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 : 4148014 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 : ['2627698'] with mtr_portfolio_ids : ['20957637'] and first list_photo_ids : [] new path : /proc/4148014/ 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 : 0.3156168460845947 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Mon Mar 3 03:20:30 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 : 10814 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-03 03:20:33.358061: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-03 03:20:33.383134: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-03 03:20:33.385183: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9158000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-03 03:20:33.385245: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-03 03:20:33.389192: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-03 03:20:33.611363: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1ec41980 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-03 03:20:33.611414: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-03 03:20:33.612838: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-03 03:20:33.613245: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 03:20:33.616422: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 03:20:33.618960: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-03 03:20:33.619356: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-03 03:20:33.622167: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-03 03:20:33.623549: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-03 03:20:33.628863: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-03 03:20:33.630276: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-03 03:20:33.630345: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 03:20:33.631094: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-03 03:20:33.631112: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-03 03:20:33.631121: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-03 03:20:33.632380: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10023 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-03-03 03:20:33.878285: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-03 03:20:33.878404: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 03:20:33.878427: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 03:20:33.878450: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-03 03:20:33.878469: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-03 03:20:33.878489: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-03 03:20:33.878508: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-03 03:20:33.878529: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-03 03:20:33.880182: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-03 03:20:33.881542: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-03-03 03:20:33.881576: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-03 03:20:33.881595: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 03:20:33.881612: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-03 03:20:33.881629: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-03 03:20:33.881646: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-03 03:20:33.881663: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-03 03:20:33.881680: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-03 03:20:33.883329: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-03 03:20:33.883372: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-03 03:20:33.883383: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-03 03:20:33.883394: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-03 03:20:33.884846: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10023 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2847 thcls : [{'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5275 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5275, 'learn_RUBBIA_REFUS_AMIENS_23', 16384, 25088, 'learn_RUBBIA_REFUS_AMIENS_23', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 23, 14, 19, 39), datetime.datetime(2021, 4, 23, 14, 19, 39)) {'thcl': {'id': 2847, 'mtr_user_id': 31, 'name': 'learn_RUBBIA_REFUS_AMIENS_23', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'photo_desc_type': 5275, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'], 'list_hashtags_csv': 'background,papier,carton,metal,pet_clair,autre,pehd,pet_fonce,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3594, 'svm_hashtag_type_desc': 5275, 'photo_desc_type': 5275, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_RUBBIA_REFUS_AMIENS_23 NUM_CLASSES 9 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_RUBBIA_REFUS_AMIENS_23 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-03-03 03:20:40.553071: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-03 03:20:40.731824: 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: -118.95781 max: 150.23281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0008492469787597656 length of segment : 29 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0010106563568115234 length of segment : 56 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 1134 time to create 1 rle with old method : 0.002092123031616211 length of segment : 28 time for calcul the mask position with numpy : 4.839897155761719e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.0004935264587402344 length of segment : 35 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002741813659667969 length of segment : 19 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 765 time to create 1 rle with old method : 0.0011005401611328125 length of segment : 50 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 798 time to create 1 rle with old method : 0.0010895729064941406 length of segment : 38 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 525 time to create 1 rle with old method : 0.0007398128509521484 length of segment : 60 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.13359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.00023651123046875 nb_pixel_total : 204 time to create 1 rle with old method : 0.0005178451538085938 length of segment : 52 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1622 time to create 1 rle with old method : 0.0027151107788085938 length of segment : 33 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 213 time to create 1 rle with old method : 0.00034046173095703125 length of segment : 14 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 2350 time to create 1 rle with old method : 0.002889394760131836 length of segment : 86 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 594 time to create 1 rle with old method : 0.0008418560028076172 length of segment : 50 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.87578 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 : 5.221366882324219e-05 nb_pixel_total : 379 time to create 1 rle with old method : 0.0006976127624511719 length of segment : 29 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 492 time to create 1 rle with old method : 0.0009639263153076172 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -119.84063 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 : 3.6716461181640625e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003235340118408203 length of segment : 21 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0005977153778076172 length of segment : 46 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 229.