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 : 3155342 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 : ['2576664'] with mtr_portfolio_ids : ['20446956'] and first list_photo_ids : [] new path : /proc/3155342/ 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 , BFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 3 ; length of list_pids : 3 ; length of list_args : 3 time to download the photos : 0.43230390548706055 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 Tue Feb 11 16:20:28 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 : 10774 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-11 16:20:31.095377: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-11 16:20:31.123293: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-11 16:20:31.125539: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f1d78000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-11 16:20:31.125600: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-11 16:20:31.129680: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-11 16:20:31.266253: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x10cde200 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-11 16:20:31.266299: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-11 16:20:31.267748: 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 2025-02-11 16:20:31.268144: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 16:20:31.271327: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 16:20:31.274098: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-11 16:20:31.274510: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-11 16:20:31.277445: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-11 16:20:31.278855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-11 16:20:31.283673: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-11 16:20:31.285154: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-11 16:20:31.285226: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 16:20:31.285971: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-11 16:20:31.285986: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-11 16:20:31.285995: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-11 16:20:31.287278: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 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. 2025-02-11 16:20:31.540670: 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 2025-02-11 16:20:31.540763: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 16:20:31.540791: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 16:20:31.540815: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-11 16:20:31.540839: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-11 16:20:31.540863: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-11 16:20:31.540886: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-11 16:20:31.540910: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-11 16:20:31.543030: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-11 16:20:31.544371: 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 2025-02-11 16:20:31.544406: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-11 16:20:31.544422: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 16:20:31.544435: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-11 16:20:31.544449: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-11 16:20:31.544462: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-11 16:20:31.544476: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-11 16:20:31.544490: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-11 16:20:31.545775: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-11 16:20:31.545802: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-11 16:20:31.545811: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-11 16:20:31.545818: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-11 16:20:31.547120: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9985 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 : [] 2025-02-11 16:20:38.265830: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-11 16:20:38.486271: 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 : 3 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: -121.68047 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 0.00017523765563964844 nb_pixel_total : 826 time to create 1 rle with old method : 0.005169868469238281 length of segment : 53 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 328 time to create 1 rle with old method : 0.0004775524139404297 length of segment : 45 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0005269050598144531 length of segment : 22 time for calcul the mask position with numpy : 0.000186920166015625 nb_pixel_total : 1003 time to create 1 rle with old method : 0.0013880729675292969 length of segment : 71 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 1012 time to create 1 rle with old method : 0.006501197814941406 length of segment : 33 time for calcul the mask position with numpy : 0.00013136863708496094 nb_pixel_total : 2021 time to create 1 rle with old method : 0.0033080577850341797 length of segment : 79 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 970 time to create 1 rle with old method : 0.0018680095672607422 length of segment : 24 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0005145072937011719 length of segment : 35 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1572 time to create 1 rle with old method : 0.0021409988403320312 length of segment : 86 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.24297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 15 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00028705596923828125 length of segment : 22 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 168 time to create 1 rle with old method : 0.00022649765014648438 length of segment : 20 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 936 time to create 1 rle with old method : 0.0011789798736572266 length of segment : 62 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00024271011352539062 length of segment : 18 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005509853363037109 length of segment : 43 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00015854835510253906 length of segment : 7 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004029273986816406 length of segment : 15 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 802 time to create 1 rle with old method : 0.0010025501251220703 length of segment : 33 