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 : 3101445 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 : ['2746775'] with mtr_portfolio_ids : ['22305853'] and first list_photo_ids : [] new path : /proc/3101445/ 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 : 2.3903164863586426 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 01:00:31 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 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 : 3724 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-04-12 01:00:34.408012: 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 01:00:34.443174: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-04-12 01:00:34.445649: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f686c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-04-12 01:00:34.445694: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-04-12 01:00:34.452875: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-04-12 01:00:34.734709: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x4131fb90 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-04-12 01:00:34.734798: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-04-12 01:00:34.735999: 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 01:00:34.736785: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-12 01:00:34.741417: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-12 01:00:34.771892: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-12 01:00:34.772894: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-12 01:00:34.809194: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-12 01:00:34.814672: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-12 01:00:34.874823: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-12 01:00:34.876052: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-12 01:00:34.876512: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-12 01:00:34.877106: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-12 01:00:34.877121: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-12 01:00:34.877130: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-12 01:00:34.878703: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3272 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. 2025-04-12 01:00:35.244974: 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 01:00:35.245107: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-12 01:00:35.245130: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-12 01:00:35.245149: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-12 01:00:35.245168: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-12 01:00:35.245184: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-12 01:00:35.245202: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-12 01:00:35.245220: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-12 01:00:35.246291: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-12 01:00:35.247664: 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 01:00:35.247715: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-04-12 01:00:35.247735: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-12 01:00:35.247752: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-04-12 01:00:35.247768: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-04-12 01:00:35.247785: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-04-12 01:00:35.247801: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-04-12 01:00:35.247818: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-12 01:00:35.248865: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-04-12 01:00:35.248912: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-04-12 01:00:35.248923: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-04-12 01:00:35.248933: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-04-12 01:00:35.250055: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3272 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 : [] 2025-04-12 01:00:48.389615: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-04-12 01:00:48.614930: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-04-12 01:00:50.793198: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.793830: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.43G (2606432256 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.794363: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.18G (2345788928 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.794394: 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 01:00:50.794958: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.794975: 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 01:00:50.805459: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.805481: 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 01:00:50.806065: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.806080: 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 01:00:50.813109: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.813131: 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 01:00:50.813715: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.813731: 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 01:00:50.854625: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.854653: 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 01:00:50.855208: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.855224: 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 01:00:50.861621: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.861642: 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. 2025-04-12 01:00:50.862223: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.862239: 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. 2025-04-12 01:00:50.900662: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.901222: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.903827: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.904381: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.949805: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.950407: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.952497: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.953046: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.985349: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.985906: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.988140: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.988730: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.996807: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.997375: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.999057: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:50.999629: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.008457: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