python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 10 -a ' -a 4234 -l 5 ' -s datou_current_4234 -M 0 -S 0 -U 95,95,80 import MySQLdb succeeded Import error (python version) ['/Users/moilerat/Documents/Fotonower/install/caffe/distribute/python', '/home/admin/workarea/git/Velours/python/prod', '/home/admin/workarea/install/caffe_cuda8_python3/python', '/home/admin/workarea/install/darknet', '/home/admin/workarea/git/Velours/python', '/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python', '/home/admin/mtr/.credentials', '/home/admin/workarea/install/caffe/python', '/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools', '/home/admin/workarea/git/fotonowerpip', '/home/admin/workarea/install/segment-anything', '/home/admin/workarea/git/pyfvs', '/usr/lib/python38.zip', '/usr/lib/python3.8', '/usr/lib/python3.8/lib-dynload', '/home/admin/.local/lib/python3.8/site-packages', '/usr/local/lib/python3.8/dist-packages', '/usr/lib/python3/dist-packages'] process id : 725812 load datou : 4234 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5561, 'learn_rubbia_refus_2500', 2048, 2048, 'learn_rubbia_refus_2500', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2021, 12, 2, 19, 10, 8), datetime.datetime(2021, 12, 2, 19, 10, 8)) load thcls load THCL from format json or kwargs add thcl : 2847 in CacheModelConfig load THCL from format json or kwargs add thcl : 3237 in CacheModelConfig load pdts add pdt : 5275 in CacheModelConfig add pdt : 5561 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2537544'] with mtr_portfolio_ids : ['20142068'] and first list_photo_ids : [] new path : /proc/725812/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.26482629776000977 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Sat Feb 1 15:20:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-01 15:20:31.102721: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-01 15:20:31.127617: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493020000 Hz 2025-02-01 15:20:31.129113: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f50c0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-01 15:20:31.129165: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-01 15:20:31.132203: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-01 15:20:31.436302: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xbcef7b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-01 15:20:31.436367: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-01 15:20:31.437823: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-01 15:20:31.438252: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 15:20:31.441673: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 15:20:31.444740: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 15:20:31.445051: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 15:20:31.447268: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 15:20:31.448308: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 15:20:31.452624: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 15:20:31.454054: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 15:20:31.454126: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 15:20:31.454865: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-01 15:20:31.454880: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-01 15:20:31.454889: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-01 15:20:31.456202: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-02-01 15:20:31.709627: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-01 15:20:31.709732: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 15:20:31.709759: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 15:20:31.709785: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 15:20:31.709810: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 15:20:31.709833: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 15:20:31.709858: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 15:20:31.709883: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 15:20:31.711600: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 15:20:31.713066: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-02-01 15:20:31.713131: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-01 15:20:31.713158: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 15:20:31.713182: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-01 15:20:31.713207: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-01 15:20:31.713232: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-01 15:20:31.713257: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-01 15:20:31.713282: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-01 15:20:31.715063: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-01 15:20:31.715101: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-01 15:20:31.715112: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-01 15:20:31.715123: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-01 15:20:31.717007: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-01 15:20:38.758070: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-01 15:20:38.946803: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 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 : 2 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.95781 max: 147.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0009322166442871094 length of segment : 27 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 89 time to create 1 rle with old method : 0.0001938343048095703 length of segment : 22 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 912 time to create 1 rle with old method : 0.0017161369323730469 length of segment : 36 time for calcul the mask position with numpy : 0.0003437995910644531 nb_pixel_total : 13087 time to create 1 rle with old method : 0.02237868309020996 length of segment : 175 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.0001430511474609375 length of segment : 28 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 786 time to create 1 rle with old method : 0.0010263919830322266 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.02813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 2638 time to create 1 rle with old method : 0.003828287124633789 length of segment : 55 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1033 time to create 1 rle with old method : 0.0012879371643066406 length of segment : 44 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 