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 : 445301 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 : ['2538473'] with mtr_portfolio_ids : ['20047140'] and first list_photo_ids : [] new path : /proc/445301/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 11415 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11419 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11419 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11416 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11417 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11417 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11422 split_time_score have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 2 of step 11418 have datatype=6 We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11419 doesn't seem to be define in the database( WARNING : output 1 of step 11415 have datatype=7 whereas input 2 of step 11419 have datatype=None WARNING : type of output 3 of step 11419 doesn't seem to be define in the database( WARNING : type of input 1 of step 11416 doesn't seem to be define in the database( WARNING : type of output 1 of step 11416 doesn't seem to be define in the database( WARNING : type of input 3 of step 11417 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11416 have datatype=10 whereas input 0 of step 11420 have datatype=18 WARNING : type of input 5 of step 11418 doesn't seem to be define in the database( WARNING : output 0 of step 11420 have datatype=11 whereas input 5 of step 11418 have datatype=None WARNING : type of input 2 of step 11416 doesn't seem to be define in the database( WARNING : output 0 of step 11421 have datatype=5 whereas input 2 of step 11416 have datatype=None WARNING : output 0 of step 11418 have datatype=10 whereas input 0 of step 11422 have datatype=18 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, brightness, blur_detection, rle_unique_nms_with_priority, crop_condition, thcl, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 2 ; length of list_pids : 2 ; length of list_args : 2 time to download the photos : 0.5125105381011963 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 Feb 2 21:20:30 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 2025-02-02 21:20:32.883197: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-02 21:20:32.911507: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493020000 Hz 2025-02-02 21:20:32.913733: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa5e0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-02 21:20:32.913794: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-02 21:20:32.917826: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-02 21:20:33.157516: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x26c31620 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-02 21:20:33.157560: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-02 21:20:33.158957: 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 2025-02-02 21:20:33.159374: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 21:20:33.162484: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 21:20:33.165553: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-02 21:20:33.166060: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-02 21:20:33.169633: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-02 21:20:33.171496: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-02 21:20:33.176416: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-02 21:20:33.177830: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-02 21:20:33.177905: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 21:20:33.178642: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-02 21:20:33.178658: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-02 21:20:33.178666: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-02 21:20:33.179962: 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. 2025-02-02 21:20:33.430846: 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 2025-02-02 21:20:33.430946: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 21:20:33.430976: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 21:20:33.431003: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-02 21:20:33.431031: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-02 21:20:33.431056: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-02 21:20:33.431082: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-02 21:20:33.431107: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-02 21:20:33.433230: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-02 21:20:33.435118: 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 2025-02-02 21:20:33.435183: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-02 21:20:33.435215: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 21:20:33.435243: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-02 21:20:33.435270: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-02 21:20:33.435297: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-02 21:20:33.435343: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-02 21:20:33.435375: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-02 21:20:33.437531: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-02 21:20:33.437569: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-02 21:20:33.437585: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-02 21:20:33.437599: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-02 21:20:33.439911: 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 : [] 2025-02-02 21:20:40.706548: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-02 21:20:40.892860: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23 /data/models_weight/learn_RUBBIA_REFUS_AMIENS_23/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2021-08-09 09:43:22 create time in s3 : 2021-08-06 18:54:04 mask_model.h5 already exist and didn't need to update list_images length : 2 NEW PHOTO pour l'instant on ne peut pas sauvegarder la photo dans les tile Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.41094 max: 145.73672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 55 time to create 1 rle with old method : 0.0001933574676513672 length of segment : 14 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.0004024505615234375 length of segment : 32 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 926 time to create 1 rle with old method : 0.0016827583312988281 length of segment : 40 length of segment : 0 length of segment : 0 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 1037 time to create 1 rle with old method : 0.004167318344116211 length of segment : 38 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 124 time to create 1 rle with old method : 0.0020275115966796875 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.02813 max: 148.99844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 1499 time to create 1 rle with old method : 0.0018396377563476562 length of segment : 52 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 710 time to create 1 rle with old method : 0.0009927749633789062 length of segment : 27 time for calcul the mask position with numpy : 3.0279159545898438e-05 nb_pixel_total : 112 time to create 1 rle with old method : 0.0001766681671142578 length of segment : 14 time for calcul the mask position with numpy : 2.7894973754882812e-05 nb_pixel_total : 161 time to create 1 rle with old method : 0.00022840499877929688 length of segment : 16 time for calcul the mask position with numpy : 3.5762786865234375e-05 nb_pixel_total : 413 time to create 1 rle with old method : 0.0005540847778320312 length of segment : 25 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0006024837493896484 length of segment : 36 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1415 time to create 1 rle with old method : 0.002175569534301758 length of segment : 22 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.32891 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 9.918212890625e-05 nb_pixel_total : 5481 time to create 1 rle with old method : 0.007040739059448242 length of segment : 155 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.20000 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 : 0.0001049041748046875 nb_pixel_total : 5055 time to create 1 rle with old method : 0.0068247318267822266 length of segment : 135 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003998279571533203 length of segment : 18 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.00037741661071777344 length of segment : 23 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 554 time to create 1 rle with old method : 0.0010068416595458984 length of segment : 31 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 218.