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 : 2485431 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 : ['2571322'] with mtr_portfolio_ids : ['20404182'] and first list_photo_ids : [] new path : /proc/2485431/ 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 : 0.4216456413269043 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 Mon Feb 10 14:20:30 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 : 10553 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-10 14:20:33.833492: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-10 14:20:33.859195: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-10 14:20:33.860760: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f11d0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-10 14:20:33.860791: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-10 14:20:33.864022: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-10 14:20:34.108802: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x33d40f70 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-10 14:20:34.108852: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-10 14:20:34.109660: 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 2025-02-10 14:20:34.144608: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-10 14:20:34.149929: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-10 14:20:34.152762: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-10 14:20:34.153291: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-10 14:20:34.156491: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-10 14:20:34.158062: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-10 14:20:34.164541: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-10 14:20:34.166600: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-10 14:20:34.166742: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-10 14:20:34.167827: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-10 14:20:34.167852: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-10 14:20:34.167868: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-10 14:20:34.169953: 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. 2025-02-10 14:20:34.516075: 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 2025-02-10 14:20:34.516194: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-10 14:20:34.516217: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-10 14:20:34.516237: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-10 14:20:34.516255: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-10 14:20:34.516274: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-10 14:20:34.516291: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-10 14:20:34.516310: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-10 14:20:34.517862: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-10 14:20:34.519388: 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 2025-02-10 14:20:34.519475: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-10 14:20:34.519497: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-10 14:20:34.519517: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-10 14:20:34.519536: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-10 14:20:34.519555: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-10 14:20:34.519573: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-10 14:20:34.519592: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-10 14:20:34.521165: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-10 14:20:34.521209: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-10 14:20:34.521220: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-10 14:20:34.521229: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-10 14:20:34.522861: 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 : [] 2025-02-10 14:20:41.439542: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-10 14:20:41.764898: 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: -120.07500 max: 147.26797 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 879 time to create 1 rle with old method : 0.0019245147705078125 length of segment : 45 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 33 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 17 time to create 1 rle with old method : 9.989738464355469e-05 length of segment : 8 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 60 time to create 1 rle with old method : 0.00019121170043945312 length of segment : 31 time for calcul the mask position with numpy : 0.0004792213439941406 nb_pixel_total : 19993 time to create 1 rle with old method : 0.03677487373352051 length of segment : 132 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.00039887428283691406 length of segment : 13 length of segment : 0 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 15 time to create 1 rle with old method : 0.00011229515075683594 length of segment : 4 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 747 time to create 1 rle with old method : 0.0012731552124023438 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: -114.61797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0008132457733154297 length of segment : 29 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 531 time to create 1 rle with old method : 0.001004934310913086 length of segment : 38 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 28 time to create 1 rle with old method : 8.225440979003906e-05 length of segment : 6 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 2224 time to create 1 rle with old method : 0.004195451736450195 length of segment : 64 time for calcul the mask position with numpy : 8.0108642578125e-05 nb_pixel_total : 2066 time to create 1 rle with old method : 0.003763914108276367 length of segment : 52 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -93.55547 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00010323524475097656 nb_pixel_total : 2516 time to create 1 rle with old method : 0.004873514175415039 length of segment : 56 time for calcul the mask position with numpy : 9.202957153320312e-05 nb_pixel_total : 1593 time to