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 : 1684181 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 : ['2655793'] with mtr_portfolio_ids : ['21243455'] and first list_photo_ids : [] new path : /proc/1684181/ 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 : 0.28107500076293945 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 11 00:20:30 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 3955 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-11 00:20:33.175424: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-11 00:20:33.203174: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-11 00:20:33.205183: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9f78000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-11 00:20:33.205262: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-11 00:20:33.209289: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-11 00:20:33.502810: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2b305870 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-11 00:20:33.502879: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-11 00:20:33.503902: 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 2025-03-11 00:20:33.504454: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 00:20:33.507897: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 00:20:33.511793: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-11 00:20:33.512259: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-11 00:20:33.515044: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-11 00:20:33.516412: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-11 00:20:33.522793: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 00:20:33.524201: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-11 00:20:33.524389: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 00:20:33.525184: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-11 00:20:33.525202: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-11 00:20:33.525213: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-11 00:20:33.526283: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3503 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. 2025-03-11 00:20:33.900177: 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 2025-03-11 00:20:33.900355: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 00:20:33.900381: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 00:20:33.900403: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-11 00:20:33.900423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-11 00:20:33.900442: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-11 00:20:33.900460: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-11 00:20:33.900482: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 00:20:33.901589: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-11 00:20:33.903512: 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 2025-03-11 00:20:33.903623: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-11 00:20:33.903648: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 00:20:33.903734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-11 00:20:33.903759: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-11 00:20:33.903780: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-11 00:20:33.903801: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-11 00:20:33.903823: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 00:20:33.904899: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-11 00:20:33.904950: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-11 00:20:33.904961: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-11 00:20:33.904972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-11 00:20:33.906173: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3503 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 : [] 2025-03-11 00:20:42.989378: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-11 00:20:43.153848: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-11 00:20:44.682419: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.436623: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-03-11 00:20:45.502636: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.502727: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.503923: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.503957: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.67GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.510867: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.510911: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.29GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.517165: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.517188: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.517797: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.517812: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.78GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.566561: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.566656: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.567691: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.567718: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 63.85MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.568749: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.568772: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.569789: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.569813: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.26GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-03-11 00:20:45.578596: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.579618: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.597882: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.599058: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.600027: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.600792: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.605371: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.606258: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.607134: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.607877: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.609089: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.609107: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-03-11 00:20:45.619406: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.620057: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.629646: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.630346: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.631015: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.631641: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.632267: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-03-11 00:20:45.632887: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.92G (3138256896 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 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: 199.00000 molded_images shape: (1, 640, 640, 3) min: -123.54766 max: 90.77578 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.00010943412780761719 nb_pixel_total : 984 time to create 1 rle with old method : 0.0018510818481445312 length of segment : 57 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 73 time to create 1 rle with old method : 0.00019621849060058594 length of segment : 24 time for calcul the mask position with numpy : 6.270408630371094e-05 nb_pixel_total : 493 time to create 1 rle with old method : 0.0010035037994384766 length of segment : 58 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 220.00000 molded_images shape: (1, 640, 640, 3) min: -121.61797 max: 101.39297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 6.318092346191406e-05 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0018863677978515625 length of segment : 65 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 216 time to create 1 rle with old method : 0.0003597736358642578 length of segment : 14 time for calcul the mask position with numpy : 0.00010013580322265625 nb_pixel_total : 1416 time to create 1 rle with old method : 0.001890420913696289 length of segment : 67 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 206.00000 molded_images shape: (1, 640, 640, 3) min: -122.70391 max: 87.60391 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 222 time to create 1 rle with old method : 0.0005297660827636719 length of segment : 15 time for calcul the mask position with numpy : 0.00011777877807617188 nb_pixel_total : 2259 time to create 1 rle with old method : 0.003387451171875 length of segment : 69 time for calcul the mask position with numpy : 0.00011420249938964844 nb_pixel_total : 437 time to create 1 rle with old method : 0.0009450912475585938 length of segment : 21 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 489 time to create 1 rle with old method : 0.001051187515258789 length of segment : 21 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 987 time to create 1 rle with old method : 0.0018126964569091797 length of segment : 39 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 967 time to create 1 rle with old method : 0.001917123794555664 length of segment : 43 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 913 time to create 1 rle with old method : 0.002248525619506836 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 172.00000 molded_images shape: (1, 640, 640, 3) min: -115.65313 max: 59.47109 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 5.4836273193359375e-05 nb_pixel_total : 146 time to create 1 rle with old method : 0.0003483295440673828 length of segment : 17 time for calcul the mask position with numpy : 7.772445678710938e-05 nb_pixel_total : 706 time to create 1 rle with old method : 0.0013842582702636719 length of segment : 51 Processing 1 images image shape: (400, 400, 3) min: 27.00000 max: 167.00000 molded_images shape: (1, 640, 640, 3) min: -91.89531 max: 61.94766 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0009768009185791016 length of segment : 42 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.36797 max: 150.52578 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 8.368492126464844e-05 nb_pixel_total : 2619 time to create 1 rle with old method : 0.0037424564361572266 length of segment : 60 time for calcul the mask position with numpy : 0.00018167495727539062 nb_pixel_total : 5743 time to create 1 rle with old method : 0.008553028106689453 length of segment : 134 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 250.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 126.86953 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0001513957977294922 nb_pixel_total : 2715 time to create 1 rle with old method : 0.004072904586791992 length of segment : 129 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.13359 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 9.369850158691406e-05 nb_pixel_total : 2312 time to create 1 rle with old method : 0.002824544906616211 length of segment : 93 time for calcul the mask position with numpy : 0.0002872943878173828 nb_pixel_total : 4872 time to create 1 rle with old method : 0.008760213851928711 length of segment : 86 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 971 time to create 1 rle with old method : 0.0013363361358642578 length of segment : 37 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00020551681518554688 length of segment : 16 time for calcul the mask position with numpy : 0.00010538101196289062 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006833076477050781 length of segment : 65 time for calcul the mask position with numpy : 8.869171142578125e-05 nb_pixel_total : 2134 time to create 1 rle with old method : 0.0033419132232666016 length of segment : 26 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1132 time to create 1 rle with old method : 0.0016429424285888672 length of segment : 28 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.24297 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 0.00011754035949707031 nb_pixel_total : 4384 time to create 1 rle with old method : 0.0058176517486572266 length of segment : 76 time for calcul the mask position with numpy : 0.00016069412231445312 nb_pixel_total : 521 time to create 1 rle with old method : 0.0011067390441894531 length of segment : 28 time for calcul the mask position with numpy : 7.462501525878906e-05 nb_pixel_total : 601 time to create 1 rle with old method : 0.0013027191162109375 length of segment : 36 time for calcul the mask position with numpy : 0.00026106834411621094 nb_pixel_total : 5572 time to create 1 rle with old method : 0.012523412704467773 length of segment : 59 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.48125 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 : 0.00011968612670898438 nb_pixel_total : 1525 time to create 1 rle with old method : 0.0029764175415039062 length of segment : 63 time for calcul the mask position with numpy : 0.00013065338134765625 nb_pixel_total : 3313 time to create 1 rle with old method : 0.00559544563293457 length of segment : 81 time for calcul the mask position with numpy : 7.963180541992188e-05 nb_pixel_total : 2495 time to create 1 rle with old method : 0.0031538009643554688 length of segment : 46 time for calcul the mask position with numpy : 7.939338684082031e-05 nb_pixel_total : 2284 time to create 1 rle with old method : 0.003170490264892578 length of segment : 52 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.0004036426544189453 length of segment : 55 time for calcul the mask position with numpy : 7.43865966796875e-05 nb_pixel_total : 220 time to create 1 rle with old method : 0.00045871734619140625 length of segment : 28 time for calcul the mask position with numpy : 0.0003666877746582031 nb_pixel_total : 15851 time to create 1 rle with old method : 0.020125865936279297 length of segment : 145 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00023674964904785156 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -120.03594 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 9.632110595703125e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.0006611347198486328 length of segment : 36 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 214 time to create 1 rle with old method : 0.00044846534729003906 length of segment : 32 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 436 time to create 1 rle with old method : 0.0009238719940185547 length of segment : 21 time for calcul the mask position with numpy : 0.00012493133544921875 nb_pixel_total : 2963 time to create 1 rle with old method : 0.0049591064453125 length of segment : 78 time for calcul the mask position with numpy : 0.00029850006103515625 nb_pixel_total : 8126 time to create 1 rle with old method : 0.013533830642700195 length of segment : 130 time for calcul the mask position with numpy : 0.0003883838653564453 nb_pixel_total : 10373 time to create 1 rle with old method : 0.024042367935180664 length of segment : 224 Processing 1 images image shape: (400, 400, 3) min: 57.00000 max: 193.00000 molded_images shape: (1, 640, 640, 3) min: -66.70000 max: 75.80703 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.42656 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 2 time for calcul the mask position with numpy : 0.00016355514526367188 nb_pixel_total : 7218 time to create 1 rle with old method : 0.009148120880126953 length of segment : 319 time for calcul the mask position with numpy : 0.003305673599243164 nb_pixel_total : 95922 time to create 1 rle with old method : 0.10794401168823242 length of segment : 458 Processing 1 images image shape: (400, 160, 3) min: 1.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 142.21328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 8.153915405273438e-05 nb_pixel_total : 648 time to create 1 rle with old method : 0.0009877681732177734 length of segment : 80 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0007412433624267578 length of segment : 37 time for calcul the mask position with numpy : 0.000225067138671875 nb_pixel_total : 11146 time to create 1 rle with old method : 0.012981653213500977 length of segment : 250 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -121.68828 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.0002262592315673828 length of segment : 15 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.29375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 6 time for calcul the mask position with numpy : 0.0007121562957763672 nb_pixel_total : 55684 time to create 1 rle with old method : 0.09358692169189453 length of segment : 404 time for calcul the mask position with numpy : 0.0001385211944580078 nb_pixel_total : 2035 time to create 1 rle with old method : 0.0033822059631347656 length of segment : 51 time for calcul the mask position with numpy : 5.984306335449219e-05 nb_pixel_total : 376 time to create 1 rle with old method : 0.0007059574127197266 length of segment : 13 time for calcul the mask position with numpy : 0.00011610984802246094 nb_pixel_total : 2455 time to create 1 rle with old method : 0.004217386245727539 length of segment : 53 time for calcul the mask position with numpy : 6.365776062011719e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.0004088878631591797 length of segment : 44 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.0004947185516357422 length of segment : 49 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.61797 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 17 time for calcul the mask position with numpy : 9.417533874511719e-05 nb_pixel_total : 3157 time to create 1 rle with old method : 0.005250215530395508 length of segment : 45 time for calcul the mask position with numpy : 0.0002200603485107422 nb_pixel_total : 4502 time to create 1 rle with old method : 0.0060122013092041016 length of segment : 106 time for calcul the mask position with numpy : 0.00012230873107910156 nb_pixel_total : 3444 time to create 1 rle with old method : 0.006033182144165039 length of segment : 94 time for calcul the mask position with numpy : 7.319450378417969e-05 nb_pixel_total : 1323 time to create 1 rle with old method : 0.0016641616821289062 length of segment : 40 time for calcul the mask position with numpy : 6.508827209472656e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.0012392997741699219 length of segment : 78 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 903 time to create 1 rle with old method : 0.001275777816772461 length of segment : 43 time for calcul the mask position with numpy : 0.00011849403381347656 nb_pixel_total : 3854 time to create 1 rle with old method : 0.004858493804931641 length of segment : 98 time for calcul the mask position with numpy : 9.393692016601562e-05 nb_pixel_total : 2700 time to create 1 rle with old method : 0.0036385059356689453 length of segment : 40 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1428 time to create 1 rle with old method : 0.0019767284393310547 length of segment : 47 time for calcul the mask position with numpy : 5.936622619628906e-05 nb_pixel_total : 974 time to create 1 rle with old method : 0.0014109611511230469 length of segment : 42 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 663 time to create 1 rle with old method : 0.0009171962738037109 length of segment : 31 time for calcul the mask position with numpy : 0.00014781951904296875 nb_pixel_total : 5842 time to create 1 rle with old method : 0.008764505386352539 length of segment : 156 time for calcul the mask position with numpy : 8.463859558105469e-05 nb_pixel_total : 1009 time to create 1 rle with old method : 0.0018830299377441406 length of segment : 46 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 286 time to create 1 rle with old method : 0.0005822181701660156 length of segment : 30 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 914 time to create 1 rle with old method : 0.0017426013946533203 length of segment : 33 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 2556 time to create 1 rle with old method : 0.0046291351318359375 length of segment : 150 time for calcul the mask position with numpy : 0.0001595020294189453 nb_pixel_total : 4125 time to create 1 rle with old method : 0.005600929260253906 length of segment : 131 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.11797 max: 150.95937 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 0.0001385211944580078 nb_pixel_total : 7227 time to create 1 rle with old method : 0.00969839096069336 length of segment : 166 time for calcul the mask position with numpy : 0.00019979476928710938 nb_pixel_total : 7736 time to create 1 rle with old method : 0.010352134704589844 length of segment : 122 time for calcul the mask position with numpy : 0.00015783309936523438 nb_pixel_total : 3816 time to create 1 rle with old method : 0.0049896240234375 length of segment : 124 time for calcul the mask position with numpy : 0.00013208389282226562 nb_pixel_total : 3671 time to create 1 rle with old method : 0.004487037658691406 length of segment : 117 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 478 time to create 1 rle with old method : 0.0007588863372802734 length of segment : 26 time for calcul the mask position with numpy : 8.273124694824219e-05 nb_pixel_total : 976 time to create 1 rle with old method : 0.0014028549194335938 length of segment : 43 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 289 time to create 1 rle with old method : 0.00043582916259765625 length of segment : 25 time for calcul the mask position with numpy : 6.29425048828125e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.00089263916015625 length of segment : 26 time for calcul the mask position with numpy : 6.437301635742188e-05 nb_pixel_total : 496 time to create 1 rle with old method : 0.0007090568542480469 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 77.00000 max: 197.00000 molded_images shape: (1, 640, 640, 3) min: -43.82109 max: 88.88516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 4 time for calcul the mask position with numpy : 5.507469177246094e-05 nb_pixel_total : 681 time to create 1 rle with old method : 0.0010564327239990234 length of segment : 50 time for calcul the mask position with numpy : 0.0006840229034423828 nb_pixel_total : 14642 time to create 1 rle with old method : 0.018437623977661133 length of segment : 249 time for calcul the mask position with numpy : 9.679794311523438e-05 nb_pixel_total : 1170 time to create 1 rle with old method : 0.0017583370208740234 length of segment : 65 time for calcul the mask position with numpy : 0.0003809928894042969 nb_pixel_total : 21528 time to create 1 rle with old method : 0.027767658233642578 length of segment : 167 Processing 1 images image shape: (400, 400, 3) min: 20.