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 92.79141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.0007982254028320312 length of segment : 18 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 3047 time to create 1 rle with old method : 0.004461765289306641 length of segment : 56 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 955 time to create 1 rle with old method : 0.0013966560363769531 length of segment : 75 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 457 time to create 1 rle with old method : 0.000720977783203125 length of segment : 28 time for calcul the mask position with numpy : 0.0006513595581054688 nb_pixel_total : 56538 time to create 1 rle with old method : 0.07192325592041016 length of segment : 268 Processing 1 images image shape: (400, 400, 3) min: 21.00000 max: 207.00000 molded_images shape: (1, 640, 640, 3) min: -90.69219 max: 86.39687 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.45000 max: 147.08437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 1390 time to create 1 rle with old method : 0.0019674301147460938 length of segment : 52 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0005600452423095703 length of segment : 17 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0004646778106689453 length of segment : 17 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 491 time to create 1 rle with old method : 0.0007729530334472656 length of segment : 21 time for calcul the mask position with numpy : 7.414817810058594e-05 nb_pixel_total : 819 time to create 1 rle with old method : 0.0014226436614990234 length of segment : 46 time for calcul the mask position with numpy : 0.0003578662872314453 nb_pixel_total : 15338 time to create 1 rle with old method : 0.02025628089904785 length of segment : 190 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -117.17266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.0004940032958984375 length of segment : 42 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 117 time to create 1 rle with old method : 0.0002186298370361328 length of segment : 14 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.0003135204315185547 length of segment : 18 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 92 time to create 1 rle with old method : 0.00017905235290527344 length of segment : 8 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 207 time to create 1 rle with old method : 0.00031375885009765625 length of segment : 19 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 717 time to create 1 rle with old method : 0.0011675357818603516 length of segment : 39 time for calcul the mask position with numpy : 7.62939453125e-05 nb_pixel_total : 864 time to create 1 rle with old method : 0.0014405250549316406 length of segment : 46 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 633 time to create 1 rle with old method : 0.001065969467163086 length of segment : 31 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.00042748451232910156 length of segment : 14 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 666 time to create 1 rle with old method : 0.0009644031524658203 length of segment : 28 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 74 time to create 1 rle with old method : 0.0001480579376220703 length of segment : 10 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 239 time to create 1 rle with old method : 0.0003814697265625 length of segment : 16 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 924 time to create 1 rle with old method : 0.0013263225555419922 length of segment : 38 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.0002620220184326172 length of segment : 8 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -105.52422 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 : 5.173683166503906e-05 nb_pixel_total : 827 time to create 1 rle with old method : 0.0010981559753417969 length of segment : 38 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00034165382385253906 length of segment : 24 time for calcul the mask position with numpy : 0.00040411949157714844 nb_pixel_total : 19783 time to create 1 rle with old method : 0.024985313415527344 length of segment : 285 time for calcul the mask position with numpy : 0.00012993812561035156 nb_pixel_total : 593 time to create 1 rle with old method : 0.0009164810180664062 length of segment : 112 time for calcul the mask position with numpy : 0.00020074844360351562 nb_pixel_total : 3472 time to create 1 rle with old method : 0.004682302474975586 length of segment : 101 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 241.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 108.71328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 1728 time to create 1 rle with old method : 0.002374887466430664 length of segment : 83 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 695 time to create 1 rle with old method : 0.0010666847229003906 length of segment : 41 time for calcul the mask position with numpy : 0.0002384185791015625 nb_pixel_total : 3880 time to create 1 rle with old method : 0.005646944046020508 length of segment : 230 time for calcul the mask position with numpy : 0.0001366138458251953 nb_pixel_total : 1230 time to create 1 rle with old method : 0.001856088638305664 length of segment : 112 time for calcul the mask position with numpy : 0.000125885009765625 nb_pixel_total : 2585 time to create 1 rle with old method : 0.0034301280975341797 length of segment : 181 time for calcul the mask position with numpy : 0.0001666545867919922 nb_pixel_total : 2116 time to create 1 rle with old method : 0.0030934810638427734 length of segment : 119 Processing 1 images image shape: (280, 400, 3) min: 20.00000 max: 180.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 66.16641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0011582374572753906 nb_pixel_total : 106225 time to create 1 rle with old method : 0.13931989669799805 length of segment : 282 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.25625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.00040841102600097656 length of segment : 24 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003311634063720703 length of segment : 19 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 453 time to create 1 rle with old method : 0.0006308555603027344 length of segment : 32 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 433 time to create 1 rle with old method : 0.0006210803985595703 length of segment : 20 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004515647888183594 length of segment : 26 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 634 time to create 1 rle with old method : 0.0008854866027832031 length of segment : 39 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 890 time to create 1 rle with old method : 0.001127004623413086 length of segment : 50 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 72 time to create 1 rle with old method : 0.00012922286987304688 length of segment : 11 time for calcul the mask position with numpy : 8.893013000488281e-05 nb_pixel_total : 3048 time to create 1 rle with old method : 0.003701448440551758 length of segment : 63 time for calcul the mask position with numpy : 0.00015878677368164062 nb_pixel_total : 9559 time to create 1 rle with old method : 0.011788606643676758 length of segment : 73 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1394 time to create 1 rle with old method : 0.0016710758209228516 length of segment : 60 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.0004267692565917969 length of segment : 23 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: 145.89297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 260 time to create 1 rle with old method : 0.00038313865661621094 length of segment : 24 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.0002524852752685547 length of segment : 10 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 484 time to create 1 rle with old method : 0.0007266998291015625 length of segment : 26 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 302 time to create 1 rle with old method : 0.00043129920959472656 length of segment : 24 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.0003256797790527344 length of segment : 15 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 603 time to create 1 rle with old method : 0.0007414817810058594 length of segment : 50 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0002663135528564453 length of segment : 11 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.0006921291351318359 length of segment : 27 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006055831909179688 length of segment : 25 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 826 time to create 1 rle with old method : 0.0010759830474853516 length of segment : 37 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 513 time to create 1 rle with old method : 0.0006659030914306641 length of segment : 26 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: 151.04141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.00029015541076660156 length of segment : 20 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 1069 time to create 1 rle with old method : 0.00148773193359375 length of segment : 55 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: 144.47500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 743 time to create 1 rle with old method : 0.0009217262268066406 length of segment : 56 time for calcul the mask position with numpy : 7.104873657226562e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003466606140136719 length of segment : 57 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: -116.95391 max: 145.73672 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 47 time to create 1 rle with old method : 0.00012445449829101562 length of segment : 14 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.00041365623474121094 length of segment : 30 time for calcul the mask position with numpy : 0.0002448558807373047 nb_pixel_total : 