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 112.03750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 541 time to create 1 rle with old method : 0.0008037090301513672 length of segment : 18 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.00037169456481933594 length of segment : 20 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 524 time to create 1 rle with old method : 0.0010652542114257812 length of segment : 46 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 443 time to create 1 rle with old method : 0.0005681514739990234 length of segment : 52 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.00047135353088378906 length of segment : 46 time for calcul the mask position with numpy : 0.00069427490234375 nb_pixel_total : 68427 time to create 1 rle with old method : 0.08213639259338379 length of segment : 292 Processing 1 images image shape: (400, 400, 3) min: 24.00000 max: 198.00000 molded_images shape: (1, 640, 640, 3) min: -91.50469 max: 80.78750 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: -114.18828 max: 150.61953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 498 time to create 1 rle with old method : 0.000682830810546875 length of segment : 29 time for calcul the mask position with numpy : 6.890296936035156e-05 nb_pixel_total : 2376 time to create 1 rle with old method : 0.0030965805053710938 length of segment : 48 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 118 time to create 1 rle with old method : 0.00019478797912597656 length of segment : 16 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.00035500526428222656 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -115.06719 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.0003123283386230469 length of segment : 17 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 722 time to create 1 rle with old method : 0.0009164810180664062 length of segment : 30 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 796 time to create 1 rle with old method : 0.0010776519775390625 length of segment : 31 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 399 time to create 1 rle with old method : 0.0006279945373535156 length of segment : 30 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.0008046627044677734 length of segment : 20 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 468 time to create 1 rle with old method : 0.0006120204925537109 length of segment : 31 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 627 time to create 1 rle with old method : 0.0009307861328125 length of segment : 29 time for calcul the mask position with numpy : 3.170967102050781e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.00032138824462890625 length of segment : 11 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00036025047302246094 length of segment : 12 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 628 time to create 1 rle with old method : 0.0009191036224365234 length of segment : 21 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.18438 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1474 time to create 1 rle with old method : 0.0019731521606445312 length of segment : 43 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1316 time to create 1 rle with old method : 0.0016613006591796875 length of segment : 41 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 1487 time to create 1 rle with old method : 0.0019466876983642578 length of segment : 106 time for calcul the mask position with numpy : 0.000244140625 nb_pixel_total : 9484 time to create 1 rle with old method : 0.011118412017822266 length of segment : 272 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0009992122650146484 length of segment : 36 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 1330 time to create 1 rle with old method : 0.001661539077758789 length of segment : 40 time for calcul the mask position with numpy : 4.076957702636719e-05 nb_pixel_total : 797 time to create 1 rle with old method : 0.0009980201721191406 length of segment : 38 time for calcul the mask position with numpy : 0.000217437744140625 nb_pixel_total : 6780 time to create 1 rle with old method : 0.008194684982299805 length of segment : 199 time for calcul the mask position with numpy : 7.152557373046875e-05 nb_pixel_total : 1097 time to create 1 rle with old method : 0.0015745162963867188 length of segment : 44 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 236.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 98.35781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0008227825164794922 length of segment : 66 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.0003085136413574219 length of segment : 29 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 1211 time to create 1 rle with old method : 0.0016477108001708984 length of segment : 126 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 1282 time to create 1 rle with old method : 0.0016481876373291016 length of segment : 80 time for calcul the mask position with numpy : 0.00017905235290527344 nb_pixel_total : 4124 time to create 1 rle with old method : 0.005047798156738281 length of segment : 194 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0006525516510009766 length of segment : 62 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 717 time to create 1 rle with old method : 0.0010361671447753906 length of segment : 36 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003750324249267578 length of segment : 30 Processing 1 images image shape: (280, 400, 3) min: 17.00000 max: 182.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 70.47109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 499 time to create 1 rle with old method : 0.0007023811340332031 length of segment : 68 time for calcul the mask position with numpy : 0.0010008811950683594 nb_pixel_total : 102998 time to create 1 rle with old method : 0.12283468246459961 length of segment : 283 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: 151.08828 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 1728 time to create 1 rle with old method : 0.0021626949310302734 length of segment : 39 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 3106 time to create 1 rle with old method : 0.0039899349212646484 length of segment : 47 time for calcul the mask position with numpy : 9.989738464355469e-05 nb_pixel_total : 3814 time to create 1 rle with old method : 0.00488591194152832 length of segment : 78 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 865 time to create 1 rle with old method : 0.001140594482421875 length of segment : 38 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 500 time to create 1 rle with old method : 0.0006892681121826172 length of segment : 29 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 140 time to create 1 rle with old method : 0.00020074844360351562 length of segment : 26 time for calcul the mask position with numpy : 0.00010251998901367188 nb_pixel_total : 4454 time to create 1 rle with old method : 0.00551295280456543 length of segment : 75 time for calcul the mask position with numpy : 9.703636169433594e-05 nb_pixel_total : 3496 time to create 1 rle with old method : 0.0043506622314453125 length of segment : 83 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 206 time to create 1 rle with old method : 0.0002658367156982422 length of segment : 55 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 189 time to create 1 rle with old method : 0.0003170967102050781 length of segment : 16 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: 139.23281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003044605255126953 length of segment : 17 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 254 time to create 1 rle with old method : 0.00032830238342285156 length of segment : 20 time for calcul the mask position with numpy : 3.123283386230469e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.0003707408905029297 length