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 : 3389144 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 : ['2568534'] with mtr_portfolio_ids : ['20359221'] and first list_photo_ids : [] new path : /proc/3389144/ 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 : 0.4578413963317871 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 8 10:20:26 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 : 10332 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-08 10:20:29.367868: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-08 10:20:29.395123: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-08 10:20:29.397076: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fc888000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-08 10:20:29.397137: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-08 10:20:29.400551: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-08 10:20:29.643161: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x30bc8ca0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-08 10:20:29.643229: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-08 10:20:29.644319: 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 2025-02-08 10:20:29.644685: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-08 10:20:29.646615: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-08 10:20:29.648918: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-08 10:20:29.649224: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-08 10:20:29.652706: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-08 10:20:29.653803: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-08 10:20:29.658929: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-08 10:20:29.660501: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-08 10:20:29.660586: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-08 10:20:29.661389: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-08 10:20:29.661407: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-08 10:20:29.661417: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-08 10:20:29.662733: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9777 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. 2025-02-08 10:20:29.942119: 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 2025-02-08 10:20:29.942292: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-08 10:20:29.942324: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-08 10:20:29.942350: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-08 10:20:29.942375: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-08 10:20:29.942398: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-08 10:20:29.942423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-08 10:20:29.942449: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-08 10:20:29.944592: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-08 10:20:29.950556: 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 2025-02-08 10:20:29.950717: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-08 10:20:29.950768: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-08 10:20:29.950813: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-08 10:20:29.950856: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-08 10:20:29.950917: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-08 10:20:29.950964: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-08 10:20:29.951008: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-08 10:20:29.954494: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-08 10:20:29.954635: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-08 10:20:29.954680: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-08 10:20:29.954717: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-08 10:20:29.957573: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9777 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 : [] 2025-02-08 10:20:36.591778: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-08 10:20:36.744636: 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: 34.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -75.52813 max: 148.12734 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 0.00012803077697753906 nb_pixel_total : 792 time to create 1 rle with old method : 0.001669168472290039 length of segment : 27 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.0005283355712890625 length of segment : 23 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 1373 time to create 1 rle with old method : 0.002462148666381836 length of segment : 57 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0008490085601806641 length of segment : 23 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.001264810562133789 length of segment : 40 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 310 time to create 1 rle with old method : 0.0006084442138671875 length of segment : 25 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0007350444793701172 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 47.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -71.98906 max: 150.72891 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 9.965896606445312e-05 nb_pixel_total : 1916 time to create 1 rle with old method : 0.002413034439086914 length of segment : 68 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 2440 time to create 1 rle with old method : 0.0030448436737060547 length of segment : 53 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003178119659423828 length of segment : 20 time for calcul the mask position with numpy : 7.557868957519531e-05 nb_pixel_total : 2771 time to create 1 rle with old method : 0.0033986568450927734 length of segment : 71 time for calcul the mask position with numpy : 0.0002474784851074219 nb_pixel_total : 16005 time to create 1 rle with old method : 0.01868581771850586 length of segment : 136 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.000408172607421875 length of segment : 54 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1529 time to create 1 rle with old method : 0.0018606185913085938 length of segment : 46 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 2146 time to create 1 rle with old method : 0.0027208328247070312 length of segment : 38 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0007071495056152344 length of segment : 32 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.00048828125 length of segment : 17 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 242 time to create 1 rle with old method : 0.0003509521484375 length of segment : 31 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 368 time to create 1 rle with old method : 0.0006194114685058594 length of segment : 20 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 64 time to create 1 rle with old method : 0.0001468658447265625 length of segment : 8 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 2016 time to create 1 rle with old method : 0.0025207996368408203 length of segment : 64 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1849 time to create 1 rle with old method : 0.002359151840209961 length of segment : 40 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0006687641143798828 length of segment : 47 time for calcul the mask position with numpy : 7.677078247070312e-05 nb_pixel_total : 2258 time to create 1 rle with old method : 0.0027391910552978516 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 45.