.009004: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.010547: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.011155: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.047003: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.047606: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.048190: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.048750: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.053972: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.054525: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.073477: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.074047: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.074632: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.075227: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.090010: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.090599: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.091204: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.091793: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.096936: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.097543: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.104436: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.105027: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.118521: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.119135: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.124416: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.125011: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.125600: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.126187: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.126946: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.127537: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.139062: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.139660: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.140264: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.140848: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.141433: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.142017: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.142604: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.143197: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.160230: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.160833: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.214812: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.215469: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.216104: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.216691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.224606: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.225228: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.249168: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.250102: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.250946: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.251712: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.256402: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.257117: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.257743: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.258335: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.260553: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.260630: 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. 2025-04-12 01:00:51.270784: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.271803: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.281991: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.282893: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.283767: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.284514: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.285391: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-04-12 01:00:51.286244: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.70G (2896035840 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 : 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 : 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 : 54 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 : 59 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 : 24 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 : 25 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 : 49 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 : 50 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 : 52 Detection mask done ! Trying to reset tf kernel 3102444 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2531 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 finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 3724 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 : 0.008342742919921875 nb_pixel_total : 184621 time to create 1 rle with new method : 0.021544456481933594 length of segment : 571 time for calcul the mask position with numpy : 0.00022459030151367188 nb_pixel_total : 6066 time to create 1 rle with old method : 0.007286787033081055 length of segment : 158 time for calcul the mask position with numpy : 0.0019023418426513672 nb_pixel_total : 43958 time to create 1 rle with old method : 0.04995536804199219 length of segment : 470 time for calcul the mask position with numpy : 0.0008349418640136719 nb_pixel_total : 27228 time to create 1 rle with old method : 0.031099557876586914 length of segment : 291 time for calcul the mask position with numpy : 0.000392913818359375 nb_pixel_total : 13651 time to create 1 rle with old method : 0.015766620635986328 length of segment : 124 time for calcul the mask position with numpy : 0.0005426406860351562 nb_pixel_total : 20762 time to create 1 rle with old method : 0.02734851837158203 length of segment : 207 time for calcul the mask position with numpy : 0.0009784698486328125 nb_pixel_total : 45079 time to create 1 rle with old method : 0.056165456771850586 length of segment : 473 time for calcul the mask position with numpy : 0.0036749839782714844 nb_pixel_total : 133400 time to create 1 rle with old method : 0.1565110683441162 length of segment : 435 time for calcul the mask position with numpy : 0.0052127838134765625 nb_pixel_total : 209937 time to create 1 rle with new method : 0.020229816436767578 length of segment : 850 time for calcul the mask position with numpy : 0.00020003318786621094 nb_pixel_total : 5621 time to create 1 rle with old method : 0.007102251052856445 length of segment : 53 time for calcul the mask position with numpy : 0.0020647048950195312 nb_pixel_total : 86533 time to create 1 rle with old method : 0.09718441963195801 length of segment : 584 time for calcul the mask position with numpy : 0.00045013427734375 nb_pixel_total : 10725 time to create 1 rle with old method : 