of segment : 23 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 276 time to create 1 rle with old method : 0.0005540847778320312 length of segment : 17 time for calcul the mask position with numpy : 5.030632019042969e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0010187625885009766 length of segment : 47 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 557 time to create 1 rle with old method : 0.0009205341339111328 length of segment : 41 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 150.38906 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.00029277801513671875 length of segment : 24 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 458 time to create 1 rle with old method : 0.0006618499755859375 length of segment : 23 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003540515899658203 length of segment : 28 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: 137.28750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 476 time to create 1 rle with old method : 0.0006022453308105469 length of segment : 30 time for calcul the mask position with numpy : 0.0005004405975341797 nb_pixel_total : 44415 time to create 1 rle with old method : 0.05390000343322754 length of segment : 262 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: -118.26250 max: 150.50234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 572 time to create 1 rle with old method : 0.0008444786071777344 length of segment : 54 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.0006990432739257812 length of segment : 28 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 580 time to create 1 rle with old method : 0.0009377002716064453 length of segment : 70 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 1140 time to create 1 rle with old method : 0.0017821788787841797 length of segment : 27 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 912 time to create 1 rle with old method : 0.0012090206146240234 length of segment : 36 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005352497100830078 length of segment : 34 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 1224 time to create 1 rle with old method : 0.001827239990234375 length of segment : 29 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 205 time to create 1 rle with old method : 0.000293731689453125 length of segment : 27 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.12188 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 : 7.2479248046875e-05 nb_pixel_total : 311 time to create 1 rle with old method : 0.0005419254302978516 length of segment : 40 time for calcul the mask position with numpy : 0.000217437744140625 nb_pixel_total : 1415 time to create 1 rle with old method : 0.001859426498413086 length of segment : 124 time for calcul the mask position with numpy : 0.00014591217041015625 nb_pixel_total : 996 time to create 1 rle with old method : 0.001837015151977539 length of segment : 34 time for calcul the mask position with numpy : 0.00012874603271484375 nb_pixel_total : 2171 time to create 1 rle with old method : 0.003952741622924805 length of segment : 86 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0008883476257324219 length of segment : 48 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 36 time to create 1 rle with old method : 9.965896606445312e-05 length of segment : 6 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003705024719238281 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.41094 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 : 4.100799560546875e-05 nb_pixel_total : 365 time to create 1 rle with old method : 0.0005171298980712891 length of segment : 30 time for calcul the mask position with numpy : 0.00020265579223632812 nb_pixel_total : 4835 time to create 1 rle with old method : 0.006313800811767578 length of segment : 86 time for calcul the mask position with numpy : 3.8623809814453125e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0007238388061523438 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.51641 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 : 4.0531158447265625e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.0005011558532714844 length of segment : 39 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003178119659423828 length of segment : 22 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 248.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 127.66641 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 4.410743713378906e-05 nb_pixel_total : 528 time to create 1 rle with old method : 0.00080108642578125 length of segment : 18 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 439 time to create 1 rle with old method : 0.0005307197570800781 length of segment : 51 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 787 time to create 1 rle with old method : 0.0009903907775878906 length of segment : 68 time for calcul the mask position with numpy : 0.0007135868072509766 nb_pixel_total : 69787 time to create 1 rle with old method : 0.08115744590759277 length of segment : 301 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 201.00000 molded_images shape: (1, 640, 640, 3) min: -93.53594 max: 80.45937 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: -114.42266 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.00020742416381835938 length of segment : 16 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 2470 time to create 1 rle with old method : 0.0032341480255126953 length of segment : 48 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 2587 time to create 1 rle with old method : 0.0033512115478515625 length of segment : 53 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 545 time to create 1 rle with old method : 0.0007150173187255859 length of segment : 28 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 384 time to create 1 rle with old method : 0.00060272216796875 length of segment : 18 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.25469 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 677 time to create 1 rle with old method : 0.0011296272277832031 length of segment : 29 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 784 time to create 1 rle with old method : 0.0013461112976074219 length of segment : 24 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 423 time to create 1 rle with old method : 0.0005872249603271484 length of segment : 25 time for calcul the mask position with numpy : 3.2901763916015625e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002913475036621094 length of segment : 16 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 569 time to create 1 rle with old method : 0.0008361339569091797 length of segment : 20 time for calcul the mask position with numpy : 4.458427429199219e-05 nb_pixel_total : 938 time to create 1 rle with old method : 0.0012607574462890625 length of segment : 24 time for calcul the mask position with numpy : 2.956390380859375e-05 nb_pixel_total : 166 time to create 1 rle with old method : 0.00025916099548339844 length of segment : 10 time for calcul the mask position with numpy : 2.9325485229492188e-05 nb_pixel_total : 167 time to create 1 rle with old method : 0.00026798248291015625 length of segment : 10 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.49297 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 : 5.412101745605469e-05 nb_pixel_total : 764 time to create 1 rle with old method : 0.000986337661743164 length of segment : 37 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 1303 time to create 1 rle with old method : 0.0015099048614501953 length of segment : 39 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 1575 time to create 1 rle with old method : 0.0020096302032470703 length of segment : 109 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0008058547973632812 length of segment : 109 time for calcul the mask position with numpy : 0.0002377033233642578 nb_pixel_total : 9422 time to create 1 rle with old method : 0.01135110855102539 length of segment : 246 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1290 time to create 1 rle with old method : 0.0016045570373535156 length of segment : 40 time for calcul the mask position with numpy : 6.175041198730469e-05 nb_pixel_total : 1616 time to create 1 rle with old method : 0.002158641815185547 length of segment : 42 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 240.