rle with old method : 0.023701190948486328 length of segment : 152 time for calcul the mask position with numpy : 0.029561519622802734 nb_pixel_total : 20712 time to create 1 rle with old method : 0.02997112274169922 length of segment : 177 time for calcul the mask position with numpy : 0.03625059127807617 nb_pixel_total : 13247 time to create 1 rle with old method : 0.01884174346923828 length of segment : 167 time for calcul the mask position with numpy : 0.05996108055114746 nb_pixel_total : 52443 time to create 1 rle with old method : 0.0663914680480957 length of segment : 241 time for calcul the mask position with numpy : 0.05364799499511719 nb_pixel_total : 28174 time to create 1 rle with old method : 0.03872036933898926 length of segment : 159 time for calcul the mask position with numpy : 0.03221702575683594 nb_pixel_total : 16656 time to create 1 rle with old method : 0.022572040557861328 length of segment : 143 time for calcul the mask position with numpy : 0.16285467147827148 nb_pixel_total : 122768 time to create 1 rle with old method : 0.1368253231048584 length of segment : 549 time for calcul the mask position with numpy : 0.0340571403503418 nb_pixel_total : 9420 time to create 1 rle with old method : 0.015173912048339844 length of segment : 144 time for calcul the mask position with numpy : 0.04662156105041504 nb_pixel_total : 53104 time to create 1 rle with old method : 0.07021903991699219 length of segment : 258 time for calcul the mask position with numpy : 0.02396702766418457 nb_pixel_total : 13495 time to create 1 rle with old method : 0.020531892776489258 length of segment : 232 time for calcul the mask position with numpy : 0.144362211227417 nb_pixel_total : 97098 time to create 1 rle with old method : 0.10940384864807129 length of segment : 457 time for calcul the mask position with numpy : 0.043956756591796875 nb_pixel_total : 14744 time to create 1 rle with old method : 0.0184173583984375 length of segment : 124 time for calcul the mask position with numpy : 0.027115345001220703 nb_pixel_total : 16820 time to create 1 rle with old method : 0.024414539337158203 length of segment : 161 time for calcul the mask position with numpy : 0.022917509078979492 nb_pixel_total : 11817 time to create 1 rle with old method : 0.017798662185668945 length of segment : 128 time for calcul the mask position with numpy : 0.0031113624572753906 nb_pixel_total : 15721 time to create 1 rle with old method : 0.019980192184448242 length of segment : 173 time for calcul the mask position with numpy : 0.07707023620605469 nb_pixel_total : 59698 time to create 1 rle with old method : 0.06975007057189941 length of segment : 380 time for calcul the mask position with numpy : 0.05877971649169922 nb_pixel_total : 69459 time to create 1 rle with old method : 0.07869601249694824 length of segment : 329 time for calcul the mask position with numpy : 0.009585380554199219 nb_pixel_total : 9389 time to create 1 rle with old method : 0.013231992721557617 length of segment : 80 time for calcul the mask position with numpy : 0.009246587753295898 nb_pixel_total : 14827 time to create 1 rle with old method : 0.019034147262573242 length of segment : 145 time for calcul the mask position with numpy : 0.11312150955200195 nb_pixel_total : 80692 time to create 1 rle with old method : 0.09121298789978027 length of segment : 366 time for calcul the mask position with numpy : 0.011811256408691406 nb_pixel_total : 88347 time to create 1 rle with old method : 0.09491896629333496 length of segment : 347 time for calcul the mask position with numpy : 0.028969526290893555 nb_pixel_total : 31922 time to create 1 rle with old method : 0.03895831108093262 length of segment : 173 time for calcul the mask position with numpy : 0.007931947708129883 nb_pixel_total : 5338 time to create 1 rle with old method : 0.007829666137695312 length of segment : 93 time for calcul the mask position with numpy : 0.09736394882202148 nb_pixel_total : 59303 time to create 1 rle with old method : 0.06637978553771973 length of segment : 447 time for calcul the mask position with numpy : 0.007094860076904297 nb_pixel_total : 58556 time to create 1 rle with old method : 0.06465697288513184 length of segment : 367 time for calcul the mask position with numpy : 0.008142948150634766 nb_pixel_total : 15961 time to create 1 rle with old method : 0.01965951919555664 length of segment : 235 time for calcul the mask position with numpy : 0.01843714714050293 nb_pixel_total : 21652 time to create 1 rle with old method : 0.027475833892822266 length of segment : 188 time for calcul the mask position with numpy : 0.011801958084106445 nb_pixel_total : 9710 time to create 1 rle with old method : 0.016470670700073242 length of segment : 96 time for calcul the mask position with numpy : 0.016997337341308594 nb_pixel_total : 13333 time to create 1 rle with old method : 0.019194841384887695 length of segment : 170 time for calcul the mask position with numpy : 0.0008313655853271484 nb_pixel_total : 9975 time to create 1 rle with old method : 0.011357784271240234 length of segment : 143 time for calcul the mask position with numpy : 0.06319975852966309 nb_pixel_total : 82619 time to create 1 rle with old method : 0.09349679946899414 length of segment : 433 time for calcul the mask position with numpy : 0.019840002059936523 nb_pixel_total : 25496 time to create 1 rle with old method : 0.03253173828125 length of segment : 194 time for calcul the mask position with numpy : 0.003518819808959961 nb_pixel_total : 18193 time to create 1 rle with old method : 0.023071765899658203 length of segment : 269 time for calcul the mask position with numpy : 0.057088375091552734 nb_pixel_total : 10520 time to create 1 rle with old method : 0.0174405574798584 length of segment : 238 