0.012582540512084961 length of segment : 269 time for calcul the mask position with numpy : 0.000576019287109375 nb_pixel_total : 14879 time to create 1 rle with old method : 0.017344951629638672 length of segment : 151 time for calcul the mask position with numpy : 0.0003807544708251953 nb_pixel_total : 15840 time to create 1 rle with old method : 0.01883387565612793 length of segment : 109 time for calcul the mask position with numpy : 0.0011305809020996094 nb_pixel_total : 51156 time to create 1 rle with old method : 0.058681488037109375 length of segment : 359 time for calcul the mask position with numpy : 0.0004792213439941406 nb_pixel_total : 18938 time to create 1 rle with old method : 0.022063732147216797 length of segment : 180 time for calcul the mask position with numpy : 0.0006422996520996094 nb_pixel_total : 29041 time to create 1 rle with old method : 0.038237810134887695 length of segment : 240 time for calcul the mask position with numpy : 0.0007302761077880859 nb_pixel_total : 28761 time to create 1 rle with old method : 0.033049583435058594 length of segment : 278 time for calcul the mask position with numpy : 0.0001983642578125 nb_pixel_total : 7798 time to create 1 rle with old method : 0.00915980339050293 length of segment : 108 time for calcul the mask position with numpy : 0.00011849403381347656 nb_pixel_total : 3336 time to create 1 rle with old method : 0.0041697025299072266 length of segment : 50 time for calcul the mask position with numpy : 0.0005986690521240234 nb_pixel_total : 16124 time to create 1 rle with old method : 0.01912403106689453 length of segment : 281 time for calcul the mask position with numpy : 0.0015442371368408203 nb_pixel_total : 60851 time to create 1 rle with old method : 0.0762021541595459 length of segment : 263 time for calcul the mask position with numpy : 0.009317636489868164 nb_pixel_total : 186763 time to create 1 rle with new method : 0.015931129455566406 length of segment : 544 time for calcul the mask position with numpy : 0.00038504600524902344 nb_pixel_total : 6163 time to create 1 rle with old method : 0.007298469543457031 length of segment : 59 time for calcul the mask position with numpy : 0.0007152557373046875 nb_pixel_total : 14464 time to create 1 rle with old method : 0.01721930503845215 length of segment : 132 time for calcul the mask position with numpy : 0.002911806106567383 nb_pixel_total : 29243 time to create 1 rle with old method : 0.0376286506652832 length of segment : 262 time for calcul the mask position with numpy : 0.00424647331237793 nb_pixel_total : 75477 time to create 1 rle with old method : 0.0858612060546875 length of segment : 324 time for calcul the mask position with numpy : 0.0005991458892822266 nb_pixel_total : 12914 time to create 1 rle with old method : 0.014836549758911133 length of segment : 157 time for calcul the mask position with numpy : 0.01253366470336914 nb_pixel_total : 237752 time to create 1 rle with new method : 0.029830217361450195 length of segment : 806 time for calcul the mask position with numpy : 0.008751153945922852 nb_pixel_total : 165322 time to create 1 rle with new method : 0.011521100997924805 length of segment : 384 time for calcul the mask position with numpy : 0.0011086463928222656 nb_pixel_total : 20087 time to create 1 rle with old method : 0.02271580696105957 length of segment : 200 time for calcul the mask position with numpy : 0.007626056671142578 nb_pixel_total : 159062 time to create 1 rle with new method : 0.012288331985473633 length of segment : 530 time for calcul the mask position with numpy : 0.002054452896118164 nb_pixel_total : 48270 time to create 1 rle with old method : 0.05437803268432617 length of segment : 377 time for calcul the mask position with numpy : 0.002231121063232422 nb_pixel_total : 38793 time to create 1 rle with old method : 0.0448002815246582 length of segment : 178 time for calcul the mask position with numpy : 0.0012598037719726562 nb_pixel_total : 16558 time to create 1 rle with old method : 0.019563674926757812 length of segment : 221 time for calcul the mask position with numpy : 0.0005345344543457031 nb_pixel_total : 13378 time to create 1 rle with old method : 0.01602625846862793 length of segment : 96 time for calcul the mask position with numpy : 0.004051923751831055 nb_pixel_total : 167452 time to create 1 rle with new method : 0.011771678924560547 length of segment : 386 time for calcul the mask position with numpy : 0.003327608108520508 nb_pixel_total : 103479 time to create 1 rle with old method : 0.12467575073242188 length of segment : 441 time for calcul the mask position with numpy : 0.004240512847900391 nb_pixel_total : 111710 time to create 1 rle with old method : 0.1241140365600586 length of segment : 525 time for calcul the mask position with numpy : 0.003880023956298828 nb_pixel_total : 61101 time to create 1 rle with old method : 0.0682363510131836 length of segment : 342 time for calcul the mask position with numpy : 0.035981178283691406 nb_pixel_total : 392673 time to create 1 rle with new method : 1.0820252895355225 length of segment : 531 time for calcul the mask position with numpy : 0.0013473033905029297 nb_pixel_total : 22412 time to create 1 rle with old method : 0.02560591697692871 length of segment : 181 time for calcul the mask position with numpy : 0.011461496353149414 nb_pixel_total : 356569 time to create 1 rle with new method : 0.013929605484008789 length of segment : 995 time for calcul the mask position with numpy : 0.003672361373901367 nb_pixel_total : 73162 time to create 1 rle with old method : 0.08324313163757324 length of segment : 346 time for calcul the mask position with numpy : 0.0016472339630126953 nb_pixel_total : 36626 time to create 1 rle with old method : 0.04212307929992676 length of segment : 233 time for calcul the mask position with numpy : 0.0013573169708251953 nb_pixel_total : 35861 time to create 1 rle with old method : 0.04186439514160156 length of segment : 335 time for calcul the mask position with numpy : 0.0009753704071044922 nb_pixel_total : 27624 time to create 1 rle with old method : 0.032179832458496094 length of segment : 146 time for calcul the mask position with numpy : 0.006758689880371094 nb_pixel_total : 240391 time to create 1 rle with new method : 0.008574962615966797 length of segment : 913 time for calcul the mask position with numpy : 0.0007085800170898438 nb_pixel_total : 8221 time to create 1 rle with old method : 0.009608268737792969 length of segment : 193 time for calcul the mask position with numpy : 0.0047414302825927734 nb_pixel_total : 88733 time to create 1 rle with old method : 0.10460019111633301 length of segment : 426 time for calcul the mask position with numpy : 0.003557443618774414 