create 1 rle with old method : 0.003040790557861328 length of segment : 48 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0027341842651367188 length of segment : 13 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.0027008056640625 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: -120.46953 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 1239 time to create 1 rle with old method : 0.002645730972290039 length of segment : 72 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 770 time to create 1 rle with old method : 0.0014476776123046875 length of segment : 51 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 209 time to create 1 rle with old method : 0.0004267692565917969 length of segment : 17 time for calcul the mask position with numpy : 0.00011110305786132812 nb_pixel_total : 4958 time to create 1 rle with old method : 0.010361671447753906 length of segment : 65 time for calcul the mask position with numpy : 0.0001666545867919922 nb_pixel_total : 9371 time to create 1 rle with old method : 0.011170148849487305 length of segment : 104 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.35391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0003104209899902344 length of segment : 16 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1078 time to create 1 rle with old method : 0.0013966560363769531 length of segment : 66 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 579 time to create 1 rle with old method : 0.0008580684661865234 length of segment : 22 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 1277 time to create 1 rle with old method : 0.0017237663269042969 length of segment : 42 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 1440 time to create 1 rle with old method : 0.0019307136535644531 length of segment : 100 time for calcul the mask position with numpy : 0.0005869865417480469 nb_pixel_total : 54980 time to create 1 rle with old method : 0.06388592720031738 length of segment : 253 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1010 time to create 1 rle with old method : 0.0014183521270751953 length of segment : 72 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 966 time to create 1 rle with old method : 0.0012159347534179688 length of segment : 70 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 208.00000 molded_images shape: (1, 640, 640, 3) min: -92.45000 max: 79.56328 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: -104.85234 max: 131.89531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 392 time to create 1 rle with old method : 0.0005314350128173828 length of segment : 36 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 1834 time to create 1 rle with old method : 0.0035881996154785156 length of segment : 33 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 360 time to create 1 rle with old method : 0.0008990764617919922 length of segment : 17 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0005695819854736328 length of segment : 16 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0007989406585693359 length of segment : 21 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.000728607177734375 length of segment : 24 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0004611015319824219 length of segment : 21 time for calcul the mask position with numpy : 0.00023484230041503906 nb_pixel_total : 6728 time to create 1 rle with old method : 0.012609004974365234 length of segment : 130 time for calcul the mask position with numpy : 9.72747802734375e-05 nb_pixel_total : 928 time to create 1 rle with old method : 0.0017282962799072266 length of segment : 29 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 934 time to create 1 rle with old method : 0.0017604827880859375 length of segment : 47 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 790 time to create 1 rle with old method : 0.0014863014221191406 length of segment : 42 time for calcul the mask position with numpy : 7.700920104980469e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0009799003601074219 length of segment : 37 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 610 time to create 1 rle with old method : 0.0011925697326660156 length of segment : 46 Processing 1 images image shape: (400, 400, 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 : 11 time for calcul the mask position with numpy : 0.0004975795745849609 nb_pixel_total : 17885 time to create 1 rle with old method : 0.0353550910949707 length of segment : 155 time for calcul the mask position with numpy : 8.702278137207031e-05 nb_pixel_total : 662 time to create 1 rle with old method : 0.0014464855194091797 length of segment : 20 time for calcul the mask position with numpy : 0.00017452239990234375 nb_pixel_total : 1240 time to create 1 rle with old method : 0.0026738643646240234 length of segment : 53 time for calcul the mask position with numpy : 9.894371032714844e-05 nb_pixel_total : 1599 time to create 1 rle with old method : 0.003373384475708008 length of segment : 54 time for calcul the mask position with numpy : 8.58306884765625e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.001520395278930664 length of segment : 46 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 1178 time to create 1 rle with old method : 0.0025277137756347656 length of segment : 57 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 753 time to create 1 rle with old method : 0.0016126632690429688 length of segment : 42 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0010623931884765625 length of segment : 11 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 165 time to create 1 rle with old method : 0.0003991127014160156 length of segment : 20 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.0004200935363769531 length of segment : 15 time for calcul the mask position with numpy : 0.00042128562927246094 nb_pixel_total : 17134 time to create 1 rle with old method : 0.033788442611694336 length of segment : 279 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.74297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 772 time to