329 time to create 1 rle with old method : 0.000438690185546875 length of segment : 30 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 1015 time to create 1 rle with old method : 0.0012340545654296875 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.76641 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.00011682510375976562 nb_pixel_total : 5195 time to create 1 rle with old method : 0.006513118743896484 length of segment : 139 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.00078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003781318664550781 length of segment : 18 time for calcul the mask position with numpy : 0.00013303756713867188 nb_pixel_total : 7273 time to create 1 rle with old method : 0.008972644805908203 length of segment : 100 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.0004456043243408203 length of segment : 23 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.001956462860107422 length of segment : 58 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0005519390106201172 length of segment : 21 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 184 time to create 1 rle with old method : 0.00035500526428222656 length of segment : 17 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0004870891571044922 length of segment : 20 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 840 time to create 1 rle with old method : 0.0016162395477294922 length of segment : 45 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 246.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 121.91641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 485 time to create 1 rle with old method : 0.002424955368041992 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 197.00000 molded_images shape: (1, 640, 640, 3) min: -90.59063 max: 67.30547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013995170593261719 nb_pixel_total : 154751 time to create 1 rle with new method : 0.002002716064453125 length of segment : 405 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.49297 max: 150.85391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 429 time to create 1 rle with old method : 0.0008985996246337891 length of segment : 24 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002880096435546875 length of segment : 13 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 1373 time to create 1 rle with old method : 0.002602815628051758 length of segment : 46 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.000316619873046875 length of segment : 19 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 253 time to create 1 rle with old method : 0.0003921985626220703 length of segment : 15 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003180503845214844 length of segment : 19 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0008871555328369141 length of segment : 44 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 1252 time to create 1 rle with old method : 0.0014679431915283203 length of segment : 45 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005698204040527344 length of segment : 25 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 1298 time to create 1 rle with old method : 0.0016009807586669922 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.88750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0006740093231201172 length of segment : 16 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 77 time to create 1 rle with old method : 0.0001385211944580078 length of segment : 12 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.00024819374084472656 length of segment : 17 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002911090850830078 length of segment : 20 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0007491111755371094 length of segment : 16 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.000186920166015625 length of segment : 17 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0008978843688964844 length of segment : 32 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 730 time to create 1 rle with old method : 0.0009272098541259766 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.31328 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0003058910369873047 length of segment : 18 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0007119178771972656 length of segment : 27 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 954 time to create 1 rle with old method : 0.0013246536254882812 length of segment : 26 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0008714199066162109 length of segment : 25 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 1153 time to create 1 rle with old method : 0.0014140605926513672 length of segment : 38 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 726 time to create 1 rle with old method : 0.0010364055633544922 length of segment : 26 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 1295 time to create 1 rle with old method : 0.001558065414428711 length of segment : 40 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.02187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 3207 time to create 1 rle with old method : 0.003752470016479492 length of segment : 125 time for calcul the mask position with numpy : 0.00014519691467285156 nb_pixel_total : 2584 time to create 1 rle with old method : 0.004414558410644531 length of segment : 153 time for calcul the mask position with numpy : 0.00011730194091796875 nb_pixel_total : 2796 time to create 1 rle with old method : 0.006409406661987305 length of segment : 129 time for calcul the mask position with numpy : 8.96453857421875e-05 nb_pixel_total : 689 time to create 1 rle with old method : 0.0012240409851074219 length of segment : 30 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 1652 time to create 1 rle with old method : 0.002912282943725586 length of segment : 80 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0008862018585205078 length of segment : 43 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004563331604003906 length of segment : 31 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.00043082237243652344 length of segment : 30 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1617 time to create 1 rle with old method : 0.0019083023071289062 length of segment : 81 time for calcul the mask position with numpy : 0.00016570091247558594 nb_pixel_total : 2991 time to create 1 rle with old method : 0.003488779067993164 length of segment : 197 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0009274482727050781 length of segment : 42 Processing 1 images image shape: (280, 400, 3) min: 6.00000 max: 182.