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -96.81719 max: 150.92422 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 90 time to create 1 rle with old method : 0.00024962425231933594 length of segment : 13 Processing 1 images image shape: (400, 160, 3) min: 26.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 145.56094 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 3.9577484130859375e-05 nb_pixel_total : 126 time to create 1 rle with old method : 0.00021529197692871094 length of segment : 21 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 0.0002167224884033203 nb_pixel_total : 3852 time to create 1 rle with old method : 0.006457328796386719 length of segment : 207 Processing 1 images image shape: (240, 400, 3) min: 54.00000 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 : 1 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003180503845214844 length of segment : 15 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.841255187988281e-05 nb_pixel_total : 563 time to create 1 rle with old method : 0.0008814334869384766 length of segment : 33 time for calcul the mask position with numpy : 0.0004665851593017578 nb_pixel_total : 18220 time to create 1 rle with old method : 0.022110700607299805 length of segment : 313 time for calcul the mask position with numpy : 0.0001556873321533203 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0017242431640625 length of segment : 43 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.000133514404296875 length of segment : 36 time for calcul the mask position with numpy : 4.100799560546875e-05 nb_pixel_total : 197 time to create 1 rle with old method : 0.0004715919494628906 length of segment : 12 time for calcul the mask position with numpy : 8.296966552734375e-05 nb_pixel_total : 231 time to create 1 rle with old method : 0.0007708072662353516 length of segment : 22 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 1200 time to create 1 rle with old method : 0.002093791961669922 length of segment : 42 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 1059 time to create 1 rle with old method : 0.0018143653869628906 length of segment : 39 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 2867 time to create 1 rle with old method : 0.0036280155181884766 length of segment : 79 Processing 1 images image shape: (240, 400, 3) min: 32.00000 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 : 4 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 881 time to create 1 rle with old method : 0.0013079643249511719 length of segment : 39 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 211 time to create 1 rle with old method : 0.00032782554626464844 length of segment : 20 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1921 time to create 1 rle with old method : 0.002768278121948242 length of segment : 39 time for calcul the mask position with numpy : 9.083747863769531e-05 nb_pixel_total : 3529 time to create 1 rle with old method : 0.004872322082519531 length of segment : 110 Processing 1 images image shape: (240, 400, 3) min: 48.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005652904510498047 length of segment : 35 time for calcul the mask position with numpy : 9.441375732421875e-05 nb_pixel_total : 4262 time to create 1 rle with old method : 0.005225658416748047 length of segment : 70 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 352 time to create 1 rle with old method : 0.0005588531494140625 length of segment : 19 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 568 time to create 1 rle with old method : 0.0010170936584472656 length of segment : 40 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 460 time to create 1 rle with old method : 0.0007295608520507812 length of segment : 39 time for calcul the mask position with numpy : 0.00014138221740722656 nb_pixel_total : 7327 time to create 1 rle with old method : 0.010542154312133789 length of segment : 85 time for calcul the mask position with numpy : 0.0007176399230957031 nb_pixel_total : 49624 time to create 1 rle with old method : 0.06207466125488281 length of segment : 228 time for calcul the mask position with numpy : 0.00011706352233886719 nb_pixel_total : 1850 time to create 1 rle with old method : 0.002805471420288086 length of segment : 107 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 149.89297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0002205371856689453 nb_pixel_total : 15302 time to create 1 rle with old method : 0.021966934204101562 length of segment : 175 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0007977485656738281 length of segment : 23 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 723 time to create 1 rle with old method : 0.0009496212005615234 length of segment : 44 Processing 1 images image shape: (240, 160, 3) min: 39.00000 max: 254.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 137.14135 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 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: -122.82109 max: 148.32266 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 193 time to create 1 rle with old method : 0.0004620552062988281 length of segment : 16 time for calcul the mask position with numpy : 7.009506225585938e-05 nb_pixel_total : 1104 time to create 1 rle with old method : 0.0018839836120605469 length of segment : 42 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 361 time to create 1 rle with old method : 0.0005619525909423828 length of segment : 20 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.0002541542053222656 length of segment : 30 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 1423 time to create 1 rle with old method : 0.0019986629486083984 length of segment : 49 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 296 time to create 1 rle with old method : 0.00041961669921875 length of segment : 33 time for calcul the mask position with numpy : 4.124641418457031e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004329681396484375 length of segment : 20 time for calcul the mask position with numpy : 6.818771362304688e-05 nb_pixel_total : 2130 time to create 1 rle with old method : 0.003051280975341797 length of segment : 60 time for calcul the mask position with numpy : 9.107589721679688e-05 nb_pixel_total : 1154 time to create 1 rle with old method : 0.001730203628540039 length of segment : 44 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 2346 time to create 1 rle with old method : 0.0030694007873535156 length of segment : 57 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.10234 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 13 time for calcul the mask position with numpy : 5.555152893066406e-05 nb_pixel_total : 298 time to create 1 rle with old method : 0.00052642822265625 length of segment : 23 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 857 time to create 1 rle with old method : 0.0014231204986572266 length of segment : 46 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1626 time to create 1 rle with old method : 0.0026798248291015625 length of segment : 63 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 248 time to create 1 rle with old method : 0.0003902912139892578 length of segment : 18 time for calcul the mask position with numpy : 7.796287536621094e-05 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0016477108001708984 length of segment : 51 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 313 time to create 1 rle with old method : 0.00046944618225097656 length of segment : 26 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 783 time to create 1 rle with old method : 0.0012540817260742188 length of segment : 42 time for calcul the mask position with numpy : 3.552436828613281e-05 nb_pixel_total : 136 time to create 1 rle with old method : 0.00028514862060546875 length of segment : 15 time for calcul the mask position with numpy : 6.866455078125e-05 nb_pixel_total : 1096 time to create 1 rle with old method : 0.0017676353454589844 length of segment : 43 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 114 time to create 1 rle with old method : 0.00032258033752441406 length of segment : 23 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 1095 time to create 1 rle with old method : 0.001584768295288086 length of segment : 36 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 174 time to create 1 rle with old method : 0.00027060508728027344 length of segment : 17 time for calcul the mask position with numpy : 0.00012111663818359375 nb_pixel_total : 1550 time to create 1 rle with old method : 0.002343416213989258 length of segment : 63 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.39531 max: 150.98281 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 22 time for calcul the mask position with numpy : 8.249282836914062e-05 nb_pixel_total : 864 time to create 1 rle with old method : 0.0011222362518310547 length of segment : 46 time for calcul the mask position with numpy : 0.00011157989501953125 nb_pixel_total : 2715 time to create 1 rle with old method : 0.0039789676666259766 length of segment : 83 time for calcul the mask position with numpy : 0.0001049041748046875 nb_pixel_total : 2527 time to create 1 rle with old method : 0.0033876895904541016 length of segment : 59 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1807 time to create 1 rle with old method : 0.002454519271850586 length of segment : 54 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0008907318115234375 length of segment : 22 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 195 time to create 1 rle with old method : 0.00034618377685546875 length of segment : 15 time for calcul the mask position with numpy : 0.00019073486328125 nb_pixel_total : 7354 time to create 1 rle with old method : 0.009277105331420898 length of segment : 264 time for calcul the mask position with numpy : 0.00018143653869628906 nb_pixel_total : 2843 time to create 1 rle with old method : 0.006668806076049805 length of segment : 95 time for calcul the mask position with numpy : 0.00012731552124023438 nb_pixel_total : 1899 time to create 1 rle with old method : 0.002397298812866211 length of segment : 68 time for calcul the mask position with numpy : 9.5367431640625e-05 nb_pixel_total : 1412 time to create 1 rle with old method : 0.0020825862884521484 length of segment : 45 time for calcul the mask position with numpy : 7.033348083496094e-05 nb_pixel_total : 691 time to create 1 rle with old method : 0.00102996826171875 length of segment : 32 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 139 time to create 1 rle with old method : 0.0003762245178222656 length of segment : 18 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 1767 time to create 1 rle with old method : 0.0022788047790527344 length of segment : 55 time for calcul the mask position with numpy : 4.9114227294921875e-05 nb_pixel_total : 281 time to create 1 rle with old method : 0.00045752525329589844 length of segment : 30 time for calcul the mask position with numpy : 5.9604644775390625e-05 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0017514228820800781 length of segment : 38 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1312 time to create 1 rle with old method : 0.0017538070678710938 length of segment : 38 time for calcul the mask position with numpy : 6.103515625e-05 nb_pixel_total : 1158 time to create 1 rle with old method : 0.0016422271728515625 length of segment : 38 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 744 time to create 1 rle with old method : 0.0010497570037841797 length of segment : 28 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 160 time to create 1 rle with old method : 0.00027251243591308594 length of segment : 15 time for calcul the mask position with numpy : 5.745887756347656e-05 nb_pixel_total : 978 time to create 1 rle with old method : 0.0015349388122558594 length of segment : 39 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 1509 time to create 1 rle with old method : 0.001958608627319336 length of segment : 42 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 665 time to create 1 rle with old method : 0.0011124610900878906 length of segment : 56 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.93828 max: 139.19375 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 62 time to create 1 rle with old method : 0.0001323223114013672 length of segment : 7 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 3328 time to create 1 rle with old method : 0.004965782165527344 length of segment : 109 time for calcul the mask position with numpy : 0.00012683868408203125 nb_pixel_total : 3330 time to create 1 rle with old method : 0.0053675174713134766 length of segment : 108 Processing 1 images image shape: (400, 400, 3) min: 78.00000 max: 130.00000 molded_images shape: (1, 640, 640, 3) min: -45.70000 max: 16.61172 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: 46.00000 max: 175.00000 molded_images shape: (1, 640, 640, 3) min: -75.50859 max: 61.35000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Processing 1 images image shape: (400, 160, 3) min: 12.00000 max: 152.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 41.56875 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 5.793571472167969e-05 nb_pixel_total : 374 time to create 1 rle with old method : 0.0007698535919189453 length of segment : 29 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.38750 max: 150.78359 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 9 time for calcul the mask position with numpy : 5.3882598876953125e-05 nb_pixel_total : 327 time to create 1 rle with old method : 0.0005350112915039062 length of segment : 40 time for calcul the mask position with numpy : 7.200241088867188e-05 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0019919872283935547 length of segment : 44 time for calcul the mask position with numpy : 8.940696716308594e-05 nb_pixel_total : 1240 time to create 1 rle with old method : 0.0018725395202636719 length of segment : 36 time for calcul the mask position with numpy : 8.106231689453125e-05 nb_pixel_total : 318 time to create 1 rle with old method : 0.0004947185516357422 length of segment : 18 time for calcul the mask position with numpy : 5.078315734863281e-05 nb_pixel_total : 192 time to create 1 rle with old method : 0.00042057037353515625 length of segment : 20 time for calcul the mask position with numpy : 7.081031799316406e-05 nb_pixel_total : 1334 time to create 1 rle with old method : 0.002251148223876953 length of segment : 54 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 740 time to create 1 rle with old method : 0.0015745162963867188 length of segment : 29 time for calcul the mask position with numpy : 0.00011444091796875 nb_pixel_total : 2657 time to create 1 rle with old method : 0.004628181457519531 length of segment : 93 time for calcul the mask position with numpy : 6.699562072753906e-05 nb_pixel_total : 414 time to create 1 rle with old method : 0.0008687973022460938 length of segment : 26 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.19219 max: 150.88516 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 348 time to create 1 rle with old method : 0.0005340576171875 length of segment : 21 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 422 time to create 1 rle with old method : 0.0006477832794189453 length of segment : 24 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 180 time to create 1 rle with old method : 0.00031304359436035156 length of segment : 14 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0005843639373779297 length of segment : 34 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 388 time to create 1 rle with old method : 0.0008113384246826172 length of segment : 29 time for calcul the mask position with numpy : 4.982948303222656e-05 nb_pixel_total : 406 time to create 1 rle with old method : 0.0006337165832519531 length of segment : 64 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 294 time to create 1 rle with old method : 0.0006079673767089844 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: -122.02422 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 24 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 293 time to create 1 rle with old method : 0.0006241798400878906 length of segment : 16 time for calcul the mask position with numpy : 0.00011730194091796875 nb_pixel_total : 840 time to create 1 rle with old method : 0.0018966197967529297 length of segment : 28 time for calcul the mask position with numpy : 8.130073547363281e-05 nb_pixel_total : 1404 time to create 1 rle with old method : 0.002468585968017578 length of segment : 58 time for calcul the mask position with numpy : 5.459785461425781e-05 nb_pixel_total : 382 time to create 1 rle with old method : 0.0008625984191894531 length of segment : 21 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 255 time to create 1 rle with old method : 0.0005495548248291016 length of segment : 15 time for calcul the mask position with numpy : 0.0001380443572998047 nb_pixel_total : 1027 time to create 1 rle with old method : 0.001961231231689453 length of segment : 72 time for calcul the mask position with numpy : 5.340576171875e-05 nb_pixel_total : 269 time to create 1 rle with old method : 0.0006151199340820312 length of segment : 16 time for calcul the mask position with numpy : 0.0003795623779296875 nb_pixel_total : 15943 time to create 1 rle with old method : 0.026164770126342773 length of segment : 249 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 326 time to create 1 rle with old method : 0.0005354881286621094 length of segment : 26 time for calcul the mask position with numpy : 5.8650970458984375e-05 nb_pixel_total : 356 time to create 1 rle with old method : 0.0006053447723388672 length of segment : 22 time for calcul the mask position with numpy : 9.608268737792969e-05 nb_pixel_total : 650 time to create 1 rle with old method : 0.0012731552124023438 length of segment : 44 time for calcul the mask position with numpy : 4.4345855712890625e-05 nb_pixel_total : 116 time to create 1 rle with old method : 0.00022149085998535156 length of segment : 11 time for calcul the mask position with numpy : 5.14984130859375e-05 nb_pixel_total : 115 