create 1 rle with old method : 0.0014438629150390625 length of segment : 39 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 1868 time to create 1 rle with old method : 0.0037071704864501953 length of segment : 125 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1179 time to create 1 rle with old method : 0.002157926559448242 length of segment : 41 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0006918907165527344 length of segment : 10 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 690 time to create 1 rle with old method : 0.0010361671447753906 length of segment : 51 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 1435 time to create 1 rle with old method : 0.0018463134765625 length of segment : 74 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007152557373046875 length of segment : 48 time for calcul the mask position with numpy : 0.0001704692840576172 nb_pixel_total : 3622 time to create 1 rle with old method : 0.004589080810546875 length of segment : 200 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003669261932373047 length of segment : 41 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.0007836818695068359 length of segment : 49 time for calcul the mask position with numpy : 0.0002148151397705078 nb_pixel_total : 4795 time to create 1 rle with old method : 0.006780385971069336 length of segment : 239 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 1446 time to create 1 rle with old method : 0.002111196517944336 length of segment : 64 Processing 1 images image shape: (280, 400, 3) min: 7.00000 max: 181.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 57.84844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009529590606689453 nb_pixel_total : 106378 time to create 1 rle with old method : 0.13513994216918945 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.58437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 8.416175842285156e-05 nb_pixel_total : 1905 time to create 1 rle with old method : 0.0028982162475585938 length of segment : 51 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 3150 time to create 1 rle with old method : 0.0041446685791015625 length of segment : 56 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0017142295837402344 length of segment : 29 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 653 time to create 1 rle with old method : 0.001749277114868164 length of segment : 33 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.00037550926208496094 length of segment : 9 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 106 time to create 1 rle with old method : 0.0002522468566894531 length of segment : 9 time for calcul the mask position with numpy : 0.00010919570922851562 nb_pixel_total : 2166 time to create 1 rle with old method : 0.004050254821777344 length of segment : 60 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.00042724609375 length of segment : 16 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 395 time to create 1 rle with old method : 0.0007977485656738281 length of segment : 23 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 1479 time to create 1 rle with old method : 0.003103494644165039 length of segment : 59 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 722 time to create 1 rle with old method : 0.0012192726135253906 length of segment : 53 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.000986337661743164 length of segment : 25 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 570 time to create 1 rle with old method : 0.0007951259613037109 length of segment : 29 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.000640869140625 length of segment : 51 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003483295440673828 length of segment : 20 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 2068 time to create 1 rle with old method : 0.002676725387573242 length of segment : 35 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 516 time to create 1 rle with old method : 0.0008211135864257812 length of segment : 34 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 1784 time to create 1 rle with old method : 0.002498626708984375 length of segment : 32 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 1991 time to create 1 rle with old method : 0.0027589797973632812 length of segment : 41 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 141.38516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.00041675567626953125 length of segment : 22 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 880 time to create 1 rle with old method : 0.001153707504272461 length of segment : 39 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 534 time to create 1 rle with old method : 0.0007135868072509766 length of segment : 29 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00026488304138183594 length of segment : 16 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004754066467285156 length of segment : 19 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 542 time to create 1 rle with old method : 0.0007853507995605469 length of segment : 27 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002162456512451172 length of segment : 14 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004432201385498047 length of segment : 18 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0009469985961914062 length of segment : 35 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.0005049705505371094 length of segment : 22 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.00020265579223632812 length of segment : 10 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.0003571510314941406 length of segment : 10 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 164 time to create 1 rle with old method : 0.00042700767517089844 length of segment : 34 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 54 time to create 1 rle with old method : 0.0001468658447265625 length of segment : 9 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.01016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 944 time