nb_pixel_total : 36634 time to create 1 rle with old method : 0.046605825424194336 length of segment : 304 time for calcul the mask position with numpy : 0.002592802047729492 nb_pixel_total : 72165 time to create 1 rle with old method : 0.08774304389953613 length of segment : 269 time for calcul the mask position with numpy : 0.0020720958709716797 nb_pixel_total : 71568 time to create 1 rle with old method : 0.08245372772216797 length of segment : 361 time for calcul the mask position with numpy : 0.0017385482788085938 nb_pixel_total : 42273 time to create 1 rle with old method : 0.051587820053100586 length of segment : 190 time for calcul the mask position with numpy : 0.00048065185546875 nb_pixel_total : 21411 time to create 1 rle with old method : 0.026628494262695312 length of segment : 159 time for calcul the mask position with numpy : 0.000179290771484375 nb_pixel_total : 3794 time to create 1 rle with old method : 0.009020805358886719 length of segment : 60 time for calcul the mask position with numpy : 0.0008139610290527344 nb_pixel_total : 16985 time to create 1 rle with old method : 0.02025294303894043 length of segment : 181 time for calcul the mask position with numpy : 0.0005581378936767578 nb_pixel_total : 10099 time to create 1 rle with old method : 0.012171506881713867 length of segment : 89 time for calcul the mask position with numpy : 0.0038661956787109375 nb_pixel_total : 103252 time to create 1 rle with old method : 0.12583589553833008 length of segment : 431 time for calcul the mask position with numpy : 0.0024323463439941406 nb_pixel_total : 78319 time to create 1 rle with old method : 0.09151220321655273 length of segment : 500 time for calcul the mask position with numpy : 0.0004208087921142578 nb_pixel_total : 13759 time to create 1 rle with old method : 0.016468286514282227 length of segment : 159 time for calcul the mask position with numpy : 0.0072443485260009766 nb_pixel_total : 193167 time to create 1 rle with new method : 0.007887601852416992 length of segment : 358 time for calcul the mask position with numpy : 0.0039141178131103516 nb_pixel_total : 120949 time to create 1 rle with old method : 0.17387866973876953 length of segment : 419 time for calcul the mask position with numpy : 0.0033674240112304688 nb_pixel_total : 194662 time to create 1 rle with new method : 0.007867813110351562 length of segment : 432 time for calcul the mask position with numpy : 0.0008592605590820312 nb_pixel_total : 9267 time to create 1 rle with old method : 0.010924339294433594 length of segment : 159 time for calcul the mask position with numpy : 0.0008790493011474609 nb_pixel_total : 14820 time to create 1 rle with old method : 0.017544984817504883 length of segment : 144 time for calcul the mask position with numpy : 0.0003173351287841797 nb_pixel_total : 4976 time to create 1 rle with old method : 0.006083488464355469 length of segment : 99 time for calcul the mask position with numpy : 0.0011873245239257812 nb_pixel_total : 8554 time to create 1 rle with old method : 0.011229753494262695 length of segment : 240 time for calcul the mask position with numpy : 0.012201547622680664 nb_pixel_total : 278573 time to create 1 rle with new method : 0.011651754379272461 length of segment : 733 time for calcul the mask position with numpy : 0.0007085800170898438 nb_pixel_total : 7845 time to create 1 rle with old method : 0.00915217399597168 length of segment : 150 time for calcul the mask position with numpy : 0.0007851123809814453 nb_pixel_total : 10842 time to create 1 rle with old method : 0.012615442276000977 length of segment : 171 time for calcul the mask position with numpy : 0.0033571720123291016 nb_pixel_total : 20275 time to create 1 rle with old method : 0.023143291473388672 length of segment : 171 time for calcul the mask position with numpy : 0.0010528564453125 nb_pixel_total : 18333 time to create 1 rle with old method : 0.02150726318359375 length of segment : 238 time for calcul the mask position with numpy : 0.004988670349121094 nb_pixel_total : 83226 time to create 1 rle with old method : 0.09431719779968262 length of segment : 452 time for calcul the mask position with numpy : 0.001615762710571289 nb_pixel_total : 27672 time to create 1 rle with old method : 0.031836748123168945 length of segment : 207 time for calcul the mask position with numpy : 0.002378702163696289 nb_pixel_total : 47461 time to create 1 rle with old method : 0.05402231216430664 length of segment : 244 time for calcul the mask position with numpy : 0.0054438114166259766 nb_pixel_total : 280225 time to create 1 rle with new method : 0.013613224029541016 length of segment : 729 time for calcul the mask position with numpy : 0.004573822021484375 nb_pixel_total : 81213 time to create 1 rle with old method : 0.09317970275878906 length of segment : 280 time for calcul the mask position with numpy : 0.0025458335876464844 nb_pixel_total : 48851 time to create 1 rle with old method : 0.056444406509399414 length of segment : 250 time for calcul the mask position with numpy : 0.0017359256744384766 nb_pixel_total : 38366 time to create 1 rle with old method : 0.04352116584777832 length of segment : 232 time for calcul the mask position with numpy : 0.0006220340728759766 nb_pixel_total : 13323 time to create 1 rle with old method : 0.01632976531982422 length of segment : 108 time for calcul the mask position with numpy : 0.004100322723388672 nb_pixel_total : 61864 time to create 1 rle with old method : 0.074615478515625 length of segment : 288 time for calcul the mask position with numpy : 0.0005779266357421875 nb_pixel_total : 6384 time to create 1 rle with old method : 0.008440494537353516 length of segment : 131 time for calcul the mask position with numpy : 0.0012156963348388672 nb_pixel_total : 28516 time to create 1 rle with old method : 0.034673452377319336 length of segment : 198 time for calcul the mask position with numpy : 0.004060268402099609 nb_pixel_total : 92712 time to create 1 rle with old method : 0.10746073722839355 length of segment : 511 time for calcul the mask position with numpy : 0.0007975101470947266 nb_pixel_total : 14024 time to create 1 rle with old method : 0.01627635955810547 length of segment : 248 time for calcul the mask position with numpy : 0.00030493736267089844 nb_pixel_total : 7662 time to create 1 rle with old method : 0.008974313735961914 length of segment : 89 time for calcul the mask position with numpy : 0.01436161994934082 nb_pixel_total : 411999 time to create 1 rle with new method : 0.022521257400512695 length of segment : 1003 time for calcul the mask position with numpy : 0.0009703636169433594 nb_pixel_total : 18524 time to create 1 rle with old method : 0.020766019821166992 length of segment : 233 