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 : 13008 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 we have a portfolio with more photos than limit : 67>5 please execute split_portfolio.py -i 20926680 -l 5 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 4234, datou_cur_ids : ['2623816'] with mtr_portfolio_ids : ['20926680'] and first list_photo_ids : [] new path : /proc/13008/ 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 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 1.8855555057525635 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 Sun Mar 2 05:20:32 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 : 10814 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-02 05:20:35.164468: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-02 05:20:35.195531: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-02 05:20:35.197821: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f8118000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-02 05:20:35.197892: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-02 05:20:35.202262: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-02 05:20:35.341393: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xaa1a8b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-02 05:20:35.341459: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-02 05:20:35.342989: 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 2025-03-02 05:20:35.343406: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-02 05:20:35.346455: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-02 05:20:35.349427: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-02 05:20:35.349937: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-02 05:20:35.352774: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-02 05:20:35.353841: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-02 05:20:35.358424: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-02 05:20:35.359984: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-02 05:20:35.360069: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-02 05:20:35.360853: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-02 05:20:35.360868: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-02 05:20:35.360878: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-02 05:20:35.362193: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9879 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. 2025-03-02 05:20:35.644655: 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 2025-03-02 05:20:35.644768: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-02 05:20:35.644793: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-02 05:20:35.644815: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-02 05:20:35.644836: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-02 05:20:35.644857: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-02 05:20:35.644877: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-02 05:20:35.644897: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-02 05:20:35.646498: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-02 05:20:35.648016: 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 2025-03-02 05:20:35.648090: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-02 05:20:35.648111: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-02 05:20:35.648129: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-02 05:20:35.648146: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-02 05:20:35.648164: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-02 05:20:35.648178: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-02 05:20:35.648193: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-02 05:20:35.649487: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-02 05:20:35.649530: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-02 05:20:35.649544: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-02 05:20:35.649554: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-02 05:20:35.650922: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9879 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 : [] 2025-03-02 05:20:43.726175: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-02 05:20:43.968852: 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 : 5 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: -118.75469 max: 149.61953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00010061264038085938 nb_pixel_total : 1092 time to create 1 rle with old method : 0.002001047134399414 length of segment : 31 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1024 time to create 1 rle with old method : 0.0018570423126220703 length of segment : 40 time for calcul the mask position with numpy : 0.0001652240753173828 nb_pixel_total : 4032 time to create 1 rle with old method : 0.006856679916381836 length of segment : 109 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.16484 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 : 0.000102996826171875 nb_pixel_total : 2688 time to create 1 rle with old method : 0.0037136077880859375 length of segment : 74 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 1206 time to create 1 rle with old method : 0.0015921592712402344 length of segment : 40 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002048015594482422 length of segment : 16 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1534 time to create 1 rle with old method : 0.0019006729125976562 length of segment : 34 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 49 time to create 1 rle with old method : 0.00015211105346679688 length of segment : 6 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 915 time to create 1 rle with old method : 0.0011661052703857422 length of segment : 36 time for calcul the mask position with numpy : 9.584426879882812e-05 nb_pixel_total : 2438 time to create 1 rle with old method : 0.0031473636627197266 length of segment : 51 Processing 1 images image shape: (400, 400, 3) min: 26.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -85.10625 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 : 5.4836273193359375e-05 nb_pixel_total : 1341 time to create 1 rle with old method : 0.0016827583312988281 length of segment : 29 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1295 time to create 1 rle with old method : 0.001984119415283203 length of segment : 28 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 915 time to create 1 rle with old method : 0.001299142837524414 length of segment : 24 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 945 time to create 1 rle with old method : 0.0012083053588867188 length of segment : 38 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.67266 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 : 0.00014543533325195312 nb_pixel_total : 10240 time to create 1 rle with old method : 0.01193857192993164 length of segment : 85 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0009698867797851562 length of segment : 63 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.000591278076171875 length of segment : 34 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.0010323524475097656 length of segment : 50 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 2477 time to create 1 rle with old method : 0.0029747486114501953 length of segment : 129 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 : 3 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 859 time to create 1 rle with old method : 0.001165151596069336 length of segment : 30 time for calcul the mask position with numpy : 0.0006444454193115234 nb_pixel_total : 62761 time to create 1 rle with old method : 0.06985163688659668 length of segment : 394 time