time for calcul the mask position with numpy : 0.006835460662841797 nb_pixel_total : 23671 time to create 1 rle with old method : 0.032810211181640625 length of segment : 326 time for calcul the mask position with numpy : 0.08910441398620605 nb_pixel_total : 10003 time to create 1 rle with old method : 0.017309904098510742 length of segment : 159 time for calcul the mask position with numpy : 0.011948347091674805 nb_pixel_total : 5365 time to create 1 rle with old method : 0.008924722671508789 length of segment : 166 time for calcul the mask position with numpy : 0.00532841682434082 nb_pixel_total : 3073 time to create 1 rle with old method : 0.0037517547607421875 length of segment : 69 time for calcul the mask position with numpy : 0.0018401145935058594 nb_pixel_total : 9014 time to create 1 rle with old method : 0.010596990585327148 length of segment : 100 time for calcul the mask position with numpy : 0.0022172927856445312 nb_pixel_total : 24426 time to create 1 rle with old method : 0.030646800994873047 length of segment : 121 time for calcul the mask position with numpy : 0.021864891052246094 nb_pixel_total : 39415 time to create 1 rle with old method : 0.04824185371398926 length of segment : 249 time for calcul the mask position with numpy : 0.03730463981628418 nb_pixel_total : 71069 time to create 1 rle with old method : 0.08259415626525879 length of segment : 391 time for calcul the mask position with numpy : 0.003139972686767578 nb_pixel_total : 15166 time to create 1 rle with old method : 0.01970815658569336 length of segment : 276 time for calcul the mask position with numpy : 0.019513845443725586 nb_pixel_total : 17722 time to create 1 rle with old method : 0.026131629943847656 length of segment : 276 time for calcul the mask position with numpy : 0.03175497055053711 nb_pixel_total : 30775 time to create 1 rle with old method : 0.03897666931152344 length of segment : 207 time for calcul the mask position with numpy : 0.014600276947021484 nb_pixel_total : 23752 time to create 1 rle with old method : 0.03209257125854492 length of segment : 231 time for calcul the mask position with numpy : 0.0031337738037109375 nb_pixel_total : 13193 time to create 1 rle with old method : 0.018973827362060547 length of segment : 122 time for calcul the mask position with numpy : 0.015285015106201172 nb_pixel_total : 8940 time to create 1 rle with old method : 0.015588045120239258 length of segment : 130 time for calcul the mask position with numpy : 0.0037560462951660156 nb_pixel_total : 19258 time to create 1 rle with old method : 0.022922515869140625 length of segment : 213 time for calcul the mask position with numpy : 0.02531886100769043 nb_pixel_total : 10674 time to create 1 rle with old method : 0.015955448150634766 length of segment : 167 time for calcul the mask position with numpy : 0.17331695556640625 nb_pixel_total : 60250 time to create 1 rle with old method : 0.0702965259552002 length of segment : 221 time for calcul the mask position with numpy : 0.0370180606842041 nb_pixel_total : 57420 time to create 1 rle with old method : 0.06692385673522949 length of segment : 344 time for calcul the mask position with numpy : 0.0007946491241455078 nb_pixel_total : 5209 time to create 1 rle with old method : 0.006038665771484375 length of segment : 110 time for calcul the mask position with numpy : 0.01601099967956543 nb_pixel_total : 7277 time to create 1 rle with old method : 0.01109623908996582 length of segment : 156 time for calcul the mask position with numpy : 0.0017609596252441406 nb_pixel_total : 21571 time to create 1 rle with old method : 0.023946046829223633 length of segment : 159 time for calcul the mask position with numpy : 0.08482527732849121 nb_pixel_total : 56908 time to create 1 rle with old method : 0.06667661666870117 length of segment : 401 time for calcul the mask position with numpy : 0.002736806869506836 nb_pixel_total : 38869 time to create 1 rle with old method : 0.041285037994384766 length of segment : 151 time for calcul the mask position with numpy : 0.0046727657318115234 nb_pixel_total : 22514 time to create 1 rle with old method : 0.027592897415161133 length of segment : 216 time for calcul the mask position with numpy : 0.04605555534362793 nb_pixel_total : 280497 time to create 1 rle with new method : 0.029314041137695312 length of segment : 781 time for calcul the mask position with numpy : 0.002962827682495117 nb_pixel_total : 19011 time to create 1 rle with old method : 0.02185511589050293 length of segment : 259 time for calcul the mask position with numpy : 0.019310474395751953 nb_pixel_total : 14665 time to create 1 rle with old method : 0.023527145385742188 length of segment : 182 time for calcul the mask position with numpy : 0.0529627799987793 nb_pixel_total : 33704 time to create 1 rle with old method : 0.04361152648925781 length of segment : 171 time for calcul the mask position with numpy : 0.05489945411682129 nb_pixel_total : 192751 time to create 1 rle with new method : 0.03460335731506348 length of segment : 721 time for calcul the mask position with numpy : 0.006683349609375 nb_pixel_total : 125871 time to create 1 rle with old method : 0.14568543434143066 length of segment : 420 time for calcul the mask position with numpy : 0.0645761489868164 nb_pixel_total : 61439 time to create 1 rle with old method : 0.07859134674072266 length of segment : 266 time for calcul the mask position with numpy : 0.02391672134399414 nb_pixel_total : 123133 time to create 1 rle with old method : 0.14030790328979492 length of segment : 452 time for calcul the mask position with numpy : 0.0017397403717041016 nb_pixel_total : 17944 time to create 1 rle with old method : 0.02023768424987793 length of segment : 185 time for calcul the mask position with numpy : 