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 : 3815740 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 : ['2632484'] with mtr_portfolio_ids : ['21008178'] and first list_photo_ids : [] new path : /proc/3815740/ 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 : 0.24645042419433594 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 Tue Mar 4 13:20:28 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 2025-03-04 13:20:31.666302: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-04 13:20:31.695154: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-04 13:20:31.696696: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fd130000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-04 13:20:31.696719: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-04 13:20:31.699614: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-04 13:20:31.955868: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x347f0860 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-04 13:20:31.955931: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-04 13:20:31.957255: 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 2025-03-04 13:20:31.957705: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-04 13:20:31.965094: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-04 13:20:31.968217: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-04 13:20:31.968665: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-04 13:20:31.971390: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-04 13:20:31.973053: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-04 13:20:31.978151: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-04 13:20:31.979666: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-04 13:20:31.979752: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-04 13:20:31.980555: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-04 13:20:31.980571: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-04 13:20:31.980580: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-04 13:20:31.981856: 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. 2025-03-04 13:20:32.320070: 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 2025-03-04 13:20:32.320203: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-04 13:20:32.320224: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-04 13:20:32.320243: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-04 13:20:32.320260: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-04 13:20:32.320277: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-04 13:20:32.320293: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-04 13:20:32.320311: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-04 13:20:32.321559: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-04 13:20:32.322653: 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 2025-03-04 13:20:32.322683: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-04 13:20:32.322698: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-04 13:20:32.322710: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-04 13:20:32.322723: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-04 13:20:32.322736: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-04 13:20:32.322749: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-04 13:20:32.322761: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-04 13:20:32.323939: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-04 13:20:32.323972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-04 13:20:32.323980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-04 13:20:32.323987: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-04 13:20:32.325204: 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 : [] 2025-03-04 13:20:40.507238: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-04 13:20:40.725141: 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: -119.39531 max: 148.37344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0007717609405517578 length of segment : 36 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 87 time to create 1 rle with old method : 0.00020647048950195312 length of segment : 26 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0005133152008056641 length of segment : 40 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 273 time to create 1 rle with old method : 0.0005514621734619141 length of segment : 41 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -114.23125 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 length of segment : 0 time for calcul the mask position with numpy : 8.225440979003906e-05 nb_pixel_total : 2224 time to create 1 rle with old method : 0.003576993942260742 length of segment : 88 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 933 time to create 1 rle with old method : 0.0017175674438476562 length of segment : 47 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 921 time to create 1 rle with old method : 0.0011665821075439453 length of segment : 47 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 855 time to create 1 rle with old method : 0.0010504722595214844 length of segment : 47 time for calcul the mask position with numpy : 4.935264587402344e-05 nb_pixel_total : 907 time to create 1 rle with old method : 0.0012516975402832031 length of segment : 45 time for calcul the mask position with numpy : 9.179115295410156e-05 nb_pixel_total : 3340 time to create 1 rle with old method : 0.005881309509277344 length of segment : 47 time for calcul the mask position with numpy : 8.344650268554688e-05 nb_pixel_total : 2125 time to create 1 rle with old method : 0.002707242965698242 length of segment : 89 Processing 1 images image shape: (400, 400, 3) min: 5.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -66.58750 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 503 time to create 1 rle with old method : 0.00093841552734375 length of segment : 18 time for calcul the mask position with numpy : 0.00010633468627929688 nb_pixel_total : 1951 time to create 1 rle with old method : 0.003717184066772461 length of segment : 36 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0006937980651855469 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -109.59063 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 : 6.175041198730469e-05 nb_pixel_total : 514 time to create 1 rle with old method : 0.0009505748748779297 length of segment : 27 time for calcul the mask position with numpy : 8.845329284667969e-05 nb_pixel_total : 2263 time to create 1 rle with old method : 0.004151821136474609 length of segment : 44 time for calcul the mask position with numpy : 6.747245788574219e-05 nb_pixel_total : 475 time to create 1 rle with old method : 0.0009121894836425781 length of segment : 60 time for calcul the mask position with numpy : 0.00015497207641601562 nb_pixel_total : 7152 time to create 1 rle with old method : 0.012050628662109375 length of segment : 103 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0007596015930175781 length of segment : 23 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 94 time to create 1 rle with old method : 0.00024127960205078125 length of segment : 9 time for calcul the mask position with numpy : 0.00015234947204589844 nb_pixel_total : 6138 time to create 1 rle with old method : 0.008336067199707031 length of segment : 101 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003116130828857422 length of segment : 24 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.60781 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 487 time to create 1 rle with old method : 0.0009779930114746094 length of segment : 17 time for calcul the mask position with numpy : 4.172325134277344e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00039005279541015625 length of segment : 24 time for calcul the mask position with numpy : 0.0007030963897705078 nb_pixel_total : 48781 time to create 1 rle with old method : 0.07418584823608398 length of segment : 275 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0014693737030029297 length of segment : 143 time for calcul the mask position with numpy : 0.0005400180816650391 nb_pixel_total : 52511 time to create 1 rle with old method : 0.05794787406921387 length of segment : 278 Processing 1 images image shape: (400, 400, 3) min: 10.00000 max: 175.00000 molded_images shape: (1, 640, 640, 3) min: -97.70000 max: 50.85234 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: 224.00000 molded_images shape: (1, 640, 640, 3) min: -114.02422 max: 96.19375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.0005884170532226562 nb_pixel_total : 20103 time to create 1 rle with old method : 0.039635419845581055 length of segment : 314 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 838 time to create 1 rle with old method : 0.0014522075653076172 length of segment : 45 time for calcul the mask position with numpy : 0.0004000663757324219 nb_pixel_total : 12685 time to create 1 rle with old method : 0.020047664642333984 length of segment : 223 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 358 time to create 1 rle with old method : 0.0006995201110839844 length of segment : 20 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -108.87188 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 : 7.915496826171875e-05 nb_pixel_total : 3044 time to create 1 rle with old method : 0.003781557083129883 length of segment : 63 time for calcul the mask position with numpy : 0.00020837783813476562 nb_pixel_total : 11023 time to create 1 rle with old method : 0.01321268081665039 length of segment : 111 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003883838653564453 length of segment : 24 time for calcul the mask position with numpy : 7.581710815429688e-05 nb_pixel_total : 1898 time to create 1 rle with old method : 0.002376556396484375 length of segment : 99 time for calcul the mask position with numpy : 0.00013566017150878906 nb_pixel_total : 2493 time to create 1 rle with old method : 0.0031006336212158203 length of segment : 137 time for calcul the mask position with numpy : 0.0002231597900390625 nb_pixel_total : 9835 time to create 1 rle with old method : 0.011505842208862305 length of segment : 126 time for calcul the mask position with numpy : 0.00011014938354492188 nb_pixel_total : 2560 time to create 1 rle with old method : 0.003168344497680664 length of segment : 97 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 246 time to create 1 rle with old method : 0.00034332275390625 length of segment : 24 time for calcul the mask position with numpy : 3.266334533691406e-05 nb_pixel_total : 288 time to create 1 rle with old method : 0.00038123130798339844 length of segment : 24 time for calcul the mask position with numpy : 9.512901306152344e-05 nb_pixel_total : 3926 time to create 1 rle with old method : 0.0047359466552734375 length of segment : 136 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -112.41094 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 : 0.00037097930908203125 nb_pixel_total : 25027 time to create 1 rle with old method : 0.028110980987548828 length of segment : 264 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 3 time to create 1 rle with old method : 3.170967102050781e-05 length of segment : 1 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 1083 time to create 1 rle with old method : 0.0014624595642089844 length of segment : 34 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1680 time to create 1 rle with old method : 0.0020372867584228516 length of segment : 109 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 1953 time to create 1 rle with old method : 0.0024538040161132812 length of segment : 61 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 1249 time to create 1 rle with old method : 0.0015110969543457031 length of segment : 49 time for calcul the mask position with numpy : 9.250640869140625e-05 nb_pixel_total : 2240 time to create 1 rle with old method : 0.0030069351196289062 length of segment : 44 time for calcul the mask position with numpy : 0.00023865699768066406 nb_pixel_total : 1209 time to create 1 rle with old method : 0.0016913414001464844 length of segment : 54 time for calcul the mask position with numpy : 0.0003972053527832031 nb_pixel_total : 16243 time to create 1 rle with old method : 0.020839929580688477 length of segment : 357 time for calcul the mask position with numpy : 0.0004074573516845703 nb_pixel_total : 9448 time to create 1 rle with old method : 0.011046409606933594 length of segment : 236 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 7.724761962890625e-05 nb_pixel_total : 1801 time to create 1 rle with old method : 0.0024161338806152344 length of segment : 160 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 1985 time to create 1 rle with old method : 0.0025849342346191406 length of segment : 189 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 772 time to create 1 rle with old method : 0.0010228157043457031 length of segment : 44 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 1097 time to create 1 rle with old method : 0.0014812946319580078 length of segment : 36 time for calcul the mask position with numpy : 0.0001964569091796875 nb_pixel_total : 4817 time to create 1 rle with old method : 0.005629301071166992 length of segment : 223 Processing 1 images image shape: (280, 400, 3) min: 7.00000 max: 176.