time for calcul the mask position with numpy : 0.0004603862762451172 nb_pixel_total : 10902 time to create 1 rle with old method : 0.013351678848266602 length of segment : 68 time for calcul the mask position with numpy : 0.0006594657897949219 nb_pixel_total : 11658 time to create 1 rle with old method : 0.013955116271972656 length of segment : 152 time for calcul the mask position with numpy : 0.0006070137023925781 nb_pixel_total : 3643 time to create 1 rle with old method : 0.004349470138549805 length of segment : 120 time for calcul the mask position with numpy : 0.00593113899230957 nb_pixel_total : 175796 time to create 1 rle with new method : 0.007821798324584961 length of segment : 471 time for calcul the mask position with numpy : 0.0007040500640869141 nb_pixel_total : 11557 time to create 1 rle with old method : 0.013683080673217773 length of segment : 106 time for calcul the mask position with numpy : 0.002346038818359375 nb_pixel_total : 91351 time to create 1 rle with old method : 0.10436248779296875 length of segment : 843 time for calcul the mask position with numpy : 0.0028989315032958984 nb_pixel_total : 71621 time to create 1 rle with old method : 0.08101487159729004 length of segment : 290 time for calcul the mask position with numpy : 0.003988981246948242 nb_pixel_total : 120833 time to create 1 rle with old method : 0.13687849044799805 length of segment : 561 time for calcul the mask position with numpy : 0.0005893707275390625 nb_pixel_total : 10381 time to create 1 rle with old method : 0.011841773986816406 length of segment : 185 time for calcul the mask position with numpy : 0.00033926963806152344 nb_pixel_total : 15085 time to create 1 rle with old method : 0.01792764663696289 length of segment : 143 time for calcul the mask position with numpy : 0.0006303787231445312 nb_pixel_total : 12525 time to create 1 rle with old method : 0.014631986618041992 length of segment : 126 time for calcul the mask position with numpy : 0.00044918060302734375 nb_pixel_total : 12686 time to create 1 rle with old method : 0.015144586563110352 length of segment : 75 time for calcul the mask position with numpy : 0.01295781135559082 nb_pixel_total : 313575 time to create 1 rle with new method : 0.018505096435546875 length of segment : 966 time for calcul the mask position with numpy : 0.008636713027954102 nb_pixel_total : 309734 time to create 1 rle with new method : 0.011182308197021484 length of segment : 687 time for calcul the mask position with numpy : 0.007785320281982422 nb_pixel_total : 209955 time to create 1 rle with new method : 0.009823799133300781 length of segment : 474 time for calcul the mask position with numpy : 0.0006113052368164062 nb_pixel_total : 12423 time to create 1 rle with old method : 0.014316082000732422 length of segment : 155 time for calcul the mask position with numpy : 0.0020868778228759766 nb_pixel_total : 55406 time to create 1 rle with old method : 0.06360077857971191 length of segment : 140 time for calcul the mask position with numpy : 0.004413127899169922 nb_pixel_total : 107241 time to create 1 rle with old method : 0.12824010848999023 length of segment : 315 time for calcul the mask position with numpy : 0.0027446746826171875 nb_pixel_total : 87673 time to create 1 rle with old method : 0.1263866424560547 length of segment : 325 time for calcul the mask position with numpy : 0.00556492805480957 nb_pixel_total : 111970 time to create 1 rle with old method : 0.12565279006958008 length of segment : 579 time for calcul the mask position with numpy : 0.0017571449279785156 nb_pixel_total : 35114 time to create 1 rle with old method : 0.044557809829711914 length of segment : 290 time for calcul the mask position with numpy : 0.000347137451171875 nb_pixel_total : 9071 time to create 1 rle with old method : 0.011152982711791992 length of segment : 61 time for calcul the mask position with numpy : 0.002169370651245117 nb_pixel_total : 80944 time to create 1 rle with old method : 0.09300684928894043 length of segment : 321 time for calcul the mask position with numpy : 0.00408482551574707 nb_pixel_total : 149492 time to create 1 rle with old method : 0.20091581344604492 length of segment : 481 time for calcul the mask position with numpy : 0.0003554821014404297 nb_pixel_total : 6526 time to create 1 rle with old method : 0.007612705230712891 length of segment : 123 time for calcul the mask position with numpy : 0.0019567012786865234 nb_pixel_total : 67711 time to create 1 rle with old method : 0.07656455039978027 length of segment : 328 time for calcul the mask position with numpy : 0.006190299987792969 nb_pixel_total : 209466 time to create 1 rle with new method : 0.013677358627319336 length of segment : 508 time for calcul the mask position with numpy : 0.02185225486755371 nb_pixel_total : 785631 time to create 1 rle with new method : 0.06606554985046387 length of segment : 954 time for calcul the mask position with numpy : 0.0005466938018798828 nb_pixel_total : 18540 time to create 1 rle with old method : 0.02109527587890625 length of segment : 172 time for calcul the mask position with numpy : 0.0018489360809326172 nb_pixel_total : 61465 time to create 1 rle with old method : 0.07317590713500977 length of segment : 304 time for calcul the mask position with numpy : 0.0034821033477783203 nb_pixel_total : 171998 time to create 1 rle with new method : 0.005872249603271484 length of segment : 475 time for calcul the mask position with numpy : 0.0001556873321533203 nb_pixel_total : 3393 time to create 1 rle with old method : 0.0044291019439697266 length of segment : 65 time for calcul the mask position with numpy : 0.0014243125915527344 nb_pixel_total : 38306 time to create 1 rle with old method : 0.04747319221496582 length of segment : 255 time for calcul the mask position with numpy : 0.0015206336975097656 nb_pixel_total : 25447 time to create 1 rle with old method : 0.0406339168548584 length of segment : 189 time for calcul the mask position with numpy : 0.00102996826171875 nb_pixel_total : 22844 time to create 1 rle with old method : 0.030072927474975586 length of segment : 172 time for calcul the mask position with numpy : 0.0015392303466796875 nb_pixel_total : 30604 time to create 1 rle with old method : 0.035635948181152344 length of segment : 324 time for calcul the mask position with numpy : 0.002498626708984375 nb_pixel_total : 35721 time to create 1 rle with old method : 0.04705190658569336 length of segment : 249 time for calcul the mask position with numpy : 0.005549430847167969 nb_pixel_total : 150472 time to create 1 rle with new method : 0.006340503692626953 length of segment : 539 time for calcul the mask position with numpy : 0.0041408538818359375 nb_pixel_total : 112599 time