0.0682976245880127 nb_pixel_total : 89331 time to create 1 rle with old method : 0.10031795501708984 length of segment : 367 time for calcul the mask position with numpy : 0.00494074821472168 nb_pixel_total : 36355 time to create 1 rle with old method : 0.04063224792480469 length of segment : 293 time for calcul the mask position with numpy : 0.0011463165283203125 nb_pixel_total : 21971 time to create 1 rle with old method : 0.02366948127746582 length of segment : 195 time for calcul the mask position with numpy : 0.009853363037109375 nb_pixel_total : 27529 time to create 1 rle with old method : 0.036380767822265625 length of segment : 236 time for calcul the mask position with numpy : 0.005670070648193359 nb_pixel_total : 83083 time to create 1 rle with old method : 0.09148216247558594 length of segment : 464 time for calcul the mask position with numpy : 0.0016176700592041016 nb_pixel_total : 51726 time to create 1 rle with old method : 0.05913829803466797 length of segment : 260 time for calcul the mask position with numpy : 0.008606910705566406 nb_pixel_total : 85149 time to create 1 rle with old method : 0.09775876998901367 length of segment : 281 time for calcul the mask position with numpy : 0.013202428817749023 nb_pixel_total : 77445 time to create 1 rle with old method : 0.09125852584838867 length of segment : 531 time for calcul the mask position with numpy : 0.00485539436340332 nb_pixel_total : 30760 time to create 1 rle with old method : 0.03781914710998535 length of segment : 228 time for calcul the mask position with numpy : 0.016607046127319336 nb_pixel_total : 46128 time to create 1 rle with old method : 0.05551481246948242 length of segment : 487 time for calcul the mask position with numpy : 0.021045207977294922 nb_pixel_total : 20102 time to create 1 rle with old method : 0.028239727020263672 length of segment : 167 time for calcul the mask position with numpy : 0.002687692642211914 nb_pixel_total : 92818 time to create 1 rle with old method : 0.1097249984741211 length of segment : 401 time for calcul the mask position with numpy : 0.0030167102813720703 nb_pixel_total : 84919 time to create 1 rle with old method : 0.0975942611694336 length of segment : 290 time for calcul the mask position with numpy : 0.0029144287109375 nb_pixel_total : 50504 time to create 1 rle with old method : 0.05827760696411133 length of segment : 341 time for calcul the mask position with numpy : 0.0009908676147460938 nb_pixel_total : 23842 time to create 1 rle with old method : 0.028282880783081055 length of segment : 199 time for calcul the mask position with numpy : 0.2734839916229248 nb_pixel_total : 620601 time to create 1 rle with new method : 0.5622448921203613 length of segment : 968 time for calcul the mask position with numpy : 0.04766845703125 nb_pixel_total : 38847 time to create 1 rle with old method : 0.0466923713684082 length of segment : 433 time for calcul the mask position with numpy : 0.0013666152954101562 nb_pixel_total : 31713 time to create 1 rle with old method : 0.03669095039367676 length of segment : 249 time for calcul the mask position with numpy : 0.0009670257568359375 nb_pixel_total : 52380 time to create 1 rle with old method : 0.0601193904876709 length of segment : 358 time for calcul the mask position with numpy : 0.007292985916137695 nb_pixel_total : 58414 time to create 1 rle with old method : 0.06882905960083008 length of segment : 398 time for calcul the mask position with numpy : 0.012213468551635742 nb_pixel_total : 114602 time to create 1 rle with old method : 0.13153982162475586 length of segment : 577 time for calcul the mask position with numpy : 0.001108407974243164 nb_pixel_total : 22144 time to create 1 rle with old method : 0.025354385375976562 length of segment : 189 time for calcul the mask position with numpy : 0.016262292861938477 nb_pixel_total : 195770 time to create 1 rle with new method : 0.009247779846191406 length of segment : 572 time for calcul the mask position with numpy : 0.0042324066162109375 nb_pixel_total : 19614 time to create 1 rle with old method : 0.021851301193237305 length of segment : 182 time for calcul the mask position with numpy : 0.06863069534301758 nb_pixel_total : 36159 time to create 1 rle with old method : 0.046326637268066406 length of segment : 197 time for calcul the mask position with numpy : 0.05424666404724121 nb_pixel_total : 398423 time to create 1 rle with new method : 0.03598213195800781 length of segment : 832 time for calcul the mask position with numpy : 0.0004284381866455078 nb_pixel_total : 8757 time to create 1 rle with old method : 0.009897947311401367 length of segment : 141 time for calcul the mask position with numpy : 0.0002741813659667969 nb_pixel_total : 7694 time to create 1 rle with old method : 0.008914709091186523 length of segment : 96 time for calcul the mask position with numpy : 0.04113626480102539 nb_pixel_total : 163042 time to create 1 rle with new method : 0.015452146530151367 length of segment : 907 time for calcul the mask position with numpy : 0.11356401443481445 nb_pixel_total : 265053 time to create 1 rle with new method : 0.014237642288208008 length of segment : 571 time for calcul the mask position with numpy : 0.002605438232421875 nb_pixel_total : 38484 time to create 1 rle with old method : 0.043942928314208984 length of segment : 247 time for calcul the mask position with numpy : 0.00021767616271972656 nb_pixel_total : 3279 time to create 1 rle with old method : 0.0038862228393554688 length of segment : 60 time for calcul the mask position with numpy : 0.0038580894470214844 nb_pixel_total : 31465 time to create 1 rle with old method : 0.038190603256225586 length of segment : 196 time for calcul the mask position with numpy : 0.003375530242919922 nb_pixel_total : 73130 time