python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 8 -a ' -a 4741 -l 30 ' -s datou_current_4741 -M 0 -S 0 -U 95,95,120 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 : 3909701 load datou : 4741 # 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( 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 ? [(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 ? 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 : (5732, 'mask_refus_amiens_050123', 16384, 25088, 'mask_refus_amiens_050123', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 1, 5, 13, 23, 59), datetime.datetime(2023, 1, 5, 13, 23, 59)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) load thcls load THCL from format json or kwargs add thcl : 3453 in CacheModelConfig load THCL from format json or kwargs add thcl : 3783 in CacheModelConfig load pdts add pdt : 5732 in CacheModelConfig add pdt : 5972 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 : 4741, datou_cur_ids : ['3623813'] with mtr_portfolio_ids : ['26291504'] and first list_photo_ids : [] new path : /proc/3909701/ 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, mask_detect, blur_detection, brightness, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 4 ; length of list_pids : 4 ; length of list_args : 4 time to download the photos : 0.8838274478912354 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 Thu Aug 28 15:21:28 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 6602 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 15:21:31.444705: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-08-28 15:21:31.472602: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 15:21:31.474512: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa7bc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:21:31.474535: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 15:21:31.477680: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 15:21:31.632265: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2229ca60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:21:31.632320: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 15:21:31.633378: 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 2025-08-28 15:21:31.633817: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:21:31.636877: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:21:31.643033: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:21:31.643432: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:21:31.646255: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:21:31.647566: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:21:31.652999: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:21:31.654269: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:21:31.654347: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:21:31.654990: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:21:31.655005: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:21:31.655014: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:21:31.656097: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6063 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. 2025-08-28 15:21:31.953411: 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 2025-08-28 15:21:31.953499: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:21:31.953517: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:21:31.953533: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:21:31.953547: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:21:31.953562: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:21:31.953577: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:21:31.953592: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:21:31.954651: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:21:31.955751: 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 2025-08-28 15:21:31.955801: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:21:31.955817: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:21:31.955832: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:21:31.955858: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:21:31.955873: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:21:31.955887: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:21:31.955901: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:21:31.956963: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:21:31.956993: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:21:31.957003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:21:31.957011: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:21:31.958104: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6063 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 : thcl3783 thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) {'thcl': {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'], 'list_hashtags_csv': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'svm_hashtag_type_desc': 5972, 'photo_desc_type': 5972, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', '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_entrant_syctomXV_111023 NUM_CLASSES 11 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_entrant_syctomXV_111023 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-08-28 15:21:42.596327: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:21:42.809362: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_entrant_syctomXV_111023 /data/models_weight/learn_entrant_syctomXV_111023/mask_model.h5 size_local : 256052544 size in s3 : 256052544 create time local : 2023-10-26 16:36:43 create time in s3 : 2023-10-11 13:57:17 mask_model.h5 already exist and didn't need to update list_images length : 4 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 19 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 28 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 29 NEW PHOTO Processing 1 images image shape: (3120, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 3120.00000 nb d'objets trouves : 6 Detection mask done ! Trying to reset tf kernel 3910019 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 1534 tf kernel not reseted sub process len(results) : 4 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 4 len(list_Values) 0 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 : 6823 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl3783 Catched exception ! Connect or reconnect ! thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'] time for calcul the mask position with numpy : 0.0011577606201171875 nb_pixel_total : 51851 time to create 1 rle with old method : 0.05853009223937988 length of segment : 375 time for calcul the mask position with numpy : 0.004292964935302734 nb_pixel_total : 226987 time to create 1 rle with new method : 0.008110523223876953 length of segment : 497 time for calcul the mask position with numpy : 0.0006644725799560547 nb_pixel_total : 40935 time to create 1 rle with old method : 0.04773139953613281 length of segment : 271 time for calcul the mask position with numpy : 0.0008914470672607422 nb_pixel_total : 58966 time to create 1 rle with old method : 0.06541085243225098 length of segment : 247 time for calcul the mask position with numpy : 0.0006082057952880859 nb_pixel_total : 37696 time to create 1 rle with old method : 0.04295849800109863 length of segment : 211 time for calcul the mask position with numpy : 0.0005083084106445312 nb_pixel_total : 36183 time to create 1 rle with old method : 0.04318380355834961 length of segment : 202 time for calcul the mask position with numpy : 0.0008220672607421875 nb_pixel_total : 55126 time to create 1 rle with old method : 0.0635678768157959 length of segment : 368 time for calcul the mask position with numpy : 0.0013468265533447266 nb_pixel_total : 95405 time to create 1 rle with old method : 0.11127066612243652 length of segment : 320 time for calcul the mask position with numpy : 0.0003936290740966797 nb_pixel_total : 18287 time to create 1 rle with old method : 0.02239370346069336 length of segment : 160 time for calcul the mask position with numpy : 0.4238581657409668 nb_pixel_total : 838908 time to create 1 rle with new method : 0.06338262557983398 length of segment : 1114 time for calcul the mask position with numpy : 0.0004119873046875 nb_pixel_total : 16511 time to create 1 rle with old method : 0.024233579635620117 length of segment : 193 time for calcul the mask position with numpy : 0.00034332275390625 nb_pixel_total : 18573 time to create 1 rle with old method : 0.021871328353881836 length of segment : 256 time for calcul the mask position with numpy : 0.00048279762268066406 nb_pixel_total : 20938 time to create 1 rle with old method : 0.025396108627319336 length of segment : 203 time for calcul the mask position with numpy : 0.0007402896881103516 nb_pixel_total : 18046 time to create 1 rle with old method : 0.021663427352905273 length of segment : 323 time for calcul the mask position with numpy : 0.013851404190063477 nb_pixel_total : 754756 time to create 1 rle with new method : 0.04018831253051758 length of segment : 961 time for calcul the mask position with numpy : 0.0005333423614501953 nb_pixel_total : 26218 time to create 1 rle with old method : 0.030402183532714844 length of segment : 177 time for calcul the mask position with numpy : 0.0005958080291748047 nb_pixel_total : 27685 time to create 1 rle with old method : 0.034194231033325195 length of segment : 231 time for calcul the mask position with numpy : 0.00018596649169921875 nb_pixel_total : 3077 time to create 1 rle with old method : 0.004130363464355469 length of segment : 109 time for calcul the mask position with numpy : 0.0004634857177734375 nb_pixel_total : 24958 time to create 1 rle with old method : 0.02998661994934082 length of segment : 176 time for calcul the mask position with numpy : 0.0035414695739746094 nb_pixel_total : 262046 time to create 1 rle with new method : 0.010947942733764648 length of segment : 548 time for calcul the mask position with numpy : 0.0024306774139404297 nb_pixel_total : 173174 time to create 1 rle with new method : 0.006490230560302734 length of segment : 592 time for calcul the mask position with numpy : 0.0004620552062988281 nb_pixel_total : 9848 time to create 1 rle with old method : 0.011854171752929688 length of segment : 154 time for calcul the mask position with numpy : 0.004864215850830078 nb_pixel_total : 307695 time to create 1 rle with new method : 0.012070178985595703 length of segment : 707 time for calcul the mask position with numpy : 0.0008826255798339844 nb_pixel_total : 32116 time to create 1 rle with old method : 0.047884225845336914 length of segment : 222 time for calcul the mask position with numpy : 0.0010085105895996094 nb_pixel_total : 34513 time to create 1 rle with old method : 0.04485821723937988 length of segment : 304 time for calcul the mask position with numpy : 0.004276275634765625 nb_pixel_total : 208376 time to create 1 rle with new method : 0.010948896408081055 length of segment : 630 time for calcul the mask position with numpy : 0.000965118408203125 nb_pixel_total : 55967 time to create 1 rle with old method : 0.0701298713684082 length of segment : 412 time for calcul the mask position with numpy : 0.0014879703521728516 nb_pixel_total : 78896 time to create 1 rle with old method : 0.09565567970275879 length of segment : 495 time for calcul the mask position with numpy : 0.0006978511810302734 nb_pixel_total : 34297 time to create 1 rle with old method : 0.040479183197021484 length of segment : 314 time for calcul the mask position with numpy : 0.00820016860961914 nb_pixel_total : 440271 time to create 1 rle with new method : 0.044312477111816406 length of segment : 913 time for calcul the mask position with numpy : 0.009814977645874023 nb_pixel_total : 419353 time to create 1 rle with new method : 0.1882190704345703 length of segment : 872 time for calcul the mask position with numpy : 0.000997781753540039 nb_pixel_total : 31182 time to create 1 rle with old method : 0.036132097244262695 length of segment : 195 time for calcul the mask position with numpy : 0.0013165473937988281 nb_pixel_total : 44775 time to create 1 rle with old method : 0.05181479454040527 length of segment : 278 time for calcul the mask position with numpy : 0.0014472007751464844 nb_pixel_total : 16970 time to create 1 rle with old method : 0.021120071411132812 length of segment : 305 time for calcul the mask position with numpy : 0.0013234615325927734 nb_pixel_total : 49906 time to create 1 rle with old method : 0.06991767883300781 length of segment : 231 time for calcul the mask position with numpy : 0.0020186901092529297 nb_pixel_total : 74279 time to create 1 rle with old method : 0.08550596237182617 length of segment : 309 time for calcul the mask position with numpy : 0.0022923946380615234 nb_pixel_total : 53728 time to create 1 rle with old method : 0.062139034271240234 length of segment : 482 time for calcul the mask position with numpy : 0.0003733634948730469 nb_pixel_total : 822 time to create 1 rle with old method : 0.0013294219970703125 length of segment : 82 time for calcul the mask position with numpy : 0.0010819435119628906 nb_pixel_total : 63728 time to create 1 rle with old method : 0.07263970375061035 length of segment : 399 time for calcul the mask position with numpy : 0.0010929107666015625 nb_pixel_total : 35371 time to create 1 rle with old method : 0.04310894012451172 length of segment : 286 time for calcul the mask position with numpy : 0.0024340152740478516 nb_pixel_total : 46928 time to create 1 rle with old method : 0.057973623275756836 length of segment : 478 time for calcul the mask position with numpy : 0.0005164146423339844 nb_pixel_total : 25770 time to create 1 rle with old method : 0.0317232608795166 length of segment : 196 time for calcul the mask position with numpy : 0.004344940185546875 nb_pixel_total : 197652 time to create 1 rle with new method : 0.010001182556152344 length of segment : 538 time for calcul the mask position with numpy : 0.0012469291687011719 nb_pixel_total : 44449 time to create 1 rle with old method : 0.05411076545715332 length of segment : 503 time for calcul the mask position with numpy : 0.0006189346313476562 nb_pixel_total : 36220 time to create 1 rle with old method : 0.04186248779296875 length of segment : 253 time for calcul the mask position with numpy : 0.007996797561645508 nb_pixel_total : 66925 time to create 1 rle with old method : 0.07717227935791016 length of segment : 698 time for calcul the mask position with numpy : 0.00027108192443847656 nb_pixel_total : 9249 time to create 1 rle with old method : 0.010653257369995117 length of segment : 127 time for calcul the mask position with numpy : 0.002988576889038086 nb_pixel_total : 178681 time to create 1 rle with new method : 0.006688833236694336 length of segment : 448 time for calcul the mask position with numpy : 0.002657175064086914 nb_pixel_total : 83285 time to create 1 rle with old method : 0.09606647491455078 length of segment : 325 time for calcul the mask position with numpy : 0.0009291172027587891 nb_pixel_total : 23523 time to create 1 rle with old method : 0.02901291847229004 length of segment : 184 time for calcul the mask position with numpy : 0.0007178783416748047 nb_pixel_total : 41090 time to create 1 rle with old method : 0.04785323143005371 length of segment : 220 time for calcul the mask position with numpy : 0.0009756088256835938 nb_pixel_total : 35427 time to create 1 rle with old method : 0.05253338813781738 length of segment : 289 time for calcul the mask position with numpy : 0.0022475719451904297 nb_pixel_total : 56278 time to create 1 rle with old method : 0.06984663009643555 length of segment : 412 time for calcul the mask position with numpy : 0.0006740093231201172 nb_pixel_total : 14428 time to create 1 rle with old method : 0.017412424087524414 length of segment : 179 time for calcul the mask position with numpy : 0.000621795654296875 nb_pixel_total : 21897 time to create 1 rle with old method : 0.024911165237426758 length of segment : 211 time for calcul the mask position with numpy : 0.00020647048950195312 nb_pixel_total : 9534 time to create 1 rle with old method : 0.011982440948486328 length of segment : 140 time for calcul the mask position with numpy : 0.0012059211730957031 nb_pixel_total : 52850 time to create 1 rle with old method : 0.0628049373626709 length of segment : 212 time for calcul the mask position with numpy : 0.0005841255187988281 nb_pixel_total : 22721 time to create 1 rle with old method : 0.026530981063842773 length of segment : 178 time for calcul the mask position with numpy : 0.001354217529296875 nb_pixel_total : 37382 time to create 1 rle with old method : 0.04334378242492676 length of segment : 495 time for calcul the mask position with numpy : 0.005682706832885742 nb_pixel_total : 246364 time to create 1 rle with new method : 0.01956486701965332 length of segment : 547 time for calcul the mask position with numpy : 0.0007407665252685547 nb_pixel_total : 27787 time to create 1 rle with old method : 0.03250384330749512 length of segment : 195 time for calcul the mask position with numpy : 