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 1224 time to create 1 rle with old method : 0.001512765884399414 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.50078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 724 time to create 1 rle with old method : 0.0009610652923583984 length of segment : 27 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 505 time to create 1 rle with old method : 0.0006644725799560547 length of segment : 32 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 589 time to create 1 rle with old method : 0.0010499954223632812 length of segment : 39 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 522 time to create 1 rle with old method : 0.0006940364837646484 length of segment : 33 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 2502 time to create 1 rle with old method : 0.003024578094482422 length of segment : 46 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 894 time to create 1 rle with old method : 0.0011553764343261719 length of segment : 39 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 2522 time to create 1 rle with old method : 0.003183126449584961 length of segment : 75 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0005624294281005859 length of segment : 21 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 2742 time to create 1 rle with old method : 0.003332376480102539 length of segment : 65 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.0008244514465332031 length of segment : 31 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1608 time to create 1 rle with old method : 0.0019347667694091797 length of segment : 59 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 1974 time to create 1 rle with old method : 0.002362966537475586 length of segment : 44 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1078 time to create 1 rle with old method : 0.0013802051544189453 length of segment : 72 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0003712177276611328 length of segment : 25 time for calcul the mask position with numpy : 0.00010561943054199219 nb_pixel_total : 3157 time to create 1 rle with old method : 0.0037903785705566406 length of segment : 87 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1604 time to create 1 rle with old method : 0.002031087875366211 length of segment : 54 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 280 time to create 1 rle with old method : 0.00038051605224609375 length of segment : 17 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.32500 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 21 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 949 time to create 1 rle with old method : 0.0011832714080810547 length of segment : 33 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.000698089599609375 length of segment : 37 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 756 time to create 1 rle with old method : 0.0010800361633300781 length of segment : 24 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0005211830139160156 length of segment : 27 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006425380706787109 length of segment : 24 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0005893707275390625 length of segment : 21 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 380 time to create 1 rle with old method : 0.0005517005920410156 length of segment : 20 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004825592041015625 length of segment : 24 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.00022029876708984375 length of segment : 9 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005702972412109375 length of segment : 32 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 507 time to create 1 rle with old method : 0.000682830810546875 length of segment : 30 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0006208419799804688 length of segment : 32 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0003116130828857422 length of segment : 9 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1754 time to create 1 rle with old method : 0.0021789073944091797 length of segment : 41 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.0002090930938720703 length of segment : 7 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 802 time to create 1 rle with old method : 0.0009915828704833984 length of segment : 39 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.00017070770263671875 length of segment : 12 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0007669925689697266 length of segment : 25 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 780 time to create 1 rle with old method : 0.0009684562683105469 length of segment : 37 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0008275508880615234 length of segment : 30 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005304813385009766 length of segment : 23 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.78984 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0003771781921386719 length of segment : 16 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00030875205993652344 length of segment : 15 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0003521442413330078 length of segment : 21 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 2138 time to create 1 rle with old method : 0.0026297569274902344 length of segment : 73 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 132 time to create 1 rle with old method : 0.00022339820861816406 length of segment : 10 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 748 time to create 1 rle with old method : 0.0009288787841796875 length of segment : 35 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.04375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0004966259002685547 nb_pixel_total : 43867 time to create 1 rle with old method : 0.04834413528442383 length of segment : 176 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 304 time to create 1 rle with old method : 0.00040149688720703125 length of segment : 29 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 150 time to create 1 rle with old method : 0.0003311634063720703 length of segment : 15 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 245.