to create 1 rle with old method : 0.09206151962280273 length of segment : 548 time for calcul the mask position with numpy : 0.0007493495941162109 nb_pixel_total : 15196 time to create 1 rle with old method : 0.017611026763916016 length of segment : 142 time for calcul the mask position with numpy : 0.0064847469329833984 nb_pixel_total : 12346 time to create 1 rle with old method : 0.018105745315551758 length of segment : 166 time for calcul the mask position with numpy : 0.0005533695220947266 nb_pixel_total : 6360 time to create 1 rle with old method : 0.007598400115966797 length of segment : 117 time for calcul the mask position with numpy : 0.006467103958129883 nb_pixel_total : 94055 time to create 1 rle with old method : 0.10608053207397461 length of segment : 536 time for calcul the mask position with numpy : 0.0005366802215576172 nb_pixel_total : 9994 time to create 1 rle with old method : 0.011246919631958008 length of segment : 119 time for calcul the mask position with numpy : 0.004806041717529297 nb_pixel_total : 31554 time to create 1 rle with old method : 0.03770804405212402 length of segment : 286 time for calcul the mask position with numpy : 0.029235124588012695 nb_pixel_total : 42309 time to create 1 rle with old method : 0.050737857818603516 length of segment : 266 time for calcul the mask position with numpy : 0.0010960102081298828 nb_pixel_total : 9987 time to create 1 rle with old method : 0.011452198028564453 length of segment : 91 time for calcul the mask position with numpy : 0.0005347728729248047 nb_pixel_total : 9902 time to create 1 rle with old method : 0.011307954788208008 length of segment : 99 time for calcul the mask position with numpy : 0.02138662338256836 nb_pixel_total : 122770 time to create 1 rle with old method : 0.1477525234222412 length of segment : 363 time for calcul the mask position with numpy : 0.005974292755126953 nb_pixel_total : 5922 time to create 1 rle with old method : 0.009775638580322266 length of segment : 79 time for calcul the mask position with numpy : 0.004473209381103516 nb_pixel_total : 66220 time to create 1 rle with old method : 0.07191252708435059 length of segment : 328 time for calcul the mask position with numpy : 0.0005886554718017578 nb_pixel_total : 7959 time to create 1 rle with old method : 0.009130001068115234 length of segment : 101 time for calcul the mask position with numpy : 0.0019440650939941406 nb_pixel_total : 21603 time to create 1 rle with old method : 0.024158716201782227 length of segment : 240 time for calcul the mask position with numpy : 0.044648170471191406 nb_pixel_total : 51811 time to create 1 rle with old method : 0.06456422805786133 length of segment : 185 time for calcul the mask position with numpy : 0.05585145950317383 nb_pixel_total : 61259 time to create 1 rle with old method : 0.07402467727661133 length of segment : 299 time for calcul the mask position with numpy : 0.012440681457519531 nb_pixel_total : 34526 time to create 1 rle with old method : 0.04255032539367676 length of segment : 204 time for calcul the mask position with numpy : 0.12866997718811035 nb_pixel_total : 183683 time to create 1 rle with new method : 0.016625165939331055 length of segment : 1068 time for calcul the mask position with numpy : 0.002579212188720703 nb_pixel_total : 21854 time to create 1 rle with old method : 0.025455474853515625 length of segment : 228 time for calcul the mask position with numpy : 0.0004856586456298828 nb_pixel_total : 7064 time to create 1 rle with old method : 0.008424520492553711 length of segment : 122 time for calcul the mask position with numpy : 0.016194820404052734 nb_pixel_total : 38984 time to create 1 rle with old method : 0.04278445243835449 length of segment : 320 time for calcul the mask position with numpy : 0.00035858154296875 nb_pixel_total : 5542 time to create 1 rle with old method : 0.006488323211669922 length of segment : 75 time for calcul the mask position with numpy : 0.0006132125854492188 nb_pixel_total : 10180 time to create 1 rle with old method : 0.01210927963256836 length of segment : 97 time for calcul the mask position with numpy : 0.00037360191345214844 nb_pixel_total : 4716 time to create 1 rle with old method : 0.005485057830810547 length of segment : 104 time for calcul the mask position with numpy : 0.012395381927490234 nb_pixel_total : 5079 time to create 1 rle with old method : 0.010651588439941406 length of segment : 198 time for calcul the mask position with numpy : 0.013502120971679688 nb_pixel_total : 106134 time to create 1 rle with old method : 0.11804437637329102 length of segment : 497 time for calcul the mask position with numpy : 0.005942344665527344 nb_pixel_total : 18905 time to create 1 rle with old method : 0.02581501007080078 length of segment : 164 time for calcul the mask position with numpy : 0.0009915828704833984 nb_pixel_total : 12152 time to create 1 rle with old method : 0.013504743576049805 length of segment : 146 time for calcul the mask position with numpy : 0.002346038818359375 nb_pixel_total : 20491 time to create 1 rle with old method : 0.024311065673828125 length of segment : 186 time for calcul the mask position with numpy : 0.0013916492462158203 nb_pixel_total : 22447 time to create 1 rle with old method : 0.024823427200317383 length of segment : 222 time for calcul the mask position with numpy : 0.0054302215576171875 nb_pixel_total : 5774 time to create 1 rle with old method : 0.008423089981079102 length of segment : 88 time for calcul the mask position with numpy : 0.021229028701782227 nb_pixel_total : 40089 time to create 1 rle with old method : 0.04728198051452637 length of segment : 294 time for calcul the mask position with numpy : 0.006695985794067383 nb_pixel_total : 9870 time to create 1 rle with old method : 