0.0006201267242431641 nb_pixel_total : 20337 time to create 1 rle with old method : 0.02283453941345215 length of segment : 221 time for calcul the mask position with numpy : 0.0003333091735839844 nb_pixel_total : 12810 time to create 1 rle with old method : 0.015170812606811523 length of segment : 205 time for calcul the mask position with numpy : 0.0007448196411132812 nb_pixel_total : 40239 time to create 1 rle with old method : 0.04605698585510254 length of segment : 509 time for calcul the mask position with numpy : 0.0012497901916503906 nb_pixel_total : 48581 time to create 1 rle with old method : 0.057270050048828125 length of segment : 254 time for calcul the mask position with numpy : 0.0020096302032470703 nb_pixel_total : 102506 time to create 1 rle with old method : 0.13841509819030762 length of segment : 434 time for calcul the mask position with numpy : 0.0005846023559570312 nb_pixel_total : 25503 time to create 1 rle with old method : 0.030230283737182617 length of segment : 348 time for calcul the mask position with numpy : 0.0010409355163574219 nb_pixel_total : 62848 time to create 1 rle with old method : 0.07419919967651367 length of segment : 431 time for calcul the mask position with numpy : 0.0024805068969726562 nb_pixel_total : 113001 time to create 1 rle with old method : 0.12929463386535645 length of segment : 336 time for calcul the mask position with numpy : 0.007679939270019531 nb_pixel_total : 232175 time to create 1 rle with new method : 0.039960384368896484 length of segment : 786 time for calcul the mask position with numpy : 0.0001246929168701172 nb_pixel_total : 2632 time to create 1 rle with old method : 0.0033037662506103516 length of segment : 61 time for calcul the mask position with numpy : 0.0003199577331542969 nb_pixel_total : 12646 time to create 1 rle with old method : 0.014524459838867188 length of segment : 204 time for calcul the mask position with numpy : 0.00034046173095703125 nb_pixel_total : 17364 time to create 1 rle with old method : 0.020481348037719727 length of segment : 102 time for calcul the mask position with numpy : 0.0002796649932861328 nb_pixel_total : 11210 time to create 1 rle with old method : 0.013666391372680664 length of segment : 154 time for calcul the mask position with numpy : 0.00019550323486328125 nb_pixel_total : 3403 time to create 1 rle with old method : 0.0041120052337646484 length of segment : 125 time for calcul the mask position with numpy : 0.004559993743896484 nb_pixel_total : 280024 time to create 1 rle with new method : 0.024205923080444336 length of segment : 457 time for calcul the mask position with numpy : 0.2076122760772705 nb_pixel_total : 4017797 time to create 1 rle with new method : 0.4607269763946533 length of segment : 2948 time for calcul the mask position with numpy : 0.0014424324035644531 nb_pixel_total : 95073 time to create 1 rle with old method : 0.12164616584777832 length of segment : 165 time for calcul the mask position with numpy : 0.020000219345092773 nb_pixel_total : 1141445 time to create 1 rle with new method : 0.22259974479675293 length of segment : 2354 time for calcul the mask position with numpy : 0.013179779052734375 nb_pixel_total : 1013563 time to create 1 rle with new method : 0.07087063789367676 length of segment : 575 time for calcul the mask position with numpy : 0.01335453987121582 nb_pixel_total : 462991 time to create 1 rle with new method : 0.04958963394165039 length of segment : 789 time for calcul the mask position with numpy : 0.017644166946411133 nb_pixel_total : 723380 time to create 1 rle with new method : 0.2995162010192871 length of segment : 801 time spent for convertir_results : 13.022053718566895 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 82 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 46.6655969619751 time spend to save output : 0.10888671875 total time spend for step 1 : 46.7744836807251 step2:mask_detect Thu Aug 28 15:22:15 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 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 : 6823 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-08-28 15:22:18.269379: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-08-28 15:22:18.296638: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-08-28 15:22:18.298474: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa7b8000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:22:18.298526: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-08-28 15:22:18.301821: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-08-28 15:22:18.475756: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x23901840 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-08-28 15:22:18.475808: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-08-28 15:22:18.476894: 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 2025-08-28 15:22:18.477280: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:22:18.480589: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:22:18.483448: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:22:18.484181: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:22:18.487101: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:22:18.488545: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:22:18.494629: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:22:18.495931: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:22:18.496033: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:22:18.496765: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:22:18.496783: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:22:18.496792: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:22:18.498005: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6271 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. 2025-08-28 15:22:18.627518: 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 2025-08-28 15:22:18.627596: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:22:18.627615: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:22:18.627633: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:22:18.627649: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:22:18.627666: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:22:18.627682: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:22:18.627698: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:22:18.628790: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:22:18.629774: 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 2025-08-28 15:22:18.629806: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-08-28 15:22:18.629823: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:22:18.629839: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-08-28 15:22:18.629855: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-08-28 15:22:18.629870: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-08-28 15:22:18.629886: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-08-28 15:22:18.629902: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-08-28 15:22:18.631194: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-08-28 15:22:18.631223: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-08-28 15:22:18.631232: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-08-28 15:22:18.631248: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-08-28 15:22:18.632376: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6271 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 : thcl3453 thcls : [{'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', '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': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', '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': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5732 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5732, 'mask_refus_amiens_050123', 16384, 25088, 'mask_refus_amiens_050123', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 1, 5, 13, 23, 59), datetime.datetime(2023, 1, 5, 13, 23, 59)) {'thcl': {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', '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': 4485, 'photo_desc_type': 5732, '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': 4485, 'svm_hashtag_type_desc': 5732, 'photo_desc_type': 5732, '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 mask_refus_amiens_050123 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 : mask_refus_amiens_050123 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-08-28 15:22:28.851806: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-08-28 15:22:29.030000: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/mask_refus_amiens_050123 /data/models_weight/mask_refus_amiens_050123/mask_model.h5 size_local : 256009536 size in s3 : 256009536 create time local : 2023-01-05 13:44:07 create time in s3 : 2023-01-05 12:23:52 mask_model.h5 already exist and didn't need to update list_images length : 4 NEW PHOTO Processing 1 images image shape: (3120, 3120, 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: 3120.00000 nb d'objets trouves : 63 NEW PHOTO Processing 1 images image shape: (3120, 3120, 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: 3120.00000 nb d'objets trouves : 63 NEW PHOTO Processing 1 images image shape: (3120, 3120, 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: 3120.00000 nb d'objets trouves : 80 NEW PHOTO Processing 1 images image shape: (3120, 3120, 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: 3120.00000 nb d'objets trouves : 3 Detection mask done ! Trying to reset tf kernel 3911858 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5311 tf kernel not reseted sub process len(results) : 4 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 4 len(list_Values) 0 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 : 7217 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl3453 Catched exception ! Connect or reconnect ! thcls : [{'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', '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': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'}] thcl {'id': 3453, 'mtr_user_id': 31, 'name': 'mask_refus_amiens_050123', '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': 4485, 'photo_desc_type': 5732, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5732 ['background', 'papier', 'carton', 'metal', 'pet_clair', 'autre', 'pehd', 'pet_fonce', 'environnement'] time for calcul the mask position with numpy : 0.0018150806427001953 nb_pixel_total : 43948 time to create 1 rle with old method : 0.0554499626159668 length of segment : 219 time for calcul the mask position with numpy : 0.012131690979003906 nb_pixel_total : 552463 time to create 1 rle with new method : 0.04280495643615723 length of segment : 987 time for calcul the mask position with numpy : 0.0020406246185302734 nb_pixel_total : 86011 time to create 1 rle with old method : 0.12350201606750488 length of segment : 527 time for calcul the mask position with numpy : 0.002504587173461914 nb_pixel_total : 60958 time to create 1 rle with old method : 0.08180522918701172 length of segment : 322 time for calcul the mask position with numpy : 0.0003902912139892578 nb_pixel_total : 15066 time to create 1 rle with old method : 0.02015972137451172 length of segment : 172 time for calcul the mask position with numpy : 0.0010695457458496094 nb_pixel_total : 38481 time to create 1 rle with old method : 0.051828861236572266 length of segment : 212 time for calcul the mask position with numpy : 0.0005414485931396484 nb_pixel_total : 23125 time to create 1 rle with old method : 0.030962467193603516 length of segment : 180 time for calcul the mask position with numpy : 0.0223846435546875 nb_pixel_total : 880676 time to create 1 rle with new method : 0.22648906707763672 length of segment : 1224 time for calcul the mask position with numpy : 0.016318082809448242 nb_pixel_total : 653451 time to create 1 rle with new method : 1.1304020881652832 length of segment : 1176 time for calcul the mask position with numpy : 0.0004706382751464844 nb_pixel_total : 13660 time to create 1 rle with old method : 0.01645636558532715 length of segment : 128 time for calcul the mask position with numpy : 0.023616790771484375 nb_pixel_total : 777499 time to create 1 rle with new method : 0.12000513076782227 length of segment : 986 time for calcul the mask position with numpy : 0.0012426376342773438 nb_pixel_total : 34666 time to create 1 rle with old method : 0.04123520851135254 length of segment : 224 time for calcul the mask position with numpy : 0.001215219497680664 nb_pixel_total : 49161 time to create 1 rle with old method : 0.06271052360534668 length of segment : 214 time for calcul the mask position with numpy : 0.0037605762481689453 nb_pixel_total : 103211 time to create 1 rle with old method : 0.14330363273620605 length of segment : 573 time for calcul the mask position with numpy : 0.002794027328491211 nb_pixel_total : 133889 time to create 1 rle with old method : 0.15988445281982422 length of segment : 341 time for calcul the mask position with numpy : 0.0013461112976074219 nb_pixel_total : 54846 time to create 1 rle with old method : 0.06515216827392578 length of segment : 162 time for calcul the mask position with numpy : 0.0020635128021240234 nb_pixel_total : 68929 time to create 1 rle with old method : 0.08131957054138184 length of segment : 372 time for calcul the mask position with numpy : 0.001668691635131836 nb_pixel_total : 69214 time to create 1 rle with old method : 0.08201956748962402 length of segment : 253 time for calcul the mask position with numpy : 0.0023059844970703125 nb_pixel_total : 91160 time to create 1 rle with old method : 0.10471415519714355 length of segment : 474 time for calcul the mask position with numpy : 0.0042879581451416016 nb_pixel_total : 198786 time to create 1 rle with new method : 0.011708736419677734 length of segment : 865 time for calcul the mask position with numpy : 0.0024302005767822266 nb_pixel_total : 120598 time to create 1 rle with old method : 0.13885784149169922 length of segment : 355 time for calcul the mask position with numpy : 0.005712747573852539 nb_pixel_total : 234343 time to create 1 rle with new method : 0.015863895416259766 length of segment : 593 time for calcul the mask position with numpy : 0.001523733139038086 nb_pixel_total : 70103 time to create 1 rle with old method : 0.08201766014099121 length of segment : 338 time for calcul the mask position with numpy : 0.00034117698669433594 nb_pixel_total : 13819 time to create 1 rle with old method : 0.01649951934814453 length of segment : 264 time for calcul the mask position with numpy : 0.01583266258239746 nb_pixel_total : 887400 time to create 1 rle with new method : 0.057848215103149414 length of segment : 888 time for calcul the mask position with numpy : 0.006605386734008789 nb_pixel_total : 318506 time to create 1 rle with new method : 0.018711328506469727 length of segment : 743 time for calcul the mask position with numpy : 0.007133007049560547 nb_pixel_total : 410995 time to create 1 rle with new method : 0.018732309341430664 length of segment : 637 time for calcul the mask position with numpy : 0.0013570785522460938 nb_pixel_total : 65199 time to create 1 rle with old method : 0.07637667655944824 length of segment : 386 time for calcul the mask position with numpy : 0.0014412403106689453 nb_pixel_total : 71540 time to create 1 rle with old method : 0.08414936065673828 length of segment : 469 time for calcul the mask position with numpy : 0.0016627311706542969 nb_pixel_total : 75513 time to create 1 rle with old method : 0.09037423133850098 length of segment : 518 time for calcul the mask position with numpy : 0.004043102264404297 nb_pixel_total : 183314 time to create 1 rle with new method : 0.01077127456665039 length of segment : 484 time for calcul the mask position with numpy : 0.0031926631927490234 nb_pixel_total : 190337 time to create 1 rle with new method : 0.0077245235443115234 length of segment : 420 time for calcul the mask position with numpy : 0.015833377838134766 nb_pixel_total : 789458 time to create 1 rle with new method : 0.05575847625732422 length of segment : 1296 time for calcul the mask position with numpy : 0.003909111022949219 nb_pixel_total : 213912 time to create 1 rle with new method : 0.009733200073242188 length of segment : 453 time for calcul the mask position with numpy : 0.001413106918334961 nb_pixel_total : 69391 time to create 1 rle with old method : 0.08109021186828613 length of segment : 243 time for calcul the mask position with numpy : 0.0003058910369873047 nb_pixel_total : 11522 time to create 1 rle with old method : 0.013859748840332031 length of segment : 133 time for calcul the mask position with numpy : 0.0005176067352294922 nb_pixel_total : 26019 time to create 1 rle with old method : 0.030959129333496094 length of segment : 145 time for calcul the mask position with numpy : 0.0004432201385498047 nb_pixel_total : 24068 time to create 1 rle with old method : 0.028834104537963867 length of segment : 172 time for calcul the mask position with numpy : 0.0013697147369384766 nb_pixel_total : 53089 time to create 1 rle with old method : 