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -70.75859 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 : 5.888938903808594e-05 nb_pixel_total : 1403 time to create 1 rle with old method : 0.0018513202667236328 length of segment : 32 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1091 time to create 1 rle with old method : 0.0014483928680419922 length of segment : 42 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 243 time to create 1 rle with old method : 0.0003631114959716797 length of segment : 18 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 463 time to create 1 rle with old method : 0.0006215572357177734 length of segment : 23 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 134 time to create 1 rle with old method : 0.00022602081298828125 length of segment : 11 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005950927734375 length of segment : 26 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 2073 time to create 1 rle with old method : 0.002460002899169922 length of segment : 63 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00014090538024902344 length of segment : 19 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 200 time to create 1 rle with old method : 0.0003070831298828125 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 11.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -86.91094 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1469 time to create 1 rle with old method : 0.0019023418426513672 length of segment : 46 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006930828094482422 length of segment : 23 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.00039768218994140625 length of segment : 22 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 1088 time to create 1 rle with old method : 0.0014545917510986328 length of segment : 31 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 924 time to create 1 rle with old method : 0.001104593276977539 length of segment : 39 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 657 time to create 1 rle with old method : 0.0008356571197509766 length of segment : 40 time for calcul the mask position with numpy : 0.00011396408081054688 nb_pixel_total : 5520 time to create 1 rle with old method : 0.006608247756958008 length of segment : 85 time for calcul the mask position with numpy : 0.0004076957702636719 nb_pixel_total : 24854 time to create 1 rle with old method : 0.03195977210998535 length of segment : 170 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0004703998565673828 length of segment : 29 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1043 time to create 1 rle with old method : 0.0013298988342285156 length of segment : 40 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 705 time to create 1 rle with old method : 0.0009491443634033203 length of segment : 27 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00041484832763671875 length of segment : 17 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.0001990795135498047 length of segment : 17 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0007011890411376953 length of segment : 52 time for calcul the mask position with numpy : 6.079673767089844e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0005085468292236328 length of segment : 29 time for calcul the mask position with numpy : 0.00015044212341308594 nb_pixel_total : 8350 time to create 1 rle with old method : 0.009173393249511719 length of segment : 96 time for calcul the mask position with numpy : 0.00032973289489746094 nb_pixel_total : 20656 time to create 1 rle with old method : 0.022831201553344727 length of segment : 206 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0014500617980957031 length of segment : 51 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 967 time to create 1 rle with old method : 0.001317739486694336 length of segment : 31 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1152 time to create 1 rle with old method : 0.0015654563903808594 length of segment : 69 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1326 time to create 1 rle with old method : 0.0017437934875488281 length of segment : 41 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1343 time to create 1 rle with old method : 0.0016336441040039062 length of segment : 34 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.50078 max: 150.60781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1053 time to create 1 rle with old method : 0.0014760494232177734 length of segment : 40 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 745 time to create 1 rle with old method : 0.0009944438934326172 length of segment : 33 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006542205810546875 length of segment : 25 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 483 time to create 1 rle with old method : 0.0006909370422363281 length of segment : 27 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 321 time to create 1 rle with old method : 0.0003955364227294922 length of segment : 31 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1535 time to create 1 rle with old method : 0.0019168853759765625 length of segment : 49 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002193450927734375 length of segment : 17 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 339 time to create 1 rle with old method : 0.00044798851013183594 length of segment : 28 time for calcul the mask position with numpy : 0.00018262863159179688 nb_pixel_total : 11557 time to create 1 rle with old method : 0.0129852294921875 length of segment : 93 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.0002951622009277344 length of segment : 28 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004723072052001953 length of segment : 34 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0005102157592773438 length of segment : 31 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1162 time to create 1 rle with old method : 0.0016028881072998047 length of segment : 39 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005524158477783203 length of segment : 27 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 795 time to create 1 rle with old method : 0.0010285377502441406 length of segment : 32 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 789 time to create 1 rle with old method : 0.0010094642639160156 length of segment : 32 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.24922 max: 145.54531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 1949 time to create 1 rle with old method : 0.0025331974029541016 