0.012893438339233398 length of segment : 94 time for calcul the mask position with numpy : 0.017761945724487305 nb_pixel_total : 96534 time to create 1 rle with old method : 0.11196374893188477 length of segment : 354 time for calcul the mask position with numpy : 0.027093172073364258 nb_pixel_total : 116037 time to create 1 rle with old method : 0.12748026847839355 length of segment : 437 time for calcul the mask position with numpy : 0.0011341571807861328 nb_pixel_total : 38770 time to create 1 rle with old method : 0.04431486129760742 length of segment : 286 time for calcul the mask position with numpy : 0.00193023681640625 nb_pixel_total : 24252 time to create 1 rle with old method : 0.027228593826293945 length of segment : 164 time for calcul the mask position with numpy : 0.0036191940307617188 nb_pixel_total : 15036 time to create 1 rle with old method : 0.01722240447998047 length of segment : 180 time for calcul the mask position with numpy : 0.010901212692260742 nb_pixel_total : 63747 time to create 1 rle with old method : 0.07970046997070312 length of segment : 362 time for calcul the mask position with numpy : 0.0023872852325439453 nb_pixel_total : 25523 time to create 1 rle with old method : 0.03010106086730957 length of segment : 262 time for calcul the mask position with numpy : 0.002199888229370117 nb_pixel_total : 19204 time to create 1 rle with old method : 0.02172064781188965 length of segment : 129 time for calcul the mask position with numpy : 0.0011720657348632812 nb_pixel_total : 20132 time to create 1 rle with old method : 0.022761106491088867 length of segment : 238 time for calcul the mask position with numpy : 0.0010111331939697266 nb_pixel_total : 17597 time to create 1 rle with old method : 0.0200498104095459 length of segment : 154 time for calcul the mask position with numpy : 0.002272367477416992 nb_pixel_total : 47477 time to create 1 rle with old method : 0.05565476417541504 length of segment : 322 time for calcul the mask position with numpy : 0.0023920536041259766 nb_pixel_total : 36524 time to create 1 rle with old method : 0.04078340530395508 length of segment : 243 time for calcul the mask position with numpy : 0.003851652145385742 nb_pixel_total : 58877 time to create 1 rle with old method : 0.06466197967529297 length of segment : 303 time for calcul the mask position with numpy : 0.011005401611328125 nb_pixel_total : 99545 time to create 1 rle with old method : 0.11711597442626953 length of segment : 380 time for calcul the mask position with numpy : 0.007119894027709961 nb_pixel_total : 87919 time to create 1 rle with old method : 0.10481572151184082 length of segment : 253 time for calcul the mask position with numpy : 0.004868507385253906 nb_pixel_total : 93691 time to create 1 rle with old method : 0.10595536231994629 length of segment : 323 time for calcul the mask position with numpy : 0.014997482299804688 nb_pixel_total : 225529 time to create 1 rle with new method : 0.013956785202026367 length of segment : 578 time for calcul the mask position with numpy : 0.00542759895324707 nb_pixel_total : 18009 time to create 1 rle with old method : 0.023953914642333984 length of segment : 225 time for calcul the mask position with numpy : 0.00851750373840332 nb_pixel_total : 35363 time to create 1 rle with old method : 0.04127621650695801 length of segment : 317 time for calcul the mask position with numpy : 0.01796245574951172 nb_pixel_total : 312830 time to create 1 rle with new method : 0.018515348434448242 length of segment : 491 time for calcul the mask position with numpy : 0.0026717185974121094 nb_pixel_total : 12766 time to create 1 rle with old method : 0.014272451400756836 length of segment : 129 time for calcul the mask position with numpy : 0.023716449737548828 nb_pixel_total : 185728 time to create 1 rle with new method : 0.03813815116882324 length of segment : 680 time for calcul the mask position with numpy : 0.0013589859008789062 nb_pixel_total : 20060 time to create 1 rle with old method : 0.021822214126586914 length of segment : 171 time for calcul the mask position with numpy : 0.010083913803100586 nb_pixel_total : 32803 time to create 1 rle with old method : 0.04043865203857422 length of segment : 231 time for calcul the mask position with numpy : 0.015667438507080078 nb_pixel_total : 81184 time to create 1 rle with old method : 0.09022331237792969 length of segment : 329 time for calcul the mask position with numpy : 0.0027952194213867188 nb_pixel_total : 74622 time to create 1 rle with old method : 0.08274579048156738 length of segment : 238 time for calcul the mask position with numpy : 0.005804300308227539 nb_pixel_total : 43678 time to create 1 rle with old method : 0.05143618583679199 length of segment : 222 time for calcul the mask position with numpy : 0.0019228458404541016 nb_pixel_total : 9641 time to create 1 rle with old method : 0.010883331298828125 length of segment : 188 time for calcul the mask position with numpy : 0.0006806850433349609 nb_pixel_total : 27051 time to create 1 rle with old method : 0.03064250946044922 length of segment : 122 time for calcul the mask position with numpy : 0.013517141342163086 nb_pixel_total : 73272 time to create 1 rle with old method : 0.0834043025970459 length of segment : 296 time for calcul the mask position with numpy : 0.0030336380004882812 nb_pixel_total : 22755 time to create 1 rle with old method : 0.025202274322509766 length of segment : 279 time for calcul the mask position with numpy : 0.0029556751251220703 nb_pixel_total : 53065 time to create 1 rle with old method : 0.06107735633850098 length of segment : 260 time for calcul the mask position with numpy : 0.0011701583862304688 nb_pixel_total : 17186 time to create 1 rle with old method : 0.019071578979492188 length of