time to create 1 rle with old method : 0.0002582073211669922 length of segment : 33 time for calcul the mask position with numpy : 4.029273986816406e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0005290508270263672 length of segment : 25 time for calcul the mask position with numpy : 0.00022363662719726562 nb_pixel_total : 3986 time to create 1 rle with old method : 0.005957841873168945 length of segment : 118 time for calcul the mask position with numpy : 6.937980651855469e-05 nb_pixel_total : 843 time to create 1 rle with old method : 0.0011990070343017578 length of segment : 62 time for calcul the mask position with numpy : 5.0067901611328125e-05 nb_pixel_total : 583 time to create 1 rle with old method : 0.0008449554443359375 length of segment : 38 time for calcul the mask position with numpy : 4.792213439941406e-05 nb_pixel_total : 659 time to create 1 rle with old method : 0.0009217262268066406 length of segment : 40 time for calcul the mask position with numpy : 3.457069396972656e-05 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001933574676513672 length of segment : 15 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.00033092498779296875 length of segment : 28 time for calcul the mask position with numpy : 0.00026035308837890625 nb_pixel_total : 13007 time to create 1 rle with old method : 0.015226364135742188 length of segment : 369 time for calcul the mask position with numpy : 0.0001289844512939453 nb_pixel_total : 1583 time to create 1 rle with old method : 0.001968860626220703 length of segment : 107 time for calcul the mask position with numpy : 8.034706115722656e-05 nb_pixel_total : 1830 time to create 1 rle with old method : 0.002470731735229492 length of segment : 63 time for calcul the mask position with numpy : 4.5299530029296875e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.00054168701171875 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: -121.89531 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 5.698204040527344e-05 nb_pixel_total : 630 time to create 1 rle with old method : 0.0009827613830566406 length of segment : 29 time for calcul the mask position with numpy : 3.886222839355469e-05 nb_pixel_total : 224 time to create 1 rle with old method : 0.00031948089599609375 length of segment : 21 time for calcul the mask position with numpy : 3.719329833984375e-05 nb_pixel_total : 278 time to create 1 rle with old method : 0.0004382133483886719 length of segment : 19 time for calcul the mask position with numpy : 8.630752563476562e-05 nb_pixel_total : 1447 time to create 1 rle with old method : 0.0019240379333496094 length of segment : 100 time for calcul the mask position with numpy : 0.00016570091247558594 nb_pixel_total : 7644 time to create 1 rle with old method : 0.01050424575805664 length of segment : 126 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 344 time to create 1 rle with old method : 0.0005908012390136719 length of segment : 23 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 227 time to create 1 rle with old method : 0.00034880638122558594 length of segment : 11 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.00015616416931152344 length of segment : 10 time for calcul the mask position with numpy : 5.2928924560546875e-05 nb_pixel_total : 451 time to create 1 rle with old method : 0.0006756782531738281 length of segment : 46 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 445 time to create 1 rle with old method : 0.0006556510925292969 length of segment : 30 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 1009 time to create 1 rle with old method : 0.001477956771850586 length of segment : 24 Processing 1 images image shape: (400, 400, 3) min: 106.00000 max: 208.00000 molded_images shape: (1, 640, 640, 3) min: -17.70000 max: 91.75625 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 1 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001964569091796875 length of segment : 14 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -118.75469 max: 149.96328 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 10 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 283 time to create 1 rle with old method : 0.0004589557647705078 length of segment : 25 time for calcul the mask position with numpy : 8.606910705566406e-05 nb_pixel_total : 1105 time to create 1 rle with old method : 0.0015416145324707031 length of segment : 85 time for calcul the mask position with numpy : 0.0002536773681640625 nb_pixel_total : 5325 time to create 1 rle with old method : 0.0072786808013916016 length of segment : 173 time for calcul the mask position with numpy : 6.246566772460938e-05 nb_pixel_total : 394 time to create 1 rle with old method : 0.0006124973297119141 length of segment : 34 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 272 time to create 1 rle with old method : 0.0004291534423828125 length of segment : 23 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 334 time to create 1 rle with old method : 0.0005006790161132812 length of segment : 31 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 760 time to create 1 rle with old method : 0.0011203289031982422 length of segment : 41 time for calcul the mask position with numpy : 0.000881195068359375 nb_pixel_total : 56320 time to create 1 rle with old method : 0.0723111629486084 length of segment : 350 time for calcul the mask position with numpy : 6.794929504394531e-05 nb_pixel_total : 235 time to create 1 rle with old method : 0.0004322528839111328 length of segment : 20 time for calcul the mask position with numpy : 6.771087646484375e-05 nb_pixel_total : 262 time to create 1 rle with old method : 0.00041747093200683594 length of segment : 22 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 199.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 90.38125 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 0.0001888275146484375 nb_pixel_total : 8095 time to create 1 rle with old method : 0.010602951049804688 length of segment : 125 time for calcul the mask position with numpy : 6.031990051269531e-05 nb_pixel_total : 76 time to create 1 rle with old method : 0.0001366138458251953 length of segment : 15 time for calcul the mask position with numpy : 3.528594970703125e-05 nb_pixel_total : 182 time to create 1 rle with old method : 0.0003154277801513672 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: -123.25469 max: 150.74844 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 550 time to create 1 rle with old method : 0.0008223056793212891 length of segment : 37 time for calcul the mask position with numpy : 0.00015211105346679688 nb_pixel_total : 2678 time to create 1 rle with old method : 0.003827810287475586 length of segment : 50 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 989 time to create 1 rle with old method : 0.0014214515686035156 length of segment : 33 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006864070892333984 length of segment : 23 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 215 time to create 1 rle with old method : 0.00035190582275390625 length of segment : 16 time for calcul the mask position with numpy : 7.653236389160156e-05 nb_pixel_total : 1564 time to create 1 rle with old method : 0.002138376235961914 length of segment : 45 time for calcul the mask position with numpy : 4.1484832763671875e-05 nb_pixel_total : 340 time to create 1 rle with old method : 0.0005168914794921875 length of segment : 27 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 1578 time to create 1 rle with old method : 0.002087831497192383 length of segment : 44 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.84453 max: 150.99062 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.57763671875e-05 nb_pixel_total : 391 time to create 1 rle with old method : 0.0006358623504638672 length of segment : 19 time for calcul the mask position with numpy : 6.413459777832031e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.0004322528839111328 length of segment : 15 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 299 time to create 1 rle with old method : 0.0005283355712890625 length of segment : 33 time for calcul the mask position with numpy : 5.53131103515625e-05 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0015571117401123047 length of segment : 39 time for calcul the mask position with numpy : 5.412101745605469e-05 nb_pixel_total : 95 time to create 1 rle with old method : 0.00025010108947753906 length of segment : 10 time for calcul the mask position with numpy : 8.20159912109375e-05 nb_pixel_total : 1178 time to create 1 rle with old method : 0.002255678176879883 length of segment : 41 time for calcul the mask position with numpy : 4.00543212890625e-05 nb_pixel_total : 247 time to create 1 rle with old method : 0.00036525726318359375 length of segment : 19 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.29375 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 19 time for calcul the mask position with numpy : 0.00010657310485839844 nb_pixel_total : 3213 time to create 1 rle with old method : 0.003938913345336914 length of segment : 135 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004858970642089844 length of segment : 26 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006966590881347656 length of segment : 36 time for calcul the mask position with numpy : 3.790855407714844e-05 nb_pixel_total : 238 time to create 1 rle with old method : 0.00042748451232910156 length of segment : 14 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 620 time to create 1 rle with old method : 0.001043558120727539 length of segment : 36 time for calcul the mask position with numpy : 4.696846008300781e-05 nb_pixel_total : 587 time to create 1 rle with old method : 0.0008563995361328125 length of segment : 43 time for calcul the mask position with numpy : 5.626678466796875e-05 nb_pixel_total : 537 time to create 1 rle with old method : 0.0010328292846679688 length of segment : 53 time for calcul the mask position with numpy : 6.914138793945312e-05 nb_pixel_total : 1090 time to create 1 rle with old method : 0.0019762516021728516 length of segment : 77 time for calcul the mask position with numpy : 0.0001442432403564453 nb_pixel_total : 2346 time to create 1 rle with old method : 0.010794878005981445 length of segment : 226 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1061 time to create 1 rle with old method : 0.001924276351928711 length of segment : 51 time for calcul the mask position with numpy : 6.604194641113281e-05 nb_pixel_total : 201 time to create 1 rle with old method : 0.00043845176696777344 length of segment : 43 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 1144 time to create 1 rle with old method : 0.0020651817321777344 length of segment : 111 time for calcul the mask position with numpy : 3.647804260253906e-05 nb_pixel_total : 138 time to create 1 rle with old method : 0.0002532005310058594 length of segment : 14 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 694 time to create 1 rle with old method : 0.0009551048278808594 length of segment : 52 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 228 time to create 1 rle with old method : 0.0003509521484375 length of segment : 28 time for calcul the mask position with numpy : 7.605552673339844e-05 nb_pixel_total : 2532 time to create 1 rle with old method : 0.0032014846801757812 length of segment : 114 time for calcul the mask position with numpy : 4.267692565917969e-05 nb_pixel_total : 97 time to create 1 rle with old method : 0.0002224445343017578 length of segment : 12 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 175 time to create 1 rle with old method : 0.0004200935363769531 length of segment : 14 time for calcul the mask position with numpy : 0.00042057037353515625 nb_pixel_total : 24257 time to create 1 rle with old method : 0.03136801719665527 length of segment : 331 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.54766 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 : 0.00010776519775390625 nb_pixel_total : 5984 time to create 1 rle with old method : 0.0074520111083984375 length of segment : 138 time for calcul the mask position with numpy : 6.961822509765625e-05 nb_pixel_total : 1819 time to create 1 rle with old method : 0.0024938583374023438 length of segment : 45 time for calcul the mask position with numpy : 4.2438507080078125e-05 nb_pixel_total : 405 time to create 1 rle with old method : 0.0006551742553710938 length of segment : 16 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 1598 time to create 1 rle with old method : 0.0019245147705078125 length of segment : 139 time for calcul the mask position with numpy : 6.222724914550781e-05 nb_pixel_total : 1285 time to create 1 rle with old method : 0.0016703605651855469 length of segment : 48 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005872249603271484 length of segment : 42 time for calcul the mask position with numpy : 5.817413330078125e-05 nb_pixel_total : 782 time to create 1 rle with old method : 0.0011355876922607422 length of segment : 39 time for calcul the mask position with numpy : 5.1021575927734375e-05 nb_pixel_total : 517 time to create 1 rle with old method : 0.0008544921875 length of segment : 16 Processing 1 images image shape: (400, 400, 3) min: 98.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -25.70000 max: 147.16250 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.0004611015319824219 nb_pixel_total : 30740 time to create 1 rle with old method : 0.050414323806762695 length of segment : 171 time for calcul the mask position with numpy : 0.00038743019104003906 nb_pixel_total : 25355 time to create 1 rle with old method : 0.03286266326904297 length of segment : 189 time for calcul the mask position with numpy : 0.00010395050048828125 nb_pixel_total : 568 time to create 1 rle with old method : 0.0007855892181396484 length of segment : 49 time for calcul the mask position with numpy : 0.00016164779663085938 nb_pixel_total : 7113 time to create 1 rle with old method : 0.010204315185546875 length of segment : 104 time for calcul the mask position with numpy : 7.224082946777344e-05 nb_pixel_total : 877 time to create 1 rle with old method : 0.0016553401947021484 length of segment : 40 Processing 1 images image shape: (400, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -122.94219 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 18 time for calcul the mask position with numpy : 7.176399230957031e-05 nb_pixel_total : 527 time to create 1 rle with old method : 0.0007967948913574219 length of segment : 64 time for calcul the mask position with numpy : 5.5789947509765625e-05 nb_pixel_total : 608 time to create 1 rle with old method : 0.0008702278137207031 length of segment : 32 time for calcul the mask position with numpy : 5.435943603515625e-05 nb_pixel_total : 574 time to create 1 rle with old method : 0.000751495361328125 length of segment : 35 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 316 time to create 1 rle with old method : 0.000446319580078125 length of segment : 25 time for calcul the mask position with numpy : 6.389617919921875e-05 nb_pixel_total : 1012 time to create 1 rle with old method : 0.0014066696166992188 length of segment : 48 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 651 time to create 1 rle with old method : 0.0009744167327880859 length of segment : 21 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006880760192871094 length of segment : 23 time for calcul the mask position with numpy : 0.00013828277587890625 nb_pixel_total : 2459 time to create 1 rle with old method : 0.0031702518463134766 length of segment : 118 time for calcul the mask position with numpy : 4.7206878662109375e-05 nb_pixel_total : 186 time to create 1 rle with old method : 0.00028514862060546875 length of segment : 23 time for calcul the mask position with numpy : 4.601478576660156e-05 nb_pixel_total : 555 time to create 1 rle with old method : 0.0007584095001220703 length of segment : 26 time for calcul the mask position with numpy : 3.743171691894531e-05 nb_pixel_total : 181 time to create 1 rle with old method : 0.0003101825714111328 length of segment : 15 time for calcul the mask position with numpy : 7.05718994140625e-05 nb_pixel_total : 1953 time to create 1 rle with old method : 0.00266265869140625 length of segment : 80 time for calcul the mask position with numpy : 4.291534423828125e-05 nb_pixel_total : 511 time to create 1 rle with old method : 0.0007588863372802734 length of segment : 25 time for calcul the mask position with numpy : 4.3392181396484375e-05 nb_pixel_total : 535 time to create 1 rle with old method : 0.00072479248046875 length of segment : 30 time for calcul the mask position with numpy : 3.695487976074219e-05 nb_pixel_total : 237 time to create 1 rle with old method : 0.00036907196044921875 length of segment : 20 time for calcul the mask position with numpy : 3.4332275390625e-05 nb_pixel_total : 169 time to create 1 rle with old method : 0.00027942657470703125 length of segment : 22 time for calcul the mask position with numpy : 4.482269287109375e-05 nb_pixel_total : 442 time to create 1 rle with old method : 0.0007030963897705078 length of segment : 20 time for calcul the mask position with numpy : 3.7670135498046875e-05 nb_pixel_total : 437 time to create 1 rle with old method : 0.0006463527679443359 length of segment : 20 Processing 1 images image shape: (400, 160, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 147.64297 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 7 time for calcul the mask position with numpy : 4.315376281738281e-05 nb_pixel_total : 380 time to create 1 rle with old method : 0.0005843639373779297 length of segment : 29 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 324 time to create 1 rle with old method : 0.00047779083251953125 length of segment : 28 time for calcul the mask position with numpy : 3.361701965332031e-05 nb_pixel_total : 125 time to create 1 rle with old method : 0.00018858909606933594 length of segment : 21 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 755 time to create 1 rle with old method : 0.0011446475982666016 length of segment : 45 time for calcul the mask position with numpy : 5.054473876953125e-05 nb_pixel_total : 1079 time to create 1 rle with old method : 0.0015807151794433594 length of segment : 31 time for calcul the mask position with numpy : 5.173683166503906e-05 nb_pixel_total : 1022 time to create 1 rle with old method : 0.001462697982788086 length of segment : 34 time for calcul the mask position with numpy : 4.0531158447265625e-05 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003807544708251953 length of segment : 18 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 136.13906 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 3 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 824 time to create 1 rle with old method : 0.001313924789428711 length of segment : 28 time for calcul the mask position with numpy : 6.198883056640625e-05 nb_pixel_total : 675 time to create 1 rle with old method : 0.0013251304626464844 length of segment : 36 time for calcul the mask position with numpy : 3.838539123535156e-05 nb_pixel_total : 306 time to create 1 rle with old method : 0.0005223751068115234 length of segment : 18 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 252.