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 131.49453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0001506805419921875 nb_pixel_total : 8868 time to create 1 rle with old method : 0.010092496871948242 length of segment : 150 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002810955047607422 length of segment : 44 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 229 time to create 1 rle with old method : 0.00034499168395996094 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.50469 max: 148.97109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 400 time to create 1 rle with old method : 0.0005829334259033203 length of segment : 24 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.00029969215393066406 length of segment : 21 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1657 time to create 1 rle with old method : 0.001950979232788086 length of segment : 51 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 2334 time to create 1 rle with old method : 0.0029449462890625 length of segment : 78 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1812 time to create 1 rle with old method : 0.0020933151245117188 length of segment : 86 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00031256675720214844 length of segment : 21 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1655 time to create 1 rle with old method : 0.0019519329071044922 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.70391 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0004909038543701172 length of segment : 40 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 317 time to create 1 rle with old method : 0.0004012584686279297 length of segment : 26 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 158 time to create 1 rle with old method : 0.00025177001953125 length of segment : 28 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 2646 time to create 1 rle with old method : 0.003134012222290039 length of segment : 82 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00031304359436035156 length of segment : 16 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 467 time to create 1 rle with old method : 0.0006282329559326172 length of segment : 16 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.0002124309539794922 length of segment : 21 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005998611450195312 length of segment : 35 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0005807876586914062 length of segment : 21 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0007066726684570312 length of segment : 33 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 100 time to create 1 rle with old method : 0.00016069412231445312 length of segment : 11 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00016236305236816406 length of segment : 18 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.00069427490234375 length of segment : 25 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0002410411834716797 length of segment : 15 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 880 time to create 1 rle with old method : 0.0011000633239746094 length of segment : 37 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 393 time to create 1 rle with old method : 0.000537872314453125 length of segment : 21 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 915 time to create 1 rle with old method : 0.0011229515075683594 length of segment : 70 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.25078 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 25 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 823 time to create 1 rle with old method : 0.0010600090026855469 length of segment : 38 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1438 time to create 1 rle with old method : 0.0018067359924316406 length of segment : 41 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1582 time to create 1 rle with old method : 0.0019211769104003906 length of segment : 63 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 794 time to create 1 rle with old method : 0.0009913444519042969 length of segment : 41 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0005075931549072266 length of segment : 29 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0009067058563232422 length of segment : 25 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 773 time to create 1 rle with old method : 0.0010242462158203125 length of segment : 42 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 494 time to create 1 rle with old method : 0.0007300376892089844 length of segment : 32 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0003712177276611328 length of segment : 16 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 571 time to create 1 rle with old method : 0.0007371902465820312 length of segment : 35 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002970695495605469 length of segment : 13 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002911090850830078 length of segment : 26 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 2133 time to create 1 rle with old method : 0.0026438236236572266 length of segment : 64 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003402233123779297 length of segment : 20 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.001302957534790039 length of segment : 32 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0006971359252929688 length of segment : 21 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1760 time to create 1 rle with old method : 0.002071380615234375 length of segment : 71 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 1064 time to create 1 rle with old method : 0.0014019012451171875 length of segment : 33 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1041 time to create 1 rle with old method : 0.0012788772583007812 length of segment : 67 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.0001773834228515625 length of segment : 17 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005412101745605469 length of segment : 23 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0002789497375488281 length of segment : 16 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 128 time to create 1 rle with old method : 0.0002129077911376953 length of segment : 15 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 762 time to create 1 rle with old method : 0.0009818077087402344 length of segment : 48 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00016927719116210938 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.27813 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 29 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 4388 time to create 1 rle with old method : 0.005172252655029297 length of segment : 62 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 