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 101.33047 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007767677307128906 length of segment : 69 time for calcul the mask position with numpy : 5.1975250244140625e-05 nb_pixel_total : 198 time to create 1 rle with old method : 0.0003581047058105469 length of segment : 28 time for calcul the mask position with numpy : 8.320808410644531e-05 nb_pixel_total : 1320 time to create 1 rle with old method : 0.0022661685943603516 length of segment : 62 time for calcul the mask position with numpy : 0.00012421607971191406 nb_pixel_total : 1118 time to create 1 rle with old method : 0.0022678375244140625 length of segment : 138 time for calcul the mask position with numpy : 0.00017833709716796875 nb_pixel_total : 4143 time to create 1 rle with old method : 0.004780292510986328 length of segment : 195 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 608 time to create 1 rle with old method : 0.0007715225219726562 length of segment : 44 Processing 1 images image shape: (280, 400, 3) min: 14.00000 max: 187.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 78.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0009326934814453125 nb_pixel_total : 103286 time to create 1 rle with old method : 0.11997771263122559 length of segment : 285 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: 150.98281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1577 time to create 1 rle with old method : 0.0019381046295166016 length of segment : 42 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 3335 time to create 1 rle with old method : 0.004026651382446289 length of segment : 58 time for calcul the mask position with numpy : 3.4809112548828125e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.00014352798461914062 length of segment : 21 time for calcul the mask position with numpy : 7.2479248046875e-05 nb_pixel_total : 1964 time to create 1 rle with old method : 0.0023322105407714844 length of segment : 68 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 3394 time to create 1 rle with old method : 0.004111766815185547 length of segment : 73 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.00031256675720214844 length of segment : 59 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003898143768310547 length of segment : 20 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: 140.18984 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 187 time to create 1 rle with old method : 0.0005011558532714844 length of segment : 16 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 271 time to create 1 rle with old method : 0.0004343986511230469 length of segment : 21 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 274 time to create 1 rle with old method : 0.0004754066467285156 length of segment : 16 time for calcul the mask position with numpy : 3.933906555175781e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.00047135353088378906 length of segment : 16 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0003311634063720703 length of segment : 31 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 287 time to create 1 rle with old method : 0.00040721893310546875 length of segment : 23 time for calcul the mask position with numpy : 8.082389831542969e-05 nb_pixel_total : 733 time to create 1 rle with old method : 0.0014820098876953125 length of segment : 51 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 71 time to create 1 rle with old method : 0.00024580955505371094 length of segment : 6 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: 150.38906 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 446 time to create 1 rle with old method : 0.0006387233734130859 length of segment : 22 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003037452697753906 length of segment : 25 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 362 time to create 1 rle with old method : 0.0004394054412841797 length of segment : 37 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 83 time to create 1 rle with old method : 0.00015544891357421875 length of segment : 11 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: 140.35000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.602836608886719e-05 nb_pixel_total : 27 time to create 1 rle with old method : 6.556510925292969e-05 length of segment : 13 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 452 time to create 1 rle with old method : 0.0006299018859863281 length of segment : 33 time for calcul the mask position with numpy : 3.147125244140625e-05 nb_pixel_total : 19 time to create 1 rle with old method : 5.173683166503906e-05 length of segment : 4 time for calcul the mask position with numpy : 0.0005786418914794922 nb_pixel_total : 40076 time to create 1 rle with old method : 0.06403088569641113 length of segment : 252 Detection mask done ! Trying to reset tf kernel 4148639 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4726 tf kernel not reseted sub process len(results) : 151 len(list_Values) 151 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 151 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 : 10015 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 151 chid ids of type : 4228 Number RLEs to save : 8261 save missing photos in datou_result : time spend for datou_step_exec : 21.042394638061523 time spend to save output : 4.927167177200317 total time spend for step 1 : 25.96956181526184 step2:brightness Mon Mar 3 03:20:56 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 inside step calcul brightness treat image : temp/1740968430_4148014_1340529193_7cdbc37fe8feed9b8e0f64c058f7a310.jpg treat image : temp/1740968430_4148014_1340529192_3cdbd731af16aed73c4ba83d4becbabe.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 : 0.012606382369995117 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 : 0.012850046157836914 save missing photos in datou_result : time spend for datou_step_exec : 0.5596816539764404 time spend to save output : 0.029643774032592773 total time spend for step 2 : 0.5893254280090332 step3:blur_detection Mon Mar 3 03:20:57 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/1740968430_4148014_1340529193_7cdbc37fe8feed9b8e0f64c058f7a310.jpg resize: (1080, 1920) 1340529193 -7.437391042623916 treat image : temp/1740968430_4148014_1340529192_3cdbd731af16aed73c4ba83d4becbabe.jpg resize: (1080, 1920) 1340529192 -7.438085633458052 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 : 0.013558387756347656 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 : 0.03110980987548828 save missing photos in datou_result : time spend for datou_step_exec : 1.8929669857025146 time spend to save output : 0.04952049255371094 total time spend for step 3 : 1.9424874782562256 step4:rle_unique_nms_with_priority Mon Mar 3 03:20:59 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 151 chid ids of type : 4228 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 77 nb_hashtags : 6 time to prepare the origin masks : 1.0783936977386475 time for calcul the mask position with numpy : 0.06902194023132324 nb_pixel_total : 1793204 time to create 1 rle with new method : 0.08163094520568848 time for calcul the mask position with numpy : 0.008719682693481445 nb_pixel_total : 68419 time to create 1 rle with old method : 0.07929134368896484 time for calcul the mask position with numpy : 0.008249282836914062 nb_pixel_total : 138 time to create 1 rle with old method : 0.00020456314086914062 time for calcul the mask position with numpy : 0.007980108261108398 nb_pixel_total : 350 time to create 1 rle with old method : 0.00045013427734375 time for calcul the mask position with numpy : 0.008426427841186523 nb_pixel_total : 594 time to create 1 rle with old method : 0.0006759166717529297 time for calcul the mask position with numpy : 0.008019208908081055 nb_pixel_total : 379 time to create 1 rle with old method : 0.0004138946533203125 time for calcul the mask position with numpy : 0.008289098739624023 nb_pixel_total : 55 time to create 1 rle with old method : 7.414817810058594e-05 time for calcul the mask position with numpy : 0.008248090744018555 nb_pixel_total : 451 time to create 1 rle with old method : 0.0005142688751220703 time for calcul the mask position with numpy : 0.008713006973266602 nb_pixel_total : 59 time to create 1 rle with old method : 8.726119995117188e-05 time for calcul the mask position with numpy : 0.008226156234741211 nb_pixel_total : 495 time to create 1 rle with old method : 0.0006160736083984375 time for calcul the mask position with numpy : 0.00806283950805664 nb_pixel_total : 1134 time to create 1 rle with old method : 0.001239776611328125 time for calcul the mask position with numpy : 0.008276939392089844 nb_pixel_total : 213 time to create 1 rle with old method : 0.0002560615539550781 time for calcul the mask position with numpy : 0.008309125900268555 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003619194030761719 time for calcul the mask position with numpy : 0.008312463760375977 nb_pixel_total : 204 time to create 1 rle with old method : 0.00026917457580566406 time for calcul the mask position with numpy : 0.00855255126953125 nb_pixel_total : 1622 time to create 1 rle with old method : 0.0019283294677734375 time for calcul the mask position with numpy : 0.008193254470825195 nb_pixel_total : 218 time to create 1 rle with old method : 0.0002384185791015625 time for calcul the mask position with numpy : 0.00813913345336914 nb_pixel_total : 443 time to create 1 rle with old method : 0.0004608631134033203 time for calcul the mask position with numpy : 0.008579254150390625 nb_pixel_total : 2350 time to create 1 rle with old method : 0.002650022506713867 time for calcul the mask position with numpy : 0.008205175399780273 nb_pixel_total : 3 time to create 1 rle with old method : 1.8596649169921875e-05 time for calcul the mask position with numpy : 0.008429765701293945 nb_pixel_total : 468 time to create 1 rle with old method : 0.0005631446838378906 time for calcul the mask position with numpy : 0.008432626724243164 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005943775177001953 time for calcul the mask position with numpy : 0.008196115493774414 nb_pixel_total : 254 time to create 1 rle with old method : 0.0004851818084716797 time for calcul the mask position with numpy : 0.008263587951660156 nb_pixel_total : 524 time to create 1 rle with old method : 0.0006368160247802734 time for calcul the mask position with numpy : 0.008803606033325195 nb_pixel_total : 541 time to create 1 rle with old method : 0.0006873607635498047 time for calcul the mask position with numpy : 0.008434772491455078 nb_pixel_total : 9484 time to create 1 rle with old method : 0.010589838027954102 time for calcul the mask position with numpy : 0.008329629898071289 nb_pixel_total : 1040 time to create 1 rle with old method : 0.0013470649719238281 time for calcul the mask position with numpy : 0.008278608322143555 nb_pixel_total : 722 time to create 1 rle with old method : 0.0012798309326171875 time for calcul the mask position with numpy : 0.008355379104614258 nb_pixel_total : 66 time to create 1 rle with old method : 9.632110595703125e-05 time for calcul the mask position with numpy : 0.00832366943359375 nb_pixel_total : 775 time to create 1 rle with old method : 0.0009114742279052734 time for calcul the mask position with numpy : 0.008317947387695312 nb_pixel_total : 215 time to create 1 rle with old method : 0.0002655982971191406 time for calcul the mask position with numpy : 0.00847625732421875 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002467632293701172 time for calcul the mask position with numpy : 0.008878469467163086 nb_pixel_total : 30 time to create 1 rle with old method : 5.5789947509765625e-05 time for calcul the mask position with numpy : 0.008388042449951172 nb_pixel_total : 1316 time to create 1 rle with old method : 0.0015170574188232422 time for calcul the mask position with numpy : 0.00884556770324707 nb_pixel_total : 95 time to create 1 rle with old method : 0.0001404285430908203 time for calcul the mask position with numpy : 0.008322000503540039 nb_pixel_total : 502 time to create 1 rle with old method : 0.0005538463592529297 time for calcul the mask position with numpy : 0.007942676544189453 nb_pixel_total : 269 time to create 1 rle with old method : 0.00029730796813964844 time for calcul the mask position with numpy : 0.00831460952758789 nb_pixel_total : 717 time to create 1 rle with old method : 0.0008902549743652344 time for calcul the mask position with numpy : 0.008184671401977539 nb_pixel_total : 399 time to create 1 rle with old method : 0.0004782676696777344 time for calcul the mask position with numpy : 0.008508920669555664 nb_pixel_total : 583 time to create 1 rle with old method : 0.0006856918334960938 time for calcul the mask position with numpy : 0.00821375846862793 nb_pixel_total : 1211 time to create 1 rle with old method : 0.0013394355773925781 time for calcul the mask position with numpy : 0.00847935676574707 nb_pixel_total : 4124 time to create 1 rle with old method : 0.004423618316650391 time for calcul the mask position with numpy : 0.008179426193237305 nb_pixel_total : 1474 time to create 1 rle with old method : 0.0017631053924560547 time for calcul the mask position with numpy : 0.008253812789916992 nb_pixel_total : 450 time to create 1 rle with old method : 0.0005481243133544922 time for calcul the mask position with numpy : 0.008373498916625977 nb_pixel_total : 796 time to create 1 rle with old method : 0.0009553432464599609 time for calcul the mask position with numpy : 0.008175134658813477 nb_pixel_total : 79 time to create 1 rle with old method : 0.00013875961303710938 time for calcul the mask position with numpy : 0.008428812026977539 nb_pixel_total : 563 time to create 1 rle with old method : 0.0006756782531738281 time for calcul the mask position with numpy : 0.008484125137329102 nb_pixel_total : 498 time to create 1 rle with old method : 0.0005385875701904297 time for calcul the mask position with numpy : 0.008316278457641602 nb_pixel_total : 627 time to create 1 rle with old method : 0.0007498264312744141 time for calcul the mask position with numpy : 0.007979631423950195 nb_pixel_total : 203 time to create 1 rle with old method : 0.0002582073211669922 time for calcul the mask position with numpy : 0.008152961730957031 nb_pixel_total : 1487 time to create 1 rle with old method : 0.001695394515991211 time for calcul the mask position with numpy : 0.008572578430175781 nb_pixel_total : 205 time to create 1 rle with old method : 0.0002562999725341797 time for calcul the mask position with numpy : 0.008115291595458984 nb_pixel_total : 468 time to create 1 rle with old method : 0.0005667209625244141 time for calcul the mask position with numpy : 0.008220911026000977 nb_pixel_total : 2376 time