8433 time to create 1 rle with old method : 0.012250900268554688 length of segment : 155 time for calcul the mask position with numpy : 4.649162292480469e-05 nb_pixel_total : 993 time to create 1 rle with old method : 0.0013248920440673828 length of segment : 42 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 145 time to create 1 rle with old method : 0.0001900196075439453 length of segment : 36 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 1064 time to create 1 rle with old method : 0.0013148784637451172 length of segment : 41 length of segment : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.39141 max: 149.43594 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 669 time to create 1 rle with old method : 0.0009508132934570312 length of segment : 28 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004591941833496094 length of segment : 29 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 147 time to create 1 rle with old method : 0.00022268295288085938 length of segment : 15 time for calcul the mask position with numpy : 7.390975952148438e-05 nb_pixel_total : 2467 time to create 1 rle with old method : 0.0028214454650878906 length of segment : 106 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1436 time to create 1 rle with old method : 0.002033710479736328 length of segment : 25 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 603 time to create 1 rle with old method : 0.0007841587066650391 length of segment : 29 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.000156402587890625 length of segment : 11 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.31328 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00015878677368164062 nb_pixel_total : 4152 time to create 1 rle with old method : 0.008373022079467773 length of segment : 141 time for calcul the mask position with numpy : 0.00033473968505859375 nb_pixel_total : 19968 time to create 1 rle with old method : 0.02323770523071289 length of segment : 136 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.67656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00021791458129882812 nb_pixel_total : 7128 time to create 1 rle with old method : 0.010330677032470703 length of segment : 131 time for calcul the mask position with numpy : 0.0001361370086669922 nb_pixel_total : 7249 time to create 1 rle with old method : 0.008657693862915039 length of segment : 123 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.0008563995361328125 length of segment : 30 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 227.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 105.34219 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.001065969467163086 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 22.00000 max: 196.00000 molded_images shape: (1, 640, 640, 3) min: -90.64141 max: 76.73281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0013699531555175781 nb_pixel_total : 151826 time to create 1 rle with new method : 0.002032756805419922 length of segment : 400 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.34844 max: 147.26016 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1510 time to create 1 rle with old method : 0.00200653076171875 length of segment : 49 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 284 time to create 1 rle with old method : 0.0005078315734863281 length of segment : 18 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 264 time to create 1 rle with old method : 0.0004355907440185547 length of segment : 16 time for calcul the mask position with numpy : 0.0003190040588378906 nb_pixel_total : 14894 time to create 1 rle with old method : 0.019208669662475586 length of segment : 187 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 556 time to create 1 rle with old method : 0.0007941722869873047 length of segment : 23 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0008790493011474609 length of segment : 20 time for calcul the mask position with numpy : 5.221366882324219e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.001001596450805664 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: -117.17266 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 : 5.3882598876953125e-05 nb_pixel_total : 712 time to create 1 rle with old method : 0.0010800361633300781 length of segment : 41 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 830 time to create 1 rle with old method : 0.0012161731719970703 length of segment : 35 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0003409385681152344 length of segment : 19 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001709461212158203 length of segment : 8 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 369 time to create 1 rle with old method : 0.0006380081176757812 length of segment : 22 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001697540283203125 length of segment : 12 time for calcul the mask position with numpy : 2.9802322387695312e-05 nb_pixel_total : 109 time to create 1 rle with old method : 0.00019025802612304688 length of segment : 13 Processing 1 images image shape: (400, 400, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -111.63359 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 : 5.626678466796875e-05 nb_pixel_total : 822 time to create 1 rle with old method : 0.0012750625610351562 length of segment : 37 time for calcul the mask position with numpy : 0.00010442733764648438 nb_pixel_total : 1111 time to create 1 rle with old method : 0.001497030258178711 length of segment : 136 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 586 time to create 1 rle with old method : 0.0007874965667724609 length of segment : 75 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 133 time to create 1 rle with old method : 0.00020885467529296875 length of segment : 22 time for calcul the mask position with numpy : 0.0005095005035400391 nb_pixel_total : 18472 time to create 1 rle with old method : 0.02184128761291504 length of segment : 247 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 241.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 108.04531 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.00025200843811035156 length of segment : 21 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1663 time to create 1 rle with old method : 0.001979827880859375 length of segment : 87 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 1287 time to create 1 rle with old method : 0.0015747547149658203 length of segment : 46 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1020 time to create 1 rle with old method : 0.0014154911041259766 length of segment : 36 time for calcul the mask position with numpy : 8.511543273925781e-05 nb_pixel_total : 508 time to create 1 rle with old method : 0.0007371902465820312 length of segment : 59 time for calcul the mask position with numpy : 0.00022745132446289062 nb_pixel_total : 4522 time to create 1 rle with old method : 0.005738973617553711 length of segment : 216 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 785 time to create 1 rle with old method : 0.0011227130889892578 length of segment : 43 time for calcul the mask position with numpy : 7.128715515136719e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.0011267662048339844 length of segment : 74 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0007185935974121094 length of segment : 76 Processing 1 images image shape: (280, 400, 3) min: 13.00000 max: 164.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 51.58437 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0010104179382324219 nb_pixel_total : 106108 time to create 1 rle with old method : 0.12105131149291992 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: 149.40469 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 6.461143493652344e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0005517005920410156 length of segment : 30 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00033283233642578125 length of segment : 18 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0002777576446533203 length of segment : 11 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 398 time to create 1 rle with old method : 0.0005290508270263672 length of segment : 26 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 301 time to create 1 rle with old method : 0.0004508495330810547 length of segment : 24 time for calcul the mask position with numpy : 3.981590270996094e-05 nb_pixel_total : 427 time to create 1 rle with old method : 0.0006060600280761719 length of segment : 20 time for calcul the mask position with numpy : 0.00012254714965820312 nb_pixel_total : 6700 time to create 1 rle with old method : 0.008244037628173828 length of segment : 75 time for calcul the mask position with numpy : 9.846687316894531e-05 nb_pixel_total : 3284 time to create 1 rle with old method : 0.004063844680786133 length of segment : 65 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 141 time to create 1 rle with old method : 0.000209808349609375 length of segment : 23 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003256797790527344 length of segment : 24 time for calcul the mask position with numpy : 3.218650817871094e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.00014901161193847656 length of segment : 11 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006864070892333984 length of segment : 37 time for calcul the mask position