0.062250375747680664 length of segment : 585 time for calcul the mask position with numpy : 0.0027871131896972656 nb_pixel_total : 83577 time to create 1 rle with old method : 0.09796667098999023 length of segment : 482 time for calcul the mask position with numpy : 0.0010464191436767578 nb_pixel_total : 44247 time to create 1 rle with old method : 0.05167698860168457 length of segment : 309 time for calcul the mask position with numpy : 0.003110647201538086 nb_pixel_total : 156452 time to create 1 rle with new method : 0.008944034576416016 length of segment : 391 time for calcul the mask position with numpy : 0.0015254020690917969 nb_pixel_total : 81426 time to create 1 rle with old method : 0.09589910507202148 length of segment : 296 time for calcul the mask position with numpy : 0.0034112930297851562 nb_pixel_total : 170352 time to create 1 rle with new method : 0.008847236633300781 length of segment : 381 time for calcul the mask position with numpy : 0.003712177276611328 nb_pixel_total : 230187 time to create 1 rle with new method : 0.00972747802734375 length of segment : 509 time for calcul the mask position with numpy : 0.0007429122924804688 nb_pixel_total : 36960 time to create 1 rle with old method : 0.04239845275878906 length of segment : 254 time for calcul the mask position with numpy : 0.0020313262939453125 nb_pixel_total : 112948 time to create 1 rle with old method : 0.13225555419921875 length of segment : 354 time for calcul the mask position with numpy : 0.00031447410583496094 nb_pixel_total : 8085 time to create 1 rle with old method : 0.009816646575927734 length of segment : 116 time for calcul the mask position with numpy : 0.00231170654296875 nb_pixel_total : 115963 time to create 1 rle with old method : 0.13105201721191406 length of segment : 476 time for calcul the mask position with numpy : 0.0007493495941162109 nb_pixel_total : 25230 time to create 1 rle with old method : 0.02921271324157715 length of segment : 315 time for calcul the mask position with numpy : 0.005102634429931641 nb_pixel_total : 275948 time to create 1 rle with new method : 0.014872074127197266 length of segment : 928 time for calcul the mask position with numpy : 0.0012543201446533203 nb_pixel_total : 60943 time to create 1 rle with old method : 0.0715939998626709 length of segment : 262 time for calcul the mask position with numpy : 0.0005102157592773438 nb_pixel_total : 22493 time to create 1 rle with old method : 0.02634906768798828 length of segment : 145 time for calcul the mask position with numpy : 0.0020456314086914062 nb_pixel_total : 93971 time to create 1 rle with old method : 0.10795879364013672 length of segment : 388 time for calcul the mask position with numpy : 0.0005276203155517578 nb_pixel_total : 21796 time to create 1 rle with old method : 0.02517557144165039 length of segment : 148 time for calcul the mask position with numpy : 0.0026772022247314453 nb_pixel_total : 137637 time to create 1 rle with old method : 0.15653729438781738 length of segment : 363 time for calcul the mask position with numpy : 0.00116729736328125 nb_pixel_total : 46307 time to create 1 rle with old method : 0.05366706848144531 length of segment : 248 time for calcul the mask position with numpy : 0.0022661685943603516 nb_pixel_total : 127325 time to create 1 rle with old method : 0.14588665962219238 length of segment : 277 time for calcul the mask position with numpy : 0.01474761962890625 nb_pixel_total : 606018 time to create 1 rle with new method : 0.08953118324279785 length of segment : 997 time for calcul the mask position with numpy : 0.001722574234008789 nb_pixel_total : 88733 time to create 1 rle with old method : 0.10320830345153809 length of segment : 330 time for calcul the mask position with numpy : 0.0013816356658935547 nb_pixel_total : 65299 time to create 1 rle with old method : 0.07469320297241211 length of segment : 373 time for calcul the mask position with numpy : 0.00258636474609375 nb_pixel_total : 122795 time to create 1 rle with old method : 0.14133691787719727 length of segment : 488 time for calcul the mask position with numpy : 0.002119779586791992 nb_pixel_total : 114151 time to create 1 rle with old method : 0.13293790817260742 length of segment : 400 time for calcul the mask position with numpy : 0.001104116439819336 nb_pixel_total : 52343 time to create 1 rle with old method : 0.05998659133911133 length of segment : 255 time for calcul the mask position with numpy : 0.0012364387512207031 nb_pixel_total : 59146 time to create 1 rle with old method : 0.06959152221679688 length of segment : 330 time for calcul the mask position with numpy : 0.0008516311645507812 nb_pixel_total : 28488 time to create 1 rle with old method : 0.033976078033447266 length of segment : 189 time for calcul the mask position with numpy : 0.021853208541870117 nb_pixel_total : 814650 time to create 1 rle with new method : 0.22292113304138184 length of segment : 1805 time for calcul the mask position with numpy : 0.003840923309326172 nb_pixel_total : 203872 time to create 1 rle with new method : 0.024356365203857422 length of segment : 623 time for calcul the mask position with numpy : 0.0005283355712890625 nb_pixel_total : 19587 time to create 1 rle with old method : 0.022701025009155273 length of segment : 183 time for calcul the mask position with numpy : 0.004515886306762695 nb_pixel_total : 210543 time to create 1 rle with new method : 0.009451150894165039 length of segment : 569 time for calcul the mask position with numpy : 0.020291805267333984 nb_pixel_total : 1113938 time to create 1 rle with new method : 0.08437204360961914 length of segment : 1435 time for calcul the mask position with numpy : 0.0020151138305664062 nb_pixel_total : 71190 time to create 1 rle with old method : 0.08180904388427734 length of segment : 444 time for calcul the mask position with numpy : 0.0003802776336669922 nb_pixel_total : 14868 time to create 1 rle with old method : 0.017143964767456055 length of segment : 285 time for calcul the mask position with numpy : 0.006967067718505859 nb_pixel_total : 397154 time to create 1 rle with new method : 0.018166780471801758 length of segment : 885 time for calcul the mask position with numpy : 0.0008411407470703125 nb_pixel_total : 34752 time to create 1 rle with old method : 0.04034686088562012 length of segment : 204 time for calcul the mask position with numpy : 0.0015211105346679688 nb_pixel_total : 69733 time to create 1 rle with old method : 0.08100366592407227 length of segment : 436 time for calcul the mask position with numpy : 0.0009629726409912109 nb_pixel_total : 52860 time to create 1 rle with old method : 0.06148791313171387 length of segment : 223 time for calcul the mask position with numpy : 0.0005025863647460938 nb_pixel_total : 22236 time to create 1 rle with old method : 0.026369333267211914 length of segment : 200 time for calcul the mask position with numpy : 0.005193471908569336 nb_pixel_total : 149017 time to create 1 rle with old method : 0.19867539405822754 length of segment : 643 time for calcul the mask position with numpy : 0.005514383316040039 nb_pixel_total : 286215 time to create 1 rle with new method : 0.014479637145996094 length of segment : 800 time for calcul the mask position with numpy : 0.0041561126708984375 nb_pixel_total : 158204 time to create 1 rle with new method : 0.01077723503112793 length of segment : 712 time for calcul the mask position with numpy : 0.0011639595031738281 nb_pixel_total : 46762 time to create 1 rle with old method : 0.05449414253234863 length of segment : 324 time for calcul the mask position with numpy : 0.0009822845458984375 nb_pixel_total : 43652 time to create 1 rle with old method : 0.051352739334106445 length of segment : 359 time for calcul the mask position with numpy : 0.00033593177795410156 nb_pixel_total : 13176 time to create 1 rle with old method : 0.016020536422729492 length of segment : 127 time for calcul the mask position with numpy : 0.004019975662231445 nb_pixel_total : 177435 time to create 1 rle with new method : 0.010466337203979492 length of segment : 628 time for calcul the mask position with numpy : 0.002591371536254883 nb_pixel_total : 99214 time to create 1 rle with old method : 0.11818671226501465 length of segment : 634 time for calcul the mask position with numpy : 0.011404275894165039 nb_pixel_total : 541237 time to create 1 rle with new method : 0.03474164009094238 length of segment : 695 time for calcul the mask position with numpy : 0.00964808464050293 nb_pixel_total : 388370 time to create 1 rle with new method : 0.027407169342041016 length of segment : 1175 time for calcul the mask position with numpy : 0.0007574558258056641 nb_pixel_total : 42577 time to create 1 rle with old method : 0.04997682571411133 length of segment : 181 time for calcul the mask position with numpy : 0.010819435119628906 nb_pixel_total : 447989 time to create 1 rle with new method : 0.029150962829589844 length of segment : 788 time for calcul the mask position with numpy : 0.002462625503540039 nb_pixel_total : 134888 time to create 1 rle with old method : 0.15801787376403809 length of segment : 440 time for calcul the mask position with numpy : 0.0011188983917236328 nb_pixel_total : 50266 time to create 1 rle with old method : 0.060179948806762695 length of segment : 228 time for calcul the mask position with numpy : 0.0014564990997314453 nb_pixel_total : 71174 time to create 1 rle with old method : 0.10162687301635742 length of segment : 456 time for calcul the mask position with numpy : 0.00039577484130859375 nb_pixel_total : 12229 time to create 1 rle with old method : 0.015024900436401367 length of segment : 145 time for calcul the mask position with numpy : 0.006056785583496094 nb_pixel_total : 282177 time to create 1 rle with new method : 0.01731109619140625 length of segment : 850 time for calcul the mask position with numpy : 0.004526615142822266 nb_pixel_total : 194371 time to create 1 rle with new method : 0.012961387634277344 length of segment : 635 time for calcul the mask position with numpy : 0.001561880111694336 nb_pixel_total : 53415 time to create 1 rle with old method : 0.0639486312866211 length of segment : 198 time for calcul the mask position with numpy : 0.0011420249938964844 nb_pixel_total : 41177 time to create 1 rle with old method : 0.04904937744140625 length of segment : 576 time for calcul the mask position with numpy : 0.0005323886871337891 nb_pixel_total : 27623 time to create 1 rle with old method : 0.03236722946166992 length of segment : 215 time for calcul the mask position with numpy : 0.0004487037658691406 nb_pixel_total : 14144 time to create 1 rle with old method : 0.0175783634185791 length of segment : 192 time for calcul the mask position with numpy : 0.000415802001953125 nb_pixel_total : 13180 time to create 1 rle with old method : 0.01581883430480957 length of segment : 143 time for calcul the mask position with numpy : 0.0011396408081054688 nb_pixel_total : 44757 time to create 1 rle with old method : 0.05372190475463867 length of segment : 273 time for calcul the mask position with numpy : 0.0008487701416015625 nb_pixel_total : 39018 time to create 1 rle with old method : 0.045304298400878906 length of segment : 233 time for calcul the mask position with numpy : 0.00818943977355957 nb_pixel_total : 345894 time to create 1 rle with new method : 0.02402949333190918 length of segment : 682 time for calcul the mask position with numpy : 0.0014629364013671875 nb_pixel_total : 58953 time to create 1 rle with old method : 0.06944513320922852 length of segment : 291 time for calcul the mask position with numpy : 0.00039696693420410156 nb_pixel_total : 16590 time to create 1 rle with old method : 0.020910024642944336 length of segment : 143 time for calcul the mask position with numpy : 0.0018925666809082031 nb_pixel_total : 96158 time to create 1 rle with old method : 0.11207294464111328 length of segment : 337 time for calcul the mask position with numpy : 0.00067901611328125 nb_pixel_total : 33606 time to create 1 rle with old method : 0.039568424224853516 length of segment : 178 time for calcul the mask position with numpy : 0.003547191619873047 nb_pixel_total : 175287 time to create 1 rle with new method : 0.010298013687133789 length of segment : 579 time for calcul the mask position with numpy : 0.001155853271484375 nb_pixel_total : 44068 time to create 1 rle with old method : 0.05345344543457031 length of segment : 132 time for calcul the mask position with numpy : 0.0009887218475341797 nb_pixel_total : 52167 time to create 1 rle with old method : 0.07061457633972168 length of segment : 214 time for calcul the mask position with numpy : 0.006543636322021484 nb_pixel_total : 266087 time to create 1 rle with new method : 0.018815279006958008 length of segment : 655 time for calcul the mask position with numpy : 0.002180337905883789 nb_pixel_total : 291 time to create 1 rle with old method : 0.0007717609405517578 length of segment : 39 time for calcul the mask position with numpy : 0.0040819644927978516 nb_pixel_total : 148523 time to create 1 rle with old method : 0.17563152313232422 length of segment : 635 time for calcul the mask position with numpy : 0.006505250930786133 nb_pixel_total : 231725 time to create 1 rle with new method : 0.018125295639038086 length of segment : 882 time for calcul the mask position with numpy : 0.00912332534790039 nb_pixel_total : 340712 time to create 1 rle with new method : 0.023189067840576172 length of segment : 975 time for calcul the mask position with numpy : 0.00336456298828125 nb_pixel_total : 173604 time to create 1 rle with new method : 0.009029388427734375 length of segment : 498 time for calcul the mask position with numpy : 0.0007271766662597656 nb_pixel_total : 31785 time to create 1 rle with old method : 0.03759026527404785 length of segment : 199 time for calcul the mask position with numpy : 0.004111051559448242 nb_pixel_total : 103083 time to create 1 rle with old method : 0.12149953842163086 length of segment : 767 time for calcul the mask position with numpy : 0.010035276412963867 nb_pixel_total : 180366 time to create 1 rle with new method : 0.043222904205322266 length of segment : 1159 time for calcul the mask position with numpy : 0.008607149124145508 nb_pixel_total : 341903 time to create 1 rle with new method : 0.026840686798095703 length of segment : 954 time for calcul the mask position with numpy : 0.0016713142395019531 nb_pixel_total : 72663 time to create 1 rle with old method : 0.08724808692932129 length of segment : 377 time for calcul the mask position with numpy : 0.00125885009765625 nb_pixel_total : 46902 time to create 1 rle with old method : 0.05674242973327637 length of segment : 261 time for calcul the mask position with numpy : 0.0014760494232177734 nb_pixel_total : 71394 time to create 1 rle with old method : 0.08516311645507812 length of segment : 368 time for calcul the mask position with numpy : 0.0017087459564208984 nb_pixel_total : 77265 time to create 1 rle with old method : 0.0925743579864502 length of segment : 325 time for calcul the mask position with numpy : 0.0013132095336914062 nb_pixel_total : 72012 time to create 1 rle with old method : 0.08632659912109375 length of segment : 374 time for calcul the mask position with numpy : 0.004405021667480469 nb_pixel_total : 209511 time to create 1 rle with new method : 0.011128425598144531 length of segment : 604 time for calcul the mask position with numpy : 0.003123044967651367 nb_pixel_total : 79316 time to create 1 rle with old method : 0.09528422355651855 length of segment : 328 time for calcul the mask position with numpy : 0.0009815692901611328 nb_pixel_total : 30655 time to create 1 rle with old method : 0.03812384605407715 length of segment : 328 time for calcul the mask position with numpy : 0.001546621322631836 nb_pixel_total : 62460 time to create 1 rle with old method : 0.07356429100036621 length of segment : 291 time for calcul the mask position with numpy : 0.0010290145874023438 nb_pixel_total : 47320 time to create 1 rle with old method : 0.055876970291137695 length of segment : 258 time for calcul the mask position with numpy : 0.0013272762298583984 nb_pixel_total : 42893 time to create 1 rle with old method : 0.05125594139099121 length of segment : 291 time for calcul the mask position with numpy : 0.0066585540771484375 nb_pixel_total : 256156 time to create 1 rle with new method : 0.017384767532348633 length of segment : 1029 time for calcul the mask position with numpy : 0.0009324550628662109 nb_pixel_total : 22884 time to create 1 rle with old method : 0.027446746826171875 length of segment : 236 time for calcul the mask position with numpy : 0.0007748603820800781 nb_pixel_total : 21830 time to create 1 rle with old method : 0.026562929153442383 length of segment : 415 time for calcul the mask position with numpy : 0.004039287567138672 nb_pixel_total : 177840 time to create 1 rle with new method : 0.012305974960327148 length of segment : 610 time for calcul the mask position with numpy : 0.001558542251586914 nb_pixel_total : 66166 time to create 1 rle with old method : 0.08339095115661621 length of segment : 253 