199 time to create 1 rle with old method : 0.0002646446228027344 length of segment : 24 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 163 time to create 1 rle with old method : 0.0002219676971435547 length of segment : 20 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003287792205810547 length of segment : 15 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0006976127624511719 length of segment : 42 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 459 time to create 1 rle with old method : 0.0006084442138671875 length of segment : 24 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 172 time to create 1 rle with old method : 0.00025916099548339844 length of segment : 18 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005617141723632812 length of segment : 22 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 3525 time to create 1 rle with old method : 0.00413823127746582 length of segment : 65 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1787 time to create 1 rle with old method : 0.002121448516845703 length of segment : 39 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 984 time to create 1 rle with old method : 0.0012302398681640625 length of segment : 49 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0003113746643066406 length of segment : 15 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00034332275390625 length of segment : 18 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0008363723754882812 length of segment : 33 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 713 time to create 1 rle with old method : 0.0008821487426757812 length of segment : 33 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 730 time to create 1 rle with old method : 0.0009024143218994141 length of segment : 30 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.0005352497100830078 length of segment : 24 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 509 time to create 1 rle with old method : 0.0006644725799560547 length of segment : 28 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00040340423583984375 length of segment : 25 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 506 time to create 1 rle with old method : 0.0006890296936035156 length of segment : 22 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 300 time to create 1 rle with old method : 0.000396728515625 length of segment : 23 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.00045490264892578125 length of segment : 23 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00011658668518066406 length of segment : 13 time for calcul the mask position with numpy : 0.0001327991485595703 nb_pixel_total : 5070 time to create 1 rle with old method : 0.005879402160644531 length of segment : 89 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 693 time to create 1 rle with old method : 0.0009071826934814453 length of segment : 32 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 1206 time to create 1 rle with old method : 0.001463174819946289 length of segment : 40 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1034 time to create 1 rle with old method : 0.001295328140258789 length of segment : 48 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002846717834472656 length of segment : 27 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 336 time to create 1 rle with old method : 0.00045180320739746094 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.16484 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.000591278076171875 length of segment : 55 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1698 time to create 1 rle with old method : 0.0023627281188964844 length of segment : 70 time for calcul the mask position with numpy : 0.00017952919006347656 nb_pixel_total : 740 time to create 1 rle with old method : 0.0012996196746826172 length of segment : 76 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.0004420280456542969 length of segment : 16 time for calcul the mask position with numpy : 0.00011181831359863281 nb_pixel_total : 900 time to create 1 rle with old method : 0.0015871524810791016 length of segment : 36 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.0004913806915283203 length of segment : 16 time for calcul the mask position with numpy : 7.867813110351562e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0008397102355957031 length of segment : 27 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0009138584136962891 length of segment : 43 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 632 time to create 1 rle with old method : 0.0011513233184814453 length of segment : 32 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.0004596710205078125 length of segment : 26 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 176 time to create 1 rle with old method : 0.000370025634765625 length of segment : 17 time for calcul the mask position with numpy : 0.0001819133758544922 nb_pixel_total : 1530 time to create 1 rle with old method : 0.002541065216064453 length of segment : 89 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.0002579689025878906 length of segment : 11 time for calcul the mask position with numpy : 8.177757263183594e-05 nb_pixel_total : 615 time to create 1 rle with old method : 0.0011181831359863281 length of segment : 31 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 177 time to create 1 rle with old method : 0.0002684593200683594 length of segment : 16 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 482 time to create 1 rle with old method : 0.0006434917449951172 length of segment : 22 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.0003597736358642578 length of segment : 28 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.00032401084899902344 length of segment : 16 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 373 time to create 1 rle with old method : 0.0005037784576416016 length of segment : 22 time for calcul the mask position with numpy : 0.00011539459228515625 nb_pixel_total : 2763 time to create 1 rle with old method : 0.003223419189453125 length of segment : 53 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.62969 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00041985511779785156 length of segment : 21 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 325 time to create 1 rle with old method : 0.0004875659942626953 length of segment : 16 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0007476806640625 length of segment : 37 