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 64.75234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 539 time to create 1 rle with old method : 0.0007236003875732422 length of segment : 49 time for calcul the mask position with numpy : 0.00106048583984375 nb_pixel_total : 105946 time to create 1 rle with old method : 0.14267587661743164 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.99844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1629 time to create 1 rle with old method : 0.0019350051879882812 length of segment : 89 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00018095970153808594 length of segment : 13 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.0002110004425048828 length of segment : 14 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.0002646446228027344 length of segment : 13 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.00035500526428222656 length of segment : 19 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0004849433898925781 length of segment : 33 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0005841255187988281 length of segment : 40 time for calcul the mask position with numpy : 7.987022399902344e-05 nb_pixel_total : 1835 time to create 1 rle with old method : 0.0022699832916259766 length of segment : 82 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0003681182861328125 length of segment : 13 time for calcul the mask position with numpy : 7.486343383789062e-05 nb_pixel_total : 2483 time to create 1 rle with old method : 0.002953767776489258 length of segment : 103 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006055831909179688 length of segment : 31 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1935 time to create 1 rle with old method : 0.002405405044555664 length of segment : 79 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003197193145751953 length of segment : 19 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 51 time for calcul the mask position with numpy : 0.0001201629638671875 nb_pixel_total : 495 time to create 1 rle with old method : 0.0011150836944580078 length of segment : 28 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0009317398071289062 length of segment : 25 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0002994537353515625 length of segment : 21 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0007259845733642578 length of segment : 25 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00018143653869628906 length of segment : 14 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00019431114196777344 length of segment : 14 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00032138824462890625 length of segment : 21 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 455 time to create 1 rle with old method : 0.0006251335144042969 length of segment : 18 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0003535747528076172 length of segment : 17 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.000213623046875 length of segment : 23 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.000255584716796875 length of segment : 19 time for calcul the mask position with numpy : 7.915496826171875e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0008857250213623047 length of segment : 45 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1160 time to create 1 rle with old method : 0.0013897418975830078 length of segment : 29 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.00046896934509277344 length of segment : 36 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.00041794776916503906 length of segment : 21 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 349 time to create 1 rle with old method : 0.0004923343658447266 length of segment : 33 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003554821014404297 length of segment : 13 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.00020503997802734375 length of segment : 17 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 886 time to create 1 rle with old method : 0.0010211467742919922 length of segment : 42 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 20 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0007805824279785156 length of segment : 34 time for calcul the mask position with numpy : 2.6941299438476562e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.00010824203491210938 length of segment : 9 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0004563331604003906 length of segment : 37 time for calcul the mask position with numpy : 2.7418136596679688e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00011515617370605469 length of segment : 11 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 697 time to create 1 rle with old method : 0.0008654594421386719 length of segment : 37 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00019979476928710938 length of segment : 14 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 742 time to create 1 rle with old method : 0.0008711814880371094 length of segment : 34 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007717609405517578 length of segment : 25 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 119 time to create 1 rle with old method : 0.00018405914306640625 length of segment : 13 time for calcul the mask position with numpy : 2.86102294921875e-05 nb_pixel_total : 51 time to create 1 rle with old method : 8.940696716308594e-05 length of segment : 8 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006759166717529297 length of segment : 26 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.00021839141845703125 length of segment : 14 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1326 time to create 1 rle with old method : 0.0015857219696044922 length of segment : 73 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00018739700317382812 length of segment : 9 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.00017404556274414062 length of segment : 12 time for calcul the mask position with numpy : 7.891654968261719e-05 nb_pixel_total : 1837 time to create 1 rle with old method : 0.0021126270294189453 length of segment : 44 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006511211395263672 length of segment : 28 