to create 1 rle with old method : 0.1618666648864746 length of segment : 331 time for calcul the mask position with numpy : 0.0030472278594970703 nb_pixel_total : 87512 time to create 1 rle with old method : 0.09923076629638672 length of segment : 287 time for calcul the mask position with numpy : 0.0046846866607666016 nb_pixel_total : 63702 time to create 1 rle with old method : 0.07353639602661133 length of segment : 461 time for calcul the mask position with numpy : 0.0015397071838378906 nb_pixel_total : 32163 time to create 1 rle with old method : 0.03719830513000488 length of segment : 245 time for calcul the mask position with numpy : 0.0005555152893066406 nb_pixel_total : 9127 time to create 1 rle with old method : 0.011623382568359375 length of segment : 157 time for calcul the mask position with numpy : 0.003946065902709961 nb_pixel_total : 76950 time to create 1 rle with old method : 0.10177803039550781 length of segment : 374 time for calcul the mask position with numpy : 0.0012383460998535156 nb_pixel_total : 40479 time to create 1 rle with old method : 0.053052425384521484 length of segment : 216 time for calcul the mask position with numpy : 0.018949508666992188 nb_pixel_total : 415678 time to create 1 rle with new method : 0.03912830352783203 length of segment : 768 time for calcul the mask position with numpy : 0.008370637893676758 nb_pixel_total : 254342 time to create 1 rle with new method : 0.010971784591674805 length of segment : 513 time for calcul the mask position with numpy : 0.0034160614013671875 nb_pixel_total : 75830 time to create 1 rle with old method : 0.09162402153015137 length of segment : 511 time for calcul the mask position with numpy : 0.0002453327178955078 nb_pixel_total : 5383 time to create 1 rle with old method : 0.006331205368041992 length of segment : 107 time for calcul the mask position with numpy : 0.0009028911590576172 nb_pixel_total : 23978 time to create 1 rle with old method : 0.03273630142211914 length of segment : 145 time for calcul the mask position with numpy : 0.001584768295288086 nb_pixel_total : 44293 time to create 1 rle with old method : 0.06809329986572266 length of segment : 179 time for calcul the mask position with numpy : 0.00450897216796875 nb_pixel_total : 107551 time to create 1 rle with old method : 0.12080717086791992 length of segment : 308 time for calcul the mask position with numpy : 0.0015935897827148438 nb_pixel_total : 48039 time to create 1 rle with old method : 0.056371450424194336 length of segment : 265 time for calcul the mask position with numpy : 0.0006177425384521484 nb_pixel_total : 17523 time to create 1 rle with old method : 0.020154953002929688 length of segment : 172 time for calcul the mask position with numpy : 0.001013040542602539 nb_pixel_total : 20452 time to create 1 rle with old method : 0.023859500885009766 length of segment : 220 time for calcul the mask position with numpy : 0.0010221004486083984 nb_pixel_total : 14246 time to create 1 rle with old method : 0.016193389892578125 length of segment : 250 time for calcul the mask position with numpy : 0.0009489059448242188 nb_pixel_total : 27853 time to create 1 rle with old method : 0.031983137130737305 length of segment : 231 time for calcul the mask position with numpy : 0.0012195110321044922 nb_pixel_total : 28425 time to create 1 rle with old method : 0.03311347961425781 length of segment : 255 time for calcul the mask position with numpy : 0.002092599868774414 nb_pixel_total : 70059 time to create 1 rle with old method : 0.08038949966430664 length of segment : 350 time for calcul the mask position with numpy : 0.001497507095336914 nb_pixel_total : 58006 time to create 1 rle with old method : 0.07551932334899902 length of segment : 267 time for calcul the mask position with numpy : 0.0022585391998291016 nb_pixel_total : 55516 time to create 1 rle with old method : 0.0628654956817627 length of segment : 332 time for calcul the mask position with numpy : 0.002062082290649414 nb_pixel_total : 62494 time to create 1 rle with old method : 0.07109546661376953 length of segment : 222 time for calcul the mask position with numpy : 0.0003695487976074219 nb_pixel_total : 8509 time to create 1 rle with old method : 0.013070821762084961 length of segment : 112 time for calcul the mask position with numpy : 0.001973867416381836 nb_pixel_total : 74797 time to create 1 rle with old method : 0.09451007843017578 length of segment : 347 time for calcul the mask position with numpy : 0.002165079116821289 nb_pixel_total : 85420 time to create 1 rle with old method : 0.09683465957641602 length of segment : 406 time for calcul the mask position with numpy : 0.0050754547119140625 nb_pixel_total : 91317 time to create 1 rle with old method : 0.1231834888458252 length of segment : 300 time for calcul the mask position with numpy : 0.020632028579711914 nb_pixel_total : 470717 time to create 1 rle with new method : 0.06573271751403809 length of segment : 1013 time for calcul the mask position with numpy : 0.010412216186523438 nb_pixel_total : 187423 time to create 1 rle with new method : 0.019091367721557617 length of segment : 563 time for calcul the mask position with numpy : 0.0006651878356933594 nb_pixel_total : 13035 time to create 1 rle with old method : 0.024252653121948242 length of segment : 145 time for calcul the mask position with numpy : 0.004609346389770508 nb_pixel_total : 100580 time to create 1 rle with old method : 0.2819681167602539 length of segment : 460 time for calcul the mask position with numpy : 0.005104541778564453 nb_pixel_total : 176582 time to create 1 rle with new method : 0.007298707962036133 length of segment : 485 time for calcul the mask position with numpy : 0.02812981605529785 nb_pixel_total : 617261 time to create 1 rle with new method : 0.1199045181274414 length of segment : 1222 time for calcul the mask position with numpy : 0.0026803016662597656 nb_pixel_total : 120751 time to create 1 rle with old method : 0.14702916145324707 length of segment : 409 time for calcul the mask position with numpy : 0.0011205673217773438 nb_pixel_total : 37910 time to create 1 rle with old method : 0.045319318771362305 length of segment : 224 time for calcul the mask position with numpy : 0.010938167572021484 nb_pixel_total : 214574 time to create 1 rle with new method : 0.015449762344360352 length of segment : 557 time for calcul the mask position with numpy : 0.0016083717346191406 nb_pixel_total : 35347 time to create 1 rle with old method : 0.04714155197143555 length of segment : 224 time for calcul the mask position with numpy : 0.004305124282836914 nb_pixel_total : 67724 time to create 1 rle with old method : 0.08531737327575684 length of segment : 301 time for calcul the mask