with numpy : 0.0001316070556640625 nb_pixel_total : 6855 time to create 1 rle with old method : 0.008435726165771484 length of segment : 81 time for calcul the mask position with numpy : 3.600120544433594e-05 nb_pixel_total : 68 time to create 1 rle with old method : 0.00011730194091796875 length of segment : 10 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: 147.29141 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004444122314453125 length of segment : 28 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.0002148151397705078 length of segment : 11 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 1153 time to create 1 rle with old method : 0.0014681816101074219 length of segment : 28 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 230 time to create 1 rle with old method : 0.0003674030303955078 length of segment : 16 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 673 time to create 1 rle with old method : 0.0008103847503662109 length of segment : 53 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 683 time to create 1 rle with old method : 0.0009000301361083984 length of segment : 42 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006127357482910156 length of segment : 26 time for calcul the mask position with numpy : 3.314018249511719e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0003769397735595703 length of segment : 25 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007455348968505859 length of segment : 29 time for calcul the mask position with numpy : 3.0994415283203125e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.00024771690368652344 length of segment : 10 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 469 time to create 1 rle with old method : 0.0006291866302490234 length of segment : 26 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 1141 time to create 1 rle with old method : 0.0015244483947753906 length of segment : 54 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.0001933574676513672 length of segment : 16 time for calcul the mask position with numpy : 2.9087066650390625e-05 nb_pixel_total : 62 time to create 1 rle with old method : 0.00011944770812988281 length of segment : 10 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 465 time to create 1 rle with old method : 0.0006148815155029297 length of segment : 29 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 330 time to create 1 rle with old method : 0.0004589557647705078 length of segment : 23 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 821 time to create 1 rle with old method : 0.0010564327239990234 length of segment : 91 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002999305725097656 length of segment : 18 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003807544708251953 length of segment : 15 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: 148.81484 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0004904270172119141 length of segment : 57 time for calcul the mask position with numpy : 8.749961853027344e-05 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0015769004821777344 length of segment : 51 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002593994140625 length of segment : 20 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 81 time to create 1 rle with old method : 0.00015473365783691406 length of segment : 29 time for calcul the mask position with numpy : 0.0003914833068847656 nb_pixel_total : 20158 time to create 1 rle with old method : 0.024274349212646484 length of segment : 175 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 91 time to create 1 rle with old method : 0.00015735626220703125 length of segment : 12 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0002868175506591797 length of segment : 29 time for calcul the mask position with numpy : 3.1948089599609375e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.00022912025451660156 length of segment : 15 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 595 time to create 1 rle with old method : 0.0008332729339599609 length of segment : 42 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005486011505126953 length of segment : 31 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 188 time to create 1 rle with old method : 0.0002841949462890625 length of segment : 24 time for calcul the mask position with numpy : 2.8848648071289062e-05 nb_pixel_total : 151 time to create 1 rle with old method : 0.00022792816162109375 length of segment : 15 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: 138.41250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 371 time to create 1 rle with old method : 0.0006277561187744141 length of segment : 46 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.0001621246337890625 length of segment : 11 time for calcul the mask position with numpy : 3.0040740966796875e-05 nb_pixel_total : 79 time to create 1 rle with old method : 0.000156402587890625 length of segment : 9 Detection mask done ! Trying to reset tf kernel 445669 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4465 tf kernel not reseted sub process len(results) : 181 len(list_Values) 181 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 181 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 9680 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Catched exception ! Connect or reconnect ! Number saved : None batch 1 Loaded 181 chid ids of type : 4228 Number RLEs to save : 9386 save missing photos in datou_result : time spend for datou_step_exec : 22.10413646697998 time spend to save output : 0.9155912399291992 total time spend for step 1 : 23.01972770690918 step2:brightness Sun Feb 2 21:20:53 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step calcul brightness treat image : temp/1738527629_445301_1332708752_a0a486fd0426e90f51022dc95b9b56bc.jpg treat image : temp/1738527629_445301_1332708746_e93f06fc806db3ed4106756882b515c2.jpg Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.011895418167114258 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.0159454345703125 save missing photos in datou_result : time spend for datou_step_exec : 0.5348489284515381 time spend to save output : 0.03204989433288574 total time spend for step 2 : 0.5668988227844238 step3:blur_detection Sun Feb 2 21:20:53 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure inside step blur_detection methode: ratio et variance treat image : temp/1738527629_445301_1332708752_a0a486fd0426e90f51022dc95b9b56bc.jpg resize: (1080, 1920) 1332708752 -7.46179827515616 treat image : temp/1738527629_445301_1332708746_e93f06fc806db3ed4106756882b515c2.jpg resize: (1080, 1920) 1332708746 -7.456165969511036 Inside saveOutput : final : False verbose : 0 begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 2 time used for this insertion : 0.011443853378295898 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 2 time used for this insertion : 0.013056755065917969 save missing photos in datou_result : time spend for datou_step_exec : 2.3010165691375732 time spend to save output : 0.028784990310668945 total time spend for step 3 : 2.329801559448242 step4:rle_unique_nms_with_priority Sun Feb 2 21:20:56 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 181 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 81 nb_hashtags : 5 time to prepare the origin masks : 1.065575361251831 time for calcul the mask position with numpy : 0.07505059242248535 nb_pixel_total : 1810573 time to create 1 rle with new method : 0.3084876537322998 time for calcul the mask position with numpy : 0.008322477340698242 nb_pixel_total : 55 time to create 1 rle with old method : 7.867813110351562e-05 time for calcul the mask position with numpy : 0.00832366943359375 nb_pixel_total : 124 time to create 1 rle with old method : 0.00014019012451171875 time for calcul the mask position with numpy : 0.008201360702514648 nb_pixel_total : 710 time to create 1 rle with old method : 0.0008087158203125 time for calcul the mask position with numpy : 0.008435487747192383 nb_pixel_total : 926 time to create 1 rle with old method : 0.0011281967163085938 time for calcul the mask position with numpy : 0.008433341979980469 nb_pixel_total : 132 time to create 1 rle with old method : 0.0001964569091796875 time for calcul the mask position with numpy : 0.008541584014892578 nb_pixel_total : 53491 time to create 1 rle with old method : 0.06140875816345215 time for calcul the mask position with numpy : 0.008518695831298828 nb_pixel_total : 192 time to create 1 rle with old method : 0.00025010108947753906 time for calcul the mask position with numpy : 0.008331775665283203 nb_pixel_total : 413 time to create 1 rle with old method : 0.0005190372467041016 time for calcul the mask position with numpy : 0.008313179016113281 nb_pixel_total : 1415 time to create 1 rle with old method : 0.0017039775848388672 time for calcul the mask position with numpy : 0.0082244873046875 nb_pixel_total : 226 time to create 1 rle with old method : 0.0002772808074951172 time for calcul the mask position with numpy : 0.008406877517700195 nb_pixel_total : 1499 time to create 1 rle with old method : 0.0017745494842529297 time for calcul the mask position with numpy : 0.008455038070678711 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005319118499755859 time for calcul the mask position with numpy : 0.00844264030456543 nb_pixel_total : 161 time to create 1 rle