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 35.00078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0015833377838134766 nb_pixel_total : 105785 time to create 1 rle with old method : 0.1696157455444336 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 250.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 126.82500 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 320 time to create 1 rle with old method : 0.0004780292510986328 length of segment : 17 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 849 time to create 1 rle with old method : 0.001132965087890625 length of segment : 42 time for calcul the mask position with numpy : 0.0003075599670410156 nb_pixel_total : 13184 time to create 1 rle with old method : 0.01534128189086914 length of segment : 223 time for calcul the mask position with numpy : 0.00011205673217773438 nb_pixel_total : 3341 time to create 1 rle with old method : 0.004275083541870117 length of segment : 48 time for calcul the mask position with numpy : 0.00012087821960449219 nb_pixel_total : 4950 time to create 1 rle with old method : 0.006252765655517578 length of segment : 77 time for calcul the mask position with numpy : 0.00019240379333496094 nb_pixel_total : 4684 time to create 1 rle with old method : 0.006860017776489258 length of segment : 81 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 220.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 107.20547 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 16 time for calcul the mask position with numpy : 4.76837158203125e-05 nb_pixel_total : 309 time to create 1 rle with old method : 0.00044536590576171875 length of segment : 20 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 474 time to create 1 rle with old method : 0.0006265640258789062 length of segment : 28 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 208 time to create 1 rle with old method : 0.0002999305725097656 length of segment : 17 time for calcul the mask position with numpy : 3.814697265625e-05 nb_pixel_total : 438 time to create 1 rle with old method : 0.0006251335144042969 length of segment : 25 time for calcul the mask position with numpy : 3.6716461181640625e-05 nb_pixel_total : 359 time to create 1 rle with old method : 0.0005257129669189453 length of segment : 23 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.00029397010803222656 length of segment : 21 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 1938 time to create 1 rle with old method : 0.002474069595336914 length of segment : 43 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 551 time to create 1 rle with old method : 0.0007581710815429688 length of segment : 30 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 232 time to create 1 rle with old method : 0.0003268718719482422 length of segment : 19 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 721 time to create 1 rle with old method : 0.0009238719940185547 length of segment : 63 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0011091232299804688 length of segment : 24 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 178 time to create 1 rle with old method : 0.00037384033203125 length of segment : 14 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 354 time to create 1 rle with old method : 0.0006754398345947266 length of segment : 23 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 947 time to create 1 rle with old method : 0.0017199516296386719 length of segment : 37 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 225 time to create 1 rle with old method : 0.0004336833953857422 length of segment : 19 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 763 time to create 1 rle with old method : 0.0013802051544189453 length of segment : 28 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.50234 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 226 time to create 1 rle with old method : 0.0003845691680908203 length of segment : 25 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 581 time to create 1 rle with old method : 0.0008568763732910156 length of segment : 49 time for calcul the mask position with numpy : 5.6743621826171875e-05 nb_pixel_total : 447 time to create 1 rle with old method : 0.0008139610290527344 length of segment : 36 time for calcul the mask position with numpy : 4.363059997558594e-05 nb_pixel_total : 282 time to create 1 rle with old method : 0.0004413127899169922 length of segment : 17 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 3622 time to create 1 rle with old method : 0.004594564437866211 length of segment : 69 time for calcul the mask position with numpy : 0.00013780593872070312 nb_pixel_total : 4158 time to create 1 rle with old method : 0.0052835941314697266 length of segment : 140 time for calcul the mask position with numpy : 0.0003459453582763672 nb_pixel_total : 14395 time to create 1 rle with old method : 0.017745018005371094 length of segment : 161 time for calcul the mask position with numpy : 6.0558319091796875e-05 nb_pixel_total : 251 time to create 1 rle with old method : 0.0003554821014404297 length of segment : 27 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.00040602684020996094 length of segment : 19 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 744 time to create 1 rle with old method : 0.0013222694396972656 length of segment : 34 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 495 time to create 1 rle with old method : 0.0006520748138427734 length of segment : 31 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 130 time to create 1 rle with old method : 0.00026035308837890625 length of segment : 39 time for calcul the mask position with numpy : 0.00012564659118652344 nb_pixel_total : 3591 time to create 1 rle with old method : 0.004611968994140625 length of segment : 66 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 210 time to create 1 rle with old method : 0.0003752708435058594 length of segment : 23 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: 134.78750 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 107 time to create 1 rle with old method : 0.0003707408905029297 length of segment : 28 time for calcul the mask position with numpy : 4.673004150390625e-05 nb_pixel_total : 154 time to create 1 rle with old method : 0.0003509521484375 length of segment : 17 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.000843048095703125 length of segment : 55 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: -117.83672 max: 148.37344 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0005168914794921875 length of segment : 30 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 103 time to create 1 rle with old method : 0.00023937225341796875 length of segment : 23 time for calcul the mask position with numpy : 6.008148193359375e-05 nb_pixel_total : 265 time to create 1 rle with old method : 0.0006365776062011719 length of segment : 37 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -113.34844 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.888938903808594e-05 nb_pixel_total : 952 time to create 1 rle with old method : 0.0017452239990234375 length of segment : 52 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 968 time to create 1 rle with old method : 0.0017399787902832031 length of segment : 47 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 337 time to create 1 rle with old method : 0.0006356239318847656 length of segment : 35 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 3289 time to create 1 rle with old method : 0.0057675838470458984 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 64.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -58.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 8.916854858398438e-05 nb_pixel_total : 1383 time to create 1 rle with old method : 0.0026276111602783203 length of segment : 30 time for calcul the mask position with numpy : 0.00022125244140625 nb_pixel_total : 3885 time to create 1 rle with old method : 0.006578683853149414 length of segment : 96 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.0009472370147705078 length of segment : 21 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 41 time to create 1 rle with old method : 0.00010824203491210938 length of segment : 8 time for calcul the mask position with numpy : 0.0002682209014892578 nb_pixel_total : 7450 time to create 1 rle with old method : 0.010288238525390625 length of segment : 111 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -116.16484 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 8.797645568847656e-05 nb_pixel_total : 4576 time to create 1 rle with old method : 0.00556492805480957 length of segment : 68 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 660 time to create 1 rle with old method : 0.0008676052093505859 length of segment : 35 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007781982421875 length of segment : 47 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0005121231079101562 length of segment : 24 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.0002446174621582031 length of segment : 19 time for calcul the mask position with numpy : 0.0001125335693359375 nb_pixel_total : 5695 time to create 1 rle with old method : 0.0072057247161865234 length of segment : 91 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 86 time to create 1 rle with old method : 0.0001552104949951172 length of segment : 8 time for calcul the mask position with numpy : 0.0001087188720703125 nb_pixel_total : 5943 time to create 1 rle with old method : 0.007103443145751953 length of segment : 86 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 144.44375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0007369518280029297 length of segment : 17 time for calcul the mask position with numpy : 3.337860107421875e-05 nb_pixel_total : 183 time to create 1 rle with old method : 0.00030040740966796875 length of segment : 23 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 530 time to create 1 rle with old method : 0.0007085800170898438 length of segment : 29 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 1233 time to create 1 rle with old method : 0.0015366077423095703 length of segment : 132 time for calcul the mask position with numpy : 0.0007677078247070312 nb_pixel_total : 59790 time to create 1 rle with old method : 0.06646156311035156 length of segment : 363 Processing 1 images image shape: (400, 400, 3) min: 12.00000 max: 178.00000 molded_images shape: (1, 640, 640, 3) min: -96.02422 max: 51.04375 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: 222.00000 molded_images shape: (1, 640, 640, 3) min: -116.73516 max: 90.25625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.0002808570861816406 nb_pixel_total : 19517 time to create 1 rle with old method : 0.030884981155395508 length of segment : 232 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 761 time to create 1 rle with old method : 0.0009233951568603516 length of segment : 45 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 59 time to create 1 rle with old method : 0.00010657310485839844 length of segment : 8 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0004601478576660156 length of segment : 18 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005984306335449219 length of segment : 25 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -110.49688 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 : 6.031990051269531e-05 nb_pixel_total : 420 time to create 1 rle with old method : 0.0006957054138183594 length of segment : 49 time for calcul the mask position with numpy : 0.000156402587890625 nb_pixel_total : 7080 time to create 1 rle with old method : 0.00890970230102539 length of segment : 101 time for calcul the mask position with numpy : 9.751319885253906e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0014123916625976562 length of segment : 56 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 105 time to create 1 rle with old method : 0.0002181529998779297 length of segment : 13 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 553 time to create 1 rle with old method : 0.0007407665252685547 length of segment : 36 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 603 time to create 1 rle with old method : 0.0008625984191894531 length of segment : 43 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0019762516021728516 length of segment : 29 time for calcul the mask position with numpy : 8.654594421386719e-05 nb_pixel_total : 1689 time to create 1 rle with old method : 0.002202749252319336 length of segment : 78 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 565 time to create 1 rle with old method : 0.0007452964782714844 length of segment : 26 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 1260 time to create 1 rle with old method : 0.0016434192657470703 length of segment : 45 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -107.28203 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 12 time for calcul the mask position with numpy : 0.0003635883331298828 nb_pixel_total : 23977 time to create 1 rle with old method : 0.027918338775634766 length of segment : 239 time for calcul the mask position with numpy : 0.000118255615234375 nb_pixel_total : 173 time to create 1 rle with old method : 0.0005209445953369141 length of segment : 27 time for calcul the mask position with numpy : 7.82012939453125e-05 nb_pixel_total : 1473 time to create 1 rle with old method : 0.0018131732940673828 length of segment : 99 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1201 time to create 1 rle with old method : 0.0015323162078857422 length of segment : 46 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 1039 time to create 1 rle with old method : 0.0014390945434570312 length of segment : 33 time for calcul the mask position with numpy : 0.00010204315185546875 nb_pixel_total : 2908 time to create 1 rle with old method : 0.005383491516113281 length of segment : 66 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 2694 time to create 1 rle with old method : 0.004514455795288086 length of segment : 78 time for calcul the mask position with numpy : 8.821487426757812e-05 nb_pixel_total : 2674 time to create 1 rle with old method : 0.0045032501220703125 length of segment : 82 time for calcul the mask position with numpy : 0.0004429817199707031 nb_pixel_total : 6550 time to create 1 rle with old method : 0.010929346084594727 length of segment : 192 time for calcul the mask position with numpy : 0.00011777877807617188 nb_pixel_total : 799 time to create 1 rle with old method : 0.0010423660278320312 length of segment : 71 time for calcul the mask position with numpy : 0.0003972053527832031 nb_pixel_total : 24863 time to create 1 rle with old method : 0.03423666954040527 length of segment : 214 time for calcul the mask position with numpy : 9.894371032714844e-05 nb_pixel_total : 1126 time to create 1 rle with old method : 0.0021889209747314453 length of segment : 24 Processing 1 images image shape: (400, 320, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 0.00011706352233886719 nb_pixel_total : 1366 time to create 1 rle with old method : 0.0026314258575439453 length of segment : 148 time for calcul the mask position with numpy : 8.535385131835938e-05 nb_pixel_total : 1884 time to create 1 rle with old method : 0.002510547637939453 length of segment : 139 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 221 time to create 1 rle with old method : 0.0003228187561035156 length of segment : 31 time for calcul the mask position with numpy : 0.0002560615539550781 nb_pixel_total : 4803 time to create 1 rle with old method : 0.005946159362792969 length of segment : 224 time for calcul the mask position with numpy : 0.00022125244140625 nb_pixel_total : 3305 time to create 1 rle with old method : 0.004268646240234375 length of segment : 187 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 689 time to create 1 rle with old method : 0.001026153564453125 length of segment : 39 time for calcul the mask position with numpy : 0.0002474784851074219 nb_pixel_total : 4916 time to create 1 rle with old method : 0.0066814422607421875 length of segment : 220 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006592273712158203 length of segment : 26 Processing 1 images image shape: (280, 400, 3) min: 8.00000 max: 172.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 32.25078 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0020363330841064453 nb_pixel_total : 105048 time to create 1 rle with old method : 0.13322734832763672 length of segment : 280 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 246.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 123.42656 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 4.9591064453125e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004360675811767578 length of segment : 15 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 2540 time to create 1 rle with old method : 0.0032088756561279297 length of segment : 52 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 775 time to create 1 rle with old method : 0.0010623931884765625 length of segment : 39 time for calcul the mask position with numpy : 0.0002837181091308594 nb_pixel_total : 14578 time to create 1 rle with old method : 0.017487287521362305 length of segment : 167 time for calcul the mask position with numpy : 0.00014472007751464844 nb_pixel_total : 5100 time to create 1 rle with old method : 0.006385326385498047 length of segment : 81 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 345 time to create 1 rle with old method : 0.0004925727844238281 length of segment : 32 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 213.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 97.81875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 0.00010848045349121094 nb_pixel_total : 2108 time to create 1 rle with old method : 0.002628803253173828 length of segment : 44 time for calcul the mask position with numpy : 5.269050598144531e-05 nb_pixel_total : 920 time to create 1 rle with old method : 0.0012483596801757812 length of segment : 31 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 643 time to create 1 rle with old method : 0.0008759498596191406 length of segment : 30 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005567073822021484 length of segment : 24 time for calcul the mask position with numpy : 5.364418029785156e-05 nb_pixel_total : 942 time to create 1 rle with old method : 0.0012068748474121094 length of segment : 41 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 196 time to create 1 rle with old method : 0.0003094673156738281 length of segment : 17 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 375 time to create 1 rle with old method : 0.000514984130859375 length of segment : 32 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005729198455810547 length of segment : 31 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 688 time to create 1 rle with old method : 0.0009260177612304688 length of segment : 24 time for calcul the mask position with numpy : 3.075599670410156e-05 nb_pixel_total : 58 time to create 1 rle with old method : 0.00011515617370605469 length of segment : 8 time for calcul the mask position with numpy : 3.409385681152344e-05 nb_pixel_total : 234 time to create 1 rle with old method : 0.000339508056640625 length of segment : 18 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 377 time to create 1 rle with old method : 0.0005319118499755859 length of segment : 24 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 108 time to create 1 rle with old method : 0.00017023086547851562 length of segment : 16 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 1071 time to create 1 rle with old method : 0.0013489723205566406 length of segment : 40 time for calcul the mask position with numpy : 3.24249267578125e-05 nb_pixel_total : 84 time to create 1 rle with old method : 0.00013875961303710938 length of segment : 16 time for calcul the mask position with numpy : 4.506111145019531e-05 nb_pixel_total : 770 time to create 1 rle with old method : 0.0010159015655517578 length of segment : 38 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 645 time to create 1 rle with old method : 0.0008955001831054688 length of segment : 22 Processing 1 images image shape: (280, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.75625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 14 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 204 time to create 1 rle with old method : 0.00037097930908203125 length of segment : 25 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 665 time to create 1 rle with old method : 0.001102447509765625 length of segment : 64 time for calcul the mask position with numpy : 5.125999450683594e-05 nb_pixel_total : 397 time to create 1 rle with old method : 0.0005979537963867188 length of segment : 19 time for calcul the mask position with numpy : 4.863739013671875e-05 nb_pixel_total : 564 time to create 1 rle with old method : 0.0007789134979248047 length of segment : 34 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0004363059997558594 length of segment : 15 time for calcul the mask position with numpy : 8.392333984375e-05 nb_pixel_total : 2176 time to create 1 rle with old method : 0.002660512924194336 length of segment : 79 time for calcul the mask position with numpy : 4.6253204345703125e-05 nb_pixel_total : 244 time to create 1 rle with old method : 0.00036263465881347656 length of segment : 17 time for calcul the mask position with numpy : 7.367134094238281e-05 nb_pixel_total : 1720 time to create 1 rle with old method : 0.0022737979888916016 length of segment : 95 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 292 time to create 1 rle with old method : 0.0006036758422851562 length of segment : 22 time for calcul the mask position with numpy : 0.00012755393981933594 nb_pixel_total : 3512 time to create 1 rle with old method : 0.00451970100402832 length of segment : 66 time for calcul the mask position with numpy : 0.00010418891906738281 nb_pixel_total : 3559 time to create 1 rle with old method : 0.004572153091430664 length of segment : 67 time for calcul the mask position with numpy : 9.489059448242188e-05 nb_pixel_total : 2083 time to create 1 rle with old method : 0.002688169479370117 length of segment : 73 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 179 time to create 1 rle with old method : 0.0002713203430175781 length of segment : 25 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 502 time to create 1 rle with old method : 0.0007965564727783203 length of segment : 35 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: 132.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0004584789276123047 nb_pixel_total : 38928 time to create 1 rle with old method : 0.044435739517211914 length of segment : 254 Detection mask done ! Trying to reset tf kernel 3816128 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 4726 tf kernel not reseted sub process len(results) : 196 len(list_Values) 196 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 196 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 196 chid ids of type : 4228 Number RLEs to save : 13590 save missing photos in datou_result : time spend for datou_step_exec : 25.676498651504517 time spend to save output : 0.9485619068145752 total time spend for step 1 : 26.625060558319092 step2:brightness Tue Mar 4 13:20:55 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/1741090828_3815740_1340795898_c06c87f2c0d7e50be02e172c9251e090.jpg treat image : temp/1741090828_3815740_1340795895_d2adc5a84ea8b2591ee414eb0289d964.