segment : 221 time for calcul the mask position with numpy : 0.10855698585510254 nb_pixel_total : 100995 time to create 1 rle with old method : 0.11637639999389648 length of segment : 361 time for calcul the mask position with numpy : 0.0006647109985351562 nb_pixel_total : 9554 time to create 1 rle with old method : 0.010982036590576172 length of segment : 147 time for calcul the mask position with numpy : 0.052941083908081055 nb_pixel_total : 23448 time to create 1 rle with old method : 0.03167271614074707 length of segment : 221 time for calcul the mask position with numpy : 0.15709471702575684 nb_pixel_total : 196032 time to create 1 rle with new method : 0.010691165924072266 length of segment : 543 time for calcul the mask position with numpy : 0.15981030464172363 nb_pixel_total : 179273 time to create 1 rle with new method : 0.014565467834472656 length of segment : 651 time for calcul the mask position with numpy : 0.22520804405212402 nb_pixel_total : 164758 time to create 1 rle with new method : 0.010901689529418945 length of segment : 641 time for calcul the mask position with numpy : 0.023996353149414062 nb_pixel_total : 70304 time to create 1 rle with old method : 0.07958412170410156 length of segment : 249 time for calcul the mask position with numpy : 0.22028875350952148 nb_pixel_total : 262932 time to create 1 rle with new method : 0.012626886367797852 length of segment : 661 time for calcul the mask position with numpy : 0.09324860572814941 nb_pixel_total : 76235 time to create 1 rle with old method : 0.08895277976989746 length of segment : 279 time for calcul the mask position with numpy : 0.03209090232849121 nb_pixel_total : 68529 time to create 1 rle with old method : 0.07369446754455566 length of segment : 548 time for calcul the mask position with numpy : 0.010122060775756836 nb_pixel_total : 22516 time to create 1 rle with old method : 0.028241634368896484 length of segment : 177 time for calcul the mask position with numpy : 0.0010941028594970703 nb_pixel_total : 9346 time to create 1 rle with old method : 0.01076817512512207 length of segment : 127 time for calcul the mask position with numpy : 0.01659989356994629 nb_pixel_total : 64153 time to create 1 rle with old method : 0.0763845443725586 length of segment : 449 time for calcul the mask position with numpy : 0.03333401679992676 nb_pixel_total : 41139 time to create 1 rle with old method : 0.0500645637512207 length of segment : 226 time for calcul the mask position with numpy : 0.028394222259521484 nb_pixel_total : 32691 time to create 1 rle with old method : 0.04127621650695801 length of segment : 350 time for calcul the mask position with numpy : 0.0340266227722168 nb_pixel_total : 88143 time to create 1 rle with old method : 0.10115528106689453 length of segment : 401 time for calcul the mask position with numpy : 0.0006165504455566406 nb_pixel_total : 19663 time to create 1 rle with old method : 0.023109912872314453 length of segment : 535 time for calcul the mask position with numpy : 0.0050716400146484375 nb_pixel_total : 32644 time to create 1 rle with old method : 0.04622030258178711 length of segment : 217 time for calcul the mask position with numpy : 0.009102106094360352 nb_pixel_total : 27284 time to create 1 rle with old method : 0.035337209701538086 length of segment : 239 time for calcul the mask position with numpy : 0.12459969520568848 nb_pixel_total : 185643 time to create 1 rle with new method : 0.021941661834716797 length of segment : 828 time for calcul the mask position with numpy : 0.0065844058990478516 nb_pixel_total : 76857 time to create 1 rle with old method : 0.09938549995422363 length of segment : 467 time for calcul the mask position with numpy : 0.03547382354736328 nb_pixel_total : 91725 time to create 1 rle with old method : 0.11577606201171875 length of segment : 586 time for calcul the mask position with numpy : 0.01905679702758789 nb_pixel_total : 42107 time to create 1 rle with old method : 0.05601906776428223 length of segment : 227 time for calcul the mask position with numpy : 0.0025832653045654297 nb_pixel_total : 69197 time to create 1 rle with old method : 0.08170199394226074 length of segment : 485 time for calcul the mask position with numpy : 0.024017333984375 nb_pixel_total : 95781 time to create 1 rle with old method : 0.11547684669494629 length of segment : 466 time for calcul the mask position with numpy : 0.0018520355224609375 nb_pixel_total : 28170 time to create 1 rle with old method : 0.04015302658081055 length of segment : 238 time for calcul the mask position with numpy : 0.011469602584838867 nb_pixel_total : 73317 time to create 1 rle with old method : 0.08872628211975098 length of segment : 344 time for calcul the mask position with numpy : 0.021616697311401367 nb_pixel_total : 35651 time to create 1 rle with old method : 0.0468142032623291 length of segment : 203 time for calcul the mask position with numpy : 0.003125429153442383 nb_pixel_total : 13668 time to create 1 rle with old method : 0.01972365379333496 length of segment : 275 time for calcul the mask position with numpy : 0.024161577224731445 nb_pixel_total : 89379 time to create 1 rle with old method : 0.1094961166381836 length of segment : 352 time for calcul the mask position with numpy : 0.004597663879394531 nb_pixel_total : 9159 time to create 1 rle with old method : 0.013197183609008789 length of segment : 98 time for calcul the mask position with numpy : 0.0016925334930419922 nb_pixel_total : 17464 time to create 1 rle with old method : 0.02040863037109375 length of segment : 253 time for calcul the mask position with numpy : 0.07549095153808594 nb_pixel_total : 257678 time to create 1 rle with new method : 0.014799356460571289 length of segment : 336 time for calcul the mask position with