to create 1 rle with old method : 0.0027840137481689453 time for calcul the mask position with numpy : 0.008440017700195312 nb_pixel_total : 1097 time to create 1 rle with old method : 0.0012891292572021484 time for calcul the mask position with numpy : 0.00818943977355957 nb_pixel_total : 118 time to create 1 rle with old method : 0.000152587890625 time for calcul the mask position with numpy : 0.008429527282714844 nb_pixel_total : 102748 time to create 1 rle with old method : 0.11426591873168945 time for calcul the mask position with numpy : 0.008251190185546875 nb_pixel_total : 3433 time to create 1 rle with old method : 0.003794431686401367 time for calcul the mask position with numpy : 0.008456945419311523 nb_pixel_total : 458 time to create 1 rle with old method : 0.0005519390106201172 time for calcul the mask position with numpy : 0.008294105529785156 nb_pixel_total : 140 time to create 1 rle with old method : 0.00018858909606933594 time for calcul the mask position with numpy : 0.008643627166748047 nb_pixel_total : 43946 time to create 1 rle with old method : 0.05137467384338379 time for calcul the mask position with numpy : 0.008638620376586914 nb_pixel_total : 3106 time to create 1 rle with old method : 0.0035715103149414062 time for calcul the mask position with numpy : 0.008612632751464844 nb_pixel_total : 600 time to create 1 rle with old method : 0.0006923675537109375 time for calcul the mask position with numpy : 0.008948087692260742 nb_pixel_total : 196 time to create 1 rle with old method : 0.0002491474151611328 time for calcul the mask position with numpy : 0.008788108825683594 nb_pixel_total : 13 time to create 1 rle with old method : 3.6716461181640625e-05 time for calcul the mask position with numpy : 0.010680675506591797 nb_pixel_total : 254 time to create 1 rle with old method : 0.0005118846893310547 time for calcul the mask position with numpy : 0.009072065353393555 nb_pixel_total : 3814 time to create 1 rle with old method : 0.004438877105712891 time for calcul the mask position with numpy : 0.008521795272827148 nb_pixel_total : 492 time to create 1 rle with old method : 0.0005805492401123047 time for calcul the mask position with numpy : 0.008625984191894531 nb_pixel_total : 1728 time to create 1 rle with old method : 0.0019676685333251953 time for calcul the mask position with numpy : 0.008505105972290039 nb_pixel_total : 865 time to create 1 rle with old method : 0.0010182857513427734 time for calcul the mask position with numpy : 0.00841069221496582 nb_pixel_total : 245 time to create 1 rle with old method : 0.0003159046173095703 time for calcul the mask position with numpy : 0.008570432662963867 nb_pixel_total : 288 time to create 1 rle with old method : 0.00036144256591796875 time for calcul the mask position with numpy : 0.008510589599609375 nb_pixel_total : 276 time to create 1 rle with old method : 0.0003311634063720703 time for calcul the mask position with numpy : 0.008470773696899414 nb_pixel_total : 476 time to create 1 rle with old method : 0.00055694580078125 time for calcul the mask position with numpy : 0.008630752563476562 nb_pixel_total : 4454 time to create 1 rle with old method : 0.005089282989501953 time for calcul the mask position with numpy : 0.009039640426635742 nb_pixel_total : 499 time to create 1 rle with old method : 0.0009391307830810547 time for calcul the mask position with numpy : 0.01079106330871582 nb_pixel_total : 206 time to create 1 rle with old method : 0.0004177093505859375 time for calcul the mask position with numpy : 0.012993812561035156 nb_pixel_total : 189 time to create 1 rle with old method : 0.0003764629364013672 time for calcul the mask position with numpy : 0.011257648468017578 nb_pixel_total : 196 time to create 1 rle with old method : 0.0004565715789794922 create new chi : 1.143247365951538 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 : 0.014020442962646484 batch 1 Loaded 78 chid ids of type : 4230 Number RLEs to save : 8751 TO DO : save crop sub photo not yet done ! save time : 1.2534186840057373 nb_obj : 74 nb_hashtags : 6 time to prepare the origin masks : 1.9266114234924316 time for calcul the mask position with numpy : 0.038665056228637695 nb_pixel_total : 1799748 time to create 1 rle with new method : 0.1459052562713623 time for calcul the mask position with numpy : 0.011646509170532227 nb_pixel_total : 4835 time to create 1 rle with old method : 0.00588679313659668 time for calcul the mask position with numpy : 0.010407209396362305 nb_pixel_total : 996 time to create 1 rle with old method : 0.0011703968048095703 time for calcul the mask position with numpy : 0.007087230682373047 nb_pixel_total : 69787 time to create 1 rle with old method : 0.0831441879272461 time for calcul the mask position with numpy : 0.006521940231323242 nb_pixel_total : 379 time to create 1 rle with old method : 0.0004863739013671875 time for calcul the mask position with numpy : 0.007213115692138672 nb_pixel_total : 152 time to create 1 rle with old method : 0.00032591819763183594 time for calcul the mask position with numpy : 0.010499000549316406 nb_pixel_total : 535 time to create 1 rle with old method : 0.0009584426879882812 time for calcul the mask position with numpy : 0.0067005157470703125 nb_pixel_total : 64 time to create 1 rle with old method : 0.0001513957977294922 time for calcul the mask position with numpy : 0.008679628372192383 nb_pixel_total : 497 time to create 1 rle with old method : 0.0008449554443359375 time for calcul the mask position with numpy : 0.013215780258178711 nb_pixel_total : 365 time to create 1 rle with old method : 0.0006785392761230469 time for calcul the mask position with numpy : 0.013946533203125 nb_pixel_total : 4 time to create 1 rle with old method : 4.57763671875e-05 time for calcul the mask position with numpy : 0.015482425689697266 nb_pixel_total : 311 time to create 1 rle with old method : 0.0005602836608886719 time for calcul the mask position with numpy : 0.011747360229492188 nb_pixel_total : 572 time to create 1 rle with old method : 0.0009946823120117188 time for calcul the mask position with numpy : 0.010978937149047852 nb_pixel_total : 1140 time to create 1 rle with old method : 0.0012996196746826172 time for calcul the mask position with numpy : 0.010266542434692383 nb_pixel_total : 36 time to create 1 rle with old method : 6.175041198730469e-05 time for calcul the mask position with numpy : 0.010051965713500977 nb_pixel_total : 105 time to create 1 rle with old method : 0.0001800060272216797 time for calcul the mask position with numpy : 0.010343313217163086 nb_pixel_total : 1415 time to create 1 rle with old method : 0.0029239654541015625 time for calcul the mask position with numpy : 0.011953353881835938 nb_pixel_total : 225 time to create 1 rle with old method : 0.0003955364227294922 time for calcul the mask position with numpy : 0.009795904159545898 nb_pixel_total : 439 time to create 1 rle with old method : 0.0007789134979248047 time for calcul the mask position with numpy : 0.006836414337158203 nb_pixel_total : 2171 time to create 1 rle with old method : 0.002540111541748047 time for calcul the mask position with numpy : 0.0063250064849853516 nb_pixel_total : 787 time to create 1 rle with old method : 0.0012583732604980469 time for calcul the mask position with numpy : 0.0066945552825927734 nb_pixel_total : 203 time to create 1 rle with old method : 0.0003447532653808594 time for calcul the mask position with numpy : 0.006563663482666016 nb_pixel_total : 384 time to create 1 rle with old method : 0.0006299018859863281 time for calcul the mask position with numpy : 0.006730318069458008 nb_pixel_total : 439 time to create 1 rle with old method : 0.0007519721984863281 time for calcul the mask position with numpy : 0.006859302520751953 nb_pixel_total : 528 time to create 1 rle with old method : 0.0009174346923828125 time for calcul the mask position with numpy : 0.0068209171295166016 nb_pixel_total : 9422 time to create 1 rle with old method : 0.011184930801391602 time for calcul the mask position with numpy : 0.006207704544067383 nb_pixel_total : 677 time to create 1 rle with old method : 0.0007762908935546875 time for calcul the mask position with numpy : 0.006778240203857422 nb_pixel_total : 764 time to create 1 rle with old method : 0.0011086463928222656 time for calcul the mask position with numpy : 0.006475687026977539 nb_pixel_total : 198 time to create 1 rle with old method : 0.00025653839111328125 time for calcul the mask position with numpy : 0.007076263427734375 nb_pixel_total : 11 time to create 1 rle with old method : 4.792213439941406e-05 time for calcul the mask position with numpy : 0.006539821624755859 nb_pixel_total : 166 time to create 1 rle with old method : 0.00023102760314941406 time for calcul the mask position with numpy : 0.0064809322357177734 nb_pixel_total : 74 time to create 1 rle with old method : 0.000164031982421875 time for calcul the mask position with numpy : 0.006853818893432617 nb_pixel_total : 1303 time to create 1 rle with old method : 0.002044200897216797 time for calcul the mask position with numpy : 0.006972074508666992 nb_pixel_total : 608 time to create 1 rle with old method : 0.0009741783142089844 time for calcul the mask position with numpy : 0.006249427795410156 nb_pixel_total : 938 time to create 1 rle with old method : 0.0010898113250732422 time for calcul the mask position with numpy : 0.00627589225769043 nb_pixel_total : 423 time to create 1 rle with old method : 0.0004892349243164062 time for calcul the mask position with numpy : 0.006376743316650391 nb_pixel_total : 4143 time to create 1 rle with old method : 0.004655599594116211 time for calcul the mask position with numpy : 0.006012916564941406 nb_pixel_total : 555 time to create 1 rle with old method : 0.0006442070007324219 time for calcul the mask position with numpy : 0.005789041519165039 nb_pixel_total : 1616 time to create 1 rle with old method : 0.0017442703247070312 time for calcul the mask position with numpy : 0.006860017776489258 nb_pixel_total : 1320 time to create 1 rle with old method : 0.0022878646850585938 time for calcul the mask position with numpy : 0.007035493850708008 nb_pixel_total : 784 time to create 1 rle with old method : 0.0013158321380615234 time for calcul the mask position with numpy : 0.006635904312133789 nb_pixel_total : 569 time to create 1 rle with old method : 0.0006763935089111328 time for calcul the mask position with numpy : 0.006493091583251953 nb_pixel_total : 545 time to create 1 rle with old method : 0.0006427764892578125 time for calcul the mask position with numpy : 0.006307363510131836 nb_pixel_total : 1575 time to create 1 rle with old method : 0.0018472671508789062 time for calcul the mask position with numpy : 0.006181955337524414 nb_pixel_total : 384 time to create 1 rle with old method : 0.00046253204345703125 time for calcul the mask position with numpy : 0.006213188171386719 nb_pixel_total : 630 time to create 1 rle with old method : 0.0007264614105224609 time for calcul the mask position with numpy : 0.00644683837890625 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005445480346679688 time for calcul the mask position with numpy : 0.006337404251098633 nb_pixel_total : 193 time to create 1 rle with old method : 0.00024271011352539062 time for calcul the mask position with numpy : 0.0063745975494384766 nb_pixel_total : 161 time to create 1 rle with old method : 0.0002837181091308594 time for calcul the mask position with numpy : 0.006344795227050781 nb_pixel_total : 2470 time to create 1 rle with old method : 0.0028209686279296875 time for calcul the mask position with numpy : 0.006270647048950195 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001556873321533203 time for calcul the mask position with numpy : 0.007767438888549805 nb_pixel_total : 103286 time to create 1 rle with old method : 0.11473298072814941 time for calcul the mask position with numpy : 0.006333827972412109 nb_pixel_total : 3383 time to create 1 rle with old method : 0.0038557052612304688 time for calcul the mask position with numpy : 0.007325410842895508 nb_pixel_total : 27 time to create 1 rle with old method : 8.177757263183594e-05 time for calcul the mask position with numpy : 0.007248878479003906 nb_pixel_total : 446 time to create 1 rle with old method : 0.0008044242858886719 time for calcul the mask position with numpy : 0.0076291561126708984 nb_pixel_total : 97 time to create 1 rle with old method : 0.00014400482177734375 time for calcul the mask position with numpy : 0.007153987884521484 nb_pixel_total : 39630 time to create 1 rle with old method : 0.0453944206237793 time for calcul the mask position with numpy : 0.006153583526611328 nb_pixel_total : 3335 time to create 1 rle with old method : 0.0037627220153808594 time for calcul the mask position with numpy : 0.005931377410888672 nb_pixel_total : 733 time to create 1 rle with old method : 0.0008378028869628906 time for calcul the mask position with numpy : 0.006241798400878906 nb_pixel_total : 187 time to create 1 rle with old method : 0.0002455711364746094 time for calcul the mask position with numpy : 0.00618290901184082 nb_pixel_total : 271 time to create 1 rle with old method : 0.0003306865692138672 time for calcul the mask position with numpy : 0.0073468685150146484 nb_pixel_total : 1964 time to create 1 rle with old method : 0.004158735275268555 time for calcul the mask position with numpy : 0.00701904296875 nb_pixel_total : 1577 time to create 1 rle with old method : 0.0018391609191894531 time for calcul the mask position with numpy : 0.0061948299407958984 nb_pixel_total : 37 time to create 1 rle with old method : 6.365776062011719e-05 time for calcul the mask position with numpy : 0.006100654602050781 nb_pixel_total : 362 time to create 1 rle with old method : 0.0007340908050537109 time for calcul the mask position with numpy : 0.007179975509643555 nb_pixel_total : 287 time to create 1 rle with old method : 0.00034117698669433594 time for calcul the mask position with numpy : 0.006371498107910156 nb_pixel_total : 11 time to create 1 rle with old method : 4.553794860839844e-05 time for calcul the mask position with numpy : 0.006827354431152344 nb_pixel_total : 274 time to create 1 rle with old method : 0.0003249645233154297 time for calcul the mask position with numpy : 0.0061187744140625 nb_pixel_total : 452 time to create 1 rle with old method : 0.0005397796630859375 time for calcul the mask position with numpy : 0.0070343017578125 nb_pixel_total : 19 time to create 1 rle with old method : 4.863739013671875e-05 time for calcul the mask position with numpy : 0.006702899932861328 nb_pixel_total : 231 time to create 1 rle with old method : 0.0003173351287841797 time for calcul the mask position with numpy : 0.006130218505859375 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003304481506347656 time for calcul the mask position with numpy : 0.006211042404174805 nb_pixel_total : 235 time to create 1 rle with old method : 0.00034809112548828125 time for calcul the mask position with numpy : 0.006114959716796875 nb_pixel_total : 210 time to create 1 rle with old method : 0.0002655982971191406 time for calcul the mask position with numpy : 0.006124973297119141 nb_pixel_total : 71 time to create 1 rle with old method : 0.00010538101196289062 create new chi : 1.0664141178131104 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 : 0.0010466575622558594 batch 1 Loaded 75 chid ids of type : 4230 Number RLEs to save : 8487 TO DO : save crop sub photo not yet done ! save time : 1.4361770153045654 map_output_result : {1340529193: (0.0, 'Should be the crop_list due to order', 0.0), 1340529192: (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 [1340529193, 1340529192] Looping around the photos to save general results len do output : 2 /1340529193.Didn't retrieve data . /1340529192.