time for calcul the mask position with numpy : 0.0034079551696777344 nb_pixel_total : 154360 time to create 1 rle with new method : 0.008847951889038086 length of segment : 599 time for calcul the mask position with numpy : 0.006499052047729492 nb_pixel_total : 285976 time to create 1 rle with new method : 0.019426584243774414 length of segment : 444 time for calcul the mask position with numpy : 0.0014367103576660156 nb_pixel_total : 61642 time to create 1 rle with old method : 0.0729672908782959 length of segment : 276 time for calcul the mask position with numpy : 0.0024650096893310547 nb_pixel_total : 77224 time to create 1 rle with old method : 0.09138631820678711 length of segment : 439 time for calcul the mask position with numpy : 0.004793405532836914 nb_pixel_total : 221910 time to create 1 rle with new method : 0.014040708541870117 length of segment : 475 time for calcul the mask position with numpy : 0.0031998157501220703 nb_pixel_total : 126517 time to create 1 rle with old method : 0.14781451225280762 length of segment : 405 time for calcul the mask position with numpy : 0.0006549358367919922 nb_pixel_total : 19274 time to create 1 rle with old method : 0.023681640625 length of segment : 188 time for calcul the mask position with numpy : 0.014440774917602539 nb_pixel_total : 644035 time to create 1 rle with new method : 0.03507494926452637 length of segment : 1554 time for calcul the mask position with numpy : 0.0006344318389892578 nb_pixel_total : 21089 time to create 1 rle with old method : 0.025281190872192383 length of segment : 180 time for calcul the mask position with numpy : 0.0007343292236328125 nb_pixel_total : 26184 time to create 1 rle with old method : 0.030989885330200195 length of segment : 329 time for calcul the mask position with numpy : 0.00895071029663086 nb_pixel_total : 447593 time to create 1 rle with new method : 0.024824142456054688 length of segment : 1536 time for calcul the mask position with numpy : 0.0006136894226074219 nb_pixel_total : 24039 time to create 1 rle with old method : 0.029062271118164062 length of segment : 119 time for calcul the mask position with numpy : 0.0007016658782958984 nb_pixel_total : 18846 time to create 1 rle with old method : 0.02348494529724121 length of segment : 155 time for calcul the mask position with numpy : 0.0017993450164794922 nb_pixel_total : 87354 time to create 1 rle with old method : 0.10317754745483398 length of segment : 267 time for calcul the mask position with numpy : 0.0007798671722412109 nb_pixel_total : 35913 time to create 1 rle with old method : 0.04282665252685547 length of segment : 259 time for calcul the mask position with numpy : 0.0008111000061035156 nb_pixel_total : 23752 time to create 1 rle with old method : 0.028841257095336914 length of segment : 218 time for calcul the mask position with numpy : 0.0008220672607421875 nb_pixel_total : 19020 time to create 1 rle with old method : 0.02389812469482422 length of segment : 277 time for calcul the mask position with numpy : 0.005323648452758789 nb_pixel_total : 245175 time to create 1 rle with new method : 0.014023303985595703 length of segment : 626 time for calcul the mask position with numpy : 0.0023026466369628906 nb_pixel_total : 75209 time to create 1 rle with old method : 0.08735179901123047 length of segment : 513 time for calcul the mask position with numpy : 0.0003509521484375 nb_pixel_total : 7203 time to create 1 rle with old method : 0.010858297348022461 length of segment : 113 time for calcul the mask position with numpy : 0.0005502700805664062 nb_pixel_total : 9337 time to create 1 rle with old method : 0.01175832748413086 length of segment : 198 time for calcul the mask position with numpy : 0.0006296634674072266 nb_pixel_total : 27783 time to create 1 rle with old method : 0.0328221321105957 length of segment : 206 time for calcul the mask position with numpy : 0.001196146011352539 nb_pixel_total : 48618 time to create 1 rle with old method : 0.057273149490356445 length of segment : 357 time for calcul the mask position with numpy : 0.002277851104736328 nb_pixel_total : 65761 time to create 1 rle with old method : 0.07704496383666992 length of segment : 433 time for calcul the mask position with numpy : 0.0009081363677978516 nb_pixel_total : 24217 time to create 1 rle with old method : 0.02886795997619629 length of segment : 163 time for calcul the mask position with numpy : 0.001190185546875 nb_pixel_total : 40271 time to create 1 rle with old method : 0.047504425048828125 length of segment : 269 time for calcul the mask position with numpy : 0.017195701599121094 nb_pixel_total : 640297 time to create 1 rle with new method : 0.3170456886291504 length of segment : 1252 time for calcul the mask position with numpy : 0.0004949569702148438 nb_pixel_total : 16785 time to create 1 rle with old method : 0.020166397094726562 length of segment : 180 time for calcul the mask position with numpy : 0.0038225650787353516 nb_pixel_total : 179108 time to create 1 rle with new method : 0.010740041732788086 length of segment : 487 time for calcul the mask position with numpy : 0.0016357898712158203 nb_pixel_total : 54333 time to create 1 rle with old method : 0.07585692405700684 length of segment : 267 time for calcul the mask position with numpy : 0.0032989978790283203 nb_pixel_total : 119938 time to create 1 rle with old method : 0.144514799118042 length of segment : 463 time for calcul the mask position with numpy : 0.002821207046508789 nb_pixel_total : 124154 time to create 1 rle with old method : 0.14646697044372559 length of segment : 386 time for calcul the mask position with numpy : 0.00032711029052734375 nb_pixel_total : 8751 time to create 1 rle with old method : 0.010833740234375 length of segment : 83 time for calcul the mask position with numpy : 0.003618478775024414 nb_pixel_total : 164099 time to create 1 rle with new method : 0.010070085525512695 length of segment : 438 time for calcul the mask position with numpy : 0.002023458480834961 nb_pixel_total : 64149 time to create 1 rle with old method : 0.08815145492553711 length of segment : 301 time for calcul the mask position with numpy : 0.004904508590698242 nb_pixel_total : 144511 time to create 1 rle with old method : 0.17244625091552734 length of segment : 890 time for calcul the mask position with numpy : 0.002237558364868164 nb_pixel_total : 96110 time to create 1 rle with old method : 0.11203289031982422 length of segment : 358 time for calcul the mask position with numpy : 0.005453348159790039 nb_pixel_total : 274358 time to create 1 rle with new method : 0.019106149673461914 length of segment : 549 time for calcul the mask position with numpy : 0.0010986328125 nb_pixel_total : 31546 time to create 1 rle with old method : 0.03753972053527832 length of segment : 372 time for calcul the mask position with numpy : 0.0003902912139892578 nb_pixel_total : 13661 time to create 1 rle with old method : 0.017066478729248047 length of segment : 110 time for calcul the mask position with numpy : 0.0067005157470703125 nb_pixel_total : 196882 time to create 1 rle with new method : 0.018569469451904297 length of segment : 806 time for calcul the mask position with numpy : 0.010261297225952148 nb_pixel_total : 381489 time to create 1 rle with new method : 0.036870479583740234 length of segment : 705 time for calcul the mask position with numpy : 0.001043558120727539 nb_pixel_total : 38332 time to create 1 rle with old method : 0.04580497741699219 length of segment : 186 time for calcul the mask position with numpy : 0.00021767616271972656 nb_pixel_total : 3479 time to create 1 rle with old method : 0.004459857940673828 length of segment : 63 time for calcul the mask position with numpy : 0.0006518363952636719 nb_pixel_total : 22867 time to create 1 rle with old method : 0.027480602264404297 length of segment : 158 time for calcul the mask position with numpy : 0.0005128383636474609 nb_pixel_total : 18507 time to create 1 rle with old method : 0.02215290069580078 length of segment : 170 time for calcul the mask position with numpy : 0.005319118499755859 nb_pixel_total : 270658 time to create 1 rle with new method : 0.016978979110717773 length of segment : 661 time for calcul the mask position with numpy : 0.007629871368408203 nb_pixel_total : 322772 time to create 1 rle with new method : 0.021245479583740234 length of segment : 610 time for calcul the mask position with numpy : 0.003178119659423828 nb_pixel_total : 110231 time to create 1 rle with old method : 0.1405775547027588 length of segment : 300 time for calcul the mask position with numpy : 0.001561880111694336 nb_pixel_total : 41228 time to create 1 rle with old method : 0.04948282241821289 length of segment : 231 time for calcul the mask position with numpy : 0.005011081695556641 nb_pixel_total : 197521 time to create 1 rle with new method : 0.015238761901855469 length of segment : 919 time for calcul the mask position with numpy : 0.0002541542053222656 nb_pixel_total : 4789 time to create 1 rle with old method : 0.008322477340698242 length of segment : 81 time for calcul the mask position with numpy : 0.010334968566894531 nb_pixel_total : 249755 time to create 1 rle with new method : 0.03235292434692383 length of segment : 729 time for calcul the mask position with numpy : 0.014012813568115234 nb_pixel_total : 491240 time to create 1 rle with new method : 0.04214143753051758 length of segment : 1340 time for calcul the mask position with numpy : 0.0011258125305175781 nb_pixel_total : 34218 time to create 1 rle with old method : 0.03986024856567383 length of segment : 302 time for calcul the mask position with numpy : 0.003147602081298828 nb_pixel_total : 120950 time to create 1 rle with old method : 0.14090871810913086 length of segment : 589 time for calcul the mask position with numpy : 0.0023725032806396484 nb_pixel_total : 67118 time to create 1 rle with old method : 0.07817363739013672 length of segment : 348 time for calcul the mask position with numpy : 0.0009908676147460938 nb_pixel_total : 34505 time to create 1 rle with old method : 0.04120969772338867 length of segment : 189 time for calcul the mask position with numpy : 0.00634765625 nb_pixel_total : 219576 time to create 1 rle with new method : 0.021626710891723633 length of segment : 849 time for calcul the mask position with numpy : 0.00498652458190918 nb_pixel_total : 280572 time to create 1 rle with new method : 0.015141963958740234 length of segment : 1614 time for calcul the mask position with numpy : 0.0009181499481201172 nb_pixel_total : 35973 time to create 1 rle with old method : 0.05808854103088379 length of segment : 238 time for calcul the mask position with numpy : 0.0006825923919677734 nb_pixel_total : 25471 time to create 1 rle with old method : 0.03461909294128418 length of segment : 116 time for calcul the mask position with numpy : 0.004846096038818359 nb_pixel_total : 179265 time to create 1 rle with new method : 0.014060735702514648 length of segment : 491 time for calcul the mask position with numpy : 0.010394811630249023 nb_pixel_total : 338522 time to create 1 rle with new method : 0.033148765563964844 length of segment : 538 time for calcul the mask position with numpy : 0.0035905838012695312 nb_pixel_total : 136606 time to create 1 rle with old method : 0.16460561752319336 length of segment : 608 time for calcul the mask position with numpy : 0.009441614151000977 nb_pixel_total : 302993 time to create 1 rle with new method : 0.021334171295166016 length of segment : 553 time for calcul the mask position with numpy : 0.0009913444519042969 nb_pixel_total : 22393 time to create 1 rle with old method : 0.034860849380493164 length of segment : 426 time for calcul the mask position with numpy : 0.001155853271484375 nb_pixel_total : 34952 time to create 1 rle with old method : 0.045233726501464844 length of segment : 202 time for calcul the mask position with numpy : 0.0019137859344482422 nb_pixel_total : 87168 time to create 1 rle with old method : 0.10591435432434082 length of segment : 600 time for calcul the mask position with numpy : 0.604341983795166 nb_pixel_total : 4420001 time to create 1 rle with new method : 0.8589775562286377 length of segment : 3498 time for calcul the mask position with numpy : 0.0007300376892089844 nb_pixel_total : 65239 time to create 1 rle with old method : 0.07760763168334961 length of segment : 122 time for calcul the mask position with numpy : 0.0002410411834716797 nb_pixel_total : 14730 time to create 1 rle with old method : 0.017987728118896484 length of segment : 128 time spent for convertir_results : 33.755409240722656 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 291 chid ids of type : 4854 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 86.10455226898193 time spend to save output : 0.17730927467346191 total time spend for step 2 : 86.2818615436554 step3:blur_detection Thu Aug 28 15:23:41 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 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 inside step blur_detection methode: variance laplacian (3120, 3120) 519.9012158683921 (3120, 3120) 470.3560496453144 (3120, 3120) 885.9160354957713 (3120, 3120) 329.09399776015306 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 : 4 time used for this insertion : 0.014688491821289062 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.012501001358032227 save missing photos in datou_result : time spend for datou_step_exec : 2.1170432567596436 time spend to save output : 0.03285956382751465 total time spend for step 3 : 2.149902820587158 step4:brightness Thu Aug 28 15:23:43 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 inside step calcul brightness treat image : temp/1756387287_3909701_1379844884_bc8079241d3f51b06863b2118bd3c6c5.jpg treat image : temp/1756387287_3909701_1379844865_f0f3eeeb3c06f1ec6bd59d8c4796252c.jpg treat image : temp/1756387287_3909701_1379844831_4eae2b9ddfb5e8f49cb337dff324d1ef.jpg treat image : temp/1756387287_3909701_1379844813_265d8ba00a460e05fbb98e3b8e5d984d.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 : 4 time used for this insertion : 0.013144969940185547 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 4 time used for this insertion : 0.01726818084716797 save missing photos in datou_result : time spend for datou_step_exec : 4.922236919403076 time spend to save output : 0.03524065017700195 total time spend for step 4 : 4.957477569580078 step5:rle_unique_nms_with_priority Thu Aug 28 15:23:48 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 expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms batch 1 Loaded 291 chid ids of type : 4854 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 79 nb_hashtags : 11 time to prepare the origin masks : 45.11541390419006 time for calcul the mask position with numpy : 0.4816091060638428 nb_pixel_total : 1910701 time to create 1 rle with new method : 0.8557250499725342 time for calcul the mask position with numpy : 0.039044857025146484 nb_pixel_total : 94978 time to create 1 rle with old method : 0.10805416107177734 time for calcul the mask position with numpy : 0.038743019104003906 nb_pixel_total : 21000 time to create 1 rle with old method : 0.023921489715576172 time for calcul the mask position with numpy : 0.04645180702209473 nb_pixel_total : 799200 time to create 1 rle with new method : 0.6835050582885742 time for calcul the mask position with numpy : 0.040351152420043945 nb_pixel_total : 10161 time to create 1 rle with old method : 0.011782169342041016 time for calcul the mask position with numpy : 0.04061150550842285 nb_pixel_total : 317208 time to create 1 rle with new method : 0.6807897090911865 time for calcul the mask position with numpy : 0.044127464294433594 nb_pixel_total : 621288 time to create 1 rle with new method : 0.7272357940673828 time for calcul the mask position with numpy : 0.039971351623535156 nb_pixel_total : 46330 time to create 1 rle with old method : 0.05266618728637695 time for calcul the mask position with numpy : 0.03970980644226074 nb_pixel_total : 51795 time to create 1 rle with old method : 0.06417703628540039 time for calcul the mask position with numpy : 0.04009103775024414 nb_pixel_total : 88244 time to create 1 rle with old method : 0.10706806182861328 time for calcul the mask position with numpy : 0.04022717475891113 nb_pixel_total : 1344 time to create 1 rle with old method : 0.0018267631530761719 time for calcul the mask position with numpy : 0.04027843475341797 nb_pixel_total : 64153 time to create 1 rle with old method : 0.07430577278137207 time for calcul the mask position with numpy : 0.03935885429382324 nb_pixel_total : 3852 time to create 1 rle with old method : 0.004546165466308594 time for calcul the mask position with numpy : 0.03985786437988281 nb_pixel_total : 34604 time to create 1 rle with old method : 0.043039560317993164 time for calcul the mask position with numpy : 0.04015302658081055 nb_pixel_total : 38419 time to create 1 rle with old method : 0.04446840286254883 time for calcul the mask position with numpy : 0.04035043716430664 nb_pixel_total : 89126 time to create 1 rle with old method : 0.1017310619354248 time for calcul the mask