numpy : 0.025997161865234375 nb_pixel_total : 106580 time to create 1 rle with old method : 0.1265110969543457 length of segment : 359 time for calcul the mask position with numpy : 0.004884004592895508 nb_pixel_total : 69425 time to create 1 rle with old method : 0.0798640251159668 length of segment : 498 time for calcul the mask position with numpy : 0.008880615234375 nb_pixel_total : 114278 time to create 1 rle with old method : 0.13726806640625 length of segment : 437 time for calcul the mask position with numpy : 0.008708000183105469 nb_pixel_total : 89173 time to create 1 rle with old method : 0.10463285446166992 length of segment : 318 time for calcul the mask position with numpy : 0.001661539077758789 nb_pixel_total : 18606 time to create 1 rle with old method : 0.021452665328979492 length of segment : 160 time for calcul the mask position with numpy : 0.002832651138305664 nb_pixel_total : 28692 time to create 1 rle with old method : 0.0333096981048584 length of segment : 505 time for calcul the mask position with numpy : 0.0010085105895996094 nb_pixel_total : 14144 time to create 1 rle with old method : 0.016359329223632812 length of segment : 118 time for calcul the mask position with numpy : 0.0007596015930175781 nb_pixel_total : 25486 time to create 1 rle with old method : 0.02916097640991211 length of segment : 172 time for calcul the mask position with numpy : 0.021829605102539062 nb_pixel_total : 101756 time to create 1 rle with old method : 0.14547252655029297 length of segment : 555 time for calcul the mask position with numpy : 0.004889965057373047 nb_pixel_total : 51359 time to create 1 rle with old method : 0.060218095779418945 length of segment : 314 time for calcul the mask position with numpy : 0.015262365341186523 nb_pixel_total : 94431 time to create 1 rle with old method : 0.10931897163391113 length of segment : 431 time for calcul the mask position with numpy : 0.09849739074707031 nb_pixel_total : 733430 time to create 1 rle with new method : 0.4765768051147461 length of segment : 1059 time for calcul the mask position with numpy : 0.037229299545288086 nb_pixel_total : 69211 time to create 1 rle with old method : 0.08616137504577637 length of segment : 455 time for calcul the mask position with numpy : 0.0012438297271728516 nb_pixel_total : 15200 time to create 1 rle with old method : 0.017758607864379883 length of segment : 138 time for calcul the mask position with numpy : 0.0009987354278564453 nb_pixel_total : 16547 time to create 1 rle with old method : 0.01946258544921875 length of segment : 153 time for calcul the mask position with numpy : 0.0009484291076660156 nb_pixel_total : 11176 time to create 1 rle with old method : 0.013366460800170898 length of segment : 107 time for calcul the mask position with numpy : 0.001336812973022461 nb_pixel_total : 20285 time to create 1 rle with old method : 0.023389339447021484 length of segment : 237 time for calcul the mask position with numpy : 0.0011913776397705078 nb_pixel_total : 10113 time to create 1 rle with old method : 0.012264728546142578 length of segment : 188 time for calcul the mask position with numpy : 0.0014209747314453125 nb_pixel_total : 26509 time to create 1 rle with old method : 0.03147077560424805 length of segment : 248 time for calcul the mask position with numpy : 0.000698089599609375 nb_pixel_total : 8658 time to create 1 rle with old method : 0.011148452758789062 length of segment : 157 time for calcul the mask position with numpy : 0.00099945068359375 nb_pixel_total : 18130 time to create 1 rle with old method : 0.0201265811920166 length of segment : 189 time for calcul the mask position with numpy : 0.0015478134155273438 nb_pixel_total : 22134 time to create 1 rle with old method : 0.02504134178161621 length of segment : 245 time for calcul the mask position with numpy : 0.0008676052093505859 nb_pixel_total : 14951 time to create 1 rle with old method : 0.017377853393554688 length of segment : 143 time for calcul the mask position with numpy : 0.00023436546325683594 nb_pixel_total : 12159 time to create 1 rle with old method : 0.014335870742797852 length of segment : 99 time for calcul the mask position with numpy : 0.003171682357788086 nb_pixel_total : 59491 time to create 1 rle with old method : 0.06766343116760254 length of segment : 477 time for calcul the mask position with numpy : 0.0014472007751464844 nb_pixel_total : 27390 time to create 1 rle with old method : 0.031754255294799805 length of segment : 198 time for calcul the mask position with numpy : 0.0020761489868164062 nb_pixel_total : 21232 time to create 1 rle with old method : 0.02448105812072754 length of segment : 161 time for calcul the mask position with numpy : 0.0012767314910888672 nb_pixel_total : 25391 time to create 1 rle with old method : 0.028863191604614258 length of segment : 204 time for calcul the mask position with numpy : 0.0022521018981933594 nb_pixel_total : 40711 time to create 1 rle with old method : 0.04453134536743164 length of segment : 341 time for calcul the mask position with numpy : 0.0004353523254394531 nb_pixel_total : 7073 time to create 1 rle with old method : 0.008119821548461914 length of segment : 71 time for calcul the mask position with numpy : 0.0004603862762451172 nb_pixel_total : 5637 time to create 1 rle with old method : 0.006489992141723633 length of segment : 72 time for calcul the mask position with numpy : 0.0007419586181640625 nb_pixel_total : 11057 time to create 1 rle with old method : 0.01241159439086914 length of segment : 104 time for calcul the mask position with numpy : 0.0011780261993408203 nb_pixel_total : 13146 time to create 1 rle with old method : 0.015058279037475586 length of segment : 298 time for calcul the mask position with numpy : 0.0012063980102539062 