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, '2627698') ('4234', '20957637', '1340529193', None, None, None, None, None, '2627698') ('4234', None, None, None, None, None, None, None, '2627698') ('4234', '20957637', '1340529192', None, None, None, None, None, '2627698') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.021279335021972656 save_final save missing photos in datou_result : time spend for datou_step_exec : 8.281773805618286 time spend to save output : 0.021526336669921875 total time spend for step 4 : 8.303300142288208 step5:crop_condition Mon Mar 3 03:21:07 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 153 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 ! map_result returned by crop_photo_return_map_crop : length : 48 About to insert : list_path_to_insert length 48 new photo from crops ! About to upload 48 photos upload in portfolio : 4869462 init cache_photo without model_param we have 48 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740968468_4148014 we have uploaded 48 photos in the portfolio 4869462 time of upload the photos Elapsed time : 12.759767055511475 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 ! map_result returned by crop_photo_return_map_crop : length : 13 About to insert : list_path_to_insert length 13 new photo from crops ! About to upload 13 photos upload in portfolio : 4869462 init cache_photo without model_param we have 13 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740968481_4148014 we have uploaded 13 photos in the portfolio 4869462 time of upload the photos Elapsed time : 5.886024236679077 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 ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! About to upload 5 photos upload in portfolio : 4869462 init cache_photo without model_param we have 5 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740968487_4148014 we have uploaded 5 photos in the portfolio 4869462 time of upload the photos Elapsed time : 3.275855779647827 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 ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 4869462 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1740968491_4148014 we have uploaded 27 photos in the portfolio 4869462 time of upload the photos Elapsed time : 6.86700177192688 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 [1340529193, 1340529192] Looping around the photos to save general results len do output : 93 /1340568425Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568426Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568427Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568428Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568454Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568455Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568457Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568458Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568459Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568460Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568462Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568463Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568464Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568466Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568467Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568468Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568469Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568470Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568474Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568475Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568490Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340568522Didn'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, '2627698') ('4234', '20957637', '1340529193', None, None, None, None, None, '2627698') ('4234', None, None, None, None, None, None, None, '2627698') ('4234', '20957637', '1340529192', None, None, None, None, None, '2627698') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 281 time used for this insertion : 0.2339191436767578 save_final save missing photos in datou_result : time spend for datou_step_exec : 30.84355354309082 time spend to save output : 0.23763418197631836 total time spend for step 5 : 31.08118772506714 step6:thcl Mon Mar 3 03:21:38 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 : 0.0029823780059814453 time to convert the images to numpy array : 0.009293079376220703 time to import caffe and check if the image exist : 0.009285449981689453 time to convert the images to numpy array : 0.020629405975341797 time to import caffe and check if the image exist : 0.004866361618041992 time to convert the images to numpy array : 0.026315689086914062 time to import caffe and check if the image exist : 0.00976705551147461 time to convert the images to numpy array : 0.023005247116088867 time to import caffe and check if the image exist : 0.008807182312011719 time to convert the images to numpy array : 0.026432037353515625 time to import caffe and check if the image exist : 0.006993770599365234 time to convert the images to numpy array : 0.028271198272705078 time to import caffe and check if the image exist : 0.009832620620727539 time to convert the images to numpy array : 0.02629566192626953 time to import caffe and check if the image exist : 0.006704568862915039 time to convert the images to numpy array : 0.030295133590698242 time to import caffe and check if the image exist : 0.018373489379882812 time to convert the images to numpy array : 0.01787543296813965 time to import caffe and check if the image exist : 0.006979703903198242 time to convert the images to numpy array : 0.031094789505004883 total time to convert the images to numpy array : 0.25212907791137695 list photo_ids error: [] list photo_ids correct : [1340568520, 1340568521, 1340568522, 1340568455, 1340568456, 1340568457, 1340568458, 1340568459, 1340568460, 1340568461, 1340568462, 1340568463, 1340568464, 1340568425, 1340568426, 1340568427, 1340568428, 1340568429, 1340568430, 1340568431, 1340568432, 1340568433, 1340568434, 1340568465, 1340568466, 1340568467, 1340568468, 1340568469, 1340568470, 1340568471, 1340568472, 1340568474, 1340568475, 1340568435, 1340568436, 1340568437, 1340568438, 1340568439, 1340568440, 1340568441, 1340568442, 1340568443, 1340568444, 1340568476, 1340568477, 1340568478, 1340568479, 1340568480, 1340568481, 1340568482, 1340568483, 1340568484, 1340568485, 1340568486, 1340568488, 1340568490, 1340568491, 1340568492, 1340568493, 1340568495, 1340568496, 1340568497, 1340568499, 1340568500, 1340568501, 1340568502, 1340568503, 1340568504, 1340568505, 1340568506, 1340568507, 1340568508, 1340568509, 1340568510, 1340568511, 1340568512, 1340568513, 1340568514, 1340568515, 1340568516, 1340568517, 1340568518, 1340568519, 1340568445, 1340568446, 1340568447, 1340568448, 1340568449, 1340568450, 1340568451, 1340568452, 1340568453, 1340568454] number of photos to traite : 93 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 : 5525 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 F0303 03:21:43.639827 4148014 math_functions.cu:26] Check failed: status == CUBLAS_STATUS_SUCCESS (14 vs. 0) CUBLAS_STATUS_INTERNAL_ERROR *** Check failure stack trace: *** Command terminated by signal 6 26.40user 20.14system 1:18.59elapsed 59%CPU (0avgtext+0avgdata 2484864maxresident)k 688inputs+4224outputs (5major+1796798minor)pagefaults 0swaps