position with numpy : 0.039812326431274414 nb_pixel_total : 169957 time to create 1 rle with new method : 0.5918023586273193 time for calcul the mask position with numpy : 0.04011726379394531 nb_pixel_total : 2208 time to create 1 rle with old method : 0.003917217254638672 time for calcul the mask position with numpy : 0.04666614532470703 nb_pixel_total : 234220 time to create 1 rle with new method : 0.6714825630187988 time for calcul the mask position with numpy : 0.039025068283081055 nb_pixel_total : 15024 time to create 1 rle with old method : 0.01722431182861328 time for calcul the mask position with numpy : 0.04160332679748535 nb_pixel_total : 551359 time to create 1 rle with new method : 0.714066743850708 time for calcul the mask position with numpy : 0.04108905792236328 nb_pixel_total : 13614 time to create 1 rle with old method : 0.015487194061279297 time for calcul the mask position with numpy : 0.04057645797729492 nb_pixel_total : 213529 time to create 1 rle with new method : 0.6370887756347656 time for calcul the mask position with numpy : 0.03946399688720703 nb_pixel_total : 1411 time to create 1 rle with old method : 0.001749277114868164 time for calcul the mask position with numpy : 0.03883218765258789 nb_pixel_total : 11486 time to create 1 rle with old method : 0.013275861740112305 time for calcul the mask position with numpy : 0.03986167907714844 nb_pixel_total : 58714 time to create 1 rle with old method : 0.06696414947509766 time for calcul the mask position with numpy : 0.039353132247924805 nb_pixel_total : 11479 time to create 1 rle with old method : 0.013446807861328125 time for calcul the mask position with numpy : 0.03953075408935547 nb_pixel_total : 18551 time to create 1 rle with old method : 0.021138429641723633 time for calcul the mask position with numpy : 0.04008960723876953 nb_pixel_total : 154748 time to create 1 rle with new method : 0.7876749038696289 time for calcul the mask position with numpy : 0.03916478157043457 nb_pixel_total : 51778 time to create 1 rle with old method : 0.0609891414642334 time for calcul the mask position with numpy : 0.04047393798828125 nb_pixel_total : 115388 time to create 1 rle with old method : 0.1327502727508545 time for calcul the mask position with numpy : 0.043788909912109375 nb_pixel_total : 837288 time to create 1 rle with new method : 0.616734504699707 time for calcul the mask position with numpy : 0.03875732421875 nb_pixel_total : 2941 time to create 1 rle with old method : 0.003520965576171875 time for calcul the mask position with numpy : 0.03882169723510742 nb_pixel_total : 442 time to create 1 rle with old method : 0.0007193088531494141 time for calcul the mask position with numpy : 0.039191484451293945 nb_pixel_total : 21560 time to create 1 rle with old method : 0.02504253387451172 time for calcul the mask position with numpy : 0.03950333595275879 nb_pixel_total : 3737 time to create 1 rle with old method : 0.004209995269775391 time for calcul the mask position with numpy : 0.03870201110839844 nb_pixel_total : 32720 time to create 1 rle with old method : 0.038012027740478516 time for calcul the mask position with numpy : 0.038736581802368164 nb_pixel_total : 17057 time to create 1 rle with old method : 0.019723892211914062 time for calcul the mask position with numpy : 0.03914690017700195 nb_pixel_total : 1538 time to create 1 rle with old method : 0.002538919448852539 time for calcul the mask position with numpy : 0.043257713317871094 nb_pixel_total : 734993 time to create 1 rle with new method : 0.6290059089660645 time for calcul the mask position with numpy : 0.0392765998840332 nb_pixel_total : 578 time to create 1 rle with old method : 0.0007073879241943359 time for calcul the mask position with numpy : 0.03952360153198242 nb_pixel_total : 55035 time to create 1 rle with old method : 0.06269979476928711 time for calcul the mask position with numpy : 0.03986477851867676 nb_pixel_total : 40606 time to create 1 rle with old method : 0.0467226505279541 time for calcul the mask position with numpy : 0.039833784103393555 nb_pixel_total : 56267 time to create 1 rle with old method : 0.06469106674194336 time for calcul the mask position with numpy : 0.03969001770019531 nb_pixel_total : 1798 time to create 1 rle with old method : 0.002437591552734375 time for calcul the mask position with numpy : 0.03971982002258301 nb_pixel_total : 3792 time to create 1 rle with old method : 0.0054776668548583984 time for calcul the mask position with numpy : 0.03973031044006348 nb_pixel_total : 37535 time to create 1 rle with old method : 0.04319262504577637 time for calcul the mask position with numpy : 0.041017770767211914 nb_pixel_total : 3252 time to create 1 rle with old method : 0.0038225650787353516 time for calcul the mask position with numpy : 0.04026913642883301 nb_pixel_total : 140659 time to create 1 rle with old method : 0.16302871704101562 time for calcul the mask position with numpy : 0.040161848068237305 nb_pixel_total : 49122 time to create 1 rle with old method : 0.05701851844787598 time for calcul the mask position with numpy : 0.039841651916503906 nb_pixel_total : 85895 time to create 1 rle with old method : 0.09811973571777344 time for calcul the mask position with numpy : 0.03968954086303711 nb_pixel_total : 17585 time to create 1 rle with old method : 0.020852088928222656 time for calcul the mask position with numpy : 0.040103912353515625 nb_pixel_total : 69368 time to create 1 rle with old method : 0.10402345657348633 time for calcul the mask position with numpy : 0.040343523025512695 nb_pixel_total : 24137 time to create 1 rle with old method : 0.028260231018066406 time for calcul the mask position with numpy : 0.04043722152709961 nb_pixel_total : 22745 time to create 1 rle with old method : 0.026475191116333008 time for calcul the mask position with numpy : 0.04025864601135254 nb_pixel_total : 6232 time to create 1 rle with old method : 0.007387399673461914 time for calcul the mask position with numpy : 0.04591631889343262 nb_pixel_total : 416360 time to create 1 rle with new method : 0.7222769260406494 time for calcul the mask position with numpy : 0.04079031944274902 nb_pixel_total : 120438 time to create 1 rle with old method : 0.1418750286102295 time for calcul the mask position with numpy : 0.04021191596984863 nb_pixel_total : 65059 time to create 1 rle with old method : 0.07518815994262695 time for calcul the mask position with numpy : 0.04043221473693848 nb_pixel_total : 43843 time to create 1 rle with old method : 0.051232337951660156 time for calcul the mask position with numpy : 0.04031705856323242 nb_pixel_total : 69937 time to create 1 rle with old method : 0.08121895790100098 time for calcul the mask position with numpy : 0.03901267051696777 nb_pixel_total : 23053 time to create 1 rle with old method : 0.026468515396118164 time for calcul the mask position with numpy : 0.0398712158203125 nb_pixel_total : 18184 time to create 1 rle with old method : 0.02126002311706543 time for calcul the mask position with numpy : 0.0411829948425293 nb_pixel_total : 293361 time to create 1 rle with new method : 0.6927671432495117 time for calcul the mask position with numpy : 0.03969836235046387 nb_pixel_total : 117 time to create 1 rle with old method : 0.00035834312438964844 time for calcul the mask position with numpy : 0.03882193565368652 nb_pixel_total : 4300 time to create 1 rle with old method : 0.005287885665893555 time for calcul the mask position with numpy : 0.03967165946960449 nb_pixel_total : 1767 time to create 1 rle with old method : 0.002231121063232422 time for calcul the mask position with numpy : 0.039465904235839844 nb_pixel_total : 8352 time to create 1 rle with old method : 0.010250329971313477 time for calcul the mask position with numpy : 0.03908658027648926 nb_pixel_total : 90783 time to create 1 rle with old method : 0.10619950294494629 time for calcul the mask position with numpy : 0.03978896141052246 nb_pixel_total : 226821 time to create 1 rle with new method : 0.5305500030517578 time for calcul the mask position with numpy : 0.039902687072753906 nb_pixel_total : 1979 time to create 1 rle with old method : 0.0024232864379882812 time for calcul the mask position with numpy : 0.03984808921813965 nb_pixel_total : 7688 time to create 1 rle with old method : 0.008931159973144531 time for calcul the mask position with numpy : 0.03993797302246094 nb_pixel_total : 13769 time to create 1 rle with old method : 0.016240835189819336 time for calcul the mask position with numpy : 0.04051351547241211 nb_pixel_total : 68852 time to create 1 rle with old method : 0.08302998542785645 time for calcul the mask position with numpy : 0.040120840072631836 nb_pixel_total : 60656 time to create 1 rle with old method : 0.07002663612365723 time for calcul the mask position with numpy : 0.03975963592529297 nb_pixel_total : 10297 time to create 1 rle with old method : 0.01211404800415039 time for calcul the mask position with numpy : 0.039534807205200195 nb_pixel_total : 8149 time to create 1 rle with old method : 0.00986623764038086 time for calcul the mask position with numpy : 0.03986763954162598 nb_pixel_total : 54594 time to create 1 rle with old method : 0.06344819068908691 time for calcul the mask position with numpy : 0.03970074653625488 nb_pixel_total : 12465 time to create 1 rle with old method : 0.014866113662719727 time for calcul the mask position with numpy : 0.03957247734069824 nb_pixel_total : 30825 time to create 1 rle with old method : 0.036858558654785156 create new chi : 16.306074619293213 time to delete rle : 0.0341341495513916 batch 1 Loaded 80 chid ids of type : 4855 Number RLEs to save : 49858 TO DO : save crop sub photo not yet done ! save time : 2.592118263244629 nb_obj : 86 nb_hashtags : 9 time to prepare the origin masks : 38.93466281890869 time for calcul the mask position with numpy : 0.06079745292663574 nb_pixel_total : 2368522 time to create 1 rle with new method : 1.22426438331604 time for calcul the mask position with numpy : 0.040491342544555664 nb_pixel_total : 34377 time to create 1 rle with old method : 0.04338335990905762 time for calcul the mask position with numpy : 0.04358530044555664 nb_pixel_total : 21595 time to create 1 rle with old method : 0.0244748592376709 time for calcul the mask position with numpy : 0.03968691825866699 nb_pixel_total : 42517 time to create 1 rle with old method : 0.049478769302368164 time for calcul the mask position with numpy : 0.04127383232116699 nb_pixel_total : 12732 time to create 1 rle with old method : 0.015314579010009766 time for calcul the mask position with numpy : 0.04452681541442871 nb_pixel_total : 241785 time to create 1 rle with new method : 0.7610747814178467 time for calcul the mask position with numpy : 0.0400691032409668 nb_pixel_total : 137574 time to create 1 rle with old method : 0.1548159122467041 time for calcul the mask position with numpy : 0.04239082336425781 nb_pixel_total : 307353 time to create 1 rle with new method : 0.7175140380859375 time for calcul the mask position with numpy : 0.03997349739074707 nb_pixel_total : 59696 time to create 1 rle with old method : 0.06725525856018066 time for calcul the mask position with numpy : 0.039610862731933594 nb_pixel_total : 16822 time to create 1 rle with old method : 0.01949334144592285 time for calcul the mask position with numpy : 0.0415647029876709 nb_pixel_total : 193183 time to create 1 rle with new method : 0.8659887313842773 time for calcul the mask position with numpy : 0.040764808654785156 nb_pixel_total : 18230 time to create 1 rle with old method : 0.022628307342529297 time for calcul the mask position with numpy : 0.04110598564147949 nb_pixel_total : 93168 time to create 1 rle with old method : 0.10860633850097656 time for calcul the mask position with numpy : 0.04001116752624512 nb_pixel_total : 9671 time to create 1 rle with old method : 0.011398077011108398 time for calcul the mask position with numpy : 0.039704322814941406 nb_pixel_total : 21956 time to create 1 rle with old method : 0.025682687759399414 time for calcul the mask position with numpy : 0.04008197784423828 nb_pixel_total : 88387 time to create 1 rle with old method : 0.11433720588684082 time for calcul the mask position with numpy : 0.04537463188171387 nb_pixel_total : 25716 time to create 1 rle with old method : 0.033577919006347656 time for calcul the mask position with numpy : 0.04003429412841797 nb_pixel_total : 3898 time to create 1 rle with old method : 0.004761934280395508 time for calcul the mask position with numpy : 0.0401766300201416 nb_pixel_total : 32042 time to create 1 rle with old method : 0.037325382232666016 time for calcul the mask position with numpy : 0.039931297302246094 nb_pixel_total : 19038 time to create 1 rle with old method : 0.022533893585205078 time for calcul the mask position with numpy : 0.04272961616516113 nb_pixel_total : 513 time to create 1 rle with old method : 0.0009927749633789062 time for calcul the mask position with numpy : 0.04939842224121094 nb_pixel_total : 35276 time to create 1 rle with old method : 0.03984475135803223 time for calcul the mask position with numpy : 0.03977465629577637 nb_pixel_total : 43544 time to create 1 rle with old method : 0.05092048645019531 time for calcul the mask position with numpy : 0.0398867130279541 nb_pixel_total : 710 time to create 1 rle with old method : 0.0010309219360351562 time for calcul the mask position with numpy : 0.04020047187805176 nb_pixel_total : 177016 time to create 1 rle with new method : 0.8503813743591309 time for calcul the mask position with numpy : 0.03971743583679199 nb_pixel_total : 53988 time to create 1 rle with old method : 0.06280517578125 time for calcul the mask position with numpy : 0.04047369956970215 nb_pixel_total : 74168 time to create 1 rle with old method : 0.08569169044494629 time for calcul the mask position with numpy : 0.03993630409240723 nb_pixel_total : 180903 time to create 1 rle with new method : 0.7131993770599365 time for calcul the mask position with numpy : 0.0408933162689209 nb_pixel_total : 261747 time to create 1 rle with new method : 0.8165218830108643 time for calcul the mask position with numpy : 0.04149675369262695 nb_pixel_total : 9759 time to create 1 rle with old method : 0.011751413345336914 time for calcul the mask position with numpy : 0.04051542282104492 nb_pixel_total : 55753 time to create 1 rle with old method : 0.06539225578308105 time for calcul the mask position with numpy : 0.04062509536743164 nb_pixel_total : 78658 time to create 1 rle with old method : 0.09729385375976562 time for calcul the mask position with numpy : 0.04084205627441406 nb_pixel_total : 44929 time to create 1 rle with old method : 0.05294466018676758 time for calcul the mask position with numpy : 0.039644479751586914 nb_pixel_total : 14756 time to create 1 rle with old method : 0.016866683959960938 time for calcul the mask position with numpy : 0.03953194618225098 nb_pixel_total : 31082 time to create 1 rle with old method : 0.03544735908508301 time for calcul the mask position with numpy : 0.04001045227050781 nb_pixel_total : 34715 time to create 1 rle with old method : 0.04041314125061035 time for calcul the mask position with numpy : 0.04009103775024414 nb_pixel_total : 1496 time to create 1 rle with old method : 0.0017919540405273438 time for calcul the mask position with numpy : 0.03857779502868652 nb_pixel_total : 46895 time to create 1 rle with old method : 0.0535891056060791 time for calcul the mask position with numpy : 0.0390625 nb_pixel_total : 25382 time to create 1 rle with old method : 0.029334068298339844 time for calcul the mask position with numpy : 0.039954423904418945 nb_pixel_total : 69572 time to create 1 rle with old method : 0.10658788681030273 time for calcul the mask position with numpy : 0.04131293296813965 nb_pixel_total : 210265 time to create 1 rle with new method : 0.7770323753356934 time for calcul the mask position with numpy : 0.04251742362976074 nb_pixel_total : 25869 time to create 1 rle with old method : 0.02943253517150879 time for calcul the mask position with numpy : 0.03860282897949219 nb_pixel_total : 34121 time to create 1 rle with old method : 0.03922605514526367 time for calcul the mask position with numpy : 0.03994178771972656 nb_pixel_total : 30063 time to create 1 rle with old method : 0.03563666343688965 time for calcul the mask position with numpy : 0.04171156883239746 nb_pixel_total : 233673 time to create 1 rle with new method : 0.8866512775421143 time for calcul the mask position with numpy : 0.0402369499206543 nb_pixel_total : 64271 time to create 1 rle with old method : 0.07473158836364746 time for calcul the mask position with numpy : 0.03970026969909668 nb_pixel_total : 11578 time to create 1 rle with old method : 0.013396024703979492 time for calcul the mask position with numpy : 0.03891777992248535 nb_pixel_total : 12198 time to create 1 rle with old method : 0.013829946517944336 time for calcul the mask position with numpy : 0.039655447006225586 nb_pixel_total : 157842 time to create 1 rle with new method : 0.9441845417022705 time for calcul the mask position with numpy : 0.038880109786987305 