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 146.27578 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 8.988380432128906e-05 nb_pixel_total : 927 time to create 1 rle with old method : 0.0015940666198730469 length of segment : 30 time for calcul the mask position with numpy : 4.887580871582031e-05 nb_pixel_total : 315 time to create 1 rle with old method : 0.0005328655242919922 length of segment : 22 time for calcul the mask position with numpy : 5.316734313964844e-05 nb_pixel_total : 338 time to create 1 rle with old method : 0.0005495548248291016 length of segment : 26 time for calcul the mask position with numpy : 6.985664367675781e-05 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006368160247802734 length of segment : 37 time for calcul the mask position with numpy : 4.220008850097656e-05 nb_pixel_total : 120 time to create 1 rle with old method : 0.0002181529998779297 length of segment : 14 time for calcul the mask position with numpy : 0.0002484321594238281 nb_pixel_total : 16460 time to create 1 rle with old method : 0.021823883056640625 length of segment : 81 time for calcul the mask position with numpy : 9.226799011230469e-05 nb_pixel_total : 2435 time to create 1 rle with old method : 0.0033588409423828125 length of segment : 36 time for calcul the mask position with numpy : 0.0002942085266113281 nb_pixel_total : 18085 time to create 1 rle with old method : 0.024713993072509766 length of segment : 76 Processing 1 images image shape: (240, 400, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 8 time for calcul the mask position with numpy : 4.744529724121094e-05 nb_pixel_total : 486 time to create 1 rle with old method : 0.0006494522094726562 length of segment : 29 time for calcul the mask position with numpy : 4.38690185546875e-05 nb_pixel_total : 355 time to create 1 rle with old method : 0.0004994869232177734 length of segment : 21 time for calcul the mask position with numpy : 3.62396240234375e-05 nb_pixel_total : 121 time to create 1 rle with old method : 0.00019097328186035156 length of segment : 17 time for calcul the mask position with numpy : 4.8160552978515625e-05 nb_pixel_total : 554 time to create 1 rle with old method : 0.0009028911590576172 length of segment : 24 time for calcul the mask position with numpy : 3.3855438232421875e-05 nb_pixel_total : 85 time to create 1 rle with old method : 0.00016260147094726562 length of segment : 10 time for calcul the mask position with numpy : 4.553794860839844e-05 nb_pixel_total : 218 time to create 1 rle with old method : 0.00043511390686035156 length of segment : 13 time for calcul the mask position with numpy : 3.504753112792969e-05 nb_pixel_total : 152 time to create 1 rle with old method : 0.00026798248291015625 length of segment : 14 time for calcul the mask position with numpy : 6.628036499023438e-05 nb_pixel_total : 1912 time to create 1 rle with old method : 0.0027093887329101562 length of segment : 67 Processing 1 images image shape: (240, 400, 3) min: 67.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 5 time for calcul the mask position with numpy : 0.0002067089080810547 nb_pixel_total : 15118 time to create 1 rle with old method : 0.02060675621032715 length of segment : 134 time for calcul the mask position with numpy : 6.842613220214844e-05 nb_pixel_total : 1165 time to create 1 rle with old method : 0.0016641616821289062 length of segment : 40 time for calcul the mask position with numpy : 7.343292236328125e-05 nb_pixel_total : 2393 time to create 1 rle with old method : 0.0030667781829833984 length of segment : 52 time for calcul the mask position with numpy : 7.510185241699219e-05 nb_pixel_total : 2076 time to create 1 rle with old method : 0.0031480789184570312 length of segment : 43 time for calcul the mask position with numpy : 6.532669067382812e-05 nb_pixel_total : 546 time to create 1 rle with old method : 0.0008032321929931641 length of segment : 34 Processing 1 images image shape: (240, 400, 3) min: 105.00000 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 : 4 time for calcul the mask position with numpy : 6.580352783203125e-05 nb_pixel_total : 2592 time to create 1 rle with old method : 0.003664255142211914 length of segment : 33 time for calcul the mask position with numpy : 0.0001354217529296875 nb_pixel_total : 7076 time to create 1 rle with old method : 0.010885477066040039 length of segment : 114 time for calcul the mask position with numpy : 6.67572021484375e-05 nb_pixel_total : 1900 time to create 1 rle with old method : 0.0024580955505371094 length of segment : 37 time for calcul the mask position with numpy : 5.650520324707031e-05 nb_pixel_total : 1712 time to create 1 rle with old method : 0.0023736953735351562 length of segment : 40 Processing 1 images image shape: (240, 400, 3) min: 6.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 11 time for calcul the mask position with numpy : 0.00012683868408203125 nb_pixel_total : 7548 time to create 1 rle with old method : 0.009654045104980469 length of segment : 143 time for calcul the mask position with numpy : 5.91278076171875e-05 nb_pixel_total : 818 time to create 1 rle with old method : 0.0011298656463623047 length of segment : 39 time for calcul the mask position with numpy : 4.1961669921875e-05 nb_pixel_total : 658 time to create 1 rle with old method : 0.0009164810180664062 length of segment : 44 time for calcul the mask position with numpy : 6.151199340820312e-05 nb_pixel_total : 1212 time to create 1 rle with old method : 0.0016903877258300781 length of segment : 62 time for calcul the mask position with numpy : 6.651878356933594e-05 nb_pixel_total : 2346 time to create 1 rle with old method : 0.003319263458251953 length of segment : 62 time for calcul the mask position with numpy : 7.271766662597656e-05 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0016939640045166016 length of segment : 82 time for calcul the mask position with numpy : 5.7697296142578125e-05 nb_pixel_total : 470 time to create 1 rle with old method : 0.0006351470947265625 length of segment : 85 time for calcul the mask position with numpy : 0.00014925003051757812 nb_pixel_total : 7975 time to create 1 rle with old method : 0.010873079299926758 length of segment : 145 time for calcul the mask position with numpy : 6.4849853515625e-05 nb_pixel_total : 410 time to create 1 rle with old method : 0.000720977783203125 length of segment : 30 time for calcul the mask position with numpy : 6.341934204101562e-05 nb_pixel_total : 1161 time to create 1 rle with old method : 0.001729726791381836 length of segment : 61 time for calcul the mask position with numpy : 0.0002467632293701172 nb_pixel_total : 10071 time to create 1 rle with old method : 0.013061285018920898 length of segment : 286 Processing 1 images image shape: (240, 160, 3) min: 0.00000 max: 185.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 69.07791 image_metas shape: (1, 17) min: 0.00000 max: 640.00000 nb d'objets trouves : 0 Detection mask done ! Trying to reset tf kernel 1684961 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1963 tf kernel not reseted sub process len(results) : 339 len(list_Values) 339 None max_time_sub_proc : 3600 parent process len(results) : 0 len(list_Values) 339 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 : 3156 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 339 chid ids of type : 4228 Number RLEs to save : 20324 save missing photos in datou_result : time spend for datou_step_exec : 31.289802074432373 time spend to save output : 1.771177053451538 total time spend for step 1 : 33.06097912788391 step2:brightness Tue Mar 11 00:21:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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/1741648829_1684181_1342514379_1ffd45c56437eefc399db16940449f61.jpg treat image : temp/1741648829_1684181_1342512313_c352c7009e3f3686c2f9dc83b1496ba9.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 : 0.015106201171875 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 : 0.013978958129882812 save missing photos in datou_result : time spend for datou_step_exec : 1.210954189300537 time spend to save output : 0.034067392349243164 total time spend for step 2 : 1.2450215816497803 step3:blur_detection Tue Mar 11 00:21:04 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/1741648829_1684181_1342514379_1ffd45c56437eefc399db16940449f61.jpg resize: (1440, 2560) 1342514379 -7.402684628166873 treat image : temp/1741648829_1684181_1342512313_c352c7009e3f3686c2f9dc83b1496ba9.jpg resize: (1440, 2560) 1342512313 -7.1250300533835045 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 : 0.012356281280517578 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 : 0.01201009750366211 save missing photos in datou_result : time spend for datou_step_exec : 4.624453544616699 time spend to save output : 0.029103994369506836 total time spend for step 3 : 4.653557538986206 step4:rle_unique_nms_with_priority Tue Mar 11 00:21:09 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 339 chid ids of type : 4228 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 110 nb_hashtags : 7 time to prepare the origin masks : 1.9949283599853516 time for calcul the mask position with numpy : 0.1349046230316162 nb_pixel_total : 3247262 time to create 1 rle with new method : 0.46117210388183594 time for calcul the mask position with numpy : 0.01505732536315918 nb_pixel_total : 441 time to create 1 rle with old method : 0.0006265640258789062 time for calcul the mask position with numpy : 0.014957904815673828 nb_pixel_total : 73 time to create 1 rle with old method : 0.00010657310485839844 time for calcul the mask position with numpy : 0.014979362487792969 nb_pixel_total : 583 time to create 1 rle with old method : 0.0007169246673583984 time for calcul the mask position with numpy : 0.015117883682250977 nb_pixel_total : 984 time to create 1 rle with old method : 0.0012118816375732422 time for calcul the mask position with numpy : 0.015047550201416016 nb_pixel_total : 2715 time to create 1 rle with old method : 0.0033750534057617188 time for calcul the mask position with numpy : 0.015056133270263672 nb_pixel_total : 1354 time to create 1 rle with old method : 0.0017180442810058594 time for calcul the mask position with numpy : 0.015020132064819336 nb_pixel_total : 81 time to create 1 rle with old method : 0.00013947486877441406 time for calcul the mask position with numpy : 0.015078306198120117 nb_pixel_total : 2259 time to create 1 rle with old method : 0.0027763843536376953 time for calcul the mask position with numpy : 0.015126228332519531 nb_pixel_total : 216 time to create 1 rle with old method : 0.000286102294921875 time for calcul the mask position with numpy : 0.015108585357666016 nb_pixel_total : 222 time to create 1 rle with old method : 0.0002956390380859375 time for calcul the mask position with numpy : 0.015457630157470703 nb_pixel_total : 489 time to create 1 rle with old method : 0.0006284713745117188 time for calcul the mask position with numpy : 0.015348196029663086 nb_pixel_total : 4872 time to create 1 rle with old method : 0.006017446517944336 time for calcul the mask position with numpy : 0.01513051986694336 nb_pixel_total : 706 time to create 1 rle with old method : 0.0009484291076660156 time for calcul the mask position with numpy : 0.015019655227661133 nb_pixel_total : 967 time to create 1 rle with old method : 0.0012297630310058594 time for calcul the mask position with numpy : 0.015013933181762695 nb_pixel_total : 2619 time to create 1 rle with old method : 0.003244161605834961 time for calcul the mask position with numpy : 0.015024185180664062 nb_pixel_total : 146 time to create 1 rle with old method : 0.00020003318786621094 time for calcul the mask position with numpy : 0.014995574951171875 nb_pixel_total : 437 time to create 1 rle with old method : 0.0005638599395751953 time for calcul the mask position with numpy : 0.014966249465942383 nb_pixel_total : 987 time to create 1 rle with old method : 0.001251220703125 time for calcul the mask position with numpy : 0.015138387680053711 nb_pixel_total : 51 time to create 1 rle with old method : 0.00011181831359863281 time for calcul the mask position with numpy : 0.01528310775756836 nb_pixel_total : 218 time to create 1 rle with old method : 0.00031876564025878906 time for calcul the mask position with numpy : 0.01534581184387207 nb_pixel_total : 10436 time to create 1 rle with old method : 0.016048908233642578 time for calcul the mask position with numpy : 0.01750349998474121 nb_pixel_total : 7218 time to create 1 rle with old method : 0.009876251220703125 time for calcul the mask position with numpy : 0.015554189682006836 nb_pixel_total : 194 time to create 1 rle with old method : 0.00027871131896972656 time for calcul the mask position with numpy : 0.015445947647094727 nb_pixel_total : 2284 time to create 1 rle with old method : 0.0028350353240966797 time for calcul the mask position with numpy : 0.01643681526184082 nb_pixel_total : 95922 time to create 1 rle with old method : 0.11358070373535156 time for calcul the mask position with numpy : 0.016095399856567383 nb_pixel_total : 971 time to create 1 rle with old method : 0.0012669563293457031 time for calcul the mask position with numpy : 0.015099287033081055 nb_pixel_total : 220 time to create 1 rle with old method : 0.00029015541076660156 time for calcul the mask position with numpy : 0.015003681182861328 nb_pixel_total : 1525 time to create 1 rle with old method : 0.0017271041870117188 time for calcul the mask position with numpy : 0.015040397644042969 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003714561462402344 time for calcul the mask position with numpy : 0.015008687973022461 nb_pixel_total : 116 time to create 1 rle with old method : 0.00015783309936523438 time for calcul the mask position with numpy : 0.015089273452758789 nb_pixel_total : 648 time to create 1 rle with old method : 0.0008485317230224609 time for calcul the mask position with numpy : 0.015149593353271484 nb_pixel_total : 116 time to create 1 rle with old method : 0.00016641616821289062 time for calcul the mask position with numpy : 0.015033960342407227 nb_pixel_total : 135 time to create 1 rle with old method : 0.0002129077911376953 time for calcul the mask position with numpy : 0.015074014663696289 nb_pixel_total : 2312 time to create 1 rle with old method : 0.002828359603881836 time for calcul the mask position with numpy : 0.015007972717285156 nb_pixel_total : 6973 time to create 1 rle with old method : 0.009177684783935547 time for calcul the mask position with numpy : 0.015114784240722656 nb_pixel_total : 436 time to create 1 rle with old method : 0.0005600452423095703 time for calcul the mask position with numpy : 0.014878034591674805 nb_pixel_total : 8126 time to create 1 rle with old method : 0.009115219116210938 time for calcul the mask position with numpy : 0.01495671272277832 nb_pixel_total : 15851 time to create 1 rle with old method : 0.01959848403930664 time for calcul the mask position with numpy : 0.015023946762084961 nb_pixel_total : 3313 time to create 1 rle with old method : 0.0039212703704833984 time for calcul the mask position with numpy : 0.01510000228881836 nb_pixel_total : 4384 time to create 1 rle with old method : 0.005502939224243164 time for calcul the mask position with numpy : 0.01581120491027832 nb_pixel_total : 2963 time to create 1 rle with old method : 0.0035736560821533203 time for calcul the mask position with numpy : 0.01526951789855957 nb_pixel_total : 195 time to create 1 rle with old method : 0.0003211498260498047 time for calcul the mask position with numpy : 0.017676830291748047 nb_pixel_total : 4872 time to create 1 rle with old method : 0.008210420608520508 time for calcul the mask position with numpy : 0.01728510856628418 nb_pixel_total : 923 time to create 1 rle with old method : 0.0015511512756347656 time for calcul the mask position with numpy : 0.017141342163085938 nb_pixel_total : 527 time to create 1 rle with old method : 0.0009319782257080078 time for calcul the mask position with numpy : 0.017112016677856445 nb_pixel_total : 5572 time to create 1 rle with old method : 0.0063440799713134766 time for calcul the mask position with numpy : 0.0150146484375 nb_pixel_total : 2495 time to create 1 rle with old method : 0.0030405521392822266 time for calcul the mask position with numpy : 0.015127897262573242 nb_pixel_total : 601 time to create 1 rle with old method : 0.0007328987121582031 time for calcul the mask position with numpy : 0.01545262336730957 nb_pixel_total : 2134 time to create 1 rle with old method : 0.0027794837951660156 time for calcul the mask position with numpy : 0.015399932861328125 nb_pixel_total : 663 time to create 1 rle with old method : 0.0009052753448486328 time for calcul the mask position with numpy : 0.015234708786010742 nb_pixel_total : 136 time to create 1 rle with old method : 0.000179290771484375 time for calcul the mask position with numpy : 0.015069723129272461 nb_pixel_total : 1 time to create 1 rle with old method : 1.1444091796875e-05 time for calcul the mask position with numpy : 0.0150604248046875 nb_pixel_total : 55684 time to create 1 rle with old method : 0.06782150268554688 time for calcul the mask position with numpy : 0.015077352523803711 nb_pixel_total : 617 time to create 1 rle with old method : 0.000865936279296875 time for calcul the mask position with numpy : 0.01494145393371582 nb_pixel_total : 286 time to create 1 rle with old method : 0.0003674030303955078 time for calcul the mask position with numpy : 0.015077590942382812 nb_pixel_total : 1991 time to create 1 rle with old method : 0.002568483352661133 time for calcul the mask position with numpy : 0.015148639678955078 nb_pixel_total : 2700 time to create 1 rle with old method : 0.003415822982788086 time for calcul the mask position with numpy : 0.015205144882202148 nb_pixel_total : 903 time to create 1 rle with old method : 0.0011224746704101562 time for calcul the mask position with numpy : 0.014950037002563477 nb_pixel_total : 1323 time to create 1 rle with old method : 0.0016551017761230469 time for calcul the mask position with numpy : 0.015558481216430664 nb_pixel_total : 976 time to create 1 rle with old method : 0.0012388229370117188 time for calcul the mask position with numpy : 0.015210151672363281 nb_pixel_total : 5837 time to create 1 rle with old method : 0.006731510162353516 time for calcul the mask position with numpy : 0.015211343765258789 nb_pixel_total : 1428 time to create 1 rle with old method : 0.0016803741455078125 time for calcul the mask position with numpy : 0.015217304229736328 nb_pixel_total : 2556 time to create 1 rle with old method : 0.0033321380615234375 time for calcul the mask position with numpy : 0.015032052993774414 nb_pixel_total : 487 time to create 1 rle with old method : 0.0006349086761474609 time for calcul the mask position with numpy : 0.015136003494262695 nb_pixel_total : 305 time to create 1 rle with old method : 0.0004973411560058594 time for calcul the mask position with numpy : 0.014979362487792969 nb_pixel_total : 7227 time to create 1 rle with old method : 0.009074926376342773 time for calcul the mask position with numpy : 0.015091657638549805 nb_pixel_total : 141 time to create 1 rle with old method : 0.0002162456512451172 time for calcul the mask position with numpy : 0.01584172248840332 nb_pixel_total : 289 time to create 1 rle with old method : 0.0003685951232910156 time for calcul the mask position with numpy : 0.0161898136138916 nb_pixel_total : 3854 time to create 1 rle with old method : 0.005021810531616211 time for calcul the mask position with numpy : 0.017328262329101562 nb_pixel_total : 3060 time to create 1 rle with old method : 0.0046193599700927734 time for calcul the mask position with numpy : 0.017155885696411133 nb_pixel_total : 68 time to create 1 rle with old method : 0.0001609325408935547 time for calcul the mask position with numpy : 0.01771068572998047 nb_pixel_total : 974 time to create 1 rle with old method : 0.0013108253479003906 time for calcul the mask position with numpy : 0.01578831672668457 nb_pixel_total : 90 time to create 1 rle with old method : 0.00015878677368164062 time for calcul the mask position with numpy : 0.01542210578918457 nb_pixel_total : 90 time to create 1 rle with old method : 0.00016760826110839844 time for calcul the mask position with numpy : 0.01605391502380371 nb_pixel_total : 478 time to create 1 rle with old method : 0.0006697177886962891 time for calcul the mask position with numpy : 0.016538381576538086 nb_pixel_total : 4502 time to create 1 rle with old method : 0.00626826286315918 time for calcul the mask position with numpy : 0.0167086124420166 nb_pixel_total : 14642 time to create 1 rle with old method : 0.019743680953979492 time for calcul the mask position with numpy : 0.016007661819458008 nb_pixel_total : 3816 time to create 1 rle with old method : 0.004942417144775391 time for calcul the mask position with numpy : 0.015653610229492188 nb_pixel_total : 7911 time to create 1 rle with old method : 0.0091094970703125 time for calcul the mask position with numpy : 0.015289783477783203 nb_pixel_total : 20 time to create 1 rle with old method : 5.888938903808594e-05 time for calcul the mask position with numpy : 0.014989852905273438 nb_pixel_total : 3444 time to create 1 rle with old method : 0.004332780838012695 time for calcul the mask position with numpy : 0.020854473114013672 nb_pixel_total : 881 time to create 1 rle with old method : 0.0011169910430908203 time for calcul the mask position with numpy : 0.014274835586547852 nb_pixel_total : 3157 time to create 