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 : 0.011624813079833984 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 : 0.011493682861328125 save missing photos in datou_result : time spend for datou_step_exec : 0.5403895378112793 time spend to save output : 0.028305530548095703 total time spend for step 2 : 0.568695068359375 step3:blur_detection Tue Mar 4 13:20:56 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 blur_detection methode: ratio et variance treat image : temp/1741090828_3815740_1340795898_c06c87f2c0d7e50be02e172c9251e090.jpg resize: (1080, 1920) 1340795898 -7.129180427843427 treat image : temp/1741090828_3815740_1340795895_d2adc5a84ea8b2591ee414eb0289d964.jpg resize: (1080, 1920) 1340795895 -7.1236251822195 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 : 0.012277603149414062 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 : 0.01127171516418457 save missing photos in datou_result : time spend for datou_step_exec : 2.1162796020507812 time spend to save output : 0.02852010726928711 total time spend for step 3 : 2.1447997093200684 step4:rle_unique_nms_with_priority Tue Mar 4 13:20:58 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 196 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 96 nb_hashtags : 7 time to prepare the origin masks : 1.1817502975463867 time for calcul the mask position with numpy : 0.4768943786621094 nb_pixel_total : 1715215 time to create 1 rle with new method : 0.3337118625640869 time for calcul the mask position with numpy : 0.008371829986572266 nb_pixel_total : 352 time to create 1 rle with old method : 0.000377655029296875 time for calcul the mask position with numpy : 0.008465051651000977 nb_pixel_total : 7492 time to create 1 rle with old method : 0.008316755294799805 time for calcul the mask position with numpy : 0.008011102676391602 nb_pixel_total : 166 time to create 1 rle with old method : 0.00021910667419433594 time for calcul the mask position with numpy : 0.008484601974487305 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004792213439941406 time for calcul the mask position with numpy : 0.008236885070800781 nb_pixel_total : 42 time to create 1 rle with old method : 7.939338684082031e-05 time for calcul the mask position with numpy : 0.008209228515625 nb_pixel_total : 933 time to create 1 rle with old method : 0.0010657310485839844 time for calcul the mask position with numpy : 0.008447885513305664 nb_pixel_total : 87 time to create 1 rle with old method : 0.00011181831359863281 time for calcul the mask position with numpy : 0.008270263671875 nb_pixel_total : 208 time to create 1 rle with old method : 0.00025963783264160156 time for calcul the mask position with numpy : 0.008336544036865234 nb_pixel_total : 34 time to create 1 rle with old method : 8.130073547363281e-05 time for calcul the mask position with numpy : 0.008323907852172852 nb_pixel_total : 48781 time to create 1 rle with old method : 0.05273842811584473 time for calcul the mask position with numpy : 0.008593320846557617 nb_pixel_total : 3340 time to create 1 rle with old method : 0.0037603378295898438 time for calcul the mask position with numpy : 0.008587360382080078 nb_pixel_total : 182 time to create 1 rle with old method : 0.00023365020751953125 time for calcul the mask position with numpy : 0.00851750373840332 nb_pixel_total : 855 time to create 1 rle with old method : 0.0009839534759521484 time for calcul the mask position with numpy : 0.008595943450927734 nb_pixel_total : 1218 time to create 1 rle with old method : 0.0014870166778564453 time for calcul the mask position with numpy : 0.008582115173339844 nb_pixel_total : 29 time to create 1 rle with old method : 7.033348083496094e-05 time for calcul the mask position with numpy : 0.008533000946044922 nb_pixel_total : 2224 time to create 1 rle with old method : 0.002691984176635742 time for calcul the mask position with numpy : 0.008577585220336914 nb_pixel_total : 94 time to create 1 rle with old method : 0.0001366138458251953 time for calcul the mask position with numpy : 0.008431434631347656 nb_pixel_total : 475 time to create 1 rle with old method : 0.0005669593811035156 time for calcul the mask position with numpy : 0.008328676223754883 nb_pixel_total : 386 time to create 1 rle with old method : 0.0004508495330810547 time for calcul the mask position with numpy : 0.008170604705810547 nb_pixel_total : 514 time to create 1 rle with old method : 0.0005600452423095703 time for calcul the mask position with numpy : 0.00835561752319336 nb_pixel_total : 1951 time to create 1 rle with old method : 0.0021173954010009766 time for calcul the mask position with numpy : 0.008121013641357422 nb_pixel_total : 7152 time to create 1 rle with old method : 0.007767438888549805 time for calcul the mask position with numpy : 0.008366584777832031 nb_pixel_total : 15 time to create 1 rle with old method : 8.749961853027344e-05 time for calcul the mask position with numpy : 0.008253812789916992 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002257823944091797 time for calcul the mask position with numpy : 0.008079767227172852 nb_pixel_total : 2263 time to create 1 rle with old method : 0.0025191307067871094 time for calcul the mask position with numpy : 0.008378982543945312 nb_pixel_total : 503 time to create 1 rle with old method : 0.0005536079406738281 time for calcul the mask position with numpy : 0.008264780044555664 nb_pixel_total : 487 time to create 1 rle with old method : 0.0005462169647216797 time for calcul the mask position with numpy : 0.008274316787719727 nb_pixel_total : 1317 time to create 1 rle with old method : 0.001544952392578125 time for calcul the mask position with numpy : 0.00824427604675293 nb_pixel_total : 440 time to create 1 rle with old method : 0.0005719661712646484 time for calcul the mask position with numpy : 0.008188962936401367 nb_pixel_total : 2493 time to create 1 rle with old method : 0.0029032230377197266 time for calcul the mask position with numpy : 0.008273601531982422 nb_pixel_total : 2240 time to create 1 rle with old method : 0.002521514892578125 time for calcul the mask position with numpy : 0.008167505264282227 nb_pixel_total : 1066 time to create 1 rle with old method : 0.0011839866638183594 time for calcul the mask position with numpy : 0.008151769638061523 nb_pixel_total : 1204 time to create 1 rle with old method : 0.0013797283172607422 time for calcul the mask position with numpy : 0.00800323486328125 nb_pixel_total : 644 time to create 1 rle with old method : 0.0007948875427246094 time for calcul the mask position with numpy : 0.00820302963256836 nb_pixel_total : 11023 time to create 1 rle with old method : 0.011983394622802734 time for calcul the mask position with numpy : 0.008131265640258789 nb_pixel_total : 25027 time to create 1 rle with old method : 0.026813507080078125 time for calcul the mask position with numpy : 0.008533954620361328 nb_pixel_total : 3 time to create 1 rle with old method : 1.3589859008789062e-05 time for calcul the mask position with numpy : 0.008199453353881836 nb_pixel_total : 772 time to create 1 rle with old method : 0.0008599758148193359 time for calcul the mask position with numpy : 0.008254528045654297 nb_pixel_total : 20103 time to create 1 rle with old method : 0.021773815155029297 time for calcul the mask position with numpy : 0.008419036865234375 nb_pixel_total : 16243 time to create 1 rle with old method : 0.022044658660888672 time for calcul the mask position with numpy : 0.008560419082641602 nb_pixel_total : 542 time to create 1 rle with old method : 0.0006530284881591797 time for calcul the mask position with numpy : 0.008637189865112305 nb_pixel_total : 12685 time to create 1 rle with old method : 0.013899803161621094 time for calcul the mask position with numpy : 0.008630514144897461 nb_pixel_total : 1801 time to create 1 rle with old method : 0.0020875930786132812 time for calcul the mask position with numpy : 0.008650541305541992 nb_pixel_total : 1074 time to create 1 rle with old method : 0.0016765594482421875 time for calcul the mask position with numpy : 0.008911848068237305 nb_pixel_total : 3044 time to create 1 rle with old method : 0.003387451171875 time for calcul the mask position with numpy : 0.008612632751464844 nb_pixel_total : 4817 time to create 1 rle with old method : 0.005411386489868164 time for calcul the mask position with numpy : 0.008640289306640625 nb_pixel_total : 906 time to create 1 rle with old method : 0.0010678768157958984 time for calcul the mask position with numpy : 0.008758783340454102 nb_pixel_total : 1680 time to create 1 rle with old method : 0.0019207000732421875 time for calcul the mask position with numpy : 0.008654594421386719 nb_pixel_total : 9 time to create 1 rle with old method : 3.075599670410156e-05 time for calcul the mask position with numpy : 0.00907135009765625 nb_pixel_total : 1953 time to create 1 rle with old method : 0.0026276111602783203 time for calcul the mask position with numpy : 0.008563041687011719 nb_pixel_total : 1898 time to create 1 rle with old method : 0.002161264419555664 time for calcul the mask position with numpy : 0.008476495742797852 nb_pixel_total : 281 time to create 1 rle with old method : 0.0003285408020019531 time for calcul the mask position with numpy : 0.008570671081542969 nb_pixel_total : 14 time to create 1 rle with old method : 4.291534423828125e-05 time for calcul the mask position with numpy : 0.008552074432373047 nb_pixel_total : 12 time to create 1 rle with old method : 3.9577484130859375e-05 time for calcul the mask position with numpy : 0.008605241775512695 nb_pixel_total : 833 time to create 1 rle with old method : 0.0009474754333496094 time for calcul the mask position with numpy : 0.008600950241088867 nb_pixel_total : 1249 time to create 1 rle with old method : 0.0014319419860839844 time for calcul the mask position with numpy : 0.009549140930175781 nb_pixel_total : 105785 time to create 1 rle with old method : 0.11764693260192871 time for calcul the mask position with numpy : 0.008580684661865234 nb_pixel_total : 13184 time to create 1 rle with old method : 0.014664649963378906 time for calcul the mask position with numpy : 0.008419513702392578 nb_pixel_total : 54 time to create 1 rle with old method : 0.00015044212341308594 time for calcul the mask position with numpy : 0.008393526077270508 nb_pixel_total : 3622 time to create 1 rle with old method : 0.00402069091796875 time for calcul the mask position with numpy : 0.008496284484863281 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003204345703125 time for calcul the mask position with numpy : 0.008455038070678711 nb_pixel_total : 107 time to create 1 rle with old method : 0.00016927719116210938 time for calcul the mask position with numpy : 0.008400201797485352 nb_pixel_total : 78 time to create 1 rle with old method : 0.00011873245239257812 time for calcul the mask position with numpy : 0.008358240127563477 nb_pixel_total : 418 time to create 1 rle with old method : 0.00048542022705078125 time for calcul the mask position with numpy : 0.00839090347290039 nb_pixel_total : 688 time to create 1 rle with old method : 0.00077056884765625 time for calcul the mask position with numpy : 0.008414983749389648 nb_pixel_total : 178 time to create 1 rle with old method : 0.00020503997802734375 time for calcul the mask position with numpy : 0.008374452590942383 nb_pixel_total : 226 time to create 1 rle with old method : 0.0002837181091308594 time for calcul the mask position with numpy : 0.008373022079467773 nb_pixel_total : 232 time to create 1 rle with old method : 0.0002613067626953125 time for calcul the mask position with numpy : 0.008395910263061523 nb_pixel_total : 4 time to create 1 rle with old method : 2.3603439331054688e-05 time for calcul the mask position with numpy : 0.008371591567993164 nb_pixel_total : 359 time to create 1 rle with old method : 0.0004162788391113281 time for calcul the mask position with numpy : 0.00835418701171875 nb_pixel_total : 208 time to create 1 rle with old method : 0.00023412704467773438 time for calcul the mask position with numpy : 0.008394002914428711 nb_pixel_total : 211 time to create 1 rle with old method : 0.0002524852752685547 time for calcul the mask position with numpy : 0.008428335189819336 nb_pixel_total : 24 time to create 1 rle with old method : 4.696846008300781e-05 time for calcul the mask position with numpy : 0.008469820022583008 nb_pixel_total : 4950 time to create 1 rle with old method : 0.005440235137939453 time for calcul the mask position with numpy : 0.008489370346069336 nb_pixel_total : 947 time to create 1 rle with old method : 0.0010833740234375 time for calcul the mask position with numpy : 0.008463859558105469 nb_pixel_total : 551 time to create 1 rle with old method : 0.0006923675537109375 time for calcul the mask position with numpy : 0.008441925048828125 nb_pixel_total : 130 time to create 1 rle with old method : 0.000179290771484375 time for calcul the mask position with numpy : 0.008443593978881836 nb_pixel_total : 309 time to create 1 rle with old method : 0.00037598609924316406 time for calcul the mask position with numpy : 0.008426427841186523 nb_pixel_total : 4158 time to create 1 rle with old method : 0.005213260650634766 