to create 1 rle with old method : 0.0013926029205322266 length of segment : 36 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 1589 time to create 1 rle with old method : 0.00205230712890625 length of segment : 48 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1558 time to create 1 rle with old method : 0.0020644664764404297 length of segment : 51 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 412 time to create 1 rle with old method : 0.0006561279296875 length of segment : 33 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 257 time to create 1 rle with old method : 0.00037980079650878906 length of segment : 19 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 892 time to create 1 rle with old method : 0.001188516616821289 length of segment : 41 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.00045228004455566406 length of segment : 44 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 1163 time to create 1 rle with old method : 0.0015337467193603516 length of segment : 69 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00016427040100097656 length of segment : 10 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 24 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 102 time to create 1 rle with old method : 0.00017690658569335938 length of segment : 12 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.000553131103515625 length of segment : 27 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.00031447410583496094 length of segment : 26 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1627 time to create 1 rle with old method : 0.002253293991088867 length of segment : 52 time for calcul the mask position with numpy : 6.127357482910156e-05 nb_pixel_total : 614 time to create 1 rle with old method : 0.0008707046508789062 length of segment : 46 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00025963783264160156 length of segment : 16 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006666183471679688 length of segment : 20 Processing 1 images image shape: (280, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 133.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0005195140838623047 length of segment : 59 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 156 time to create 1 rle with old method : 0.00037980079650878906 length of segment : 10 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 20 time to create 1 rle with old method : 7.128715515136719e-05 length of segment : 4 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.0005524158477783203 length of segment : 16 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0005631446838378906 length of segment : 14 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00026416778564453125 length of segment : 11 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: -119.42266 max: 146.74453 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 912 time to create 1 rle with old method : 0.0013010501861572266 length of segment : 47 time for calcul the mask position with numpy : 0.00034356117248535156 nb_pixel_total : 18179 time to create 1 rle with old method : 0.02335524559020996 length of segment : 149 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 270 time to create 1 rle with old method : 0.00040411949157714844 length of segment : 34 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 50 time to create 1 rle with old method : 0.00013113021850585938 length of segment : 11 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 19 time to create 1 rle with old method : 0.00010657310485839844 length of segment : 4 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001246929168701172 length of segment : 32 time for calcul the mask position with numpy : 0.0003681182861328125 nb_pixel_total : 19533 time to create 1 rle with old method : 0.025037288665771484 length of segment : 147 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 99 time to create 1 rle with old method : 0.0003247261047363281 length of segment : 10 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 236 time to create 1 rle with old method : 0.0003612041473388672 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.16484 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 : 7.295608520507812e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.0012366771697998047 length of segment : 40 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 2614 time to create 1 rle with old method : 0.0056760311126708984 length of segment : 64 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 28 time to create 1 rle with old method : 9.632110595703125e-05 length of segment : 6 time for calcul the mask position with numpy : 0.00012183189392089844 nb_pixel_total : 2151 time to create 1 rle with old method : 0.004683256149291992 length of segment : 67 time for calcul the mask position with numpy : 9.012222290039062e-05 nb_pixel_total : 1820 time to create 1 rle with old method : 0.0038127899169921875 length of segment : 33 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 416 time to create 1 rle with old method : 0.0009491443634033203 length of segment : 36 Processing 1 images image shape: (400, 400, 3) min: 7.