position with numpy : 0.004697561264038086 nb_pixel_total : 100935 time to create 1 rle with old method : 0.115814208984375 length of segment : 358 time for calcul the mask position with numpy : 0.003785848617553711 nb_pixel_total : 69225 time to create 1 rle with old method : 0.07851624488830566 length of segment : 319 time for calcul the mask position with numpy : 0.001375436782836914 nb_pixel_total : 20368 time to create 1 rle with old method : 0.023354291915893555 length of segment : 231 time for calcul the mask position with numpy : 0.004071474075317383 nb_pixel_total : 108716 time to create 1 rle with old method : 0.12338089942932129 length of segment : 494 time for calcul the mask position with numpy : 0.0006198883056640625 nb_pixel_total : 9253 time to create 1 rle with old method : 0.010923147201538086 length of segment : 128 time for calcul the mask position with numpy : 0.0008716583251953125 nb_pixel_total : 19240 time to create 1 rle with old method : 0.02353525161743164 length of segment : 172 time for calcul the mask position with numpy : 0.0005240440368652344 nb_pixel_total : 21252 time to create 1 rle with old method : 0.024674177169799805 length of segment : 149 time for calcul the mask position with numpy : 0.0027594566345214844 nb_pixel_total : 53202 time to create 1 rle with old method : 0.06251955032348633 length of segment : 384 time for calcul the mask position with numpy : 0.005219221115112305 nb_pixel_total : 119481 time to create 1 rle with old method : 0.14903569221496582 length of segment : 227 time for calcul the mask position with numpy : 0.011891841888427734 nb_pixel_total : 247580 time to create 1 rle with new method : 0.5003645420074463 length of segment : 714 time for calcul the mask position with numpy : 0.0017840862274169922 nb_pixel_total : 41779 time to create 1 rle with old method : 0.05033254623413086 length of segment : 186 time for calcul the mask position with numpy : 0.002946615219116211 nb_pixel_total : 55956 time to create 1 rle with old method : 0.06456446647644043 length of segment : 359 time for calcul the mask position with numpy : 0.010006904602050781 nb_pixel_total : 210593 time to create 1 rle with new method : 0.01348733901977539 length of segment : 795 time for calcul the mask position with numpy : 0.0022559165954589844 nb_pixel_total : 30152 time to create 1 rle with old method : 0.03774595260620117 length of segment : 236 time for calcul the mask position with numpy : 0.010398626327514648 nb_pixel_total : 223854 time to create 1 rle with new method : 0.01536250114440918 length of segment : 381 time for calcul the mask position with numpy : 0.0026221275329589844 nb_pixel_total : 85524 time to create 1 rle with old method : 0.10169386863708496 length of segment : 398 time for calcul the mask position with numpy : 0.007554054260253906 nb_pixel_total : 152337 time to create 1 rle with new method : 0.009985923767089844 length of segment : 377 time for calcul the mask position with numpy : 0.0017664432525634766 nb_pixel_total : 50638 time to create 1 rle with old method : 0.05792069435119629 length of segment : 304 time for calcul the mask position with numpy : 0.0029687881469726562 nb_pixel_total : 96349 time to create 1 rle with old method : 0.1328587532043457 length of segment : 428 time for calcul the mask position with numpy : 0.0011181831359863281 nb_pixel_total : 27798 time to create 1 rle with old method : 0.03359699249267578 length of segment : 183 time for calcul the mask position with numpy : 0.002863645553588867 nb_pixel_total : 43331 time to create 1 rle with old method : 0.05010366439819336 length of segment : 517 time for calcul the mask position with numpy : 0.0014100074768066406 nb_pixel_total : 28537 time to create 1 rle with old method : 0.032974958419799805 length of segment : 275 time for calcul the mask position with numpy : 0.00110626220703125 nb_pixel_total : 22074 time to create 1 rle with old method : 0.025745868682861328 length of segment : 270 time for calcul the mask position with numpy : 0.002820730209350586 nb_pixel_total : 67670 time to create 1 rle with old method : 0.08516287803649902 length of segment : 381 time for calcul the mask position with numpy : 0.010848283767700195 nb_pixel_total : 214121 time to create 1 rle with new method : 0.013568878173828125 length of segment : 632 time for calcul the mask position with numpy : 0.0011286735534667969 nb_pixel_total : 27125 time to create 1 rle with old method : 0.038632869720458984 length of segment : 201 time for calcul the mask position with numpy : 0.0014660358428955078 nb_pixel_total : 22506 time to create 1 rle with old method : 0.028219223022460938 length of segment : 273 time for calcul the mask position with numpy : 0.0007090568542480469 nb_pixel_total : 13263 time to create 1 rle with old method : 0.015950918197631836 length of segment : 155 time for calcul the mask position with numpy : 0.004393339157104492 nb_pixel_total : 65463 time to create 1 rle with old method : 0.09231328964233398 length of segment : 316 time for calcul the mask position with numpy : 0.0010113716125488281 nb_pixel_total : 22975 time to create 1 rle with old method : 0.02761077880859375 length of segment : 209 time for calcul the mask position with numpy : 0.0005145072937011719 nb_pixel_total : 9038 time to create 1 rle with old method : 0.01092839241027832 length of segment : 103 time for calcul the mask position with numpy : 0.004119157791137695 nb_pixel_total : 88432 time to create 1 rle with old method : 0.10837268829345703 length of segment : 264 time for calcul the mask position with numpy : 0.005730152130126953 nb_pixel_total : 106041 time to create 1 rle with old method : 0.12795805931091309 length of segment : 367 time for calcul the mask position with numpy : 0.0005710124969482422 nb_pixel_total : 11299 time to create 1 rle with old method : 0.013339042663574219 length of segment : 110 time for calcul the mask position with numpy : 0.001432657241821289 nb_pixel_total : 24534 time to create 1 rle with old method : 0.029094934463500977 length of segment : 191 time for calcul the mask position with numpy : 0.009695768356323242 nb_pixel_total : 204671 time to create 1 rle with new method : 0.014550209045410156 length of segment : 580 time for calcul the mask position with numpy : 0.0023207664489746094 nb_pixel_total : 44240 time to create 1 rle with old method : 0.05240678787231445 length of segment : 271 time for calcul the mask position with numpy : 0.0017468929290771484 nb_pixel_total : 33881 time to create 1 rle with old method : 0.041254520416259766 length of segment : 251 time for calcul the mask position with numpy : 0.0028285980224609375 nb_pixel_total : 57112 time to create 1 rle with old method : 