time for calcul the mask position with numpy : 0.008436203002929688 nb_pixel_total : 721 time to create 1 rle with old method : 0.0008635520935058594 time for calcul the mask position with numpy : 0.008410930633544922 nb_pixel_total : 13692 time to create 1 rle with old method : 0.016040325164794922 time for calcul the mask position with numpy : 0.008391141891479492 nb_pixel_total : 195 time to create 1 rle with old method : 0.00023674964904785156 time for calcul the mask position with numpy : 0.008387088775634766 nb_pixel_total : 4 time to create 1 rle with old method : 1.6450881958007812e-05 time for calcul the mask position with numpy : 0.008365392684936523 nb_pixel_total : 4684 time to create 1 rle with old method : 0.0051920413970947266 time for calcul the mask position with numpy : 0.008275508880615234 nb_pixel_total : 849 time to create 1 rle with old method : 0.0009832382202148438 time for calcul the mask position with numpy : 0.008306741714477539 nb_pixel_total : 154 time to create 1 rle with old method : 0.000186920166015625 time for calcul the mask position with numpy : 0.00838613510131836 nb_pixel_total : 581 time to create 1 rle with old method : 0.0007300376892089844 time for calcul the mask position with numpy : 0.008399248123168945 nb_pixel_total : 320 time to create 1 rle with old method : 0.0003790855407714844 time for calcul the mask position with numpy : 0.008135795593261719 nb_pixel_total : 495 time to create 1 rle with old method : 0.0005688667297363281 time for calcul the mask position with numpy : 0.008304119110107422 nb_pixel_total : 225 time to create 1 rle with old method : 0.0002651214599609375 time for calcul the mask position with numpy : 0.008188247680664062 nb_pixel_total : 282 time to create 1 rle with old method : 0.00032329559326171875 time for calcul the mask position with numpy : 0.008388757705688477 nb_pixel_total : 474 time to create 1 rle with old method : 0.0005445480346679688 time for calcul the mask position with numpy : 0.00818324089050293 nb_pixel_total : 1938 time to create 1 rle with old method : 0.0022253990173339844 time for calcul the mask position with numpy : 0.008111953735351562 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005478858947753906 time for calcul the mask position with numpy : 0.008249998092651367 nb_pixel_total : 447 time to create 1 rle with old method : 0.0005850791931152344 time for calcul the mask position with numpy : 0.007993221282958984 nb_pixel_total : 438 time to create 1 rle with old method : 0.0005052089691162109 create new chi : 2.0353479385375977 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 : 0.009896516799926758 batch 1 Loaded 97 chid ids of type : 4230 Number RLEs to save : 13224 TO DO : save crop sub photo not yet done ! save time : 0.7203538417816162 nb_obj : 99 nb_hashtags : 7 time to prepare the origin masks : 2.1550889015197754 time for calcul the mask position with numpy : 0.07750153541564941 nb_pixel_total : 1714412 time to create 1 rle with new method : 0.10345816612243652 time for calcul the mask position with numpy : 0.008766651153564453 nb_pixel_total : 3885 time to create 1 rle with old method : 0.004323244094848633 time for calcul the mask position with numpy : 0.008977651596069336 nb_pixel_total : 3589 time to create 1 rle with old method : 0.004344940185546875 time for calcul the mask position with numpy : 0.0065042972564697266 nb_pixel_total : 345 time to create 1 rle with old method : 0.0003960132598876953 time for calcul the mask position with numpy : 0.006552219390869141 nb_pixel_total : 41 time to create 1 rle with old method : 6.508827209472656e-05 time for calcul the mask position with numpy : 0.0066623687744140625 nb_pixel_total : 337 time to create 1 rle with old method : 0.0004019737243652344 time for calcul the mask position with numpy : 0.00818324089050293 nb_pixel_total : 59601 time to create 1 rle with old method : 0.06673693656921387 time for calcul the mask position with numpy : 0.00617218017578125 nb_pixel_total : 53 time to create 1 rle with old method : 0.00011134147644042969 time for calcul the mask position with numpy : 0.014332294464111328 nb_pixel_total : 952 time to create 1 rle with old method : 0.0010788440704345703 time for calcul the mask position with numpy : 0.009529352188110352 nb_pixel_total : 103 time to create 1 rle with old method : 0.00013637542724609375 time for calcul the mask position with numpy : 0.012154102325439453 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003178119659423828 time for calcul the mask position with numpy : 0.01123666763305664 nb_pixel_total : 265 time to create 1 rle with old method : 0.0003552436828613281 time for calcul the mask position with numpy : 0.010944128036499023 nb_pixel_total : 3289 time to create 1 rle with old method : 0.003660917282104492 time for calcul the mask position with numpy : 0.00646662712097168 nb_pixel_total : 138 time to create 1 rle with old method : 0.0001811981201171875 time for calcul the mask position with numpy : 0.006377220153808594 nb_pixel_total : 1233 time to create 1 rle with old method : 0.001373291015625 time for calcul the mask position with numpy : 0.0063092708587646484 nb_pixel_total : 86 time to create 1 rle with old method : 0.00011134147644042969 time for calcul the mask position with numpy : 0.006224155426025391 nb_pixel_total : 600 time to create 1 rle with old method : 0.0007219314575195312 time for calcul the mask position with numpy : 0.00627446174621582 nb_pixel_total : 352 time to create 1 rle with old method : 0.0004153251647949219 time for calcul the mask position with numpy : 0.010244131088256836 nb_pixel_total : 660 time to create 1 rle with old method : 0.0007328987121582031 time for calcul the mask position with numpy : 0.010172605514526367 nb_pixel_total : 1383 time to create 1 rle with old method : 0.0015680789947509766 time for calcul the mask position with numpy : 0.010065555572509766 nb_pixel_total : 5695 time to create 1 rle with old method : 0.006608486175537109 time for calcul the mask position with numpy : 0.009983301162719727 nb_pixel_total : 396 time to create 1 rle with old method : 0.0005960464477539062 time for calcul the mask position with numpy : 0.011618852615356445 nb_pixel_total : 530 time to create 1 rle with old method : 0.0006108283996582031 time for calcul the mask position with numpy : 0.010071516036987305 nb_pixel_total : 4576 time to create 1 rle with old method : 0.005318880081176758 time for calcul the mask position with numpy : 0.009915351867675781 nb_pixel_total : 183 time to create 1 rle with old method : 0.0002193450927734375 time for calcul the mask position with numpy : 0.009944677352905273 nb_pixel_total : 497 time to create 1 rle with old method : 0.0006184577941894531 time for calcul the mask position with numpy : 0.009919881820678711 nb_pixel_total : 1126 time to create 1 rle with old method : 0.001361846923828125 time for calcul the mask position with numpy : 0.00989675521850586 nb_pixel_total : 799 time to create 1 rle with old method : 0.0009090900421142578 time for calcul the mask position with numpy : 0.010129451751708984 nb_pixel_total : 2908 time to create 1 rle with old method : 0.0032618045806884766 time for calcul the mask position with numpy : 0.010048866271972656 nb_pixel_total : 1035 time to create 1 rle with old method : 0.0011720657348632812 time for calcul the mask position with numpy : 0.010156393051147461 nb_pixel_total : 23977 time to create 1 rle with old method : 0.027142047882080078 time for calcul the mask position with numpy : 0.01018667221069336 nb_pixel_total : 105 time to create 1 rle with old method : 0.00014591217041015625 time for calcul the mask position with numpy : 0.010137081146240234 nb_pixel_total : 173 time to create 1 rle with old method : 0.0002810955047607422 time for calcul the mask position with numpy : 0.009434223175048828 nb_pixel_total : 221 time to create 1 rle with old method : 0.00027298927307128906 time for calcul the mask position with numpy : 0.0068967342376708984 nb_pixel_total : 7080 time to create 1 rle with old method : 0.007892370223999023 time for calcul the mask position with numpy : 0.007012605667114258 nb_pixel_total : 565 time to create 1 rle with old method : 0.0006847381591796875 time for calcul the mask position with numpy : 0.006416797637939453 nb_pixel_total : 3109 time to create 1 rle with old method : 0.003945589065551758 time for calcul the mask position with numpy : 0.00651860237121582 nb_pixel_total : 689 time to create 1 rle with old method : 0.0008332729339599609 time for calcul the mask position with numpy : 0.006676197052001953 nb_pixel_total : 19517 time to create 1 rle with old method : 0.02560901641845703 time for calcul the mask position with numpy : 0.007613658905029297 nb_pixel_total : 20 time to create 1 rle with old method : 0.00015115737915039062 time for calcul the mask position with numpy : 0.007623910903930664 nb_pixel_total : 1050 time to create 1 rle with old method : 0.0019774436950683594 time for calcul the mask position with numpy : 0.007363319396972656 nb_pixel_total : 512 time to create 1 rle with old method : 0.001032114028930664 time for calcul the mask position with numpy : 0.007364034652709961 nb_pixel_total : 497 time to create 1 rle with old method : 0.0008928775787353516 time for calcul the mask position with numpy : 0.0072710514068603516 nb_pixel_total : 946 time to create 1 rle with old method : 0.0019490718841552734 time for calcul the mask position with numpy : 0.007420063018798828 nb_pixel_total : 1366 time to create 1 rle with old method : 0.002569437026977539 time for calcul the mask position with numpy : 0.007269859313964844 nb_pixel_total : 4803 time to create 1 rle with old method : 0.008650779724121094 time for calcul the mask position with numpy : 0.006836891174316406 nb_pixel_total : 603 time to create 1 rle with old method : 0.0007257461547851562 time for calcul the mask position with numpy : 0.006327629089355469 nb_pixel_total : 420 time to create 1 rle with old method : 0.0005164146423339844 time for calcul the mask position with numpy : 0.006269931793212891 nb_pixel_total : 293 time to create 1 rle with old method : 0.0004425048828125 time for calcul the mask position with numpy : 0.006448030471801758 nb_pixel_total : 162 time to create 1 rle with old method : 0.0002536773681640625 time for calcul the mask position with numpy : 0.0065135955810546875 nb_pixel_total : 6550 time to create 1 rle with old method : 0.0073566436767578125 time for calcul the mask position with numpy : 0.006533145904541016 nb_pixel_total : 11 time to create 1 rle with old method : 3.8623809814453125e-05 time for calcul the mask position with numpy : 0.007327079772949219 nb_pixel_total : 1473 time to create 1 rle with old method : 0.0017650127410888672 time for calcul the mask position with numpy : 0.007245540618896484 nb_pixel_total : 2694 time to create 1 rle with old method : 0.0029892921447753906 time for calcul the mask position with numpy : 0.007195949554443359 nb_pixel_total : 92 time to create 1 rle with old method : 0.00016641616821289062 time for calcul the mask position with numpy : 0.008805274963378906 nb_pixel_total : 553 time to create 1 rle with old method : 0.0006451606750488281 time for calcul the mask position with numpy : 0.0072596073150634766 nb_pixel_total : 761 time to create 1 rle with old method : 0.0008563995361328125 time for calcul the mask position with numpy : 0.007190227508544922 nb_pixel_total : 59 time to create 1 rle with old method : 8.344650268554688e-05 time for calcul the mask position with numpy : 0.006159305572509766 nb_pixel_total : 444 time to create 1 rle with old method : 0.0005838871002197266 time for calcul the mask position with numpy : 0.006933927536010742 nb_pixel_total : 1201 time to create 1 rle with old method : 0.0013844966888427734 time for calcul the mask position with numpy : 0.006523609161376953 nb_pixel_total : 665 time to create 1 rle with old method : 0.0007605552673339844 time for calcul the mask position with numpy : 0.007025480270385742 nb_pixel_total : 105048 time to create 1 rle with old method : 0.11433029174804688 time for calcul the mask position with numpy : 0.006231546401977539 nb_pixel_total : 397 time to create 1 rle with old method : 0.00047135353088378906 time for calcul the mask position with numpy : 0.006207466125488281 nb_pixel_total : 12104 time to create 1 rle with old method : 0.013491153717041016 time for calcul the mask position with numpy : 0.0067903995513916016 nb_pixel_total : 38928 time to create 1 rle with old method : 