with old method : 0.00019216537475585938 time for calcul the mask position with numpy : 0.008435964584350586 nb_pixel_total : 3047 time to create 1 rle with old method : 0.003650188446044922 time for calcul the mask position with numpy : 0.008452177047729492 nb_pixel_total : 112 time to create 1 rle with old method : 0.00013756752014160156 time for calcul the mask position with numpy : 0.008446216583251953 nb_pixel_total : 554 time to create 1 rle with old method : 0.0006909370422363281 time for calcul the mask position with numpy : 0.008441925048828125 nb_pixel_total : 205 time to create 1 rle with old method : 0.00026345252990722656 time for calcul the mask position with numpy : 0.008408546447753906 nb_pixel_total : 5481 time to create 1 rle with old method : 0.0061969757080078125 time for calcul the mask position with numpy : 0.008429288864135742 nb_pixel_total : 5055 time to create 1 rle with old method : 0.005502939224243164 time for calcul the mask position with numpy : 0.008101463317871094 nb_pixel_total : 457 time to create 1 rle with old method : 0.0005168914794921875 time for calcul the mask position with numpy : 0.008084535598754883 nb_pixel_total : 955 time to create 1 rle with old method : 0.0011684894561767578 time for calcul the mask position with numpy : 0.008631229400634766 nb_pixel_total : 503 time to create 1 rle with old method : 0.0006010532379150391 time for calcul the mask position with numpy : 0.008467912673950195 nb_pixel_total : 3472 time to create 1 rle with old method : 0.003992319107055664 time for calcul the mask position with numpy : 0.008401870727539062 nb_pixel_total : 593 time to create 1 rle with old method : 0.0007145404815673828 time for calcul the mask position with numpy : 0.008424997329711914 nb_pixel_total : 827 time to create 1 rle with old method : 0.000997781753540039 time for calcul the mask position with numpy : 0.011062383651733398 nb_pixel_total : 126 time to create 1 rle with old method : 0.00021910667419433594 time for calcul the mask position with numpy : 0.010604143142700195 nb_pixel_total : 717 time to create 1 rle with old method : 0.0008962154388427734 time for calcul the mask position with numpy : 0.008425235748291016 nb_pixel_total : 695 time to create 1 rle with old method : 0.0008573532104492188 time for calcul the mask position with numpy : 0.00805521011352539 nb_pixel_total : 1390 time to create 1 rle with old method : 0.001495361328125 time for calcul the mask position with numpy : 0.008107185363769531 nb_pixel_total : 224 time to create 1 rle with old method : 0.0002810955047607422 time for calcul the mask position with numpy : 0.008457660675048828 nb_pixel_total : 19783 time to create 1 rle with old method : 0.02325129508972168 time for calcul the mask position with numpy : 0.008987188339233398 nb_pixel_total : 491 time to create 1 rle with old method : 0.0006337165832519531 time for calcul the mask position with numpy : 0.008555412292480469 nb_pixel_total : 1587 time to create 1 rle with old method : 0.002154111862182617 time for calcul the mask position with numpy : 0.008624792098999023 nb_pixel_total : 178 time to create 1 rle with old method : 0.0002980232238769531 time for calcul the mask position with numpy : 0.008528947830200195 nb_pixel_total : 1230 time to create 1 rle with old method : 0.0016353130340576172 time for calcul the mask position with numpy : 0.008703231811523438 nb_pixel_total : 14291 time to create 1 rle with old method : 0.016719818115234375 time for calcul the mask position with numpy : 0.008468151092529297 nb_pixel_total : 3872 time to create 1 rle with old method : 0.004633665084838867 time for calcul the mask position with numpy : 0.008494138717651367 nb_pixel_total : 117 time to create 1 rle with old method : 0.00014972686767578125 time for calcul the mask position with numpy : 0.008297920227050781 nb_pixel_total : 864 time to create 1 rle with old method : 0.0010139942169189453 time for calcul the mask position with numpy : 0.008220195770263672 nb_pixel_total : 316 time to create 1 rle with old method : 0.0003876686096191406 time for calcul the mask position with numpy : 0.007946014404296875 nb_pixel_total : 633 time to create 1 rle with old method : 0.0007350444793701172 time for calcul the mask position with numpy : 0.008075952529907227 nb_pixel_total : 330 time to create 1 rle with old method : 0.0003886222839355469 time for calcul the mask position with numpy : 0.008419275283813477 nb_pixel_total : 113 time to create 1 rle with old method : 0.00014281272888183594 time for calcul the mask position with numpy : 0.008682489395141602 nb_pixel_total : 819 time to create 1 rle with old method : 0.001129150390625 time for calcul the mask position with numpy : 0.008579015731811523 nb_pixel_total : 207 time to create 1 rle with old method : 0.00025916099548339844 time for calcul the mask position with numpy : 0.008501291275024414 nb_pixel_total : 92 time to create 1 rle with old method : 0.00012087821960449219 time for calcul the mask position with numpy : 0.00851750373840332 nb_pixel_total : 924 time to create 1 rle with old method : 0.0010821819305419922 time for calcul the mask position with numpy : 0.008590936660766602 nb_pixel_total : 1728 time to create 1 rle with old method : 0.001995563507080078 time for calcul the mask position with numpy : 0.00872492790222168 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003666877746582031 time for calcul the mask position with numpy : 0.008800268173217773 nb_pixel_total : 666 time to create 1 rle with old method : 0.00079345703125 time for calcul the mask position with numpy : 0.008751153945922852 nb_pixel_total : 15 time to create 1 rle with old method : 4.124641418457031e-05 time for calcul the mask position with numpy : 0.008506059646606445 nb_pixel_total : 259 time to create 1 rle with old method : 0.0003476142883300781 time for calcul the mask position with numpy : 0.01017308235168457 nb_pixel_total : 74 time to create 1 rle with old method : 0.000125885009765625 time for calcul the mask position with numpy : 0.009322643280029297 nb_pixel_total : 106225 time to create 1 rle with old method : 0.1219325065612793 time for calcul the mask position with numpy : 0.008692026138305664 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002999305725097656 time for calcul the mask position with numpy : 0.008689641952514648 nb_pixel_total : 342 time to create 1 rle with old method : 0.0004622936248779297 time for calcul the mask position with numpy : 0.008712053298950195 nb_pixel_total : 1394 time to create 1 rle with old method : 0.0016734600067138672 time for calcul the mask position with numpy : 0.008634805679321289 nb_pixel_total : 302 time to create 1 rle with old method : 0.0003726482391357422 time for calcul the mask position with numpy : 0.008489847183227539 nb_pixel_total : 154 time to create 1 rle with old method : 0.0001876354217529297 time for calcul the mask position with numpy : 0.008452177047729492 nb_pixel_total : 634 time to create 1 rle with old method : 0.0007648468017578125 time for calcul the mask position with numpy : 0.008238554000854492 nb_pixel_total : 484 time to create 1 rle with old method : 0.0005507469177246094 time for calcul the mask position with numpy : 0.00792694091796875 nb_pixel_total : 183 time to create 1 rle with old method : 0.000225067138671875 time for calcul the mask position with numpy : 0.007976055145263672 nb_pixel_total : 3048 time to create 1 rle with old method : 0.003635883331298828 time for calcul the mask position with numpy : 0.008217096328735352 nb_pixel_total : 72 time to create 1 rle with old method : 0.00011134147644042969 time for calcul the mask position with numpy : 0.008347511291503906 nb_pixel_total : 260 time to create 1 rle with old method : 0.00033020973205566406 time for calcul the mask position with numpy : 0.008394956588745117 nb_pixel_total : 130 time to create 1 rle with old method : 0.00016236305236816406 time for calcul the mask position with numpy : 0.008633136749267578 nb_pixel_total : 282 time to create 1 rle with old method : 0.0003509521484375 time for calcul the mask position with numpy : 0.00858616828918457 nb_pixel_total : 43 time to create 1 rle with old method : 8.702278137207031e-05 time for calcul the mask position with numpy : 0.008550405502319336 nb_pixel_total : 470 time to create 1 rle with old method : 0.0005762577056884766 time for calcul the mask position with numpy : 0.008576631546020508 nb_pixel_total : 453 time to create 1 rle with old method : 0.0005517005920410156 time for calcul the mask position with numpy : 0.008490324020385742 nb_pixel_total : 826 time to create 1 rle with old method : 0.0009510517120361328 time for calcul the mask position with numpy : 0.008511781692504883 nb_pixel_total : 1069 time to create 1 rle with old method : 0.0014336109161376953 time for calcul the mask position with numpy : 0.008469343185424805 nb_pixel_total : 743 time to create 1 rle with old method : 0.0010061264038085938 time for calcul the mask position with numpy : 0.008462905883789062 nb_pixel_total : 433 time to create 1 rle with old method : 0.0005667209625244141 time for calcul the mask position with numpy : 0.008485794067382812 nb_pixel_total : 9470 time to create 1 rle with old method : 0.011624336242675781 time for calcul the mask position with numpy : 0.008175373077392578 nb_pixel_total : 218 time to create 1 rle with old method : 