length of segment : 50 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00038743019104003906 length of segment : 19 time for calcul the mask position with numpy : 0.0001399517059326172 nb_pixel_total : 4403 time to create 1 rle with old method : 0.0054628849029541016 length of segment : 92 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 1463 time to create 1 rle with old method : 0.0018782615661621094 length of segment : 51 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004956722259521484 length of segment : 16 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 250 time to create 1 rle with old method : 0.00034928321838378906 length of segment : 18 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.00033283233642578125 length of segment : 29 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 942 time to create 1 rle with old method : 0.007270097732543945 length of segment : 49 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1277 time to create 1 rle with old method : 0.0026340484619140625 length of segment : 33 time for calcul the mask position with numpy : 0.0001392364501953125 nb_pixel_total : 4749 time to create 1 rle with old method : 0.005689859390258789 length of segment : 92 Processing 1 images image shape: (400, 160, 3) min: 36.00000 max: 140.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 33.74062 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: 8.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.43438 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0007297992706298828 length of segment : 27 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 267 time to create 1 rle with old method : 0.00044465065002441406 length of segment : 20 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003368854522705078 length of segment : 16 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 190 time to create 1 rle with old method : 0.00028824806213378906 length of segment : 21 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 1421 time to create 1 rle with old method : 0.001760244369506836 length of segment : 61 time for calcul the mask position with numpy : 9.298324584960938e-05 nb_pixel_total : 3380 time to create 1 rle with old method : 0.004110813140869141 length of segment : 94 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 162 time to create 1 rle with old method : 0.00029206275939941406 length of segment : 10 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1141 time to create 1 rle with old method : 0.0014765262603759766 length of segment : 42 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0004286766052246094 length of segment : 13 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 2300 time to create 1 rle with old method : 0.0028014183044433594 length of segment : 70 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0005319118499755859 length of segment : 37 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005848407745361328 length of segment : 24 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 909 time to create 1 rle with old method : 0.0013883113861083984 length of segment : 33 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 1332 time to create 1 rle with old method : 0.0017364025115966797 length of segment : 33 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.0003540515899658203 length of segment : 17 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003349781036376953 length of segment : 53 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 1148 time to create 1 rle with old method : 0.0017333030700683594 length of segment : 22 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 2072 time to create 1 rle with old method : 0.002763986587524414 length of segment : 85 time for calcul the mask position with numpy : 9.799003601074219e-05 nb_pixel_total : 725 time to create 1 rle with old method : 0.0009570121765136719 length of segment : 44 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1320 time to create 1 rle with old method : 0.0017237663269042969 length of segment : 34 time for calcul the mask position with numpy : 0.00011038780212402344 nb_pixel_total : 2121 time to create 1 rle with old method : 0.0026693344116210938 length of segment : 88 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 2006 time to create 1 rle with old method : 0.0023851394653320312 length of segment : 39 Processing 1 images image shape: (400, 400, 3) min: 17.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -95.76250 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 : 6.4849853515625e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0004189014434814453 length of segment : 22 time for calcul the mask position with numpy : 8.678436279296875e-05 nb_pixel_total : 3225 time to create 1 rle with old method : 0.0038101673126220703 length of segment : 51 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1038 time to create 1 rle with old method : 0.001420736312866211 length of segment : 34 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1541 time to create 1 rle with old method : 0.0020558834075927734 length of segment : 22 time for calcul the mask position with numpy : 0.00012302398681640625 nb_pixel_total : 5409 time to create 1 rle with old method : 0.006505489349365234 length of segment : 82 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0008306503295898438 length of segment : 27 time for calcul the mask position with numpy : 0.0004355907440185547 nb_pixel_total : 18197 time to create 1 rle with old method : 0.02860093116760254 length of segment : 197 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 1279 time to create 1 rle with old method : 0.0022449493408203125 length of segment : 39 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 1213 time to create 1 rle with old method : 0.0023148059844970703 length of segment : 36 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 679 time to create 1 rle with old method : 0.0008263587951660156 length of segment : 44 time for calcul the mask position with numpy : 0.0001347064971923828 nb_pixel_total : 5049 time to create 1 rle with old method : 0.005887031555175781 length of segment : 148 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0015840530395507812 length of segment : 84 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1175 time to create 1 rle with old method : 0.001485586166381836 length of segment : 60 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 894 time to create 1 rle with old method : 0.001173257827758789 length of segment : 40 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1814 time to create 1 rle with old method : 0.0022661685943603516 length of segment : 51 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006458759307861328 length of segment : 36 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 402 time to create 1 rle with old method : 0.0006017684936523438 length of segment : 23 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0007960796356201172 length of segment : 30 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 4554 time to create 1 rle with old method : 0.005396366119384766 length of segment : 79 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1713 time to create 1 rle with old method : 0.0019752979278564453 length of segment : 39 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 685 time to create 1 rle with old method : 0.0008466243743896484 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 9.