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0005714893341064453 length of segment : 21 time for calcul the mask position with numpy : 7.534027099609375e-05 nb_pixel_total : 632 time to create 1 rle with old method : 0.001348257064819336 length of segment : 59 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0004153251647949219 length of segment : 16 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00018930435180664062 length of segment : 5 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 93 time to create 1 rle with old method : 0.0001938343048095703 length of segment : 9 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00015234947204589844 length of segment : 9 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006201267242431641 length of segment : 24 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.00019216537475585938 length of segment : 17 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 1822 time to create 1 rle with old method : 0.0021703243255615234 length of segment : 45 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.00032591819763183594 length of segment : 17 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 408 time to create 1 rle with old method : 0.0004966259002685547 length of segment : 23 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.00016641616821289062 length of segment : 12 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.00045299530029296875 length of segment : 22 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 385 time to create 1 rle with old method : 0.0005025863647460938 length of segment : 25 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.49453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003376007080078125 length of segment : 18 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 40 time to create 1 rle with old method : 0.00010156631469726562 length of segment : 20 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0002913475036621094 length of segment : 15 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 3024 time to create 1 rle with old method : 0.0034868717193603516 length of segment : 87 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00046539306640625 length of segment : 18 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 604 time to create 1 rle with old method : 0.0007569789886474609 length of segment : 47 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 744 time to create 1 rle with old method : 0.00095367431640625 length of segment : 61 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002944469451904297 length of segment : 14 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 319 time to create 1 rle with old method : 0.00044918060302734375 length of segment : 22 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 1203 time to create 1 rle with old method : 0.0017185211181640625 length of segment : 48 time for calcul the mask position with numpy : 0.00011157989501953125 nb_pixel_total : 2551 time to create 1 rle with old method : 0.003171682357788086 length of segment : 135 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 2823 time to create 1 rle with old method : 0.0033919811248779297 length of segment : 71 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 139.53750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.00037217140197753906 length of segment : 26 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 56 time to create 1 rle with old method : 0.00011491775512695312 length of segment : 9 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 1986 time to create 1 rle with old method : 0.002514362335205078 length of segment : 136 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.00048661231994628906 length of segment : 33 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 185 time to create 1 rle with old method : 0.0002644062042236328 length of segment : 17 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003800392150878906 length of segment : 45 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 263 time to create 1 rle with old method : 0.00036978721618652344 length of segment : 24 time for calcul the mask position with numpy : 2.8371810913085938e-05 nb_pixel_total : 15 time to create 1 rle with old method : 4.506111145019531e-05 length of segment : 3 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 252 time to create 1 rle with old method : 0.000347137451171875 length of segment : 23 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00032711029052734375 length of segment : 25 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.24688 max: 147.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 472 time to create 1 rle with old method : 0.0006020069122314453 length of segment : 28 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.000179290771484375 length of segment : 30 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 858 time to create 1 rle with old method : 0.001066446304321289 length of segment : 39 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001506805419921875 length of segment : 23 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1657 time to create 1 rle with old method : 0.002172231674194336 length of segment : 52 time for calcul the mask position with numpy : 0.00023818016052246094 nb_pixel_total : 9305 time to create 1 rle with old method : 0.010950565338134766 length of segment : 172 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 96 time to create 1 rle with old method : 0.00015044212341308594 length of segment : 27 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007581710815429688 length of segment : 50 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 718 time to create 1 rle with old method : 0.0009317398071289062 length of segment : 36 time for calcul the mask position with numpy : 2.6941299438476562e-05 nb_pixel_total : 1 time to create 1 rle with old method : 1.5974044799804688e-05 length of segment : 1 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 2025-02-01 15:20:45.457543: F tensorflow/core/kernels/bias_op_gpu.cu.cc:97] Non-OK-status: GpuLaunchKernel(BiasNCHWKernel, config.block_count, config.thread_per_block, 0, d.stream(), config.virtual_thread_count, input, bias, output, bias_size, image_size) status: Internal: an illegal memory access was encountered Command terminated by signal 15 1.13user 0.51system 12:00.43elapsed 0%CPU (0avgtext+0avgdata 100220maxresident)k 0inputs+1104outputs (0major+39753minor)pagefaults 0swaps