0.042429447174072266 time for calcul the mask position with numpy : 0.006242513656616211 nb_pixel_total : 3512 time to create 1 rle with old method : 0.003939628601074219 time for calcul the mask position with numpy : 0.006296873092651367 nb_pixel_total : 70 time to create 1 rle with old method : 0.00015997886657714844 time for calcul the mask position with numpy : 0.006217002868652344 nb_pixel_total : 244 time to create 1 rle with old method : 0.0003662109375 time for calcul the mask position with numpy : 0.007311582565307617 nb_pixel_total : 688 time to create 1 rle with old method : 0.000789642333984375 time for calcul the mask position with numpy : 0.005883216857910156 nb_pixel_total : 13 time to create 1 rle with old method : 3.600120544433594e-05 time for calcul the mask position with numpy : 0.0061037540435791016 nb_pixel_total : 204 time to create 1 rle with old method : 0.0002372264862060547 time for calcul the mask position with numpy : 0.006438016891479492 nb_pixel_total : 2540 time to create 1 rle with old method : 0.0029180049896240234 time for calcul the mask position with numpy : 0.0060482025146484375 nb_pixel_total : 386 time to create 1 rle with old method : 0.0004470348358154297 time for calcul the mask position with numpy : 0.005965709686279297 nb_pixel_total : 196 time to create 1 rle with old method : 0.00024199485778808594 time for calcul the mask position with numpy : 0.0065076351165771484 nb_pixel_total : 5100 time to create 1 rle with old method : 0.0058155059814453125 time for calcul the mask position with numpy : 0.006108283996582031 nb_pixel_total : 643 time to create 1 rle with old method : 0.0007457733154296875 time for calcul the mask position with numpy : 0.0060956478118896484 nb_pixel_total : 5 time to create 1 rle with old method : 3.600120544433594e-05 time for calcul the mask position with numpy : 0.006147861480712891 nb_pixel_total : 770 time to create 1 rle with old method : 0.0008580684661865234 time for calcul the mask position with numpy : 0.006120920181274414 nb_pixel_total : 2176 time to create 1 rle with old method : 0.002607583999633789 time for calcul the mask position with numpy : 0.006151914596557617 nb_pixel_total : 108 time to create 1 rle with old method : 0.0001399517059326172 time for calcul the mask position with numpy : 0.006435394287109375 nb_pixel_total : 39 time to create 1 rle with old method : 9.584426879882812e-05 time for calcul the mask position with numpy : 0.006069660186767578 nb_pixel_total : 1654 time to create 1 rle with old method : 0.0019199848175048828 time for calcul the mask position with numpy : 0.0061969757080078125 nb_pixel_total : 179 time to create 1 rle with old method : 0.0002238750457763672 time for calcul the mask position with numpy : 0.0062100887298583984 nb_pixel_total : 775 time to create 1 rle with old method : 0.0008826255798339844 time for calcul the mask position with numpy : 0.006220340728759766 nb_pixel_total : 920 time to create 1 rle with old method : 0.0010349750518798828 time for calcul the mask position with numpy : 0.00632023811340332 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008265972137451172 time for calcul the mask position with numpy : 0.0061953067779541016 nb_pixel_total : 286 time to create 1 rle with old method : 0.0004062652587890625 time for calcul the mask position with numpy : 0.006437063217163086 nb_pixel_total : 345 time to create 1 rle with old method : 0.00040459632873535156 time for calcul the mask position with numpy : 0.006452322006225586 nb_pixel_total : 564 time to create 1 rle with old method : 0.0006546974182128906 time for calcul the mask position with numpy : 0.0066471099853515625 nb_pixel_total : 234 time to create 1 rle with old method : 0.00027561187744140625 time for calcul the mask position with numpy : 0.006426334381103516 nb_pixel_total : 293 time to create 1 rle with old method : 0.000362396240234375 time for calcul the mask position with numpy : 0.0059239864349365234 nb_pixel_total : 432 time to create 1 rle with old method : 0.0005037784576416016 time for calcul the mask position with numpy : 0.006013393402099609 nb_pixel_total : 16 time to create 1 rle with old method : 3.600120544433594e-05 time for calcul the mask position with numpy : 0.006079912185668945 nb_pixel_total : 2108 time to create 1 rle with old method : 0.002351045608520508 time for calcul the mask position with numpy : 0.005961894989013672 nb_pixel_total : 375 time to create 1 rle with old method : 0.00039649009704589844 time for calcul the mask position with numpy : 0.006035566329956055 nb_pixel_total : 942 time to create 1 rle with old method : 0.0011327266693115234 time for calcul the mask position with numpy : 0.006070613861083984 nb_pixel_total : 133 time to create 1 rle with old method : 0.00023794174194335938 time for calcul the mask position with numpy : 0.008289575576782227 nb_pixel_total : 58 time to create 1 rle with old method : 7.462501525878906e-05 time for calcul the mask position with numpy : 0.00847482681274414 nb_pixel_total : 220 time to create 1 rle with old method : 0.0003116130828857422 time for calcul the mask position with numpy : 0.00841522216796875 nb_pixel_total : 292 time to create 1 rle with old method : 0.00037479400634765625 create new chi : 1.3492965698242188 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 : 0.001459360122680664 batch 1 Loaded 100 chid ids of type : 4230 Number RLEs to save : 12352 TO DO : save crop sub photo not yet done ! save time : 0.7218701839447021 map_output_result : {1340795898: (0.0, 'Should be the crop_list due to order', 0.0), 1340795895: (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 [1340795898, 1340795895] Looping around the photos to save general results len do output : 2 /1340795898.Didn't retrieve data . /1340795895.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, '2632484') ('4234', '21008178', '1340795898', None, None, None, None, None, '2632484') ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795895', None, None, None, None, None, '2632484') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.0133209228515625 save_final save missing photos in datou_result : time spend for datou_step_exec : 8.572054862976074 time spend to save output : 0.031002283096313477 total time spend for step 4 : 8.603057146072388 step5:crop_condition Tue Mar 4 13:21:06 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 197 chid ids of type : 4230 begin to crop the class : papier param for this class : {'min_score': 0.6} filtre for class : papier hashtag_id of this class : 492668766 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 64 About to insert : list_path_to_insert length 64 new photo from crops ! About to upload 64 photos upload in portfolio : 4869462 init cache_photo without model_param we have 64 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741090868_3815740 we have uploaded 64 photos in the portfolio 4869462 time of upload the photos Elapsed time : 15.98171067237854 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.6} filtre for class : carton hashtag_id of this class : 492774966 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 20 About to insert : list_path_to_insert length 20 new photo from crops ! About to upload 20 photos upload in portfolio : 4869462 init cache_photo without model_param we have 20 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741090885_3815740 we have uploaded 20 photos in the portfolio 4869462 time of upload the photos Elapsed time : 5.818533420562744 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.6} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : pet_clair param for this class : {'min_score': 0.6} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 11 About to insert : list_path_to_insert length 11 new photo from crops ! About to upload 11 photos upload in portfolio : 4869462 init cache_photo without model_param we have 11 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741090891_3815740 we have uploaded 11 photos in the portfolio 4869462 time of upload the photos Elapsed time : 4.095531225204468 we have finished the crop for the class : pet_clair begin to crop the class : autre param for this class : {'min_score': 0.6} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 29 About to insert : list_path_to_insert length 29 new photo from crops ! About to upload 29 photos upload in portfolio : 4869462 init cache_photo without model_param we have 29 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741090896_3815740 we have uploaded 29 photos in the portfolio 4869462 time of upload the photos Elapsed time : 8.593575477600098 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 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 4869462 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741090904_3815740 we have uploaded 1 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.44860100746154785 we have finished the crop for the class : pehd 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 [1340795898, 1340795895] Looping around the photos to save general results len do output : 125 /1340799476Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799477Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799478Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799479Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799480Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799481Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799482Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799483Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799484Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799485Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799486Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799487Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799488Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799489Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799491Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799492Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799493Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799494Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799495Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799496Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799497Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799498Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799499Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799500Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799501Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799502Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799503Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799504Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799505Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799506Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799507Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799508Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799509Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799510Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799511Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799512Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799513Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799514Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799515Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799516Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799517Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799518Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799519Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799520Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799521Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799522Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799523Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799524Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799525Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799526Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799527Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799528Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799529Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799530Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799531Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799532Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799533Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799534Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799535Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799536Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799537Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799538Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799539Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799540Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799544Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799545Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799546Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799547Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799551Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799559Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799563Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799571Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799576Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799590Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799591Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799592Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799593Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799594Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799595Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799596Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799597Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799598Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799599Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799600Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799601Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799602Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799603Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799604Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799605Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799606Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799607Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799609Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799610Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799611Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799612Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799613Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799614Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799615Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799616Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799617Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799618Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799619Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1340799620Didn'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, '2632484') ('4234', '21008178', '1340795898', None, None, None, None, None, '2632484') ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795895', None, None, None, None, None, '2632484') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 377 time used for this insertion : 0.03139805793762207 save_final save missing photos in datou_result : time spend for datou_step_exec : 38.09797930717468 time spend to save output : 0.03496599197387695 total time spend for step 5 : 38.13294529914856 step6:thcl Tue Mar 4 13:21:44 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 : 0.009484529495239258 time to convert the images to numpy array : 0.02008795738220215 time to import caffe and check if the image exist : 0.014145612716674805 time to convert the images to numpy array : 0.03191328048706055 time to import caffe and check if the image exist : 0.010309219360351562 time to convert the images to numpy array : 0.03798174858093262 time to import caffe and check if the image exist : 0.013679981231689453 time to convert the images to numpy array : 0.03626251220703125 time to import caffe and check if the image exist : 0.012017965316772461 time to convert the images to numpy array : 0.0383453369140625 time to import caffe and check if the image exist : 0.015937089920043945 time to convert the images to numpy array : 0.03463411331176758 time to import caffe and check if the image exist : 0.00969076156616211 time to convert the images to numpy array : 0.040918588638305664 time to import caffe and check if the image exist : 0.012750625610351562 time to convert the images to numpy array : 0.038858890533447266 time to import caffe and check if the image exist : 0.017263174057006836 time to convert the images to numpy array : 0.03690481185913086 time to import caffe and check if the image exist : 0.010669946670532227 time to convert the images to numpy array : 0.04400014877319336 total time to convert the images to numpy array : 0.4616425037384033 list photo_ids error: [] list photo_ids correct : [1340799613, 1340799614, 1340799615, 1340799616, 1340799617, 1340799618, 1340799619, 1340799620, 1340799559, 1340799560, 1340799561, 1340799562, 1340799563, 1340799564, 1340799568, 1340799569, 1340799570, 1340799571, 1340799573, 1340799574, 1340799575, 1340799576, 1340799577, 1340799578, 1340799579, 1340799590, 1340799591, 1340799592, 1340799593, 1340799594, 1340799595, 1340799596, 1340799597, 1340799598, 1340799529, 1340799530, 1340799531, 1340799532, 1340799533, 1340799534, 1340799535, 1340799536, 1340799537, 1340799538, 1340799539, 1340799540, 1340799544, 1340799516, 1340799517, 1340799518, 1340799519, 1340799520, 1340799521, 1340799522, 1340799523, 1340799524, 1340799525, 1340799526, 1340799527, 1340799528, 1340799545, 1340799546, 1340799547, 1340799548, 1340799549, 1340799550, 1340799551, 1340799552, 1340799553, 1340799554, 1340799556, 1340799557, 1340799558, 1340799599, 1340799600, 1340799601, 1340799602, 1340799603, 1340799604, 1340799605, 1340799606, 1340799607, 1340799609, 1340799610, 1340799611, 1340799612, 1340799503, 1340799504, 1340799505, 1340799506, 1340799507, 1340799508, 1340799509, 1340799510, 1340799511, 1340799512, 1340799513, 1340799514, 1340799515, 1340799489, 1340799491, 1340799492, 1340799493, 1340799494, 1340799495, 1340799496, 1340799497, 1340799498, 1340799499, 1340799500, 1340799501, 1340799502, 1340799476, 1340799477, 1340799478, 1340799479, 1340799480, 1340799481, 1340799482, 1340799483, 1340799484, 1340799485, 1340799486, 1340799487, 1340799488] number of photos to traite : 125 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 l 3637 free memory gpu now : 5306 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 0.5955612659454346 time used to do the prediction : 0.796095609664917 save descriptor for thcl : 3237 time to traite the descriptors : 0.7718925476074219 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1340799613 To insert : 1340799614 To insert : 1340799615 To insert : 1340799616 To insert : 1340799617 To insert : 1340799618 To insert : 1340799619 To insert : 1340799620 To insert : 1340799559 To insert : 1340799560 To insert : 1340799561 To insert : 1340799562 To insert : 1340799563 To insert : 1340799564 To insert : 1340799568 To insert : 1340799569 To insert : 1340799570 To insert : 1340799571 To insert : 1340799573 To insert : 1340799574 To insert : 1340799575 To insert : 1340799576 To insert : 1340799577 To insert : 1340799578 To insert : 1340799579 To insert : 1340799590 To insert : 1340799591 To insert : 1340799592 To insert : 1340799593 To insert : 1340799594 To insert : 1340799595 To insert : 1340799596 To insert : 1340799597 To insert : 1340799598 To insert : 1340799529 To insert : 1340799530 To insert : 1340799531 To insert : 1340799532 To insert : 1340799533 To insert : 1340799534 To insert : 1340799535 To insert : 1340799536 To insert : 1340799537 To insert : 1340799538 To insert : 1340799539 To insert : 1340799540 To insert : 1340799544 To insert : 1340799516 To insert : 1340799517 To insert : 1340799518 To insert : 1340799519 To insert : 1340799520 To insert : 1340799521 To insert : 1340799522 To insert : 1340799523 To insert : 1340799524 To insert : 1340799525 To insert : 1340799526 To insert : 1340799527 To insert : 1340799528 To insert : 1340799545 To insert : 1340799546 To insert : 1340799547 To insert : 1340799548 To insert : 1340799549 To insert : 1340799550 To insert : 1340799551 To insert : 1340799552 To insert : 1340799553 To insert : 1340799554 To insert : 1340799556 To insert : 1340799557 To insert : 1340799558 To insert : 1340799599 To insert : 1340799600 To insert : 1340799601 To insert : 1340799602 To insert : 1340799603 To insert : 1340799604 To insert : 1340799605 To insert : 1340799606 To insert : 1340799607 To insert : 1340799609 To insert : 1340799610 To insert : 1340799611 To insert : 1340799612 To insert : 1340799503 To insert : 1340799504 To insert : 1340799505 To insert : 1340799506 To insert : 1340799507 To insert : 1340799508 To insert : 1340799509 To insert : 1340799510 To insert : 1340799511 To insert : 1340799512 To insert : 1340799513 To insert : 1340799514 To insert : 1340799515 To insert : 1340799489 To insert : 1340799491 To insert : 1340799492 To insert : 1340799493 To insert : 1340799494 To insert : 1340799495 To insert : 1340799496 To insert : 1340799497 To insert : 1340799498 To insert : 1340799499 To insert : 1340799500 To insert : 1340799501 To insert : 1340799502 To insert : 1340799476 To insert : 1340799477 To insert : 1340799478 To insert : 1340799479 To insert : 1340799480 To insert : 1340799481 To insert : 1340799482 To insert : 1340799483 To insert : 1340799484 To insert : 1340799485 To insert : 1340799486 To insert : 1340799487 To insert : 1340799488 time to insert the descriptors : 23.949615955352783 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos SAVE THCL : begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 190 time used for this insertion : 0.019802570343017578 save missing photos in datou_result : time spend for datou_step_exec : 30.627891302108765 time spend to save output : 0.06434845924377441 total time spend for step 6 : 30.69223976135254 step7:ventilate_hashtags_in_portfolio Tue Mar 4 13:22:15 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 ! VR 22-3-18 : For now we do not clean correctly the datou structure beginning of datou step ventilate_hashtags_in_portfolio : To implement ! Iterating over portfolio : 21008178 get user id for portfolio 21008178 SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21008178 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','pehd','PEHD','pet_fonce','papier','autre','environnement','Tetrapak','metal','Carton','Papier','PET_fonce','mal_croppe','Film_plastique','refus','pet_clair','PET_clair','carton')) AND mptpi.`min_score`=0.6 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21008178 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','pehd','PEHD','pet_fonce','papier','autre','environnement','Tetrapak','metal','Carton','Papier','PET_fonce','mal_croppe','Film_plastique','refus','pet_clair','PET_clair','carton')) AND mptpi.`min_score`=0.6 To do Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") Catched exception ! Connect or reconnect ! (1064, "You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near ')\n and cspi.crop_hashtag_id = chi.id' at line 3") To do ! Use context local managing function ! SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21008178 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','pehd','PEHD','pet_fonce','papier','autre','environnement','Tetrapak','metal','Carton','Papier','PET_fonce','mal_croppe','Film_plastique','refus','pet_clair','PET_clair','carton')) AND mptpi.