for calcul the mask position with numpy : 0.0007908344268798828 nb_pixel_total : 69538 time to create 1 rle with old method : 0.08231711387634277 length of segment : 300 Processing 1 images image shape: (400, 400, 3) min: 20.00000 max: 164.00000 molded_images shape: (1, 640, 640, 3) min: -95.95391 max: 46.51797 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: -121.04766 max: 120.63359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.0012121200561523438 length of segment : 28 time for calcul the mask position with numpy : 5.7220458984375e-05 nb_pixel_total : 774 time to create 1 rle with old method : 0.0010228157043457031 length of segment : 32 time for calcul the mask position with numpy : 0.00023889541625976562 nb_pixel_total : 8756 time to create 1 rle with old method : 0.01047062873840332 length of segment : 129 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1550 time to create 1 rle with old method : 0.0020537376403808594 length of segment : 39 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005910396575927734 length of segment : 32 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 647 time to create 1 rle with old method : 0.0007793903350830078 length of segment : 44 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 268 time to create 1 rle with old method : 0.0003838539123535156 length of segment : 17 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0006117820739746094 length of segment : 30 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.62969 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 : 4.315376281738281e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0004410743713378906 length of segment : 40 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 899 time to create 1 rle with old method : 0.001220703125 length of segment : 89 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 110 time to create 1 rle with old method : 0.00017571449279785156 length of segment : 15 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 679 time to create 1 rle with old method : 0.000835418701171875 length of segment : 30 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 261 time to create 1 rle with old method : 0.00037741661071777344 length of segment : 25 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009565353393554688 length of segment : 31 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 835 time to create 1 rle with old method : 0.0010941028594970703 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.09844 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 : 5.1021575927734375e-05 nb_pixel_total : 959 time to create 1 rle with old method : 0.0012886524200439453 length of segment : 26 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 2105 time to create 1 rle with old method : 0.0025305747985839844 length of segment : 129 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 1279 time to create 1 rle with old method : 0.001638650894165039 length of segment : 45 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1122 time to create 1 rle with old method : 0.0015881061553955078 length of segment : 37 time for calcul the mask position with numpy : 0.00037550926208496094 nb_pixel_total : 11840 time to create 1 rle with old method : 0.013768911361694336 length of segment : 488 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1035 time to create 1 rle with old method : 0.0013446807861328125 length of segment : 30 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 : 0.0001876354217529297 nb_pixel_total : 3414 time to create 1 rle with old method : 0.004018545150756836 length of segment : 209 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 863 time to create 1 rle with old method : 0.001203775405883789 length of segment : 68 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0004553794860839844 length of segment : 28 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 285 time to create 1 rle with old method : 0.00047278404235839844 length of segment : 15 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1275 time to create 1 rle with old method : 0.0015556812286376953 length of segment : 65 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 177.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 48.35000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 232.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 112.27187 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 411 time to create 1 rle with old method : 0.0006074905395507812 length of segment : 23 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.00019788742065429688 length of segment : 9 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 2171 time to create 1 rle with old method : 0.0026388168334960938 length of segment : 82 time for calcul the mask position with numpy : 7.748603820800781e-05 nb_pixel_total : 2885 time to create 1 rle with old method : 0.0037386417388916016 length of segment : 47 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0008950233459472656 length of segment : 36 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0007729530334472656 length of segment : 38 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 947 time to create 1 rle with old method : 0.0013439655303955078 length of segment : 41 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 898 time to create 1 rle with old method : 0.0011684894561767578 length of segment : 58 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.00040435791015625 length of segment : 31 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 464 time to create 1 rle with old method : 0.0007152557373046875 length of segment : 18 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 367 time to create 1 rle with old method : 0.0004787445068359375 length of segment : 29 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.00015354156494140625 length of segment : 17 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001399517059326172 length of segment : 17 time for calcul the mask position with numpy : 0.0005242824554443359 nb_pixel_total : 36050 time to create 1 rle with old method : 0.04193544387817383 length of segment : 210 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 173 time to create 1 rle with old method : 0.00025391578674316406 length of segment : 18 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 678 time to create 1 rle with old method : 0.0008158683776855469 length of segment : 52 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 249.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 127.85000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 20 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 552 time to create 1 rle with old method : 0.0007221698760986328 length of segment : 26 time for calcul the mask position with numpy : 3.910064697265625e-05 nb_pixel_total : 308 time to create 1 rle with old method : 0.0004341602325439453 length of segment : 23 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0004892349243164062 length of segment : 35 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003466606140136719 length of segment : 21 time for calcul the mask position with numpy : 5.269050598144531e-05 2025-03-02 05:20:49.697197: F tensorflow/core/kernels/bias_op_gpu.cu.cc:97] Non-OK-status: GpuLaunchKernel(BiasNCHWKernel, config.block_count, config.thread_per_block, 0, d.stream(), config.virtual_thread_count, input, bias, output, bias_size, image_size) status: Internal: an illegal memory access was encountered 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 ! 14.57user 11.39system 1:00:08elapsed 0%CPU (0avgtext+0avgdata 2463800maxresident)k 631160inputs+2552outputs (11169major+660058minor)pagefaults 0swaps