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 5332 time to create 1 rle with old method : 0.006240367889404297 length of segment : 82 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006725788116455078 length of segment : 31 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 641 time to create 1 rle with old method : 0.0008213520050048828 length of segment : 25 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1235 time to create 1 rle with old method : 0.00153350830078125 length of segment : 32 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 331 time to create 1 rle with old method : 0.0004870891571044922 length of segment : 18 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 758 time to create 1 rle with old method : 0.0010113716125488281 length of segment : 36 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 770 time to create 1 rle with old method : 0.0009355545043945312 length of segment : 40 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 544 time to create 1 rle with old method : 0.0006952285766601562 length of segment : 32 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1302 time to create 1 rle with old method : 0.0016155242919921875 length of segment : 32 time for calcul the mask position with numpy : 3.0517578125e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.00012612342834472656 length of segment : 18 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 2215 time to create 1 rle with old method : 0.002593517303466797 length of segment : 74 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 654 time to create 1 rle with old method : 0.0008561611175537109 length of segment : 27 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 774 time to create 1 rle with old method : 0.0010535717010498047 length of segment : 35 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.00045561790466308594 length of segment : 37 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.0001862049102783203 length of segment : 11 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.00027251243591308594 length of segment : 29 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.0001366138458251953 length of segment : 10 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 148 time to create 1 rle with old method : 0.00021576881408691406 length of segment : 17 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.00030517578125 length of segment : 31 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0006825923919677734 length of segment : 44 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0005125999450683594 length of segment : 22 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0006277561187744141 length of segment : 34 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0003001689910888672 length of segment : 15 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 351 time to create 1 rle with old method : 0.0004832744598388672 length of segment : 21 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1474 time to create 1 rle with old method : 0.0018050670623779297 length of segment : 64 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.99297 max: 150.39687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.21953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 940 time to create 1 rle with old method : 0.0011982917785644531 length of segment : 31 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.0003333091735839844 length of segment : 19 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 596 time to create 1 rle with old method : 0.0007853507995605469 length of segment : 34 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 5539 time to create 1 rle with old method : 0.0062749385833740234 length of segment : 105 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 159 time to create 1 rle with old method : 0.0002582073211669922 length of segment : 11 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1093 time to create 1 rle with old method : 0.001363992691040039 length of segment : 33 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007128715515136719 length of segment : 30 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 381 time to create 1 rle with old method : 0.0004894733428955078 length of segment : 42 2025-02-11 16:20:44.392643: E tensorflow/stream_executor/cuda/cuda_driver.cc:939] could not synchronize on CUDA context: CUDA_ERROR_ILLEGAL_INSTRUCTION: an illegal instruction was encountered :: *** Begin stack trace *** tensorflow::CurrentStackTrace() stream_executor::gpu::GpuDriver::SynchronizeContext(stream_executor::gpu::GpuContext*) stream_executor::StreamExecutor::SynchronizeAllActivity() tensorflow::GPUUtil::SyncAll(tensorflow::Device*) tensorflow::BaseGPUDevice::Sync() tensorflow::TensorHandle::CopyToDevice(tensorflow::EagerContext const&, tensorflow::Device*, tensorflow::Tensor*) tensorflow::TensorHandleInterface::Resolve(tensorflow::Status*) TFE_TensorHandleResolve _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall PyObject_Call _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyObject_MakeTpCall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName _PyFunction_Vectorcall _PyEval_EvalFrameDefault _PyEval_EvalCodeWithName PyEval_EvalCode PyRun_SimpleFileExFlags Py_RunMain Py_BytesMain __libc_start_main _start *** End stack trace *** 2025-02-11 16:20:44.433795: E tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:725] failed to record completion event; therefore, failed to create inter-stream dependency 2025-02-11 16:20:44.433864: I tensorflow/stream_executor/stream.cc:4938] [stream=0x11226bc0,impl=0x112256a0] did not memcpy host-to-device; source: 0x3b596580 2025-02-11 16:20:44.433875: E tensorflow/stream_executor/stream.cc:334] Error recording event in stream: Error recording CUDA event: CUDA_ERROR_ILLEGAL_INSTRUCTION: an illegal instruction was encountered; not marking stream as bad, as the Event object may be at fault. Monitor for further errors. 2025-02-11 16:20:44.433891: E tensorflow/stream_executor/cuda/cuda_event.cc:29] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_INSTRUCTION: an illegal instruction was encountered 2025-02-11 16:20:44.433900: F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:273] Unexpected Event status: 1 max_time_sub_proc : 3600 Catched exception ! Connect or reconnect ! in case -12 caffe_path_current : About to save ! 2 After save, about to update current ! 15.09user 9.84system 1:00:05elapsed 0%CPU (0avgtext+0avgdata 2491664maxresident)k 118256inputs+4088outputs (10740major+662723minor)pagefaults 0swaps