nb_pixel_total : 13102 time to create 1 rle with old method : 0.01501917839050293 time for calcul the mask position with numpy : 0.039465904235839844 nb_pixel_total : 13106 time to create 1 rle with old method : 0.015079498291015625 time for calcul the mask position with numpy : 0.0399022102355957 nb_pixel_total : 22192 time to create 1 rle with old method : 0.028610944747924805 time for calcul the mask position with numpy : 0.04231762886047363 nb_pixel_total : 71048 time to create 1 rle with old method : 0.07979154586791992 time for calcul the mask position with numpy : 0.038248538970947266 nb_pixel_total : 46609 time to create 1 rle with old method : 0.05291390419006348 time for calcul the mask position with numpy : 0.03973031044006348 nb_pixel_total : 39830 time to create 1 rle with old method : 0.046526193618774414 time for calcul the mask position with numpy : 0.04001307487487793 nb_pixel_total : 16231 time to create 1 rle with old method : 0.018497467041015625 time for calcul the mask position with numpy : 0.0464630126953125 nb_pixel_total : 806565 time to create 1 rle with new method : 1.6840238571166992 time for calcul the mask position with numpy : 0.040194034576416016 nb_pixel_total : 92922 time to create 1 rle with old method : 0.10710906982421875 time for calcul the mask position with numpy : 0.0409085750579834 nb_pixel_total : 173219 time to create 1 rle with new method : 1.454244613647461 time for calcul the mask position with numpy : 0.039736032485961914 nb_pixel_total : 37496 time to create 1 rle with old method : 0.04390978813171387 time for calcul the mask position with numpy : 0.039804697036743164 nb_pixel_total : 6155 time to create 1 rle with old method : 0.007281303405761719 time for calcul the mask position with numpy : 0.03837323188781738 nb_pixel_total : 52161 time to create 1 rle with old method : 0.05753135681152344 time for calcul the mask position with numpy : 0.039392709732055664 nb_pixel_total : 110560 time to create 1 rle with old method : 0.13045668601989746 time for calcul the mask position with numpy : 0.03983640670776367 nb_pixel_total : 28464 time to create 1 rle with old method : 0.0327908992767334 time for calcul the mask position with numpy : 0.03978610038757324 nb_pixel_total : 27286 time to create 1 rle with old method : 0.0322415828704834 time for calcul the mask position with numpy : 0.04030108451843262 nb_pixel_total : 1634 time to create 1 rle with old method : 0.0021681785583496094 time for calcul the mask position with numpy : 0.04040789604187012 nb_pixel_total : 59038 time to create 1 rle with old method : 0.07283186912536621 time for calcul the mask position with numpy : 0.03958249092102051 nb_pixel_total : 5239 time to create 1 rle with old method : 0.006075143814086914 time for calcul the mask position with numpy : 0.03893756866455078 nb_pixel_total : 349 time to create 1 rle with old method : 0.0005993843078613281 time for calcul the mask position with numpy : 0.0395815372467041 nb_pixel_total : 931 time to create 1 rle with old method : 0.001367807388305664 time for calcul the mask position with numpy : 0.040376901626586914 nb_pixel_total : 72607 time to create 1 rle with old method : 0.08533167839050293 time for calcul the mask position with numpy : 0.03905057907104492 nb_pixel_total : 684 time to create 1 rle with old method : 0.0009903907775878906 time for calcul the mask position with numpy : 0.039095163345336914 nb_pixel_total : 19591 time to create 1 rle with old method : 0.022751808166503906 time for calcul the mask position with numpy : 0.04026222229003906 nb_pixel_total : 63237 time to create 1 rle with old method : 0.07573580741882324 time for calcul the mask position with numpy : 0.041236162185668945 nb_pixel_total : 160710 time to create 1 rle with new method : 1.0343306064605713 time for calcul the mask position with numpy : 0.04821634292602539 nb_pixel_total : 1104328 time to create 1 rle with new method : 0.7880861759185791 time for calcul the mask position with numpy : 0.04144430160522461 nb_pixel_total : 208301 time to create 1 rle with new method : 0.7186596393585205 time for calcul the mask position with numpy : 0.038390398025512695 nb_pixel_total : 16856 time to create 1 rle with old method : 0.01978921890258789 time for calcul the mask position with numpy : 0.04011249542236328 nb_pixel_total : 271843 time to create 1 rle with new method : 0.8418121337890625 time for calcul the mask position with numpy : 0.039441585540771484 nb_pixel_total : 66716 time to create 1 rle with old method : 0.07672691345214844 time for calcul the mask position with numpy : 0.03910470008850098 nb_pixel_total : 6227 time to create 1 rle with old method : 0.007211208343505859 time for calcul the mask position with numpy : 0.039658308029174805 nb_pixel_total : 5917 time to create 1 rle with old method : 0.006833553314208984 time for calcul the mask position with numpy : 0.041226863861083984 nb_pixel_total : 269783 time to create 1 rle with new method : 1.3523414134979248 time for calcul the mask position with numpy : 0.03953981399536133 nb_pixel_total : 13245 time to create 1 rle with old method : 0.015539884567260742 time for calcul the mask position with numpy : 0.03990745544433594 nb_pixel_total : 9372 time to create 1 rle with old method : 0.010971546173095703 time for calcul the mask position with numpy : 0.03911614418029785 nb_pixel_total : 34251 time to create 1 rle with old method : 0.03860902786254883 time for calcul the mask position with numpy : 0.03937053680419922 nb_pixel_total : 17591 time to create 1 rle with old method : 0.020624399185180664 create new chi : 23.351059198379517 time to delete rle : 0.006804704666137695 batch 1 Loaded 87 chid ids of type : 4855 Number RLEs to save : 61542 TO DO : save crop sub photo not yet done ! save time : 3.928316354751587 nb_obj : 109 nb_hashtags : 10 time to prepare the origin masks : 54.30421686172485 time for calcul the mask position with numpy : 0.3559587001800537 nb_pixel_total : 2165489 time to create 1 rle with new method : 0.8308403491973877 time for calcul the mask position with numpy : 0.0400240421295166 nb_pixel_total : 61742 time to create 1 rle with old method : 0.06966471672058105 time for calcul the mask position with numpy : 0.03829216957092285 nb_pixel_total : 6750 time to create 1 rle with old method : 0.008046388626098633 time for calcul the mask position with numpy : 0.03895139694213867 nb_pixel_total : 194 time to create 1 rle with old method : 0.0002636909484863281 time for calcul the mask position with numpy : 0.038366079330444336 nb_pixel_total : 8688 time to create 1 rle with old method : 0.00992727279663086 time for calcul the mask position with numpy : 0.03963208198547363 nb_pixel_total : 41083 time to create 1 rle with old method : 0.048349857330322266 time for calcul the mask position with numpy : 0.03934454917907715 nb_pixel_total : 23954 time to create 1 rle with old method : 0.027470827102661133 time for calcul the mask position with numpy : 0.03894782066345215 nb_pixel_total : 2134 time to create 1 rle with old method : 0.0027451515197753906 time for calcul the mask position with numpy : 0.039789676666259766 nb_pixel_total : 11031 time to create 1 rle with old method : 0.01297760009765625 time for calcul the mask position with numpy : 0.03911876678466797 nb_pixel_total : 519 time to create 1 rle with old method : 0.0007758140563964844 time for calcul the mask position with numpy : 0.039250850677490234 nb_pixel_total : 5098 time to create 1 rle with old method : 0.006499290466308594 time for calcul the mask position with numpy : 0.04382038116455078 nb_pixel_total : 304826 time to create 1 rle with new method : 0.9375777244567871 time for calcul the mask position with numpy : 0.04037928581237793 nb_pixel_total : 2984 time to create 1 rle with old method : 0.0037665367126464844 time for calcul the mask position with numpy : 0.0405728816986084 nb_pixel_total : 37285 time to create 1 rle with old method : 0.0435025691986084 time for calcul the mask position with numpy : 0.04077911376953125 nb_pixel_total : 176977 time to create 1 rle with new method : 1.0267987251281738 time for calcul the mask position with numpy : 0.040900230407714844 nb_pixel_total : 160675 time to create 1 rle with new method : 0.9080007076263428 time for calcul the mask position with numpy : 0.04062700271606445 nb_pixel_total : 2158 time to create 1 rle with old method : 0.002733945846557617 time for calcul the mask position with numpy : 0.0423731803894043 nb_pixel_total : 441513 time to create 1 rle with new method : 0.7452597618103027 time for calcul the mask position with numpy : 0.04084157943725586 nb_pixel_total : 83026 time to create 1 rle with old method : 0.10473942756652832 time for calcul the mask position with numpy : 0.03968501091003418 nb_pixel_total : 33087 time to create 1 rle with old method : 0.038283348083496094 time for calcul the mask position with numpy : 0.03963661193847656 nb_pixel_total : 62180 time to create 1 rle with old method : 0.0758357048034668 time for calcul the mask position with numpy : 0.040747642517089844 nb_pixel_total : 273970 time to create 1 rle with new method : 0.8229680061340332 time for calcul the mask position with numpy : 0.04609370231628418 nb_pixel_total : 35840 time to create 1 rle with old method : 0.06398916244506836 time for calcul the mask position with numpy : 0.05359196662902832 nb_pixel_total : 270656 time to create 1 rle with new method : 0.6021966934204102 time for calcul the mask position with numpy : 0.04046893119812012 nb_pixel_total : 27684 time to create 1 rle with old method : 0.034616708755493164 time for calcul the mask position with numpy : 0.040895700454711914 nb_pixel_total : 18789 time to create 1 rle with old method : 0.022119522094726562 time for calcul the mask position with numpy : 0.04027366638183594 nb_pixel_total : 22818 time to create 1 rle with old method : 0.02919745445251465 time for calcul the mask position with numpy : 0.0407252311706543 nb_pixel_total : 47224 time to create 1 rle with old method : 0.055634498596191406 time for calcul the mask position with numpy : 0.040474653244018555 nb_pixel_total : 2155 time to create 1 rle with old method : 0.0028755664825439453 time for calcul the mask position with numpy : 0.04076862335205078 nb_pixel_total : 23288 time to create 1 rle with old method : 0.02806711196899414 time for calcul the mask position with numpy : 0.04088616371154785 nb_pixel_total : 63990 time to create 1 rle with old method : 0.0743415355682373 time for calcul the mask position with numpy : 0.04103851318359375 nb_pixel_total : 86995 time to create 1 rle with old method : 0.10090804100036621 time for calcul the mask position with numpy : 0.03998446464538574 nb_pixel_total : 33547 time to create 1 rle with old method : 0.03782963752746582 time for calcul the mask position with numpy : 0.04573464393615723 nb_pixel_total : 576 time to create 1 rle with old method : 0.0011925697326660156 time for calcul the mask position with numpy : 0.03940129280090332 nb_pixel_total : 54055 time to create 1 rle with old method : 0.06024599075317383 time for calcul the mask position with numpy : 0.04002237319946289 nb_pixel_total : 79177 time to create 1 rle with old method : 0.09543442726135254 time for calcul the mask position with numpy : 0.04413127899169922 nb_pixel_total : 224919 time to create 1 rle with new method : 0.7706480026245117 time for calcul the mask position with numpy : 0.041473388671875 nb_pixel_total : 245097 time to create 1 rle with new method : 1.0672743320465088 time for calcul the mask position with numpy : 0.04150080680847168 nb_pixel_total : 64098 time to create 1 rle with old method : 0.07615089416503906 time for calcul the mask position with numpy : 0.041329383850097656 nb_pixel_total : 65617 time to create 1 rle with old method : 0.07716679573059082 time for calcul the mask position with numpy : 0.039956092834472656 nb_pixel_total : 3269 time to create 1 rle with old method : 0.0038194656372070312 time for calcul the mask position with numpy : 0.03970742225646973 nb_pixel_total : 52743 time to create 1 rle with old method : 0.061783552169799805 time for calcul the mask position with numpy : 0.04042649269104004 nb_pixel_total : 21791 time to create 1 rle with old method : 0.025467395782470703 time for calcul the mask position with numpy : 0.04195547103881836 nb_pixel_total : 195405 time to create 1 rle with new method : 0.5979385375976562 time for calcul the mask position with numpy : 0.039415597915649414 nb_pixel_total : 7491 time to create 1 rle with old method : 0.008827924728393555 time for calcul the mask position with numpy : 0.03899240493774414 nb_pixel_total : 946 time to create 1 rle with old method : 0.0012311935424804688 time for calcul the mask position with numpy : 0.040207862854003906 nb_pixel_total : 3026 time to create 1 rle with old method : 0.003770112991333008 time for calcul the mask position with numpy : 0.041259765625 nb_pixel_total : 19665 time to create 1 rle with old method : 0.022589921951293945 time for calcul the mask position with numpy : 0.03997230529785156 nb_pixel_total : 48533 time to create 1 rle with old method : 0.05613350868225098 time for calcul the mask position with numpy : 0.03983259201049805 nb_pixel_total : 40903 time to create 1 rle with old method : 0.04678797721862793 time for calcul the mask position with numpy : 0.038895368576049805 nb_pixel_total : 230 time to create 1 rle with old method : 0.00037169456481933594 time for calcul the mask position with numpy : 0.03928685188293457 nb_pixel_total : 9501 time to create 1 rle with old method : 0.01107335090637207 time for calcul the mask position with numpy : 0.04073834419250488 nb_pixel_total : 171828 time to create 1 rle with new method : 0.5456268787384033 time for calcul the mask position with numpy : 0.04020047187805176 nb_pixel_total : 20044 time to create 1 rle with old method : 0.02393054962158203 time for calcul the mask position with numpy : 0.039717912673950195 nb_pixel_total : 18947 time to create 1 rle with old method : 0.021909236907958984 time for calcul the mask position with numpy : 0.040491342544555664 nb_pixel_total : 43028 time to create 1 rle with old method : 0.0517880916595459 time for calcul the mask position with numpy : 0.04139518737792969 nb_pixel_total : 178345 time to create 1 rle with new method : 0.6267979145050049 time for calcul the mask position with numpy : 0.03978848457336426 nb_pixel_total : 41666 time to create 1 rle with old method : 0.04829239845275879 time for calcul the mask position with numpy : 0.04093599319458008 nb_pixel_total : 19606 time to create 1 rle with old method : 0.023138046264648438 time for calcul the mask position with numpy : 0.04058575630187988 nb_pixel_total : 25416 time to create 1 rle with old method : 0.031157493591308594 time for calcul the mask position with numpy : 0.045433998107910156 nb_pixel_total : 79105 time to create 1 rle with old method : 0.10219311714172363 time for calcul the mask position with numpy : 0.040640830993652344 nb_pixel_total : 35380 time to create 1 rle with old method : 0.04171133041381836 time for calcul the mask position with numpy : 0.04068922996520996 nb_pixel_total : 17355 time to create 1 rle with old method : 0.02089858055114746 time for calcul the mask position with numpy : 0.04053211212158203 nb_pixel_total : 102551 time to create 1 rle with old method : 0.1177978515625 time for calcul the mask position with numpy : 0.04007411003112793 nb_pixel_total : 92922 time to create 1 rle with old method : 0.10595035552978516 time for calcul the mask position with numpy : 0.03908705711364746 nb_pixel_total : 1481 time to create 1 rle with old method : 0.00200653076171875 time for calcul the mask position with numpy : 0.040992021560668945 nb_pixel_total : 34257 time to create 1 rle with old method : 0.04020500183105469 time for calcul the mask position with numpy : 0.04133486747741699 nb_pixel_total : 204909 time to create 1 rle with new method : 0.42067456245422363 time for calcul the mask position with numpy : 0.04088759422302246 nb_pixel_total : 54072 time to create 1 rle with old method : 0.061849355697631836 time for calcul the mask position with numpy : 0.043868064880371094 nb_pixel_total : 154236 time to create 1 rle with new method : 0.4832429885864258 time for calcul the mask position with numpy : 0.04085731506347656 nb_pixel_total : 74949 time to create 1 rle with old method : 0.08505845069885254 time for calcul the mask position with numpy : 0.041089534759521484 nb_pixel_total : 3374 time to create 1 rle with old method : 0.00394749641418457 time for calcul the mask position with numpy : 0.04017949104309082 nb_pixel_total : 38248 time to create 1 rle with old method : 0.045900583267211914 time for calcul the mask position with numpy : 0.039702415466308594 nb_pixel_total : 14391 time to create 1 rle with old method : 0.016839027404785156 time for calcul the mask position with numpy : 0.04045724868774414 nb_pixel_total : 8306 time to create 1 rle with old method : 0.010103464126586914 time for calcul the mask position with numpy : 0.040116071701049805 nb_pixel_total : 6665 time to create 1 