0.0772392749786377 length of segment : 437 time for calcul the mask position with numpy : 0.005776643753051758 nb_pixel_total : 152948 time to create 1 rle with new method : 0.008299827575683594 length of segment : 429 time for calcul the mask position with numpy : 0.0013349056243896484 nb_pixel_total : 7452 time to create 1 rle with old method : 0.009463310241699219 length of segment : 190 time for calcul the mask position with numpy : 0.0009174346923828125 nb_pixel_total : 23597 time to create 1 rle with old method : 0.029880046844482422 length of segment : 182 time for calcul the mask position with numpy : 0.006238222122192383 nb_pixel_total : 115188 time to create 1 rle with old method : 0.15675878524780273 length of segment : 244 time for calcul the mask position with numpy : 0.0025300979614257812 nb_pixel_total : 59129 time to create 1 rle with old method : 0.06779074668884277 length of segment : 420 time for calcul the mask position with numpy : 0.0008747577667236328 nb_pixel_total : 10919 time to create 1 rle with old method : 0.013983011245727539 length of segment : 148 time for calcul the mask position with numpy : 0.005759716033935547 nb_pixel_total : 112457 time to create 1 rle with old method : 0.12754368782043457 length of segment : 586 time for calcul the mask position with numpy : 0.039141178131103516 nb_pixel_total : 556495 time to create 1 rle with new method : 0.18668413162231445 length of segment : 953 time for calcul the mask position with numpy : 0.008536577224731445 nb_pixel_total : 152941 time to create 1 rle with new method : 0.011019468307495117 length of segment : 604 time for calcul the mask position with numpy : 0.0007753372192382812 nb_pixel_total : 13760 time to create 1 rle with old method : 0.015856266021728516 length of segment : 125 time for calcul the mask position with numpy : 0.008158683776855469 nb_pixel_total : 119559 time to create 1 rle with old method : 0.1428990364074707 length of segment : 580 time for calcul the mask position with numpy : 0.0002892017364501953 nb_pixel_total : 4246 time to create 1 rle with old method : 0.005881071090698242 length of segment : 70 time for calcul the mask position with numpy : 0.007351398468017578 nb_pixel_total : 143168 time to create 1 rle with old method : 0.15982604026794434 length of segment : 541 time for calcul the mask position with numpy : 0.005465030670166016 nb_pixel_total : 139540 time to create 1 rle with old method : 0.16038298606872559 length of segment : 371 time for calcul the mask position with numpy : 0.0031309127807617188 nb_pixel_total : 43642 time to create 1 rle with old method : 0.049875497817993164 length of segment : 344 time for calcul the mask position with numpy : 0.001283407211303711 nb_pixel_total : 39283 time to create 1 rle with old method : 0.04463601112365723 length of segment : 292 time for calcul the mask position with numpy : 0.0011875629425048828 nb_pixel_total : 20029 time to create 1 rle with old method : 0.023632526397705078 length of segment : 191 time for calcul the mask position with numpy : 0.0005733966827392578 nb_pixel_total : 9573 time to create 1 rle with old method : 0.01125645637512207 length of segment : 113 time for calcul the mask position with numpy : 0.00033664703369140625 nb_pixel_total : 5930 time to create 1 rle with old method : 0.007244110107421875 length of segment : 101 time for calcul the mask position with numpy : 0.0020847320556640625 nb_pixel_total : 29662 time to create 1 rle with old method : 0.047573089599609375 length of segment : 298 time for calcul the mask position with numpy : 0.0036084651947021484 nb_pixel_total : 85392 time to create 1 rle with old method : 0.09540820121765137 length of segment : 505 time for calcul the mask position with numpy : 0.0030677318572998047 nb_pixel_total : 67572 time to create 1 rle with old method : 0.07623171806335449 length of segment : 341 time for calcul the mask position with numpy : 0.014654159545898438 nb_pixel_total : 16923 time to create 1 rle with old method : 0.028719663619995117 length of segment : 88 time for calcul the mask position with numpy : 0.0007333755493164062 nb_pixel_total : 17328 time to create 1 rle with old method : 0.020534753799438477 length of segment : 113 time for calcul the mask position with numpy : 0.0004992485046386719 nb_pixel_total : 12056 time to create 1 rle with old method : 0.01605510711669922 length of segment : 90 time for calcul the mask position with numpy : 0.003279447555541992 nb_pixel_total : 38451 time to create 1 rle with old method : 0.045264244079589844 length of segment : 273 time for calcul the mask position with numpy : 0.0008604526519775391 nb_pixel_total : 10578 time to create 1 rle with old method : 0.012136459350585938 length of segment : 220 time for calcul the mask position with numpy : 0.0005817413330078125 nb_pixel_total : 7104 time to create 1 rle with old method : 0.008405447006225586 length of segment : 97 time for calcul the mask position with numpy : 0.0013668537139892578 nb_pixel_total : 23760 time to create 1 rle with old method : 0.03022623062133789 length of segment : 165 time for calcul the mask position with numpy : 0.005584716796875 nb_pixel_total : 126327 time to create 1 rle with old method : 0.14497804641723633 length of segment : 228 time for calcul the mask position with numpy : 0.00033020973205566406 nb_pixel_total : 6097 time to create 1 rle with old method : 0.007432699203491211 length of segment : 56 time for calcul the mask position with numpy : 0.002604961395263672 nb_pixel_total : 56098 time to create 1 rle with old method : 0.06288671493530273 length of segment : 295 time for calcul the mask position with numpy : 0.0016376972198486328 nb_pixel_total : 26017 time to create 1 rle with old method : 0.03922414779663086 length of segment : 204 time for calcul the mask position with numpy : 0.0010280609130859375 nb_pixel_total : 10810 time to create 1 rle with old method : 0.012735366821289062 length of segment : 230 time for calcul the mask position with numpy : 0.00017380714416503906 nb_pixel_total : 2500 time to create 1 rle with old method : 0.003247976303100586 length of segment : 46 time for calcul the mask position with numpy : 0.003935337066650391 nb_pixel_total : 67923 time to create 1 rle with old method : 0.0814969539642334 length of segment : 440 time for calcul the mask position with numpy : 0.0022935867309570312 nb_pixel_total : 55266 time to create 1 rle with old method : 0.06624126434326172 length of segment : 304 time spent for convertir_results : 29.592227458953857 Command terminated by signal 15 98.60user 74.79system 5:00.15elapsed 57%CPU (0avgtext+0avgdata 7023024maxresident)k 1746536inputs+54880outputs (13770major+12031267minor)pagefaults 0swaps