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -103.86016 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 2025 time to create 1 rle with old method : 0.002773761749267578 length of segment : 34 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 3529 time to create 1 rle with old method : 0.0042819976806640625 length of segment : 55 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 2264 time to create 1 rle with old method : 0.003032684326171875 length of segment : 61 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 539 time to create 1 rle with old method : 0.0007238388061523438 length of segment : 22 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0007953643798828125 length of segment : 33 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 3855 time to create 1 rle with old method : 0.00598907470703125 length of segment : 69 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.00043010711669921875 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: -115.51641 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 762 time to create 1 rle with old method : 0.0011444091796875 length of segment : 42 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 5655 time to create 1 rle with old method : 0.009902238845825195 length of segment : 67 time for calcul the mask position with numpy : 0.00019073486328125 nb_pixel_total : 8377 time to create 1 rle with old method : 0.014691352844238281 length of segment : 125 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 1316 time to create 1 rle with old method : 0.0027191638946533203 length of segment : 71 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 223 time to create 1 rle with old method : 0.00044155120849609375 length of segment : 20 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.0004169940948486328 length of segment : 29 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0006840229034423828 length of segment : 33 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.76406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 202 time to create 1 rle with old method : 0.0005090236663818359 length of segment : 17 time for calcul the mask position with numpy : 8.058547973632812e-05 nb_pixel_total : 1540 time to create 1 rle with old method : 0.0030374526977539062 length of segment : 104 time for calcul the mask position with numpy : 6.556510925292969e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0012736320495605469 length of segment : 21 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1145 time to create 1 rle with old method : 0.0024480819702148438 length of segment : 46 time for calcul the mask position with numpy : 0.000213623046875 nb_pixel_total : 7782 time to create 1 rle with old method : 0.01554250717163086 length of segment : 60 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 961 time to create 1 rle with old method : 0.0019268989562988281 length of segment : 67 time for calcul the mask position with numpy : 0.0008549690246582031 nb_pixel_total : 42886 time to create 1 rle with old method : 0.08172082901000977 length of segment : 252 time for calcul the mask position with numpy : 0.0007560253143310547 nb_pixel_total : 63750 time to create 1 rle with old method : 0.08259320259094238 length of segment : 328 time for calcul the mask position with numpy : 0.0004992485046386719 nb_pixel_total : 44711 time to create 1 rle with old method : 0.06271529197692871 length of segment : 280 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 212.00000 molded_images shape: (1, 640, 640, 3) min: -84.01250 max: 81.75078 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: -104.66875 max: 133.61406 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.0005295276641845703 length of segment : 15 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1839 time to create 1 rle with old method : 0.0034112930297851562 length of segment : 33 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0005316734313964844 length of segment : 35 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0004024505615234375 length of segment : 19 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 2075 time to create 1 rle with old method : 0.003734111785888672 length of segment : 84 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0007803440093994141 length of segment : 18 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.001306772232055664 length of segment : 27 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 430 time to create 1 rle with old method : 0.0008885860443115234 length of segment : 18 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 290 time to create 1 rle with old method : 0.0005669593811035156 length of segment : 18 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 845 time to create 1 rle with old method : 0.0016179084777832031 length of segment : 40 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0007677078247070312 length of segment : 27 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 846 time to create 1 rle with old method : 0.0016138553619384766 length of segment : 39 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 415 time to create 1 rle with old method : 0.002088308334350586 length of segment : 21 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0006358623504638672 length of segment : 31 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.75469 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 : 5.364418029785156e-05 nb_pixel_total : 574 time to create 1 rle with old method : 0.0007848739624023438 length of segment : 33 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 660 time to create 1 rle with old method : 0.0009524822235107422 length of segment : 20 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002961158752441406 length of segment : 15 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 757 time to create 1 rle with old method : 0.001214742660522461 length of segment : 42 time for calcul the mask position with numpy : 0.0003845691680908203 nb_pixel_total : 20049 time to create 1 rle with old method : 0.03415250778198242 length of segment : 205 time for calcul the mask position with numpy : 0.00016307830810546875 nb_pixel_total : 1244 time to create 1 rle with old method : 0.0029153823852539062 length of segment : 61 time for calcul the mask position with numpy : 0.0004267692565917969 nb_pixel_total : 15074 time to create 1 rle with old method : 0.03210568428039551 length of segment : 261 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 450 time to create 1 rle with old method : 0.0006873607635498047 length of segment : 34 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006673336029052734 length of segment : 18 time for calcul the mask position with numpy : 0.00019407272338867188 nb_pixel_total : 3319 time to create 1 rle with old method : 0.0050771236419677734 length of segment : 174 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.27031 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 : 