0.0002942085266113281 time for calcul the mask position with numpy : 0.008103132247924805 nb_pixel_total : 603 time to create 1 rle with old method : 0.0007271766662597656 time for calcul the mask position with numpy : 0.008361101150512695 nb_pixel_total : 302 time to create 1 rle with old method : 0.000392913818359375 time for calcul the mask position with numpy : 0.008350849151611328 nb_pixel_total : 890 time to create 1 rle with old method : 0.0011401176452636719 time for calcul the mask position with numpy : 0.008444547653198242 nb_pixel_total : 503 time to create 1 rle with old method : 0.0006551742553710938 time for calcul the mask position with numpy : 0.008157730102539062 nb_pixel_total : 220 time to create 1 rle with old method : 0.00024890899658203125 create new chi : 1.3915810585021973 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.018218278884887695 batch 1 Loaded 82 chid ids of type : 4230 Number RLEs to save : 9354 TO DO : save crop sub photo not yet done ! save time : 0.5280158519744873 nb_obj : 97 nb_hashtags : 5 time to prepare the origin masks : 1.981522560119629 time for calcul the mask position with numpy : 0.05193662643432617 nb_pixel_total : 1669926 time to create 1 rle with new method : 0.12984561920166016 time for calcul the mask position with numpy : 0.010906219482421875 nb_pixel_total : 19968 time to create 1 rle with old method : 0.026459455490112305 time for calcul the mask position with numpy : 0.006213665008544922 nb_pixel_total : 47 time to create 1 rle with old method : 8.082389831542969e-05 time for calcul the mask position with numpy : 0.00616002082824707 nb_pixel_total : 102 time to create 1 rle with old method : 0.00016188621520996094 time for calcul the mask position with numpy : 0.006511688232421875 nb_pixel_total : 145 time to create 1 rle with old method : 0.00019478797912597656 time for calcul the mask position with numpy : 0.0064008235931396484 nb_pixel_total : 669 time to create 1 rle with old method : 0.0007994174957275391 time for calcul the mask position with numpy : 0.007527589797973633 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002541542053222656 time for calcul the mask position with numpy : 0.011785507202148438 nb_pixel_total : 993 time to create 1 rle with old method : 0.0012216567993164062 time for calcul the mask position with numpy : 0.011152267456054688 nb_pixel_total : 103 time to create 1 rle with old method : 0.0001361370086669922 time for calcul the mask position with numpy : 0.009883403778076172 nb_pixel_total : 1436 time to create 1 rle with old method : 0.0016598701477050781 time for calcul the mask position with numpy : 0.009713888168334961 nb_pixel_total : 8433 time to create 1 rle with old method : 0.00954890251159668 time for calcul the mask position with numpy : 0.010681390762329102 nb_pixel_total : 2467 time to create 1 rle with old method : 0.0026912689208984375 time for calcul the mask position with numpy : 0.01004934310913086 nb_pixel_total : 332 time to create 1 rle with old method : 0.0004105567932128906 time for calcul the mask position with numpy : 0.009912729263305664 nb_pixel_total : 603 time to create 1 rle with old method : 0.0006654262542724609 time for calcul the mask position with numpy : 0.010210514068603516 nb_pixel_total : 147 time to create 1 rle with old method : 0.00019311904907226562 time for calcul the mask position with numpy : 0.010120630264282227 nb_pixel_total : 498 time to create 1 rle with old method : 0.0006289482116699219 time for calcul the mask position with numpy : 0.01033473014831543 nb_pixel_total : 4152 time to create 1 rle with old method : 0.0049457550048828125 time for calcul the mask position with numpy : 0.01019597053527832 nb_pixel_total : 7128 time to create 1 rle with old method : 0.00805211067199707 time for calcul the mask position with numpy : 0.013384103775024414 nb_pixel_total : 540 time to create 1 rle with old method : 0.0007510185241699219 time for calcul the mask position with numpy : 0.01106715202331543 nb_pixel_total : 524 time to create 1 rle with old method : 0.0006606578826904297 time for calcul the mask position with numpy : 0.011393308639526367 nb_pixel_total : 151826 time to create 1 rle with new method : 0.4640674591064453 time for calcul the mask position with numpy : 0.009243249893188477 nb_pixel_total : 369 time to create 1 rle with old method : 0.0004553794860839844 time for calcul the mask position with numpy : 0.009935855865478516 nb_pixel_total : 822 time to create 1 rle with old method : 0.0009720325469970703 time for calcul the mask position with numpy : 0.009915590286254883 nb_pixel_total : 785 time to create 1 rle with old method : 0.0009553432464599609 time for calcul the mask position with numpy : 0.009970903396606445 nb_pixel_total : 1510 time to create 1 rle with old method : 0.0018775463104248047 time for calcul the mask position with numpy : 0.010088443756103516 nb_pixel_total : 586 time to create 1 rle with old method : 0.0007236003875732422 time for calcul the mask position with numpy : 0.010089397430419922 nb_pixel_total : 160 time to create 1 rle with old method : 0.0001964569091796875 time for calcul the mask position with numpy : 0.010283708572387695 nb_pixel_total : 133 time to create 1 rle with old method : 0.0002617835998535156 time for calcul the mask position with numpy : 0.009758472442626953 nb_pixel_total : 1020 time to create 1 rle with old method : 0.0011658668518066406 time for calcul the mask position with numpy : 0.01022481918334961 nb_pixel_total : 71 time to create 1 rle with old method : 0.0001270771026611328 time for calcul the mask position with numpy : 0.010254621505737305 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007383823394775391 time for calcul the mask position with numpy : 0.006875038146972656 nb_pixel_total : 95 time to create 1 rle with old method : 0.00013327598571777344 time for calcul the mask position with numpy : 0.006189823150634766 nb_pixel_total : 15 time to create 1 rle with old method : 4.4345855712890625e-05 time for calcul the mask position with numpy : 0.006308078765869141 nb_pixel_total : 14622 time to create 1 rle with old method : 0.018427371978759766 time for calcul the mask position with numpy : 0.00618433952331543 nb_pixel_total : 712 time to create 1 rle with old method : 0.0009167194366455078 time for calcul the mask position with numpy : 0.00670933723449707 nb_pixel_total : 4522 time to create 1 rle with old method : 0.005347728729248047 time for calcul the mask position with numpy : 0.006456613540649414 nb_pixel_total : 18468 time to create 1 rle with old method : 0.020930767059326172 time for calcul the mask position with numpy : 0.006191730499267578 nb_pixel_total : 1111 time to create 1 rle with old method : 0.0013339519500732422 time for calcul the mask position with numpy : 0.005964040756225586 nb_pixel_total : 507 time to create 1 rle with old method : 0.0006031990051269531 time for calcul the mask position with numpy : 0.005662679672241211 nb_pixel_total : 830 time to create 1 rle with old method : 0.0009837150573730469 time for calcul the mask position with numpy : 0.005830049514770508 nb_pixel_total : 284 time to create 1 rle with old method : 0.0003285408020019531 time for calcul the mask position with numpy : 0.005734920501708984 nb_pixel_total : 1287 time to create 1 rle with old method : 0.001352548599243164 time for calcul the mask position with numpy : 0.00621342658996582 nb_pixel_total : 197 time to create 1 rle with old method : 0.00022268295288085938 time for calcul the mask position with numpy : 0.006069183349609375 nb_pixel_total : 580 time to create 1 rle with old method : 0.0007677078247070312 time for calcul the mask position with numpy : 0.006314277648925781 nb_pixel_total : 90 time to create 1 rle with old method : 0.00013017654418945312 time for calcul the mask position with numpy : 0.01459503173828125 nb_pixel_total : 33 time to create 1 rle with old method : 6.818771362304688e-05 time for calcul the mask position with numpy : 0.010835886001586914 nb_pixel_total : 1663 time to create 1 rle with old method : 0.0019865036010742188 time for calcul the mask position with numpy : 0.007348537445068359 nb_pixel_total : 556 time to create 1 rle with old method : 0.0006349086761474609 time for calcul the mask position with numpy : 0.009759187698364258 nb_pixel_total : 264 time to create 1 rle with old method : 0.00033092498779296875 time for calcul the mask position with numpy : 0.010404586791992188 nb_pixel_total : 106108 time to create 1 rle with old method : 0.12146711349487305 time for calcul the mask position with numpy : 0.01100301742553711 nb_pixel_total : 62 time to create 1 rle with old method : 9.894371032714844e-05 time for calcul the mask position with numpy : 0.010073423385620117 nb_pixel_total : 371 time to create 1 rle with old method : 0.00046539306640625 time for calcul the mask position with numpy : 0.010551929473876953 nb_pixel_total : 398 time to create 1 rle with old method : 0.0004572868347167969 time for calcul the mask position with numpy : 0.010617733001708984 nb_pixel_total : 20158 time to create 1 rle with old method : 0.022534608840942383 time for calcul the mask position with numpy : 0.009999513626098633 nb_pixel_total : 278 time to create 1 rle with old method : 0.0003814697265625 time for calcul the mask position with numpy : 0.007150888442993164 nb_pixel_total : 247 time to create 1 rle with