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -91.55547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 28 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 1351 time to create 1 rle with old method : 0.0016682147979736328 length of segment : 48 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0006120204925537109 length of segment : 23 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 4640 time to create 1 rle with old method : 0.00556182861328125 length of segment : 90 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 1534 time to create 1 rle with old method : 0.0019006729125976562 length of segment : 54 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 2257 time to create 1 rle with old method : 0.0027284622192382812 length of segment : 70 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 323 time to create 1 rle with old method : 0.0004277229309082031 length of segment : 24 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1391 time to create 1 rle with old method : 0.001859903335571289 length of segment : 64 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 2470 time to create 1 rle with old method : 0.003055572509765625 length of segment : 62 time for calcul the mask position with numpy : 0.00011134147644042969 nb_pixel_total : 2864 time to create 1 rle with old method : 0.003574371337890625 length of segment : 155 time for calcul the mask position with numpy : 9.1552734375e-05 nb_pixel_total : 2141 time to create 1 rle with old method : 0.0024847984313964844 length of segment : 65 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 867 time to create 1 rle with old method : 0.0010585784912109375 length of segment : 36 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 621 time to create 1 rle with old method : 0.0008804798126220703 length of segment : 68 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 56 time to create 1 rle with old method : 9.489059448242188e-05 length of segment : 18 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1700 time to create 1 rle with old method : 0.002163410186767578 length of segment : 48 time for calcul the mask position with numpy : 9.560585021972656e-05 nb_pixel_total : 1347 time to create 1 rle with old method : 0.002241373062133789 length of segment : 56 time for calcul the mask position with numpy : 0.0001537799835205078 nb_pixel_total : 4922 time to create 1 rle with old method : 0.006585121154785156 length of segment : 128 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 1741 time to create 1 rle with old method : 0.0022225379943847656 length of segment : 44 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 2947 time to create 1 rle with old method : 0.003862142562866211 length of segment : 57 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0008180141448974609 length of segment : 69 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0004417896270751953 length of segment : 22 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0007534027099609375 length of segment : 31 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1718 time to create 1 rle with old method : 0.002476215362548828 length of segment : 26 time for calcul the mask position with numpy : 0.00017786026000976562 nb_pixel_total : 5229 time to create 1 rle with old method : 0.00699305534362793 length of segment : 106 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 1830 time to create 1 rle with old method : 0.002279996871948242 length of segment : 30 time for calcul the mask position with numpy : 0.00013899803161621094 nb_pixel_total : 4141 time to create 1 rle with old method : 0.005393505096435547 length of segment : 86 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 1877 time to create 1 rle with old method : 0.0022172927856445312 length of segment : 65 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 1828 time to create 1 rle with old method : 0.0023882389068603516 length of segment : 32 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 1805 time to create 1 rle with old method : 0.002348661422729492 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 16.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -99.27422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 15 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 836 time to create 1 rle with old method : 0.0011489391326904297 length of segment : 25 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 808 time to create 1 rle with old method : 0.0010793209075927734 length of segment : 45 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 975 time to create 1 rle with old method : 0.001238107681274414 length of segment : 67 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 314 time to create 1 rle with old method : 0.0004544258117675781 length of segment : 25 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 2304 time to create 1 rle with old method : 0.002728700637817383 length of segment : 92 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 750 time to create 1 rle with old method : 0.0009434223175048828 length of segment : 52 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 1036 time to create 1 rle with old method : 0.0014634132385253906 length of segment : 30 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 122 time to create 1 rle with old method : 0.00027298927307128906 length of segment : 25 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 2258 time to create 1 rle with old method : 0.0029137134552001953 length of segment : 67 time for calcul the mask position with numpy : 0.00021123886108398438 nb_pixel_total : 102 time to create 1 rle with old method : 0.00016760826110839844 length of segment : 13 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 2133 time to create 1 rle with old method : 0.002510547637939453 length of segment : 63 time for calcul the mask position with numpy : 0.00018930435180664062 nb_pixel_total : 10371 time to create 1 rle with old method : 0.011990070343017578 length of segment : 201 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 549 time to create 1 rle with old method : 0.0007503032684326172 length of segment : 35 2025-02-08 10:20:42.137622: E tensorflow/stream_executor/cuda/cuda_event.cc:29] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_ADDRESS: an illegal memory access was encountered 2025-02-08 10:20:42.137698: 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 ! 13.89user 9.55system 1:00:05elapsed 0%CPU (0avgtext+0avgdata 2545384maxresident)k 144152inputs+3672outputs (10818major+602496minor)pagefaults 0swaps