1 rle with old method : 0.003640413284301758 time for calcul the mask position with numpy : 0.014499187469482422 nb_pixel_total : 563 time to create 1 rle with old method : 0.0007638931274414062 time for calcul the mask position with numpy : 0.015327692031860352 nb_pixel_total : 681 time to create 1 rle with old method : 0.0008339881896972656 time for calcul the mask position with numpy : 0.01445770263671875 nb_pixel_total : 126 time to create 1 rle with old method : 0.0001761913299560547 time for calcul the mask position with numpy : 0.014005899429321289 nb_pixel_total : 563 time to create 1 rle with old method : 0.0007066726684570312 time for calcul the mask position with numpy : 0.014510869979858398 nb_pixel_total : 18220 time to create 1 rle with old method : 0.01969456672668457 time for calcul the mask position with numpy : 0.015174388885498047 nb_pixel_total : 41755 time to create 1 rle with old method : 0.04737424850463867 time for calcul the mask position with numpy : 0.014845132827758789 nb_pixel_total : 3852 time to create 1 rle with old method : 0.0046269893646240234 time for calcul the mask position with numpy : 0.015320301055908203 nb_pixel_total : 82 time to create 1 rle with old method : 0.0004429817199707031 time for calcul the mask position with numpy : 0.015514612197875977 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005104541778564453 time for calcul the mask position with numpy : 0.01789689064025879 nb_pixel_total : 197 time to create 1 rle with old method : 0.0002834796905517578 time for calcul the mask position with numpy : 0.01546621322631836 nb_pixel_total : 15302 time to create 1 rle with old method : 0.0170438289642334 time for calcul the mask position with numpy : 0.015503406524658203 nb_pixel_total : 1215 time to create 1 rle with old method : 0.0016036033630371094 time for calcul the mask position with numpy : 0.015412569046020508 nb_pixel_total : 12 time to create 1 rle with old method : 5.53131103515625e-05 time for calcul the mask position with numpy : 0.015223979949951172 nb_pixel_total : 211 time to create 1 rle with old method : 0.0003440380096435547 time for calcul the mask position with numpy : 0.015523195266723633 nb_pixel_total : 1921 time to create 1 rle with old method : 0.0023729801177978516 time for calcul the mask position with numpy : 0.015074968338012695 nb_pixel_total : 3529 time to create 1 rle with old method : 0.004326581954956055 time for calcul the mask position with numpy : 0.01518106460571289 nb_pixel_total : 568 time to create 1 rle with old method : 0.000782012939453125 time for calcul the mask position with numpy : 0.015107870101928711 nb_pixel_total : 182 time to create 1 rle with old method : 0.00025844573974609375 time for calcul the mask position with numpy : 0.015274286270141602 nb_pixel_total : 2867 time to create 1 rle with old method : 0.0035774707794189453 time for calcul the mask position with numpy : 0.015033483505249023 nb_pixel_total : 352 time to create 1 rle with old method : 0.00047016143798828125 time for calcul the mask position with numpy : 0.015028238296508789 nb_pixel_total : 7062 time to create 1 rle with old method : 0.008791208267211914 time for calcul the mask position with numpy : 0.015271902084350586 nb_pixel_total : 4262 time to create 1 rle with old method : 0.004840373992919922 time for calcul the mask position with numpy : 0.015106678009033203 nb_pixel_total : 881 time to create 1 rle with old method : 0.0011179447174072266 time for calcul the mask position with numpy : 0.015024662017822266 nb_pixel_total : 460 time to create 1 rle with old method : 0.0005934238433837891 time for calcul the mask position with numpy : 0.01513361930847168 nb_pixel_total : 723 time to create 1 rle with old method : 0.0009663105010986328 time for calcul the mask position with numpy : 0.01503300666809082 nb_pixel_total : 13 time to create 1 rle with old method : 4.124641418457031e-05 time for calcul the mask position with numpy : 0.015008926391601562 nb_pixel_total : 449 time to create 1 rle with old method : 0.0005495548248291016 create new chi : 2.8554229736328125 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 : 0.010453224182128906 batch 1 Loaded 111 chid ids of type : 4230 Number RLEs to save : 16625 TO DO : save crop sub photo not yet done ! save time : 1.2010102272033691 nb_obj : 224 nb_hashtags : 6 time to prepare the origin masks : 4.492251634597778 time for calcul the mask position with numpy : 0.3586299419403076 nb_pixel_total : 3311486 time to create 1 rle with new method : 0.32935500144958496 time for calcul the mask position with numpy : 0.014748334884643555 nb_pixel_total : 1104 time to create 1 rle with old method : 0.0019075870513916016 time for calcul the mask position with numpy : 0.014864444732666016 nb_pixel_total : 60 time to create 1 rle with old method : 0.0001392364501953125 time for calcul the mask position with numpy : 0.012752294540405273 nb_pixel_total : 114 time to create 1 rle with old method : 0.0001842975616455078 time for calcul the mask position with numpy : 0.012387514114379883 nb_pixel_total : 313 time to create 1 rle with old method : 0.0004134178161621094 time for calcul the mask position with numpy : 0.014637231826782227 nb_pixel_total : 136 time to create 1 rle with old method : 0.00020170211791992188 time for calcul the mask position with numpy : 0.01626443862915039 nb_pixel_total : 5775 time to create 1 rle with old method : 0.007999181747436523 time for calcul the mask position with numpy : 0.020378828048706055 nb_pixel_total : 2130 time to create 1 rle with old method : 0.003245830535888672 time for calcul the mask position with numpy : 0.019866943359375 nb_pixel_total : 226 time to create 1 rle with old method : 0.00046634674072265625 time for calcul the mask position with numpy : 0.017278432846069336 nb_pixel_total : 1095 time to create 1 rle with old method : 0.0015823841094970703 time for calcul the mask position with numpy : 0.01740288734436035 nb_pixel_total : 298 time to create 1 rle with old method : 0.0004506111145019531 time for calcul the mask position with numpy : 0.016289472579956055 nb_pixel_total : 857 time to create 1 rle with old method : 0.001195669174194336 time for calcul the mask position with numpy : 0.012791156768798828 nb_pixel_total : 296 time to create 1 rle with old method : 0.00040531158447265625 time for calcul the mask position with numpy : 0.015654802322387695 nb_pixel_total : 382 time to create 1 rle with old method : 0.0005280971527099609 time for calcul the mask position with numpy : 0.016898632049560547 nb_pixel_total : 113 time to create 1 rle with old method : 0.0002162456512451172 time for calcul the mask position with numpy : 0.015359640121459961 nb_pixel_total : 1423 time to create 1 rle with old method : 0.002175569534301758 time for calcul the mask position with numpy : 0.020003795623779297 nb_pixel_total : 783 time to create 1 rle with old method : 0.0013179779052734375 time for calcul the mask position with numpy : 0.019081830978393555 nb_pixel_total : 29 time to create 1 rle with old method : 9.870529174804688e-05 time for calcul the mask position with numpy : 0.017643451690673828 nb_pixel_total : 1626 time to create 1 rle with old method : 0.002505779266357422 time for calcul the mask position with numpy : 0.013560056686401367 nb_pixel_total : 160 time to create 1 rle with old method : 0.00023865699768066406 time for calcul the mask position with numpy : 0.01810455322265625 nb_pixel_total : 2715 time to create 1 rle with old method : 0.0031304359436035156 time for calcul the mask position with numpy : 0.012534618377685547 nb_pixel_total : 1896 time to create 1 rle with old method : 0.0023849010467529297 time for calcul the mask position with numpy : 0.015427827835083008 nb_pixel_total : 2754 time to create 1 rle with old method : 0.0030875205993652344 time for calcul the mask position with numpy : 0.017455101013183594 nb_pixel_total : 174 time to create 1 rle with old method : 0.0002448558807373047 time for calcul the mask position with numpy : 0.01936507225036621 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0014224052429199219 time for calcul the mask position with numpy : 0.019383668899536133 nb_pixel_total : 248 time to create 1 rle with old method : 0.0002999305725097656 time for calcul the mask position with numpy : 0.020093679428100586 nb_pixel_total : 195 time to create 1 rle with old method : 0.0002868175506591797 time for calcul the mask position with numpy : 0.019128084182739258 nb_pixel_total : 62 time to create 1 rle with old method : 0.00010633468627929688 time for calcul the mask position with numpy : 0.019950151443481445 nb_pixel_total : 691 time to create 1 rle with old method : 0.0008852481842041016 time for calcul the mask position with numpy : 0.019240856170654297 nb_pixel_total : 281 time to create 1 rle with old method : 0.00039696693420410156 time for calcul the mask position with numpy : 0.018136024475097656 nb_pixel_total : 193 time to create 1 rle with old method : 0.00027561187744140625 time for calcul the mask position with numpy : 0.01766347885131836 nb_pixel_total : 665 time to create 1 rle with old method : 0.0008721351623535156 time for calcul the mask position with numpy : 0.01846623420715332 nb_pixel_total : 1767 time to create 1 rle with old method : 0.0021681785583496094 time for calcul the mask position with numpy : 0.01812458038330078 nb_pixel_total : 181 time to create 1 rle with old method : 0.0003421306610107422 time for calcul the mask position with numpy : 0.01994800567626953 nb_pixel_total : 3328 time to create 1 rle with old method : 0.004413604736328125 time for calcul the mask position with numpy : 0.024103641510009766 nb_pixel_total : 1807 time to create 1 rle with old method : 0.0027124881744384766 time for calcul the mask position with numpy : 0.021352291107177734 nb_pixel_total : 744 time to create 1 rle with old method : 0.0010371208190917969 time for calcul the mask position with numpy : 0.02176690101623535 nb_pixel_total : 1096 time to create 1 rle with old method : 0.0016410350799560547 time for calcul the mask position with numpy : 0.02343273162841797 nb_pixel_total : 361 time to create 1 rle with old method : 0.0004513263702392578 time for calcul the mask position with numpy : 0.02234029769897461 nb_pixel_total : 28 time to create 1 rle with old method : 0.00012302398681640625 time for calcul the mask position with numpy : 0.023229122161865234 nb_pixel_total : 1158 time to create 1 rle with old method : 0.0015156269073486328 time for calcul the mask position with numpy : 0.022808313369750977 nb_pixel_total : 864 time to create 1 rle with old method : 0.0011053085327148438 time for calcul the mask position with numpy : 0.021419525146484375 nb_pixel_total : 313 time to create 1 rle with old method : 0.00048422813415527344 time for calcul the mask position with numpy : 0.021311283111572266 nb_pixel_total : 2527 time to create 1 rle with old method : 0.003161907196044922 time for calcul the mask position with numpy : 0.021971940994262695 nb_pixel_total : 1229 time to create 1 rle with old method : 0.0014417171478271484 time for calcul the mask position with numpy : 0.013937234878540039 nb_pixel_total : 129 time to create 1 rle with old method : 0.0002186298370361328 time for calcul the mask position with numpy : 0.015573501586914062 nb_pixel_total : 119 time to create 1 rle with old method : 0.0002377033233642578 time for calcul the mask position with numpy : 0.013681650161743164 nb_pixel_total : 1412 time to create 1 rle with old method : 0.0018541812896728516 time for calcul the mask position with numpy : 0.014192819595336914 nb_pixel_total : 374 time to create 1 rle with old method : 0.0005576610565185547 time for calcul the mask position with numpy : 0.014394044876098633 nb_pixel_total : 97 time to create 1 rle with old method : 0.00019025802612304688 time for calcul the mask position with numpy : 0.014103174209594727 nb_pixel_total : 180 time to create 1 rle with old method : 0.00030422210693359375 time for calcul the mask position with numpy : 0.014340400695800781 nb_pixel_total : 293 time to create 1 rle with old method : 0.0004980564117431641 time for calcul the mask position with numpy : 0.014689207077026367 nb_pixel_total : 650 time to create 1 rle with old method : 0.0009970664978027344 time for calcul the mask position with numpy : 0.014239072799682617 nb_pixel_total : 66 time to create 1 rle with old method : 0.00018095970153808594 time for calcul the mask position with numpy : 0.015337705612182617 nb_pixel_total : 451 time to create 1 rle with old method : 0.0006253719329833984 time for calcul the mask position with numpy : 0.014569997787475586 nb_pixel_total : 115 time to create 1 rle with old method : 0.0002453327178955078 time for calcul the mask position with numpy : 0.017003297805786133 nb_pixel_total : 8095 time to create 1 rle with old method : 0.010189533233642578 time for calcul the mask position with numpy : 0.015444278717041016 nb_pixel_total : 840 time to create 1 rle with old method : 0.001535177230834961 time for calcul the mask position with numpy : 0.014737129211425781 nb_pixel_total : 269 time to create 1 rle with old method : 0.0005536079406738281 time for calcul the mask position with numpy : 0.014208793640136719 nb_pixel_total : 116 time to create 1 rle with old method : 0.0002772808074951172 time for calcul the mask position with numpy : 0.01410531997680664 nb_pixel_total : 255 time to create 1 rle with old method : 0.0004661083221435547 time for calcul the mask position with numpy : 0.013875961303710938 nb_pixel_total : 422 time to create 1 rle with old method : 0.0007803440093994141 time for calcul the mask position with numpy : 0.014281272888183594 nb_pixel_total : 382 time to create 1 rle with old method : 0.0007131099700927734 time for calcul the mask position with numpy : 0.013949871063232422 nb_pixel_total : 224 time to create 1 rle with old method : 0.00031757354736328125 time for calcul the mask position with numpy : 0.01557779312133789 nb_pixel_total : 326 time to create 1 rle with old method : 0.00044608116149902344 time for calcul the mask position with numpy : 0.015014410018920898 nb_pixel_total : 35 time to create 1 rle with old method : 0.000125885009765625 time for calcul the mask position with numpy : 0.01598644256591797 nb_pixel_total : 334 time to create 1 rle with old method : 0.0004923343658447266 time for calcul the mask position with numpy : 0.013831138610839844 nb_pixel_total : 348 time to create 1 rle with old method : 0.0004906654357910156 time for calcul the mask position with numpy : 0.016426801681518555 nb_pixel_total : 294 time to create 1 rle with old method : 0.0004324913024902344 time for calcul the mask position with numpy : 0.013611316680908203 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001761913299560547 time for calcul the mask position with numpy : 0.01501607894897461 nb_pixel_total : 82 time to create 1 rle with old method : 0.0001678466796875 time for calcul the mask position with numpy : 0.014030218124389648 nb_pixel_total : 227 time to create 1 rle with old method : 0.0003116130828857422 time for calcul the mask position with numpy : 0.011758804321289062 nb_pixel_total : 4431 time to create 1 rle with old method : 0.005527973175048828 time for calcul the mask position with numpy : 0.011202812194824219 nb_pixel_total : 3777 time to create 1 rle with old method : 0.004733562469482422 time for calcul the mask position with numpy : 0.011059761047363281 nb_pixel_total : 235 time to create 1 rle with old method : 0.0003178119659423828 time for calcul the mask position with numpy : 0.01147317886352539 nb_pixel_total : 272 time to create 1 rle with old method : 0.00036716461181640625 time for calcul the mask position with numpy : 0.011828422546386719 nb_pixel_total : 1027 time to create 1 rle with old method : 0.0013098716735839844 time for calcul the mask position with numpy : 0.018700361251831055 nb_pixel_total : 1398 time to create 1 rle with old method : 0.0017447471618652344 time for calcul the mask position with numpy : 0.018780231475830078 nb_pixel_total : 51611 time to create 1 rle with old method : 0.06225848197937012 time for calcul the mask position with numpy : 0.0183718204498291 nb_pixel_total : 6 time to create 1 rle with old method : 4.0531158447265625e-05 time for calcul the mask position with numpy : 0.01885819435119629 nb_pixel_total : 7644 time to create 1 rle with old method : 0.009576559066772461 time for calcul the mask position with numpy : 0.019259214401245117 nb_pixel_total : 760 time to create 1 rle with old method : 0.0009624958038330078 time for calcul the mask position with numpy : 0.01915597915649414 nb_pixel_total : 283 time to create 1 rle with old method : 0.0003826618194580078 time for calcul the mask position with numpy : 0.01878952980041504 nb_pixel_total : 1830 time to create 1 rle with old method : 0.0024259090423583984 time for calcul the mask position with numpy : 0.018619298934936523 nb_pixel_total : 388 time to create 1 rle with old method : 0.0004661083221435547 time for calcul the mask position with numpy : 0.01976323127746582 nb_pixel_total : 356 time to create 1 rle with old method : 0.00047087669372558594 time for calcul the mask position with numpy : 0.019824981689453125 nb_pixel_total : 1105 time to create 1 rle with old method : 0.0013780593872070312 time for calcul the mask position with numpy : 0.019312381744384766 nb_pixel_total : 2657 time to create 1 rle with old method : 0.00304412841796875 time for calcul the mask position with numpy : 0.019099950790405273 nb_pixel_total : 34 time to create 1 rle with old method : 9.72747802734375e-05 time for calcul the mask position with numpy : 0.01875782012939453 nb_pixel_total : 1009 time to create 1 rle with old method : 0.0012962818145751953 time for calcul the mask position with numpy : 0.01857137680053711 nb_pixel_total : 1240 time to create 1 rle with old method : 0.0018341541290283203 time for calcul the mask position with numpy : 0.01875162124633789 nb_pixel_total : 344 time to create 1 rle with old method : 0.00045609474182128906 time for calcul the mask position with numpy : 0.01929950714111328 nb_pixel_total : 15943 time to create 1 rle with old method : 0.019684553146362305 time for calcul the mask position with numpy : 0.011546611785888672 nb_pixel_total : 269 time to create 1 rle with old method : 0.0003552436828613281 time for calcul the mask position with numpy : 0.011486291885375977 nb_pixel_total : 406 time to create 1 rle with old method : 0.0005009174346923828 time for calcul the mask position with numpy : 0.011290311813354492 nb_pixel_total : 76 time to create 1 rle with old method : 0.00011992454528808594 time for calcul the mask position with numpy : 0.011497974395751953 nb_pixel_total : 278 time to create 1 rle with old method : 0.00037360191345214844 time for calcul the mask position with numpy : 0.011278629302978516 nb_pixel_total : 1446 time to create 1 rle with old method : 0.0018701553344726562 time for calcul the mask position with numpy : 0.011968612670898438 nb_pixel_total : 36 time to create 1 rle with old method : 0.00011849403381347656 time for calcul the mask position with numpy : 0.01217508316040039 nb_pixel_total : 192 time to create 1 rle with old method : 0.00027751922607421875 time for calcul the mask position with numpy : 0.012326240539550781 nb_pixel_total : 414 time to create 1 rle with old method : 0.0005512237548828125 time for calcul the mask position with numpy : 0.011709213256835938 nb_pixel_total : 630 time to create 1 rle with old method : 0.0007479190826416016 time for calcul the mask position with numpy : 0.01392674446105957 nb_pixel_total : 182 time to create 1 rle with old method : 0.0002658367156982422 time for calcul the mask position with numpy : 0.01236104965209961 nb_pixel_total : 583 time to create 1 rle with old method : 0.0007948875427246094 time for calcul the mask position with numpy : 0.011812448501586914 nb_pixel_total : 1240 time to create 1 rle with old method : 0.0015556812286376953 time for calcul the mask position with numpy : 0.015186071395874023 nb_pixel_total : 327 time to create 1 rle with old method : 0.0007638931274414062 time for calcul the mask position with numpy : 0.012305259704589844 nb_pixel_total : 113 time to create 1 rle with old method : 0.0001671314239501953 time for calcul the mask position with numpy : 0.012854337692260742 nb_pixel_total : 740 time to create 1 rle with old method : 0.0009386539459228516 time for calcul the mask position with numpy : 0.012992382049560547 nb_pixel_total : 1583 time to create 1 rle with old method : 0.002076387405395508 time for calcul the mask position with numpy : 0.012068986892700195 nb_pixel_total : 228 time to create 1 rle with old method : 0.00032401084899902344 time for calcul the mask position with numpy : 0.012689352035522461 nb_pixel_total : 318 time to create 1 rle with old method : 0.00042557716369628906 time for calcul the mask position with numpy : 0.011820793151855469 nb_pixel_total : 843 time to create 1 rle with old method : 0.0010924339294433594 time for calcul the mask position with numpy : 0.015431880950927734 nb_pixel_total : 1334 time to create 1 rle with old method : 0.0015370845794677734 time for calcul the mask position with numpy : 0.01544809341430664 nb_pixel_total : 1404 time to create 1 rle with old method : 0.0016326904296875 time for calcul the mask position with numpy : 0.015409231185913086 nb_pixel_total : 3213 time to create 1 rle with old method : 0.003663778305053711 time for calcul the mask position with numpy : 0.015723228454589844 nb_pixel_total : 228 time to create 1 rle with old method : 0.00030422210693359375 time for calcul the mask position with numpy : 0.01562047004699707 nb_pixel_total : 2492 time to create 1 rle with old method : 0.003622770309448242 time for calcul the mask position with numpy : 0.015298604965209961 nb_pixel_total : 1107 time to create 1 rle with old method : 0.0012717247009277344 time for calcul the mask position with numpy : 0.01527261734008789 nb_pixel_total : 129 time to create 1 rle with old method : 0.00022029876708984375 time for calcul the mask position with numpy : 0.01534128189086914 nb_pixel_total : 537 time to create 1 rle with old method : 0.0007002353668212891 time for calcul the mask position with numpy : 0.015377521514892578 nb_pixel_total : 51 time to create 1 rle with old method : 9.894371032714844e-05 time for calcul the mask position with numpy : 0.015332698822021484 nb_pixel_total : 550 time to create 1 rle with old method : 0.0007112026214599609 time for calcul the mask position with numpy : 0.015295982360839844 nb_pixel_total : 782 time to create 1 rle with old method : 0.0009984970092773438 time for calcul the mask position with numpy : 0.015243768692016602 nb_pixel_total : 2459 time to create 1 rle with old method : 0.0030319690704345703 time for calcul the mask position with numpy : 0.01544499397277832 nb_pixel_total : 125 time to create 1 rle with old method : 0.0001766681671142578 time for calcul the mask position with numpy : 0.015480995178222656 nb_pixel_total : 1819 time to create 1 rle with old method : 0.0022835731506347656 time for calcul the mask position with numpy : 0.015376806259155273 nb_pixel_total : 620 time to create 1 rle with old method : 0.0008039474487304688 time for calcul the mask position with numpy : 0.015502214431762695 nb_pixel_total : 1079 time to create 1 rle with old method : 0.0014193058013916016 time for calcul the mask position with numpy : 0.016790390014648438 nb_pixel_total : 169 time to create 1 rle with old method : 0.00023674964904785156 time for calcul the mask position with numpy : 0.015575885772705078 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006132125854492188 time for calcul the mask position with numpy : 0.01527261734008789 nb_pixel_total : 5984 time to create 1 rle with old method : 0.007467746734619141 time for calcul the mask position with numpy : 0.015273332595825195 nb_pixel_total : 41 time to create 1 rle with old method : 0.00011777877807617188 time for calcul the mask position with numpy : 0.015220165252685547 nb_pixel_total : 24111 time to create 1 rle with old method : 0.03096771240234375 time for calcul the mask position with numpy : 0.015370368957519531 nb_pixel_total : 405 time to create 1 rle with old method : 0.000537872314453125 time for calcul the mask position with numpy : 0.015677213668823242 nb_pixel_total : 193 time to create 1 rle with old method : 0.0002837181091308594 time for calcul the mask position with numpy : 0.015465497970581055 nb_pixel_total : 989 time to create 1 rle with old method : 0.0013492107391357422 time for calcul the mask position with numpy : 0.01663804054260254 nb_pixel_total : 587 time to create 1 rle with old method : 0.0007634162902832031 time for calcul the mask position with numpy : 0.015843629837036133 nb_pixel_total : 138 time to create 1 rle with old method : 0.00021600723266601562 time for calcul the mask position with numpy : 0.015294313430786133 nb_pixel_total : 2346 time to create 1 rle with old method : 0.0029604434967041016 time for calcul the mask position with numpy : 0.01563119888305664 nb_pixel_total : 555 time to create 1 rle with old method : 0.0006732940673828125 time for calcul the mask position with numpy : 0.0153961181640625 nb_pixel_total : 462 time to create 1 rle with old method : 0.0006306171417236328 time for calcul the mask position with numpy : 0.01504659652709961 nb_pixel_total : 3 time to create 1 rle with old method : 3.933906555175781e-05 time for calcul the mask position with numpy : 0.015358448028564453 nb_pixel_total : 386 time to create 1 rle with old method : 0.0005426406860351562 time for calcul the mask position with numpy : 0.020551443099975586 nb_pixel_total : 258 time to create 1 rle with old method : 0.0003459453582763672 time for calcul the mask position with numpy : 0.015324115753173828 nb_pixel_total : 181 time to create 1 rle with old method : 0.0002536773681640625 time for calcul the mask position with numpy : 0.01518869400024414 nb_pixel_total : 316 time to create 1 rle with old method : 0.0004303455352783203 time for calcul the mask position with numpy : 0.01598215103149414 nb_pixel_total : 608 time to create 1 rle with old method : 0.0008502006530761719 time for calcul the mask position with numpy : 0.015082836151123047 nb_pixel_total : 380 time to create 1 rle with old method : 0.0005021095275878906 time for calcul the mask position with numpy : 0.014888763427734375 nb_pixel_total : 1598 time to create 1 rle with old method : 0.0020248889923095703 time for calcul the mask position with numpy : 0.014908790588378906 nb_pixel_total : 527 time to create 1 rle with old method : 0.0006806850433349609 time for calcul the mask position with numpy : 0.014918804168701172 nb_pixel_total : 340 time to create 1 rle with old method : 0.0004413127899169922 time for calcul the mask position with numpy : 0.015178442001342773 nb_pixel_total : 574 time to create 1 rle with old method : 0.0006952285766601562 time for calcul the mask position with numpy : 0.016572952270507812 nb_pixel_total : 15890 time to create 1 rle with old method : 0.02531599998474121 time for calcul the mask position with numpy : 0.021338701248168945 nb_pixel_total : 833 time to create 1 rle with old method : 0.0016570091247558594 time for calcul the mask position with numpy : 0.01971602439880371 nb_pixel_total : 535 time to create 1 rle with old method : 0.0009071826934814453 time for calcul the mask position with numpy : 0.01738429069519043 nb_pixel_total : 1012 time to create 1 rle with old method : 0.0017206668853759766 time for calcul the mask position with numpy : 0.017629146575927734 nb_pixel_total : 324 time to create 1 rle with old method : 0.0005652904510498047 time for calcul the mask position with numpy : 0.017595529556274414 nb_pixel_total : 247 time to create 1 rle with old method : 0.0004341602325439453 time for calcul the mask position with numpy : 0.016990184783935547 nb_pixel_total : 175 time to create 1 rle with old method : 0.00023603439331054688 time for calcul the mask position with numpy : 0.015377998352050781 nb_pixel_total : 30740 time to create 1 rle with old method : 0.03381228446960449 time for calcul the mask position with numpy : 0.01535654067993164 nb_pixel_total : 299 time to create 1 rle with old method : 0.0004100799560546875 time for calcul the mask position with numpy : 0.016780614852905273 nb_pixel_total : 169 time to create 1 rle with old method : 0.0003261566162109375 time for calcul the mask position with numpy : 0.017508983612060547 nb_pixel_total : 755 time to create 1 rle with old method : 0.0012524127960205078 time for calcul the mask position with numpy : 0.017520666122436523 nb_pixel_total : 1564 time to create 1 rle with old method : 0.0026094913482666016 time for calcul the mask position with numpy : 0.01741957664489746 nb_pixel_total : 35 time to create 1 rle with old method : 0.0001404285430908203 time for calcul the mask position with numpy : 0.01906108856201172 nb_pixel_total : 517 time to create 1 rle with old method : 0.0007364749908447266 time for calcul the mask position with numpy : 0.01712179183959961 nb_pixel_total : 391 time to create 1 rle with old method : 0.0005118846893310547 time for calcul the mask position with numpy : 0.015455961227416992 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007691383361816406 time for calcul the mask position with numpy : 0.015468835830688477 nb_pixel_total : 1953 time to create 1 rle with old method : 0.0024504661560058594 time for calcul the mask position with numpy : 0.015471935272216797 nb_pixel_total : 207 time to create 1 rle with old method : 0.0002925395965576172 time for calcul the mask position with numpy : 0.015606880187988281 nb_pixel_total : 694 time to create 1 rle with old method : 0.0015869140625 time for calcul the mask position with numpy : 0.019980669021606445 nb_pixel_total : 186 time to create 1 rle with old method : 0.00025582313537597656 time for calcul the mask position with numpy : 0.01505589485168457 nb_pixel_total : 1090 time to create 1 rle with old method : 0.0013859272003173828 time for calcul the mask position with numpy : 0.016243934631347656 nb_pixel_total : 237 time to create 1 rle with old method : 0.0003731250762939453 time for calcul the mask position with numpy : 0.015568971633911133 nb_pixel_total : 238 time to create 1 rle with old method : 0.0003600120544433594 time for calcul the mask position with numpy : 0.016495227813720703 nb_pixel_total : 1059 time to create 1 rle with old method : 0.0013837814331054688 time for calcul the mask position with numpy : 0.01567697525024414 nb_pixel_total : 1285 time to create 1 rle with old method : 0.001657724380493164 time for calcul the mask position with numpy : 0.015402555465698242 nb_pixel_total : 312 time to create 1 rle with old method : 0.0004172325134277344 time for calcul the mask position with numpy : 0.016809701919555664 nb_pixel_total : 2678 time to create 1 rle with old method : 0.0042226314544677734 time for calcul the mask position with numpy : 0.019367456436157227 nb_pixel_total : 215 time to create 1 rle with old method : 0.0004787445068359375 time for calcul the mask position with numpy : 0.01692986488342285 nb_pixel_total : 449 time to create 1 rle with old method : 0.0006103515625 time for calcul the mask position with numpy : 0.01527714729309082 nb_pixel_total : 11 time to create 1 rle with old method : 5.340576171875e-05 time for calcul the mask position with numpy : 0.015320777893066406 nb_pixel_total : 442 time to create 1 rle with old method : 0.0006005764007568359 time for calcul the mask position with numpy : 0.015233993530273438 nb_pixel_total : 651 time to create 1 rle with old method : 0.0008656978607177734 time for calcul the mask position with numpy : 0.015057802200317383 nb_pixel_total : 95 time to create 1 rle with old method : 0.00012445449829101562 time for calcul the mask position with numpy : 0.016154050827026367 nb_pixel_total : 7 time to create 1 rle with old method : 3.5762786865234375e-05 time for calcul the mask position with numpy : 0.017073631286621094 nb_pixel_total : 85 time to create 1 rle with old method : 0.00013446807861328125 time for calcul the mask position with numpy : 0.017640352249145508 nb_pixel_total : 315 time to create 1 rle with old method : 0.0004532337188720703 time for calcul the mask position with numpy : 0.015983104705810547 nb_pixel_total : 658 time to create 1 rle with old method : 0.0009315013885498047 time for calcul the mask position with numpy : 0.01594829559326172 nb_pixel_total : 818 time to create 1 rle with old method : 0.0011353492736816406 time for calcul the mask position with numpy : 0.015642642974853516 nb_pixel_total : 379 time to create 1 rle with old method : 0.00047087669372558594 time for calcul the mask position with numpy : 0.015109777450561523 nb_pixel_total : 675 time to create 1 rle with old method : 0.0009102821350097656 time for calcul the mask position with numpy : 0.015113353729248047 nb_pixel_total : 1912 time to create 1 rle with old method : 0.0022597312927246094 time for calcul the mask position with numpy : 0.015264749526977539 nb_pixel_total : 1299 time to create 1 rle with old method : 0.001711130142211914 time for calcul the mask position with numpy : 0.015248537063598633 nb_pixel_total : 477 time to create 1 rle with old method : 0.0006392002105712891 time for calcul the mask position with numpy : 0.016649246215820312 nb_pixel_total : 486 time to create 1 rle with old method : 0.0009295940399169922 time for calcul the mask position with numpy : 0.01855778694152832 nb_pixel_total : 338 time to create 1 rle with old method : 0.00045800209045410156 time for calcul the mask position with numpy : 0.015036344528198242 nb_pixel_total : 306 time to create 1 rle with old method : 0.0004153251647949219 time for calcul the mask position with numpy : 0.01518559455871582 nb_pixel_total : 120 time to create 1 rle with old method : 0.00016999244689941406 time for calcul the mask position with numpy : 0.015192031860351562 nb_pixel_total : 404 time to create 1 rle with old method : 0.0005331039428710938 time for calcul the mask position with numpy : 0.016331195831298828 nb_pixel_total : 10071 time to create 1 rle with old method : 0.012386560440063477 time for calcul the mask position with numpy : 0.015301942825317383 nb_pixel_total : 824 time to create 1 rle with old method : 0.0010907649993896484 time for calcul the mask position with numpy : 0.015166521072387695 nb_pixel_total : 927 time to create 1 rle with old method : 0.0012085437774658203 time for calcul the mask position with numpy : 0.015243291854858398 nb_pixel_total : 152 time to create 1 rle with old method : 0.00026035308837890625 time for calcul the mask position with numpy : 0.015048027038574219 nb_pixel_total : 355 time to create 1 rle with old method : 0.0004856586456298828 time for calcul the mask position with numpy : 0.023137807846069336 nb_pixel_total : 1212 time to create 1 rle with old method : 0.0015673637390136719 time for calcul the mask position with numpy : 0.01511526107788086 nb_pixel_total : 218 time to create 1 rle with old method : 0.0003120899200439453 time for calcul the mask position with numpy : 0.015304803848266602 nb_pixel_total : 716 time to create 1 rle with old method : 0.0010571479797363281 time for calcul the mask position with numpy : 0.015241861343383789 nb_pixel_total : 15118 time to create 1 rle with old method : 0.01845860481262207 time for calcul the mask position with numpy : 0.015242815017700195 nb_pixel_total : 42 time to create 1 rle with old method : 0.0001246929168701172 time for calcul the mask position with numpy : 0.015174627304077148 nb_pixel_total : 546 time to create 1 rle with old method : 0.0006773471832275391 time for calcul the mask position with numpy : 0.018718242645263672 nb_pixel_total : 1165 time to create 1 rle with old method : 0.0014929771423339844 time for calcul the mask position with numpy : 0.015627145767211914 nb_pixel_total : 7076 time to create 1 rle with old method : 0.008549690246582031 time for calcul the mask position with numpy : 0.015471935272216797 nb_pixel_total : 141 time to create 1 rle with old method : 0.0003025531768798828 time for calcul the mask position with numpy : 0.014956235885620117 nb_pixel_total : 7548 time to create 1 rle with old method : 0.008487939834594727 time for calcul the mask position with numpy : 0.015057802200317383 nb_pixel_total : 462 time to create 1 rle with old method : 0.0008258819580078125 time for calcul the mask position with numpy : 0.015096426010131836 nb_pixel_total : 16460 time to create 1 rle with old method : 0.02002120018005371 time for calcul the mask position with numpy : 0.015325069427490234 nb_pixel_total : 2393 time to create 1 rle with old method : 0.002949237823486328 time for calcul the mask position with numpy : 0.015283584594726562 nb_pixel_total : 1025 time to create 1 rle with old method : 0.001409769058227539 time for calcul the mask position with numpy : 0.015152931213378906 nb_pixel_total : 1712 time to create 1 rle with old method : 0.001957416534423828 time for calcul the mask position with numpy : 0.015204668045043945 nb_pixel_total : 1900 time to create 1 rle with old method : 0.0022153854370117188 time for calcul the mask position with numpy : 0.016155481338500977 nb_pixel_total : 2107 time to create 1 rle with old method : 0.0036776065826416016 time for calcul the mask position with numpy : 0.017981767654418945 nb_pixel_total : 2592 time to create 1 rle with old method : 0.0043621063232421875 time for calcul the mask position with numpy : 0.01806163787841797 nb_pixel_total : 121 time to create 1 rle with old method : 0.0002579689025878906 time for calcul the mask position with numpy : 0.017336606979370117 nb_pixel_total : 554 time to create 1 rle with old method : 0.0007333755493164062 create new chi : 4.817589521408081 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 : 0.003712892532348633 batch 1 Loaded 225 chid ids of type : 4230 Number RLEs to save : 21849 TO DO : save crop sub photo not yet done ! save time : 1.855950117111206 map_output_result : {1342514379: (0.0, 'Should be the crop_list due to order', 0.0), 1342512313: (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 [1342514379, 1342512313] Looping around the photos to save general results len do output : 2 /1342514379.Didn't retrieve data . /1342512313.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, '2655793') ('4234', '21243455', '1342514379', None, None, None, None, None, '2655793') ('4234', None, None, None, None, None, None, None, '2655793') ('4234', '21243455', '1342512313', None, None, None, None, None, '2655793') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.15839028358459473 save_final save missing photos in datou_result : time spend for datou_step_exec : 18.178454160690308 time spend to save output : 0.2000563144683838 total time spend for step 4 : 18.37851047515869 step5:crop_condition Tue Mar 11 00:21:27 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 336 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 ! 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 ! 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 : 172 About to insert : list_path_to_insert length 172 new photo from crops ! About to upload 172 photos upload in portfolio : 4869462 init cache_photo without model_param we have 172 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741648893_1684181 we have uploaded 172 photos in the portfolio 4869462 time of upload the photos Elapsed time : 53.29974579811096 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 ! 