`min_score`=0.6 To do To do SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21008178 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('flou','pehd','PEHD','pet_fonce','papier','autre','environnement','Tetrapak','metal','Carton','Papier','PET_fonce','mal_croppe','Film_plastique','refus','pet_clair','PET_clair','carton')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/21008483,21008485,21008494,21008493,21008488,21008489,21008490,21008491,21008500,21008495,21008496,21008497,21008499?tags=flou,pehd,pet_fonce,papier,autre,environnement,tetrapak,metal,carton,mal_croppe,film_plastique,refus,pet_clair&datou_id_consolidate=4235&port_consolidate=21008178 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1340795898, 1340795895] Looping around the photos to save general results len do output : 1 /21008178. before output type 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, '2632484') ('4234', '21008178', '1340795898', None, None, None, None, None, '2632484') ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795895', None, None, None, None, None, '2632484') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.01204538345336914 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.2840659618377686 time spend to save output : 0.012257575988769531 total time spend for step 7 : 2.296323537826538 step8:final Tue Mar 4 13:22:17 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 ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {1340795898: ('0.2882699738249937',), 1340795895: ('0.2882699738249937',)} new output for save of step final : {1340795898: ('0.2882699738249937',), 1340795895: ('0.2882699738249937',)} [1340795898, 1340795895] Looping around the photos to save general results len do output : 2 /1340795898.Didn't retrieve data . /1340795895.Didn't retrieve data . before output type Used above Used above Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795898', None, None, None, None, None, '2632484') ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795895', None, None, None, None, None, '2632484') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.011812210083007812 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12177586555480957 time spend to save output : 0.01206350326538086 total time spend for step 8 : 0.13383936882019043 step9:velours_tree Tue Mar 4 13:22:18 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 list_portfolios : 21008483,21008485,21008494,21008493,21008488,21008489,21008490,21008491,21008500,21008495,21008496,21008497,21008499 photo desc type : 5561 - Retrieving photos to tag... query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008483 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008485 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008494 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008493 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008488 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008489 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008490 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008491 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008500 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008495 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008496 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008497 ORDER BY ph.size desc query : SELECT ph.photo_id FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008499 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 125 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [0 1 2 2 0 4 2 4 0 4 0 0 1 1 0 4 1 1 4 1 4 1 4 3 4 2 3 0 1 0 2 2 2 0 4 1 3 4 1 1 0 0 0 4 0 0 0 1 4 1 5 3 4 1 0 3 4 3 3 3 3 0 0 1 0 1 5 3 3 3 1 0 3 0 0 5 3 0 4 0 0 1 0 3 4 1 2 5 5 4 1 2 5 2 4 3 0 1 3 1 1 0 1 4 5 2 0 3 3 3 3 3 3 0 1 3 4 5 0 1 3 3 3 3 1] Elapsed time: 0.017648935317993164 graph_id used : 81403 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/21008483,21008485,21008494,21008493,21008488,21008489,21008490,21008491,21008500,21008495,21008496,21008497,21008499?tags=flou,pehd,pet_fonce,papier,autre,environnement,tetrapak,metal,carton,mal_croppe,film_plastique,refus,pet_clair&datou_id_consolidate=4235&port_consolidate=21008178&tree_id=81403 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1340795898, 1340795895] Looping around the photos to save general results len do output : 1 /21008178Didn't retrieve data . before output type 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, '2632484') ('4234', '21008178', '1340795898', None, None, None, None, None, '2632484') ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795895', None, None, None, None, None, '2632484') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012417078018188477 save_final save missing photos in datou_result : time spend for datou_step_exec : 8.129401445388794 time spend to save output : 0.012691736221313477 total time spend for step 9 : 8.142093181610107 step10:send_mail_cod Tue Mar 4 13:22:26 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec 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 complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 complete output_args for input 3 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 dans la step send mail cod work_area: /home/admin/workarea/git/Velours/python in order to get the selector url, please entre the license of selector results_Qualipapia_P21008178_04-03-2025_13_22_26.pdf 21008465 imagette210084651741090946 21008467 change filename to text .imagette210084671741090946 21008476 imagette210084761741090946 21008475 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210084751741090946 21008470 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210084701741090947 21008472 imagette210084721741090948 21008473 imagette210084731741090948 21008482 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210084821741090948 21008477 imagette210084771741090949 21008478 imagette210084781741090949 21008479 imagette210084791741090949 21008481 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette210084811741090949 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21008178 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21008483,21008485,21008494,21008493,21008488,21008489,21008490,21008491,21008500,21008495,21008496,21008497,21008499?tags=flou,pehd,pet_fonce,papier,autre,environnement,tetrapak,metal,carton,mal_croppe,film_plastique,refus,pet_clair&datou_id_consolidate=4235&port_consolidate=21008178&tree_id=81403 your option no_mail is active, we will not send the real mail to your client args[1340795898] : ((1340795898, -7.129180427843427, 492609224), (1340795898, -0.43636888675641744, 496442774), '0.2882699738249937') We are sending mail with results at cod@fotonower.com args[1340795895] : ((1340795895, -7.1236251822195, 492609224), (1340795895, -0.42555626211319886, 496442774), '0.2882699738249937') We are sending mail with results at cod@fotonower.com refus_total : 0.2882699738249937 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=21008178 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21008178_04-03-2025_13_22_26.pdf results_Qualipapia_P21008178_04-03-2025_13_22_26.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21008178_04-03-2025_13_22_26.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4234','21008178','results_Qualipapia_P21008178_04-03-2025_13_22_26.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21008178_04-03-2025_13_22_26.pdf','pdf','','0.14','0.2882699738249937') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1340795898, 1340795895] Looping around the photos to save general results len do output : 0 before output type Used above Managing all output in save final without adding information in the mtr_datou_result ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795898', None, None, None, None, None, '2632484') ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795895', None, None, None, None, None, '2632484') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.012429475784301758 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.542431116104126 time spend to save output : 0.012596368789672852 total time spend for step 10 : 4.555027484893799 step11:split_time_score Tue Mar 4 13:22:30 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 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 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 begin split time score Catched exception ! Connect or reconnect ! TODO : Insert select and so on Begin split_port_in_batch_balle thcls : [{'id': 3442, 'mtr_user_id': 31, 'name': 'classifieur_2camions_valcor_021122_v1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'deux_camions,camion_droite,camion_gauche,pas_de_camion', 'svm_portfolios_learning': '7659379,7659034,7657685,7657114', 'photo_hashtag_type': 4458, 'photo_desc_type': 5723, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107760533,2107760534,2107760535,2107760536'}] thcls : [{'id': 758, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 856, 'photo_desc_type': 3853, 'type_classification': 'caffe', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] (('10', 2),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 04032025 21008178 Nombre de photos uploadées : 2 / 23040 (0%) 04032025 21008178 Nombre de photos taguées (types de déchets): 2 / 2 (100%) 04032025 21008178 Nombre de photos taguées (volume) : 0 / 2 (0%) elapsed_time : load_data_split_time_score 2.6226043701171875e-06 elapsed_time : order_list_meta_photo_and_scores 8.58306884765625e-06 ?? elapsed_time : fill_and_build_computed_from_old_data 0.0003075599670410156 elapsed_time : insert_dashboard_record_day_entry 0.023969650268554688 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007616 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007617 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007619 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007621 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007623 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007625 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007627 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007630 order by id desc limit 1 Qualite : 0.24892527834258063 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21007632_04-03-2025_12_47_08.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21007632 order by id desc limit 1 # 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 ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21007632 AND mptpi.`type`=4230 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008149 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008150 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008151 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008152 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008154 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008156 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008159 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008161 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008163 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008165 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008167 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008169 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008171 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008174 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008176 order by id desc limit 1 Qualite : 0.2882699738249937 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21008178_04-03-2025_13_22_26.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008178 order by id desc limit 1 # 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 ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21008178 AND mptpi.`type`=4230 To do Qualite : 0.2752652575950524 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21008180_04-03-2025_13_12_00.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008180 order by id desc limit 1 # 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 ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21008180 AND mptpi.`type`=4230 To do Qualite : 0.27304455510034614 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21008182_04-03-2025_13_20_23.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21008182 order by id desc limit 1 # 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 ! TODO Duplicate data, are they consistent 3 ? Duplicate data, are they consistent 4 ? SELECT mptpi.id, mptpi.mtr_portfolio_id_1, mptpi.mtr_portfolio_id_2, mptpi.type, mptpi.hashtag_id, mptpi.min_score, mptpi.mtr_user_id, mptpi.created_at, mptpi.updated_at, mptpi.last_updated_at_desc, mptpi.last_updated_at_asc, h.hashtag FROM MTRPhoto.mtr_port_to_port_ids mptpi, MTRBack.hashtags h WHERE h.hashtag_id=mptpi.hashtag_id AND mptpi.`mtr_portfolio_id_1`=21008182 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'04032025': {'nb_upload': 2, 'nb_taggue_class': 2, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1340795898, 1340795895] Looping around the photos to save general results len do output : 1 /21008178Didn't retrieve data . before output type 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, '2632484') ('4234', '21008178', '1340795898', None, None, None, None, None, '2632484') ('4234', None, None, None, None, None, None, None, '2632484') ('4234', '21008178', '1340795895', None, None, None, None, None, '2632484') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.01203155517578125 save_final save missing photos in datou_result : time spend for datou_step_exec : 17.822471141815186 time spend to save output : 0.012218475341796875 total time spend for step 11 : 17.834689617156982 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 2 set_done_treatment 34.06user 24.68system 2:22.96elapsed 41%CPU (0avgtext+0avgdata 2477744maxresident)k 878328inputs+12104outputs (1035major+2160294minor)pagefaults 0swaps