rle with old method : 0.007814407348632812 time for calcul the mask position with numpy : 0.04153728485107422 nb_pixel_total : 454892 time to create 1 rle with new method : 0.5913701057434082 time for calcul the mask position with numpy : 0.04070258140563965 nb_pixel_total : 6694 time to create 1 rle with old method : 0.008250236511230469 time for calcul the mask position with numpy : 0.04169964790344238 nb_pixel_total : 164729 time to create 1 rle with new method : 0.5031356811523438 time for calcul the mask position with numpy : 0.04073643684387207 nb_pixel_total : 128 time to create 1 rle with old method : 0.0002589225769042969 time for calcul the mask position with numpy : 0.04010152816772461 nb_pixel_total : 52375 time to create 1 rle with old method : 0.061629533767700195 time for calcul the mask position with numpy : 0.04306840896606445 nb_pixel_total : 23465 time to create 1 rle with old method : 0.03126859664916992 time for calcul the mask position with numpy : 0.040407657623291016 nb_pixel_total : 16751 time to create 1 rle with old method : 0.019873857498168945 time for calcul the mask position with numpy : 0.040604591369628906 nb_pixel_total : 24068 time to create 1 rle with old method : 0.02825307846069336 time for calcul the mask position with numpy : 0.03992342948913574 nb_pixel_total : 30476 time to create 1 rle with old method : 0.03573894500732422 time for calcul the mask position with numpy : 0.03952527046203613 nb_pixel_total : 420 time to create 1 rle with old method : 0.0010297298431396484 time for calcul the mask position with numpy : 0.03995513916015625 nb_pixel_total : 2180 time to create 1 rle with old method : 0.002817392349243164 time for calcul the mask position with numpy : 0.03976178169250488 nb_pixel_total : 1886 time to create 1 rle with old method : 0.0025336742401123047 time for calcul the mask position with numpy : 0.04448390007019043 nb_pixel_total : 458733 time to create 1 rle with new method : 0.5875775814056396 time for calcul the mask position with numpy : 0.04003405570983887 nb_pixel_total : 15741 time to create 1 rle with old method : 0.019124984741210938 time for calcul the mask position with numpy : 0.03988075256347656 nb_pixel_total : 115 time to create 1 rle with old method : 0.00019216537475585938 time for calcul the mask position with numpy : 0.04033231735229492 nb_pixel_total : 106798 time to create 1 rle with old method : 0.12377619743347168 time for calcul the mask position with numpy : 0.0397191047668457 nb_pixel_total : 7672 time to create 1 rle with old method : 0.009042501449584961 time for calcul the mask position with numpy : 0.04028654098510742 nb_pixel_total : 4270 time to create 1 rle with old method : 0.004958629608154297 time for calcul the mask position with numpy : 0.040498971939086914 nb_pixel_total : 22646 time to create 1 rle with old method : 0.02635025978088379 time for calcul the mask position with numpy : 0.040103912353515625 nb_pixel_total : 65927 time to create 1 rle with old method : 0.07638001441955566 time for calcul the mask position with numpy : 0.040556907653808594 nb_pixel_total : 20694 time to create 1 rle with old method : 0.023641347885131836 time for calcul the mask position with numpy : 0.04058408737182617 nb_pixel_total : 255655 time to create 1 rle with new method : 0.6185147762298584 time for calcul the mask position with numpy : 0.03978776931762695 nb_pixel_total : 23477 time to create 1 rle with old method : 0.027446269989013672 time for calcul the mask position with numpy : 0.04076743125915527 nb_pixel_total : 209205 time to create 1 rle with new method : 0.5430223941802979 time for calcul the mask position with numpy : 0.0398099422454834 nb_pixel_total : 9237 time to create 1 rle with old method : 0.010785341262817383 time for calcul the mask position with numpy : 0.04009652137756348 nb_pixel_total : 126360 time to create 1 rle with old method : 0.1489255428314209 time for calcul the mask position with numpy : 0.04291248321533203 nb_pixel_total : 2924 time to create 1 rle with old method : 0.004449129104614258 time for calcul the mask position with numpy : 0.04125833511352539 nb_pixel_total : 285429 time to create 1 rle with new method : 0.8382570743560791 time for calcul the mask position with numpy : 0.04225635528564453 nb_pixel_total : 178690 time to create 1 rle with new method : 0.8246645927429199 time for calcul the mask position with numpy : 0.04039335250854492 nb_pixel_total : 1937 time to create 1 rle with old method : 0.0025382041931152344 time for calcul the mask position with numpy : 0.039957284927368164 nb_pixel_total : 10264 time to create 1 rle with old method : 0.011678695678710938 time for calcul the mask position with numpy : 0.03994441032409668 nb_pixel_total : 20906 time to create 1 rle with old method : 0.02450418472290039 time for calcul the mask position with numpy : 0.04064226150512695 nb_pixel_total : 9722 time to create 1 rle with old method : 0.011614322662353516 time for calcul the mask position with numpy : 0.04014420509338379 nb_pixel_total : 3462 time to create 1 rle with old method : 0.004019975662231445 create new chi : 23.412938117980957 time to delete rle : 0.008109331130981445 batch 1 Loaded 110 chid ids of type : 4855 Number RLEs to save : 65894 TO DO : save crop sub photo not yet done ! save time : 3.823025703430176 nb_obj : 8 nb_hashtags : 3 time to prepare the origin masks : 12.46928071975708 time for calcul the mask position with numpy : 0.06841611862182617 nb_pixel_total : 3142266 time to create 1 rle with new method : 0.6232259273529053 time for calcul the mask position with numpy : 0.028905153274536133 nb_pixel_total : 4946 time to create 1 rle with old method : 0.007339000701904297 time for calcul the mask position with numpy : 0.03365659713745117 nb_pixel_total : 292079 time to create 1 rle with new method : 1.05930495262146 time for calcul the mask position with numpy : 0.031415700912475586 nb_pixel_total : 235248 time to create 1 rle with new method : 0.5579547882080078 time for calcul the mask position with numpy : 0.032297372817993164 nb_pixel_total : 634300 time to create 1 rle with new method : 0.559420108795166 time for calcul the mask position with numpy : 0.03002619743347168 nb_pixel_total : 19828 time to create 1 rle with old method : 0.02312946319580078 time for calcul the mask position with numpy : 0.029845476150512695 nb_pixel_total : 94717 time to create 1 rle with old method : 0.11084461212158203 time for calcul the mask position with numpy : 0.03900337219238281 nb_pixel_total : 892018 time to create 1 rle with new method : 0.7228271961212158 time for calcul the mask position with numpy : 0.2771928310394287 nb_pixel_total : 4418998 time to create 1 rle with new method : 0.8882274627685547 create new chi : 5.341017723083496 time to delete rle : 0.0015110969543457031 batch 1 Loaded 9 chid ids of type : 4855 Number RLEs to save : 17913 TO DO : save crop sub photo not yet done ! save time : 1.1495518684387207 map_output_result : {1379844884: (0.76134682390364, 'Should be the crop_list due to order', 0.7652498969997622), 1379844865: (0.76134682390364, 'Should be the crop_list due to order', 0.7054782448704309), 1379844831: (0.76134682390364, 'Should be the crop_list due to order', 0.5746591537443666), 1379844813: (0.76134682390364, 'Should be the crop_list due to order', 1.0)} 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 [1379844884, 1379844865, 1379844831, 1379844813] Looping around the photos to save general results len do output : 4 /1379844884.Didn't retrieve data . /1379844865.Didn't retrieve data . /1379844831.Didn't retrieve data . /1379844813.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 ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844884', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844865', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844831', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844813', None, None, None, None, None, '3623813') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.013075590133666992 save_final save missing photos in datou_result : time spend for datou_step_exec : 231.9768009185791 time spend to save output : 0.023291587829589844 total time spend for step 5 : 232.0000925064087 step6:crop_condition Thu Aug 28 15:27:40 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 : 4855 Loading chi in step crop for list_pids : 4 ! batch 1 Loaded 286 chid ids of type : 4855 begin to crop the class : papier param for this class : {'min_score': 0.1} 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 ! map_result returned by crop_photo_return_map_crop : length : 25 About to insert : list_path_to_insert length 25 new photo from crops ! About to upload 25 photos upload in portfolio : 3015255 init cache_photo without model_param we have 25 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387674_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 25 photos in the portfolio 3015255 time of upload the photos Elapsed time : 6.9600489139556885 we have finished the crop for the class : papier begin to crop the class : carton param for this class : {'min_score': 0.1} 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 ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 3015255 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387692_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 27 photos in the portfolio 3015255 time of upload the photos Elapsed time : 7.494233131408691 we have finished the crop for the class : carton begin to crop the class : metal param for this class : {'min_score': 0.1} filtre for class : metal hashtag_id of this class : 492628673 Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! About to upload 5 photos upload in portfolio : 3015255 init cache_photo without model_param we have 5 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387701_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 5 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.9125370979309082 we have finished the crop for the class : metal begin to crop the class : pet_clair param for this class : {'min_score': 0.1} 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 ! Next one ! map_result returned by crop_photo_return_map_crop : length : 19 About to insert : list_path_to_insert length 19 new photo from crops ! About to upload 19 photos upload in portfolio : 3015255 init cache_photo without model_param we have 19 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387709_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 19 photos in the portfolio 3015255 time of upload the photos Elapsed time : 5.741781711578369 we have finished the crop for the class : pet_clair begin to crop the class : pehd param for this class : {'min_score': 0.1} filtre for class : pehd hashtag_id of this class : 628944319 Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 5 About to insert : list_path_to_insert length 5 new photo from crops ! About to upload 5 photos upload in portfolio : 3015255 init cache_photo without model_param we have 5 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387719_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 5 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.603696346282959 we have finished the crop for the class : pehd begin to crop the class : pet_fonce param for this class : {'min_score': 0.1} filtre for class : pet_fonce hashtag_id of this class : 2107755900 Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! About to upload 1 photos upload in portfolio : 3015255 init cache_photo without model_param we have 1 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387722_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 1 photos in the portfolio 3015255 time of upload the photos Elapsed time : 0.6159272193908691 we have finished the crop for the class : pet_fonce begin to crop the class : sac param for this class : {'min_score': 0.1} filtre for class : sac hashtag_id of this class : 492618350 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 24 About to insert : list_path_to_insert length 24 new photo from crops ! About to upload 24 photos upload in portfolio : 3015255 init cache_photo without model_param we have 24 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387730_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 24 photos in the portfolio 3015255 time of upload the photos Elapsed time : 6.255822420120239 we have finished the crop for the class : sac begin to crop the class : textiles param for this class : {'min_score': 0.1} filtre for class : textiles hashtag_id of this class : 494789423 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 : 8 About to insert : list_path_to_insert length 8 new photo from crops ! About to upload 8 photos upload in portfolio : 3015255 init cache_photo without model_param we have 8 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387740_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 8 photos in the portfolio 3015255 time of upload the photos Elapsed time : 2.5183231830596924 we have finished the crop for the class : textiles begin to crop the class : verre param for this class : {'min_score': 0.1} filtre for class : verre hashtag_id of this class : 492631919 begin to crop the class : organique param for this class : {'min_score': 0.1} filtre for class : organique hashtag_id of this class : 530726390 begin to crop the class : dasri param for this class : {'min_score': 0.1} filtre for class : dasri hashtag_id of this class : 1608424396 begin to crop the class : masque param for this class : {'min_score': 0.1} filtre for class : masque hashtag_id of this class : 492626781 begin to crop the class : encombrant param for this class : {'min_score': 0.1} filtre for class : encombrant hashtag_id of this class : 605975549 begin to crop the class : autre param for this class : {'min_score': 0.1} filtre for class : autre hashtag_id of this class : 494826614 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 34 About to insert : list_path_to_insert length 34 new photo from crops ! About to upload 34 photos upload in portfolio : 3015255 init cache_photo without model_param we have 34 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387784_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 34 photos in the portfolio 3015255 time of upload the photos Elapsed time : 10.986201047897339 we have finished the crop for the class : autre begin to crop the class : autre_emballage param for this class : {'min_score': 0.1} filtre for class : autre_emballage hashtag_id of this class : 2107760328 begin to crop the class : autre_non_emballage param for this class : {'min_score': 0.1} filtre for class : autre_non_emballage hashtag_id of this class : 2107760329 Next one ! Next one ! Next one ! Next one ! 