nb_pixel_total : 13976 time to create 1 rle with old method : 0.015990257263183594 length of segment : 205 time for calcul the mask position with numpy : 0.0007698535919189453 nb_pixel_total : 12425 time to create 1 rle with old method : 0.014768600463867188 length of segment : 104 time for calcul the mask position with numpy : 0.001873016357421875 nb_pixel_total : 19017 time to create 1 rle with old method : 0.021906375885009766 length of segment : 205 time for calcul the mask position with numpy : 0.001905202865600586 nb_pixel_total : 26264 time to create 1 rle with old method : 0.029763460159301758 length of segment : 192 time for calcul the mask position with numpy : 0.0015993118286132812 nb_pixel_total : 25655 time to create 1 rle with old method : 0.029031991958618164 length of segment : 191 time for calcul the mask position with numpy : 0.005414009094238281 nb_pixel_total : 77737 time to create 1 rle with old method : 0.08826136589050293 length of segment : 434 time for calcul the mask position with numpy : 0.0011830329895019531 nb_pixel_total : 18602 time to create 1 rle with old method : 0.021582365036010742 length of segment : 263 time for calcul the mask position with numpy : 0.000896453857421875 nb_pixel_total : 9665 time to create 1 rle with old method : 0.016023874282836914 length of segment : 114 time for calcul the mask position with numpy : 0.006137371063232422 nb_pixel_total : 69258 time to create 1 rle with old method : 0.08943367004394531 length of segment : 434 time for calcul the mask position with numpy : 0.0008113384246826172 nb_pixel_total : 10400 time to create 1 rle with old method : 0.01235508918762207 length of segment : 115 time for calcul the mask position with numpy : 0.001953125 nb_pixel_total : 27591 time to create 1 rle with old method : 0.03219246864318848 length of segment : 228 time for calcul the mask position with numpy : 0.0006778240203857422 nb_pixel_total : 10787 time to create 1 rle with old method : 0.015333890914916992 length of segment : 120 time for calcul the mask position with numpy : 0.0034792423248291016 nb_pixel_total : 30493 time to create 1 rle with old method : 0.03378486633300781 length of segment : 336 time for calcul the mask position with numpy : 0.0008087158203125 nb_pixel_total : 12308 time to create 1 rle with old method : 0.014251708984375 length of segment : 114 time for calcul the mask position with numpy : 0.010932445526123047 nb_pixel_total : 76216 time to create 1 rle with old method : 0.08698463439941406 length of segment : 549 time for calcul the mask position with numpy : 0.004742860794067383 nb_pixel_total : 60043 time to create 1 rle with old method : 0.06995987892150879 length of segment : 247 time for calcul the mask position with numpy : 0.002269744873046875 nb_pixel_total : 25857 time to create 1 rle with old method : 0.029560327529907227 length of segment : 228 time for calcul the mask position with numpy : 0.0009202957153320312 nb_pixel_total : 11170 time to create 1 rle with old method : 0.012578964233398438 length of segment : 164 time for calcul the mask position with numpy : 0.00267791748046875 nb_pixel_total : 20387 time to create 1 rle with old method : 0.023537158966064453 length of segment : 286 time for calcul the mask position with numpy : 0.008160591125488281 nb_pixel_total : 114312 time to create 1 rle with old method : 0.15794777870178223 length of segment : 265 time for calcul the mask position with numpy : 0.00025272369384765625 nb_pixel_total : 6970 time to create 1 rle with old method : 0.008300065994262695 length of segment : 113 time for calcul the mask position with numpy : 0.0014264583587646484 nb_pixel_total : 14862 time to create 1 rle with old method : 0.017517566680908203 length of segment : 167 time for calcul the mask position with numpy : 0.0037589073181152344 nb_pixel_total : 45705 time to create 1 rle with old method : 0.05315136909484863 length of segment : 249 time for calcul the mask position with numpy : 0.004492521286010742 nb_pixel_total : 45375 time to create 1 rle with old method : 0.05431246757507324 length of segment : 274 time for calcul the mask position with numpy : 0.011299371719360352 nb_pixel_total : 141242 time to create 1 rle with old method : 0.16652369499206543 length of segment : 436 time for calcul the mask position with numpy : 0.0012254714965820312 nb_pixel_total : 11974 time to create 1 rle with old method : 0.01629924774169922 length of segment : 280 time for calcul the mask position with numpy : 0.002330303192138672 nb_pixel_total : 11097 time to create 1 rle with old method : 0.015491247177124023 length of segment : 155 time for calcul the mask position with numpy : 0.0003604888916015625 nb_pixel_total : 7376 time to create 1 rle with old method : 0.008680105209350586 length of segment : 145 time for calcul the mask position with numpy : 0.0016102790832519531 nb_pixel_total : 14465 time to create 1 rle with old method : 0.017917871475219727 length of segment : 131 time for calcul the mask position with numpy : 0.0027382373809814453 nb_pixel_total : 29255 time to create 1 rle with old method : 0.034642934799194336 length of segment : 182 time for calcul the mask position with numpy : 0.0011544227600097656 nb_pixel_total : 17138 time to create 1 rle with old method : 0.019930362701416016 length of segment : 140 time for calcul the mask position with numpy : 0.0017724037170410156 nb_pixel_total : 20188 time to create 1 rle with old method : 0.02368760108947754 length of segment : 202 time for calcul the mask position with numpy : 0.0005521774291992188 nb_pixel_total : 6565 Command terminated by signal 15 75.64user 92.01system 3:03.15elapsed 91%CPU (0avgtext+0avgdata 6740052maxresident)k 7055632inputs+19224outputs (234052major+12315528minor)pagefaults 0swaps