old method : 0.0003554821014404297 time for calcul the mask position with numpy : 0.009409189224243164 nb_pixel_total : 146 time to create 1 rle with old method : 0.00019025802612304688 time for calcul the mask position with numpy : 0.00990748405456543 nb_pixel_total : 146 time to create 1 rle with old method : 0.00020623207092285156 time for calcul the mask position with numpy : 0.008901596069335938 nb_pixel_total : 489 time to create 1 rle with old method : 0.0005590915679931641 time for calcul the mask position with numpy : 0.009102106094360352 nb_pixel_total : 138 time to create 1 rle with old method : 0.0001785755157470703 time for calcul the mask position with numpy : 0.00970149040222168 nb_pixel_total : 115 time to create 1 rle with old method : 0.00015807151794433594 time for calcul the mask position with numpy : 0.010018587112426758 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006043910980224609 time for calcul the mask position with numpy : 0.009974241256713867 nb_pixel_total : 151 time to create 1 rle with old method : 0.00020694732666015625 time for calcul the mask position with numpy : 0.009778976440429688 nb_pixel_total : 170 time to create 1 rle with old method : 0.0002243518829345703 time for calcul the mask position with numpy : 0.011183977127075195 nb_pixel_total : 259 time to create 1 rle with old method : 0.00030493736267089844 time for calcul the mask position with numpy : 0.010718107223510742 nb_pixel_total : 81 time to create 1 rle with old method : 0.00011968612670898438 time for calcul the mask position with numpy : 0.00916290283203125 nb_pixel_total : 141 time to create 1 rle with old method : 0.00022935867309570312 time for calcul the mask position with numpy : 0.00958561897277832 nb_pixel_total : 79 time to create 1 rle with old method : 0.00011563301086425781 time for calcul the mask position with numpy : 0.009620904922485352 nb_pixel_total : 3284 time to create 1 rle with old method : 0.0037856101989746094 time for calcul the mask position with numpy : 0.009443998336791992 nb_pixel_total : 90 time to create 1 rle with old method : 0.00012922286987304688 time for calcul the mask position with numpy : 0.00989675521850586 nb_pixel_total : 68 time to create 1 rle with old method : 8.988380432128906e-05 time for calcul the mask position with numpy : 0.010658979415893555 nb_pixel_total : 84 time to create 1 rle with old method : 0.00012993812561035156 time for calcul the mask position with numpy : 0.009633541107177734 nb_pixel_total : 330 time to create 1 rle with old method : 0.0004153251647949219 time for calcul the mask position with numpy : 0.00996851921081543 nb_pixel_total : 312 time to create 1 rle with old method : 0.00038933753967285156 time for calcul the mask position with numpy : 0.008817195892333984 nb_pixel_total : 125 time to create 1 rle with old method : 0.00016999244689941406 time for calcul the mask position with numpy : 0.010192632675170898 nb_pixel_total : 301 time to create 1 rle with old method : 0.0003800392150878906 time for calcul the mask position with numpy : 0.009851217269897461 nb_pixel_total : 469 time to create 1 rle with old method : 0.0005753040313720703 time for calcul the mask position with numpy : 0.011189699172973633 nb_pixel_total : 465 time to create 1 rle with old method : 0.000583648681640625 time for calcul the mask position with numpy : 0.010250329971313477 nb_pixel_total : 399 time to create 1 rle with old method : 0.0004994869232177734 time for calcul the mask position with numpy : 0.009918928146362305 nb_pixel_total : 683 time to create 1 rle with old method : 0.0008356571197509766 time for calcul the mask position with numpy : 0.009763240814208984 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003609657287597656 time for calcul the mask position with numpy : 0.009600639343261719 nb_pixel_total : 332 time to create 1 rle with old method : 0.0003819465637207031 time for calcul the mask position with numpy : 0.008815288543701172 nb_pixel_total : 194 time to create 1 rle with old method : 0.00024628639221191406 time for calcul the mask position with numpy : 0.008097410202026367 nb_pixel_total : 427 time to create 1 rle with old method : 0.0004990100860595703 time for calcul the mask position with numpy : 0.008095264434814453 nb_pixel_total : 199 time to create 1 rle with old method : 0.00029206275939941406 time for calcul the mask position with numpy : 0.008247613906860352 nb_pixel_total : 6650 time to create 1 rle with old method : 0.0076978206634521484 time for calcul the mask position with numpy : 0.008319616317749023 nb_pixel_total : 213 time to create 1 rle with old method : 0.0002849102020263672 time for calcul the mask position with numpy : 0.008219718933105469 nb_pixel_total : 673 time to create 1 rle with old method : 0.0008466243743896484 time for calcul the mask position with numpy : 0.008152246475219727 nb_pixel_total : 821 time to create 1 rle with old method : 0.0009546279907226562 time for calcul the mask position with numpy : 0.008264303207397461 nb_pixel_total : 395 time to create 1 rle with old method : 0.0004940032958984375 time for calcul the mask position with numpy : 0.008426904678344727 nb_pixel_total : 91 time to create 1 rle with old method : 0.0001163482666015625 time for calcul the mask position with numpy : 0.008112430572509766 nb_pixel_total : 169 time to create 1 rle with old method : 0.0005340576171875 time for calcul the mask position with numpy : 0.008111715316772461 nb_pixel_total : 598 time to create 1 rle with old method : 0.0007052421569824219 time for calcul the mask position with numpy : 0.00801396369934082 nb_pixel_total : 1141 time to create 1 rle with old method : 0.0013337135314941406 time for calcul the mask position with numpy : 0.008120298385620117 nb_pixel_total : 1102 time to create 1 rle with old method : 0.0012538433074951172 time for calcul the mask position with numpy : 0.008327960968017578 nb_pixel_total : 174 time to create 1 rle with old method : 0.00021982192993164062 time for calcul the mask position with numpy : 0.0081939697265625 nb_pixel_total : 1153 time to create 1 rle with old method : 0.0012881755828857422 time for calcul the mask position with numpy : 0.009001493453979492 nb_pixel_total : 230 time to create 1 rle with old method : 0.0002689361572265625 create new chi : 1.834951639175415 after preparing all the mask , begin to delete the rle from the crop_hashtag_id => VR 28-11-20 : il faut déplacer cela apres le save_crop_hashtag_ids_obj de la ligne 9514 ! we have 0 chi objets contains the rles time to delete rle : 0.002003192901611328 batch 1 Loaded 98 chid ids of type : 4230 Number RLEs to save : 10613 TO DO : save crop sub photo not yet done ! save time : 0.5965213775634766 map_output_result : {1332708752: (0.0, 'Should be the crop_list due to order', 0.0), 1332708746: (0.0, 'Should be the crop_list due to order', 0.0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1332708752, 1332708746] Looping around the photos to save general results len do output : 2 /1332708752.Didn't retrieve data . /1332708746.Didn't retrieve data . before output type Used above Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2538473') ('4234', '20047140', '1332708752', None, None, None, None, None, '2538473') ('4234', None, None, None, None, None, None, None, '2538473') ('4234', '20047140', '1332708746', None, None, None, None, None, '2538473') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.011654138565063477 save_final save missing photos in datou_result : time spend for datou_step_exec : 7.625047445297241 time spend to save output : 0.012034177780151367 total time spend for step 4 : 7.637081623077393 step5:crop_condition Sun Feb 2 21:21:03 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure some photos are not treated, begin crop_condition Loading chi in step crop with photo_hashtag_type : 4230 Loading chi in step crop for list_pids : 2 ! batch 1 Loaded 180 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 62 About to insert : list_path_to_insert length 62 new photo from crops ! About to upload 62 photos upload in portfolio : 4869462 init cache_photo without model_param we have 62 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738527665_445301 we have uploaded 62 photos in the portfolio 4869462 time of upload the photos Elapsed time : 12.529043197631836 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 17 About to insert : list_path_to_insert length 17 new photo from crops ! About to upload 17 photos upload in portfolio : 4869462 init cache_photo without model_param we have 17 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738527678_445301 we have uploaded 17 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.556154727935791 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 11 About to insert : list_path_to_insert length 11 new photo from crops ! About to upload 11 photos upload in portfolio : 4869462 init cache_photo without model_param we have 11 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738527683_445301 we have uploaded 11 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.85830020904541 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 31 About to insert : list_path_to_insert length 31 new photo from crops ! About to upload 31 photos upload in portfolio : 4869462 init cache_photo without model_param we have 31 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1738527686_445301 