0.00011777877807617188 nb_pixel_total : 2088 time to create 1 rle with old method : 0.003756284713745117 length of segment : 131 time for calcul the mask position with numpy : 8.726119995117188e-05 nb_pixel_total : 543 time to create 1 rle with old method : 0.0010826587677001953 length of segment : 45 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0011401176452636719 length of segment : 32 time for calcul the mask position with numpy : 7.295608520507812e-05 nb_pixel_total : 1140 time to create 1 rle with old method : 0.002373933792114258 length of segment : 38 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0007081031799316406 length of segment : 15 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 291 time to create 1 rle with old method : 0.0007293224334716797 length of segment : 15 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0009064674377441406 length of segment : 53 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 353 time to create 1 rle with old method : 0.0004761219024658203 length of segment : 40 time for calcul the mask position with numpy : 0.0002338886260986328 nb_pixel_total : 2939 time to create 1 rle with old method : 0.004000663757324219 length of segment : 169 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 1602 time to create 1 rle with old method : 0.002335786819458008 length of segment : 76 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0006020069122314453 length of segment : 48 Processing 1 images image shape: (280, 400, 3) min: 14.00000 max: 191.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 66.80156 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009350776672363281 nb_pixel_total : 105643 time to create 1 rle with old method : 0.12254667282104492 length of segment : 281 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.04922 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1948 time to create 1 rle with old method : 0.0029075145721435547 length of segment : 53 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1275 time to create 1 rle with old method : 0.0018694400787353516 length of segment : 30 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0004265308380126953 length of segment : 21 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 597 time to create 1 rle with old method : 0.0008130073547363281 length of segment : 30 time for calcul the mask position with numpy : 0.00014925003051757812 nb_pixel_total : 5000 time to create 1 rle with old method : 0.006446361541748047 length of segment : 216 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.0003216266632080078 length of segment : 9 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 144 time to create 1 rle with old method : 0.0004038810729980469 length of segment : 8 time for calcul the mask position with numpy : 0.00011491775512695312 nb_pixel_total : 2178 time to create 1 rle with old method : 0.004540920257568359 length of segment : 60 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 605 time to create 1 rle with old method : 0.0013604164123535156 length of segment : 28 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 3131 time to create 1 rle with old method : 0.006467342376708984 length of segment : 53 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0008940696716308594 length of segment : 24 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 1512 time to create 1 rle with old method : 0.0031337738037109375 length of segment : 60 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.0003142356872558594 length of segment : 16 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0009191036224365234 length of segment : 24 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 1007 time to create 1 rle with old method : 0.002167940139770508 length of segment : 32 time for calcul the mask position with numpy : 0.00010800361633300781 nb_pixel_total : 1192 time to create 1 rle with old method : 0.002605915069580078 length of segment : 56 time for calcul the mask position with numpy : 0.00011992454528808594 nb_pixel_total : 3030 time to create 1 rle with old method : 0.006087779998779297 length of segment : 53 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 143.28359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 877 time to create 1 rle with old method : 0.0022437572479248047 length of segment : 37 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.0005261898040771484 length of segment : 22 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 20 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.00028586387634277344 length of segment : 17 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 370 time to create 1 rle with old method : 0.0005204677581787109 length of segment : 24 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.00039505958557128906 length of segment : 20 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002143383026123047 length of segment : 14 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003654956817626953 length of segment : 29 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 56 time to create 1 rle with old method : 0.00011706352233886719 length of segment : 8 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0006527900695800781 length of segment : 37 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 347 time to create 1 rle with old method : 0.0004980564117431641 length of segment : 20 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 510 time to create 1 rle with old method : 0.0007045269012451172 length of segment : 31 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0010852813720703125 length of segment : 32 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 582 time to create 1 rle with old method : 0.0007953643798828125 length of segment : 31 2025-02-10 14:20:51.918406: 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 2025-02-10 14:20:51.918470: 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 ! 19.22user 12.69system 1:00:07elapsed 0%CPU (0avgtext+0avgdata 2493216maxresident)k 712680inputs+1688outputs (12643major+626934minor)pagefaults 0swaps