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 : 46 About to insert : list_path_to_insert length 46 new photo from crops ! About to upload 46 photos upload in portfolio : 4869462 init cache_photo without model_param we have 46 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741648948_1684181 we have uploaded 46 photos in the portfolio 4869462 time of upload the photos Elapsed time : 15.36898922920227 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 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 4869462 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741648963_1684181 we have uploaded 2 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.8052475452423096 we have finished the crop for the class : metal 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 18 About to insert : list_path_to_insert length 18 new photo from crops ! About to upload 18 photos upload in portfolio : 4869462 init cache_photo without model_param we have 18 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741648965_1684181 we have uploaded 18 photos in the portfolio 4869462 time of upload the photos Elapsed time : 5.589309453964233 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 ! map_result returned by crop_photo_return_map_crop : length : 6 About to insert : list_path_to_insert length 6 new photo from crops ! About to upload 6 photos upload in portfolio : 4869462 init cache_photo without model_param we have 6 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741648971_1684181 we have uploaded 6 photos in the portfolio 4869462 time of upload the photos Elapsed time : 2.4351890087127686 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 ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 3 About to insert : list_path_to_insert length 3 new photo from crops ! About to upload 3 photos upload in portfolio : 4869462 init cache_photo without model_param we have 3 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1741648974_1684181 we have uploaded 3 photos in the portfolio 4869462 time of upload the photos Elapsed time : 0.9017987251281738 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 [1342514379, 1342512313] Looping around the photos to save general results len do output : 247 /1342726692Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726694Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726695Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726696Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726698Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726699Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726700Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726702Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726703Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726704Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726705Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726706Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726707Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726708Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726710Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726711Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726712Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726713Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726714Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726715Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726716Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726718Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726720Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726722Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726723Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726724Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726725Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726726Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726727Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726728Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726729Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726730Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726732Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726733Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726734Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726735Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726736Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726738Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726739Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726740Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726741Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726742Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726743Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726745Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726746Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726747Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726748Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726749Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726750Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726751Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726752Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726753Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726754Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726755Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726756Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726757Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726758Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726759Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726760Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726761Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726762Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726763Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726764Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726765Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726766Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726768Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726769Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726770Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726772Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726778Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726779Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726780Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726781Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726782Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726783Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726784Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726785Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726786Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726787Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726788Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726789Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726790Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726791Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726792Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726793Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726794Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726795Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726796Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726797Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726798Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726799Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726802Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726803Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726804Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726805Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726806Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726807Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726808Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726809Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726810Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726811Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726812Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726813Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726814Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726816Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726818Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726819Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726820Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726821Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726822Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726823Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726824Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726825Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726826Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726827Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726828Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726829Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726830Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726831Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726832Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726833Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726834Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726835Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726836Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726837Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726838Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726839Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726840Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726841Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726842Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726843Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726844Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726845Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726846Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726847Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726848Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726849Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726850Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726851Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726852Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726854Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726856Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726857Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726859Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726860Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726861Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726863Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726864Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726865Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726867Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726868Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726869Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726871Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726872Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726875Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726877Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726889Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726890Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726892Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726893Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726894Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726896Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726897Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726898Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726900Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726901Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726902Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726904Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726905Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726965Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726967Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726968Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726970Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726971Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726972Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726974Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726975Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726977Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726979Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726981Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726982Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726984Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726986Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726987Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726988Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726990Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726991Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726993Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726994Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726996Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726997Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726998Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342726999Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727001Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727002Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727004Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727005Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727006Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727007Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727009Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727010Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727014Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727015Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727017Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727020Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727021Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727022Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727024Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727025Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727026Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727028Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727029Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727030Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727031Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727033Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727064Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727067Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727101Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727102Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727104Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727107Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727108Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727120Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727121Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1342727123Didn'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, '2655793') ('4234', '21243455', '1342514379', None, None, None, None, None, '2655793') ('4234', None, None, None, None, None, None, None, '2655793') ('4234', '21243455', '1342512313', None, None, None, None, None, '2655793') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 743 time used for this insertion : 0.05109882354736328 save_final save missing photos in datou_result : time spend for datou_step_exec : 88.05030298233032 time spend to save output : 0.06100153923034668 total time spend for step 5 : 88.11130452156067 step6:thcl Tue Mar 11 00:22:55 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 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 : 0.022907018661499023 time to convert the images to numpy array : 0.07768702507019043 time to import caffe and check if the image exist : 0.023651123046875 time to convert the images to numpy array : 0.07942652702331543 time to import caffe and check if the image exist : 0.025218486785888672 time to convert the images to numpy array : 0.07899284362792969 time to import caffe and check if the image exist : 0.03842663764953613 time to convert the images to numpy array : 0.06817245483398438 time to import caffe and check if the image exist : 0.02831578254699707 time to convert the images to numpy array : 0.07920408248901367 time to import caffe and check if the image exist : 0.020796537399291992 time to convert the images to numpy array : 0.0891716480255127 time to import caffe and check if the image exist : 0.043570518493652344 time to convert the images to numpy array : 0.07164382934570312 time to import caffe and check if the image exist : 0.031736135482788086 time to convert the images to numpy array : 0.08377933502197266 time to import caffe and check if the image exist : 0.014209508895874023 time to convert the images to numpy array : 0.1014556884765625 time to import caffe and check if the image exist : 0.02938985824584961 time to convert the images to numpy array : 0.08985638618469238 total time to convert the images to numpy array : 0.6869843006134033 list photo_ids error: [] list photo_ids correct : [1342726835, 1342726836, 1342726837, 1342726838, 1342726839, 1342726840, 1342726841, 1342726842, 1342726843, 1342726844, 1342726845, 1342726846, 1342726847, 1342726848, 1342726849, 1342726850, 1342726851, 1342726852, 1342726854, 1342726856, 1342726857, 1342726859, 1342726860, 1342726861, 1342726863, 1342726721, 1342726722, 1342726723, 1342726724, 1342726725, 1342726726, 1342726727, 1342726728, 1342726729, 1342726730, 1342726732, 1342726733, 1342726734, 1342726735, 1342726736, 1342726738, 1342726739, 1342726740, 1342726741, 1342726742, 1342726743, 1342726745, 1342726746, 1342726747, 1342726748, 1342726970, 1342726971, 1342726972, 1342726974, 1342726975, 1342726977, 1342726979, 1342726981, 1342726982, 1342726984, 1342726986, 1342726987, 1342726988, 1342726990, 1342726991, 1342726993, 1342726994, 1342726996, 1342726997, 1342726998, 1342726999, 1342727001, 1342727002, 1342727004, 1342727005, 1342726781, 1342726782, 1342726783, 1342726784, 1342726785, 1342726786, 1342726787, 1342726788, 1342726789, 1342726790, 1342726791, 1342726792, 1342726793, 1342726794, 1342726795, 1342726796, 1342726797, 1342726798, 1342726799, 1342726802, 1342726803, 1342726804, 1342726805, 1342726806, 1342726807, 1342726749, 1342726750, 1342726751, 1342726752, 1342726753, 1342726754, 1342726755, 1342726756, 1342726757, 1342726758, 1342726759, 1342726760, 1342726761, 1342726762, 1342726763, 1342726764, 1342726765, 1342726766, 1342726768, 1342726769, 1342726770, 1342726772, 1342726778, 1342726779, 1342726780, 1342726692, 1342726694, 1342726695, 1342726696, 1342726698, 1342726699, 1342726700, 1342726702, 1342726703, 1342726704, 1342726705, 1342726706, 1342726707, 1342726708, 1342726710, 1342726711, 1342726712, 1342726713, 1342726714, 1342726715, 1342726716, 1342726717, 1342726718, 1342726719, 1342726720, 1342726808, 1342726809, 1342726810, 1342726811, 1342726812, 1342726813, 1342726814, 1342726816, 1342726818, 1342726819, 1342726820, 1342726821, 1342726822, 1342726823, 1342726824, 1342726825, 1342726826, 1342726827, 1342726828, 1342726829, 1342726830, 1342726831, 1342726832, 1342726833, 1342726834, 1342726864, 1342726865, 1342726867, 1342726868, 1342726869, 1342726871, 1342726872, 1342726875, 1342726877, 1342726889, 1342726890, 1342726892, 1342726893, 1342726894, 1342726896, 1342726897, 1342726898, 1342726900, 1342726901, 1342726902, 1342726904, 1342726905, 1342726965, 1342726967, 1342726968, 1342727071, 1342727073, 1342727074, 1342727076, 1342727077, 1342727078, 1342727080, 1342727081, 1342727083, 1342727084, 1342727085, 1342727087, 1342727088, 1342727101, 1342727102, 1342727104, 1342727107, 1342727108, 1342727109, 1342727120, 1342727121, 1342727123, 1342727006, 1342727007, 1342727009, 1342727010, 1342727014, 1342727015, 1342727017, 1342727020, 1342727021, 1342727022, 1342727024, 1342727025, 1342727026, 1342727028, 1342727029, 1342727030, 1342727031, 1342727033, 1342727039, 1342727040, 1342727059, 1342727062, 1342727064, 1342727067, 1342727069] number of photos to traite : 247 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 havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 962 wait 20 seconds l 3637 free memory gpu now : 962 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 : 3736 max_wait_temp : 1 max_wait : 0 dict_keys(['prob', 'pool5']) time used to do the prepocess of the images : 1.2643909454345703 time used to do the prediction : 1.0485491752624512 save descriptor for thcl : 3237 time to traite the descriptors : 1.6193585395812988 Catched exception ! Connect or reconnect ! storage_type for insertDescriptorsMulti : 3 To insert : 1342726835 To insert : 1342726836 To insert : 1342726837 To insert : 1342726838 To insert : 1342726839 To insert : 1342726840 To insert : 1342726841 To insert : 1342726842 To insert : 1342726843 To insert : 1342726844 To insert : 1342726845 To insert : 1342726846 To insert : 1342726847 To insert : 1342726848 To insert : 1342726849 To insert : 1342726850 To insert : 1342726851 To insert : 1342726852 To insert : 1342726854 To insert : 1342726856 To insert : 1342726857 To insert : 1342726859 To insert : 1342726860 To insert : 1342726861 To insert : 1342726863 To insert : 1342726721 To insert : 1342726722 To insert : 1342726723 To insert : 1342726724 To insert : 1342726725 To insert : 1342726726 To insert : 1342726727 To insert : 1342726728 To insert : 1342726729 To insert : 1342726730 To insert : 1342726732 To insert : 1342726733 To insert : 1342726734 To insert : 1342726735 To insert : 1342726736 To insert : 1342726738 To insert : 1342726739 To insert : 1342726740 To insert : 1342726741 To insert : 1342726742 To insert : 1342726743 To insert : 1342726745 To insert : 1342726746 To insert : 1342726747 To insert : 1342726748 To insert : 1342726970 To insert : 1342726971 To insert : 1342726972 To insert : 1342726974 To insert : 1342726975 To insert : 1342726977 To insert : 1342726979 To insert : 1342726981 To insert : 1342726982 To insert : 1342726984 To insert : 1342726986 To insert : 1342726987 To insert : 1342726988 To insert : 1342726990 To insert : 1342726991 To insert : 1342726993 To insert : 1342726994 To insert : 1342726996 To insert : 1342726997 To insert : 1342726998 To insert : 1342726999 To insert : 1342727001 To insert : 1342727002 To insert : 1342727004 To insert : 1342727005 To insert : 1342726781 To insert : 1342726782 To insert : 1342726783 To insert : 1342726784 To insert : 1342726785 To insert : 1342726786 To insert : 1342726787 To insert : 1342726788 To insert : 1342726789 To insert : 1342726790 To insert : 1342726791 To insert : 1342726792 To insert : 1342726793 To insert : 1342726794 To insert : 1342726795 To insert : 1342726796 To insert : 1342726797 To insert : 1342726798 To insert : 1342726799 To insert : 1342726802 To insert : 1342726803 To insert : 1342726804 To insert : 1342726805 To insert : 1342726806 To insert : 1342726807 To insert : 1342726749 To insert : 1342726750 To insert : 1342726751 To insert : 1342726752 To insert : 1342726753 To insert : 1342726754 To insert : 1342726755 To insert : 1342726756 To insert : 1342726757 To insert : 1342726758 To insert : 1342726759 To insert : 1342726760 To insert : 1342726761 To insert : 1342726762 To insert : 1342726763 To insert : 1342726764 To insert : 1342726765 To insert : 1342726766 To insert : 1342726768 To insert : 1342726769 To insert : 1342726770 To insert : 1342726772 To insert : 1342726778 To insert : 1342726779 To insert : 1342726780 To insert : 1342726692 To insert : 1342726694 To insert : 1342726695 To insert : 1342726696 To insert : 1342726698 To insert : 1342726699 To insert : 1342726700 To insert : 1342726702 To insert : 1342726703 To insert : 1342726704 To insert : 1342726705 To insert : 1342726706 To insert : 1342726707 To insert : 1342726708 To insert : 1342726710 To insert : 1342726711 To insert : 1342726712 To insert : 1342726713 To insert : 1342726714 To insert : 1342726715 To insert : 1342726716 To insert : 1342726717 To insert : 1342726718 To insert : 1342726719 To insert : 1342726720 To insert : 1342726808 To insert : 1342726809 To insert : 1342726810 To insert : 1342726811 To insert : 1342726812 To insert : 1342726813 To insert : 1342726814 To insert : 1342726816 To insert : 1342726818 To insert : 1342726819 To insert : 1342726820 To insert : 1342726821 To insert : 1342726822 To insert : 1342726823 To insert : 1342726824 To insert : 1342726825 To insert : 1342726826 To insert : 1342726827 To insert : 1342726828 To insert : 1342726829 To insert : 1342726830 To insert : 1342726831 To insert : 1342726832 To insert : 1342726833 To insert : 1342726834 To insert : 1342726864 To insert : 1342726865 To insert : 1342726867 To insert : 1342726868 To insert : 1342726869 To insert : 1342726871 To insert : 1342726872 To insert : 1342726875 To insert : 1342726877 To insert : 1342726889 To insert : 1342726890 To insert : 1342726892 To insert : 1342726893 To insert : 1342726894 To insert : 1342726896 To insert : 1342726897 To insert : 1342726898 To insert : 1342726900 To insert : 1342726901 To insert : 1342726902 To insert : 1342726904 To insert : 1342726905 To insert : 1342726965 To insert : 1342726967 To insert : 1342726968 To insert : 1342727071 To insert : 1342727073 To insert : 1342727074 To insert : 1342727076 To insert : 1342727077 To insert : 1342727078 To insert : 1342727080 To insert : 1342727081 To insert : 1342727083 To insert : 1342727084 To insert : 1342727085 To insert : 1342727087 To insert : 1342727088 To insert : 1342727101 To insert : 1342727102 To insert : 1342727104 To insert : 1342727107 To insert : 1342727108 To insert : 1342727109 To insert : 1342727120 To insert : 1342727121 To insert : 1342727123 To insert : 1342727006 To insert : 1342727007 To insert : 1342727009 To insert : 1342727010 To insert : 1342727014 To insert : 1342727015 To insert : 1342727017 To insert : 1342727020 To insert : 1342727021 To insert : 1342727022 To insert : 1342727024 To insert : 1342727025 To insert : 1342727026 To insert : 1342727028 To insert : 1342727029 To insert : 1342727030 To insert : 1342727031 To insert : 1342727033 To insert : 1342727039 To insert : 1342727040 To insert : 1342727059 To insert : 1342727062 To insert : 1342727064 To insert : 1342727067 To insert : 1342727069 time to insert the descriptors : 49.659335136413574 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 : 378 time used for this insertion : 0.03334212303161621 save missing photos in datou_result : time spend for datou_step_exec : 83.01230716705322 time spend to save output : 0.09719538688659668 total time spend for step 6 : 83.10950255393982 step7:ventilate_hashtags_in_portfolio Tue Mar 11 00:24:18 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 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 : 21243455 get user id for portfolio 21243455 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`=21243455 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','pet_clair','PET_clair','PET_fonce','Papier','Tetrapak','metal','environnement','Film_plastique','papier','refus','pehd','pet_fonce','flou','mal_croppe','PEHD','autre','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`=21243455 AND mptpi.`type`=4230 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','pet_clair','PET_clair','PET_fonce','Papier','Tetrapak','metal','environnement','Film_plastique','papier','refus','pehd','pet_fonce','flou','mal_croppe','PEHD','autre','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`=21243455 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','pet_clair','PET_clair','PET_fonce','Papier','Tetrapak','metal','environnement','Film_plastique','papier','refus','pehd','pet_fonce','flou','mal_croppe','PEHD','autre','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`=21243455 AND mptpi.`type`=4231 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('Carton','pet_clair','PET_clair','PET_fonce','Papier','Tetrapak','metal','environnement','Film_plastique','papier','refus','pehd','pet_fonce','flou','mal_croppe','PEHD','autre','carton')) AND mptpi.`min_score`=0.6 To do lien utilise dans velours : https://www.fotonower.com/velours/21247636,21247621,21247631,21247628,21247624,21247625,21247626,21247627,21247629,21247634,21247632,21247633,21247635?tags=carton,pet_clair,pet_fonce,papier,tetrapak,metal,environnement,film_plastique,refus,pehd,flou,mal_croppe,autre&datou_id_consolidate=4235&port_consolidate=21243455 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1342514379, 1342512313] Looping around the photos to save general results len do output : 1 /21243455. 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, '2655793') ('4234', '21243455', '1342514379', None, None, None, None, None, '2655793') ('4234', None, None, None, None, None, None, None, '2655793') ('4234', '21243455', '1342512313', None, None, None, None, None, '2655793') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.013071775436401367 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.846856117248535 time spend to save output : 0.013421058654785156 total time spend for step 7 : 2.8602771759033203 step8:final Tue Mar 11 00:24:21 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 : {1342514379: ('0.7716717011385036',), 1342512313: ('0.7716717011385036',)} new output for save of step final : {1342514379: ('0.7716717011385036',), 1342512313: ('0.7716717011385036',)} [1342514379, 1342512313] Looping around the photos to save general results len do output : 2 /1342514379.Didn't retrieve data . /1342512313.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, '2655793') ('4234', '21243455', '1342514379', None, None, None, None, None, '2655793') ('4234', None, None, None, None, None, None, None, '2655793') ('4234', '21243455', '1342512313', None, None, None, None, None, '2655793') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.015546083450317383 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11759233474731445 time spend to save output : 0.0159149169921875 total time spend for step 8 : 0.13350725173950195 step9:velours_tree Tue Mar 11 00:24:21 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 : 21247636,21247621,21247631,21247628,21247624,21247625,21247626,21247627,21247629,21247634,21247632,21247633,21247635 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=21247636 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=21247621 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=21247631 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=21247628 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=21247624 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=21247625 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=21247626 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=21247627 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=21247629 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=21247634 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=21247632 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=21247633 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=21247635 ORDER BY ph.size desc - Loading descriptors... Size : 2048 len(descriptors) : 247 Compute structured hierarchical clustering... ward : AgglomerativeClustering(n_clusters=6) ward.labels_ : [0 2 4 5 1 3 0 4 5 2 0 0 0 0 0 2 4 1 3 1 1 4 4 3 1 4 4 3 4 0 4 3 4 5 2 3 5 3 3 5 3 3 4 0 4 3 3 2 5 5 4 1 3 1 1 0 0 1 4 0 2 1 1 4 2 1 4 4 1 1 1 2 1 4 3 1 2 2 2 2 4 4 1 1 2 4 0 1 1 4 0 0 5 5 4 3 1 4 1 2 0 4 1 4 2 0 0 3 4 2 0 1 4 5 1 2 5 5 1 1 2 2 0 2 1 1 0 2 2 3 2 2 3 2 3 2 2 2 2 2 3 0 5 2 2 2 5 0 2 2 2 3 4 1 5 1 0 4 4 2 3 1 1 1 4 1 4 2 2 2 4 1 0 0 3 5 4 1 3 1 0 0 5 5 1 4 4 4 3 4 5 4 1 4 5 4 4 2 5 1 0 0 4 4 4 4 1 0 5 3 2 3 2 0 4 2 4 4 3 4 3 0 3 3 5 3 3 0 3 4 0 5 3 2 0 2 5 1 5 4 4 2 5 3 1 1 5] Elapsed time: 0.04478573799133301 graph_id used : 82572 - Beta version, working pretty good on 11-5-16 ! https://www.fotonower.com/velours/21247636,21247621,21247631,21247628,21247624,21247625,21247626,21247627,21247629,21247634,21247632,21247633,21247635?tags=carton,pet_clair,pet_fonce,papier,tetrapak,metal,environnement,film_plastique,refus,pehd,flou,mal_croppe,autre&datou_id_consolidate=4235&port_consolidate=21243455&tree_id=82572 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : velours_tree we use saveGeneral [1342514379, 1342512313] Looping around the photos to save general results len do output : 1 /21243455Didn'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, '2655793') ('4234', '21243455', '1342514379', None, None, None, None, None, '2655793') ('4234', None, None, None, None, None, None, None, '2655793') ('4234', '21243455', '1342512313', None, None, None, None, None, '2655793') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.012894392013549805 save_final save missing photos in datou_result : time spend for datou_step_exec : 19.58070206642151 time spend to save output : 0.01318812370300293 total time spend for step 9 : 19.59389019012451 step10:send_mail_cod Tue Mar 11 00:24:41 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_P21243455_11-03-2025_00_24_41.pdf 21247618 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 .imagette212476181741649081 21247603 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 .imagette212476031741649082 21247613 imagette212476131741649083 21247610 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 .imagette212476101741649083 21247606 imagette212476061741649084 21247607 change filename to text .change filename to text .imagette212476071741649084 21247609 imagette212476091741649084 21247611 imagette212476111741649084 21247616 change filename to text .change filename to text .change filename to text .imagette212476161741649084 21247614 imagette212476141741649084 21247615 imagette212476151741649084 21247617 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette212476171741649084 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=21243455 and hashtag_type = 4230 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/21247636,21247621,21247631,21247628,21247624,21247625,21247626,21247627,21247629,21247634,21247632,21247633,21247635?tags=carton,pet_clair,pet_fonce,papier,tetrapak,metal,environnement,film_plastique,refus,pehd,flou,mal_croppe,autre&datou_id_consolidate=4235&port_consolidate=21243455&tree_id=82572 your option no_mail is active, we will not send the real mail to your client args[1342514379] : ((1342514379, -7.402684628166873, 492609224), (1342514379, -0.1974187579877037, 496442774), '0.7716717011385036') We are sending mail with results at cod@fotonower.com args[1342512313] : ((1342512313, -7.1250300533835045, 492609224), (1342512313, -0.11518730982442611, 496442774), '0.7716717011385036') We are sending mail with results at cod@fotonower.com refus_total : 0.7716717011385036 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=21243455 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_P21243455_11-03-2025_00_24_41.pdf results_Qualipapia_P21243455_11-03-2025_00_24_41.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243455_11-03-2025_00_24_41.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','21243455','results_Qualipapia_P21243455_11-03-2025_00_24_41.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243455_11-03-2025_00_24_41.pdf','pdf','','0.17','0.7716717011385036') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1342514379, 1342512313] 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, '2655793') ('4234', '21243455', '1342514379', None, None, None, None, None, '2655793') ('4234', None, None, None, None, None, None, None, '2655793') ('4234', '21243455', '1342512313', None, None, None, None, None, '2655793') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.015527009963989258 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.345070838928223 time spend to save output : 0.015688180923461914 total time spend for step 10 : 4.360759019851685 step11:split_time_score Tue Mar 11 00:24:45 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'}] (('20', 2),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 10032025 21243455 Nombre de photos uploadées : 2 / 23040 (0%) 10032025 21243455 Nombre de photos taguées (types de déchets): 0 / 2 (0%) 10032025 21243455 Nombre de photos taguées (volume) : 0 / 2 (0%) elapsed_time : load_data_split_time_score 1.1920928955078125e-06 elapsed_time : order_list_meta_photo_and_scores 4.291534423828125e-06 ?? elapsed_time : fill_and_build_computed_from_old_data 0.00018477439880371094 elapsed_time : insert_dashboard_record_day_entry 0.036787986755371094 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 = 21243437 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243440 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243446 order by id desc limit 1 find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243449 order by id desc limit 1 Qualite : 0.8429208326903239 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243452_11-03-2025_00_20_09.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243452 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`=21243452 AND mptpi.`type`=4230 To do Qualite : 0.7716717011385036 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243455_11-03-2025_00_24_41.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243455 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`=21243455 AND mptpi.`type`=4230 To do Qualite : 0.8930035530045851 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243458_11-03-2025_00_06_34.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243458 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`=21243458 AND mptpi.`type`=4230 To do Qualite : 0.8341587099615034 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243459_10-03-2025_23_51_05.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243459 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`=21243459 AND mptpi.`type`=4230 To do Qualite : 0.9140326395495195 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243460_10-03-2025_23_32_07.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243460 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`=21243460 AND mptpi.`type`=4230 To do Qualite : 0.8494835661184195 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243461_10-03-2025_23_26_04.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243461 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`=21243461 AND mptpi.`type`=4230 To do Qualite : 0.8518894673447112 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243468_10-03-2025_23_03_51.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243468 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`=21243468 AND mptpi.`type`=4230 To do Qualite : 0.7783484577832867 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243479_10-03-2025_23_21_44.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243479 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`=21243479 AND mptpi.`type`=4230 To do Qualite : 0.6915284925830978 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243480_10-03-2025_22_51_22.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243480 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`=21243480 AND mptpi.`type`=4230 To do Qualite : 0.7890446659000176 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243481_10-03-2025_22_40_16.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243481 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`=21243481 AND mptpi.`type`=4230 To do Qualite : 0.7725544308014027 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243482_10-03-2025_22_23_21.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243482 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`=21243482 AND mptpi.`type`=4230 To do Qualite : 0.8419982158060035 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243483_10-03-2025_22_21_53.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243483 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`=21243483 AND mptpi.`type`=4230 To do Qualite : 0.8529070030224067 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243484_10-03-2025_21_59_01.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243484 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`=21243484 AND mptpi.`type`=4230 To do Qualite : 0.8959614648624126 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21243485_10-03-2025_22_03_09.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21243485 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`=21243485 AND mptpi.`type`=4230 To do Qualite : 0.8246766881022759 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Qualipapia_P21245843_10-03-2025_22_59_27.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 21245843 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`=21245843 AND mptpi.`type`=4230 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'10032025': {'nb_upload': 2, 'nb_taggue_class': 0, 'nb_taggue_densite': 0}} Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1342514379, 1342512313] Looping around the photos to save general results len do output : 1 /21243455Didn'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, '2655793') ('4234', '21243455', '1342514379', None, None, None, None, None, '2655793') ('4234', None, None, None, None, None, None, None, '2655793') ('4234', '21243455', '1342512313', None, None, None, None, None, '2655793') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.014602422714233398 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.38990044593811 time spend to save output : 0.014844655990600586 total time spend for step 11 : 4.404745101928711 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 55.78user 36.21system 4:24.21elapsed 34%CPU (0avgtext+0avgdata 4035768maxresident)k 1126328inputs+22072outputs (11020major+4387604minor)pagefaults 0swaps