we have uploaded 31 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.507085800170898 we have finished the crop for the class : autre begin to crop the class : pehd param for this class : {'min_score': 0.6} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : pet_fonce param for this class : {'min_score': 0.6} filtre for class : pet_fonce hashtag_id of this class : 2107755900 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1332708752, 1332708746] Looping around the photos to save general results len do output : 121 /1334002794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002800Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002801Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002815Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002817Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002853Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002855Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002858Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002862Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002866Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002870Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002878Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002879Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002880Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002881Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002882Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002883Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002884Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002885Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002886Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002887Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002888Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002899Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002906Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002907Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002908Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002909Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002910Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002911Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002912Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002913Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002914Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002915Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002916Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002917Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002918Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002919Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002920Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002921Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002922Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002923Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002924Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002925Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002926Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1334002927Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2538473') ('4234', '20047140', '1332708752', None, None, None, None, None, '2538473') ('4234', None, None, None, None, None, None, None, '2538473') ('4234', '20047140', '1332708746', None, None, None, None, None, '2538473') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 365 time used for this insertion : 0.028041839599609375 save_final save missing photos in datou_result : time spend for datou_step_exec : 28.888381242752075 time spend to save output : 0.031624555587768555 total time spend for step 5 : 28.920005798339844 step6:thcl Sun Feb 2 21:21:32 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 Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step Thcl ! we are using the classfication for only one thcl 3237 time to import caffe and check if the image exist : 0.0033936500549316406 time to convert the images to numpy array : 0.007254838943481445 time to import caffe and check if the image exist : 0.009618520736694336 time to convert the images to numpy array : 0.026354074478149414 time to import caffe and check if the image exist : 0.008366107940673828 time to convert the images to numpy array : 0.04262733459472656 time to import caffe and check if the image exist : 0.018474102020263672 time to convert the images to numpy array : 0.03332924842834473 time to import caffe and check if the image exist : 0.019351482391357422 time to convert the images to numpy array : 0.03264904022216797 time to import caffe and check if the image exist : 0.008583784103393555 time to convert the images to numpy array : 0.04538416862487793 time to import caffe and check if the image exist : 0.012140512466430664 time to convert the images to numpy array : 0.042894840240478516 time to import caffe and check if the image exist : 0.011575698852539062 time to convert the images to numpy array : 0.04273819923400879 time to import caffe and check if the image exist : 0.009662151336669922 time to convert the images to numpy array : 0.045885324478149414 time to import caffe and check if the image exist : 0.01597762107849121 time to convert the images to numpy array : 0.03979969024658203 total time to convert the images to numpy array : 0.30813050270080566 list photo_ids error: [] list photo_ids correct : [1334002924, 1334002925, 1334002926, 1334002927, 1334002846, 1334002847, 1334002848, 1334002849, 1334002850, 1334002851, 1334002852, 1334002853, 1334002854, 1334002855, 1334002856, 1334002857, 1334002858, 1334002820, 1334002821, 1334002822, 1334002823, 1334002824, 1334002825, 1334002826, 1334002827, 1334002828, 1334002829, 1334002830, 1334002831, 1334002832, 1334002807, 1334002808, 1334002809, 1334002810, 1334002811, 1334002812, 1334002813, 1334002814, 1334002815, 1334002816, 1334002817, 1334002818, 1334002819, 1334002897, 1334002898, 1334002899, 1334002900, 1334002901, 1334002902, 1334002904, 1334002905, 1334002906, 1334002907, 1334002908, 1334002909, 1334002910, 1334002833, 1334002834, 1334002835, 1334002836, 1334002837, 1334002838, 1334002839, 1334002840, 1334002841, 1334002842, 1334002843, 1334002844, 1334002845, 1334002794, 1334002795, 1334002796, 1334002797, 1334002798, 1334002799, 1334002800, 1334002801, 1334002802, 1334002803, 1334002804, 1334002805, 1334002806, 1334002872, 1334002878, 1334002879, 1334002880, 1334002881, 1334002882, 1334002883, 1334002884, 1334002885, 1334002886, 1334002887, 1334002888, 1334002896, 1334002859, 1334002860, 1334002861, 1334002862, 1334002863, 1334002864, 1334002865, 1334002866, 1334002867, 1334002868, 1334002869, 1334002870, 1334002871, 1334002911, 1334002912, 1334002913, 1334002914, 1334002915, 1334002916, 1334002917, 1334002918, 1334002919, 1334002920, 1334002921, 1334002922, 1334002923] number of photos to traite : 121 try to delete the photos incorrect in DB tagging for thcl : 3237 To do loadFromThcl(), then load ParamDescType : thcl3237 thcls : [{'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'}] thcl {'id': 3237, 'mtr_user_id': 31, 'name': 'learn_rubbia_refus_2500', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton,Film_plastique,PEHD,PET_clair,PET_fonce,Papier,Tetrapak,flou,mal_croppe,metal,refus', 'svm_portfolios_learning': '4865689,4865690,4865686,4865684,4865685,4865688,4865691,4865693,4865692,4865687,4865683', 'photo_hashtag_type': 4158, 'photo_desc_type': 5561, 'type_classification': 'caffe', 'hashtag_id_list': '492774966,2107756122,628944319,2107755846,2107755900,492668766,609991870,492777938,2107755527,492628673,538914404'} Update svm_hashtag_type_desc : 5561 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)) To loadFromThcl() : net_5561 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 5264 max_wait_temp : 1 max_wait : 0 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)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_rubbia_refus_2500 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_rubbia_refus_2500 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_rubbia_refus_2500 /data/models_weight/learn_rubbia_refus_2500/caffemodel size_local : 94358479 size in s3 : 94358479 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:16 caffemodel already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2021-12-03 18:29:39 create time in s3 : 2021-12-02 17:49:15 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:09:52 mean.npy already exist and didn't need to update /data/models_weight/learn_rubbia_refus_2500/synset_words.txt size_local : 334 size in s3 : 334 create time local : 2021-12-03 18:29:40 create time in s3 : 2021-12-02 18:10:06 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /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/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_rubbia_refus_2500/deploy.prototxt caffemodel_filename : /data/models_weight/learn_rubbia_refus_2500/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory WARNING: Logging before InitGoogleLogging() is written to STDERR F0202 21:21:37.825327 445301 im2col.cu:61] Check failed: error == cudaSuccess (715 vs. 0) an illegal instruction was encountered *** Check failure stack trace: *** Command terminated by signal 6 27.94user 22.68system 1:14.03elapsed 68%CPU (0avgtext+0avgdata 2457512maxresident)k 680inputs+5312outputs (6major+2150055minor)pagefaults 0swaps