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 : 16 About to insert : list_path_to_insert length 16 new photo from crops ! About to upload 16 photos upload in portfolio : 3015255 init cache_photo without model_param we have 16 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387805_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 16 photos in the portfolio 3015255 time of upload the photos Elapsed time : 3.7933239936828613 we have finished the crop for the class : autre_non_emballage begin to crop the class : environnement param for this class : {'min_score': 0.1} filtre for class : environnement hashtag_id of this class : 493012381 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 27 About to insert : list_path_to_insert length 27 new photo from crops ! About to upload 27 photos upload in portfolio : 3015255 init cache_photo without model_param we have 27 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1756387847_3909701 batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! we have uploaded 27 photos in the portfolio 3015255 time of upload the photos Elapsed time : 7.022726774215698 we have finished the crop for the class : environnement delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1379844884, 1379844865, 1379844831, 1379844813] Looping around the photos to save general results len do output : 191 /1379893039Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893040Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893041Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893042Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893043Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893044Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893045Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893046Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893047Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893048Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893049Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893050Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893051Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893052Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893053Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893054Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893055Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893056Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893057Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893058Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893059Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893060Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893061Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893062Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893063Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893096Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893099Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893109Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893110Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893111Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893112Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893113Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893124Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893125Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893126Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893127Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893128Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893129Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893130Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893131Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893132Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893133Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893134Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893135Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893137Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893138Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893139Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893140Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893141Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893142Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893143Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893147Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893148Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893149Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893150Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893151Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893154Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893162Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893183Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893239Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893240Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893241Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893242Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893246Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893247Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893248Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893257Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893258Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893259Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893261Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893262Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893263Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893264Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893265Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893266Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893267Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893268Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893269Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893282Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893548Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893549Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893550Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893552Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893553Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893554Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893556Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893557Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893558Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893560Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893561Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893562Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893564Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893565Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893566Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893568Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893569Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893570Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893572Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893573Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893574Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893575Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893577Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893578Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893579Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893581Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1379893582Didn'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 ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844884', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844865', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844831', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844813', None, None, None, None, None, '3623813') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 577 time used for this insertion : 0.0537266731262207 save_final save missing photos in datou_result : time spend for datou_step_exec : 196.16306924819946 time spend to save output : 0.057810306549072266 total time spend for step 6 : 196.22087955474854 step7:ventilate_hashtags_in_portfolio Thu Aug 28 15:30:56 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 26291504 get user id for portfolio 26291504 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`=26291504 AND mptpi.`type`=4855 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 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`=26291504 AND mptpi.`type`=4855 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 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") 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`=26291504 AND mptpi.`type`=4856 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 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`=26291504 AND mptpi.`type`=4856 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('papier','carton','metal','pet_clair','pehd','pet_fonce','pet_opaque','barquette_opaque','film_plastique','ela','sac','textiles','verre','organique','dasri','masque','encombrant','autre_emballage','autre_non_emballage','environnement','autre','flux_dev','mal_croppe','flou','film_dev_souple','sac_om_plein')) AND mptpi.`min_score`=0.1 To do lien utilise dans velours : https://www.fotonower.com/velours/26295893,26295894,26295895,26295896,26295897,26295902,26295904,26295905,26295906,26295907,26295908,26295909,26295911,26295912,26295913,26295914,26295915,26295916,26295917,26295918?tags=papier,carton,metal,pet_clair,pehd,ela,textiles,verre,organique,dasri,masque,encombrant,autre_non_emballage,environnement,autre,flux_dev,mal_croppe,flou,film_dev_souple,sac_om_plein&datou_id_consolidate=4742&port_consolidate=26291504 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1379844884, 1379844865, 1379844831, 1379844813] Looping around the photos to save general results len do output : 1 /26291504. 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 ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844884', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844865', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844831', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844813', None, None, None, None, None, '3623813') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.013442277908325195 save_final save missing photos in datou_result : time spend for datou_step_exec : 4.572855234146118 time spend to save output : 0.017035245895385742 total time spend for step 7 : 4.589890480041504 step8:final Thu Aug 28 15:31:01 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 : {1379844884: ('0.695182355009527',), 1379844865: ('0.695182355009527',), 1379844831: ('0.695182355009527',), 1379844813: ('0.695182355009527',)} new output for save of step final : {1379844884: ('0.695182355009527',), 1379844865: ('0.695182355009527',), 1379844831: ('0.695182355009527',), 1379844813: ('0.695182355009527',)} [1379844884, 1379844865, 1379844831, 1379844813] Looping around the photos to save general results len do output : 4 /1379844884.Didn't retrieve data . /1379844865.Didn't retrieve data . /1379844831.Didn't retrieve data . /1379844813.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 ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844884', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844865', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844831', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844813', None, None, None, None, None, '3623813') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 12 time used for this insertion : 0.014974832534790039 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.11535358428955078 time spend to save output : 0.01614856719970703 total time spend for step 8 : 0.1315021514892578 step9:velours_tree Thu Aug 28 15:31:01 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 can't find the photo_desc_type Inside saveOutput : final : False verbose : 0 ouput is None No outpout to save, returning out of save general time spend for datou_step_exec : 0.9473772048950195 time spend to save output : 3.933906555175781e-05 total time spend for step 9 : 0.9474165439605713 step10:send_mail_cod Thu Aug 28 15:31:02 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 complete output_args for input 2 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 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_Auto_P26291504_28-08-2025_15_31_02.pdf 26295866 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 .imagette262958661756387862 26295867 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 .imagette262958671756387864 26295868 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette262958681756387866 26295869 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 .imagette262958691756387866 26295870 change filename to text .change filename to text .change filename to text .change filename to text .change filename to text .imagette262958701756387868 26295871 change filename to text .imagette262958711756387868 26295872 imagette262958721756387868 26295873 imagette262958731756387868 26295874 imagette262958741756387868 26295875 imagette262958751756387868 26295876 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 .imagette262958761756387868 26295877 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 .imagette262958771756387870 26295878 imagette262958781756387870 26295879 imagette262958791756387870 26295880 imagette262958801756387870 26295881 imagette262958811756387870 26295883 imagette262958831756387870 26295884 imagette262958841756387870 26295885 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 .imagette262958851756387870 26295887 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 .imagette262958871756387871 26295888 imagette262958881756387873 26295889 imagette262958891756387873 26295890 imagette262958901756387873 26295891 imagette262958911756387873 26295892 imagette262958921756387873 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=26291504 and hashtag_type = 4855 and pcr.hashtag_id = h.hashtag_id; velour_link : https://www.fotonower.com/velours/26295893,26295894,26295895,26295896,26295897,26295902,26295904,26295905,26295906,26295907,26295908,26295909,26295911,26295912,26295913,26295914,26295915,26295916,26295917,26295918?tags=papier,carton,metal,pet_clair,pehd,ela,textiles,verre,organique,dasri,masque,encombrant,autre_non_emballage,environnement,autre,flux_dev,mal_croppe,flou,film_dev_souple,sac_om_plein&datou_id_consolidate=4742&port_consolidate=26291504 your option no_mail is active, we will not send the real mail to your client args[1379844884] : ((1379844884, 519.9012158683921, 492688767), (1379844884, -0.42663953423574486, 496442774), '0.695182355009527') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379844865] : ((1379844865, 470.3560496453144, 492688767), (1379844865, -0.27618525686652634, 496442774), '0.695182355009527') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379844831] : ((1379844831, 885.9160354957713, 2107751945), (1379844831, -0.19281793873694386, 496442774), '0.695182355009527') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1379844813] : ((1379844813, 329.09399776015306, 492688767), (1379844813, -0.6464873082355593, 501862349), '0.695182355009527') We are sending mail with results at report@fotonower.com,cod@fotonower.com refus_total : 0.695182355009527 2022-04-13 10:29:59 0 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291504_28-08-2025_15_31_02.pdf results_Auto_P26291504_28-08-2025_15_31_02.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291504_28-08-2025_15_31_02.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('4741','26291504','results_Auto_P26291504_28-08-2025_15_31_02.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291504_28-08-2025_15_31_02.pdf','pdf','','2.08','0.695182355009527') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1379844884, 1379844865, 1379844831, 1379844813] 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 ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844884', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844865', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844831', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844813', None, None, None, None, None, '3623813') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 4 time used for this insertion : 0.013849020004272461 save_final save missing photos in datou_result : time spend for datou_step_exec : 14.238585233688354 time spend to save output : 0.0221097469329834 total time spend for step 10 : 14.260694980621338 step11:split_time_score Thu Aug 28 15:31:16 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 expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array We expect there is only one output and this part is used while all output are not tuple or array 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 1 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': 861, 'mtr_user_id': 31, 'name': 'Rungis_class_dechets_1212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Rungis_Aluminium,Rungis_Carton,Rungis_Papier,Rungis_Plastique_clair,Rungis_Plastique_dur,Rungis_Plastique_fonce,Rungis_Tapis_vide,Rungis_Tetrapak', 'svm_portfolios_learning': '1160730,571842,571844,571839,571933,571840,571841,572307', 'photo_hashtag_type': 999, 'photo_desc_type': 3963, 'type_classification': 'caffe', 'hashtag_id_list': '2107751280,2107750907,2107750908,2107750909,2107750910,2107750911,2107750912,2107750913'}] 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'}] (('51', 1), ('52', 3)) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 26082025 26291504 Nombre de photos uploadées : 4 / 23040 (0%) 26082025 26291504 Nombre de photos taguées (types de déchets): 0 / 4 (0%) 26082025 26291504 Nombre de photos taguées (volume) : 0 / 4 (0%) elapsed_time : load_data_split_time_score 7.152557373046875e-06 elapsed_time : order_list_meta_photo_and_scores 1.4781951904296875e-05 ???? elapsed_time : fill_and_build_computed_from_old_data 0.0005500316619873047 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.22202682495117188 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps Qualite : 0.695182355009527 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291504_28-08-2025_15_31_02.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291504 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( 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`=26291504 AND mptpi.`type`=4855 To do Qualite : 0.35901833075514267 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291505_28-08-2025_14_55_06.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291505 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( 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`=26291505 AND mptpi.`type`=4855 To do Qualite : 0.42566700782808753 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291506_28-08-2025_15_22_04.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291506 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( 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`=26291506 AND mptpi.`type`=4855 To do Qualite : 0.2567984737532319 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291507_28-08-2025_14_35_28.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291507 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( 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`=26291507 AND mptpi.`type`=4855 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291508 order by id desc limit 1 Qualite : 0.44521359328707644 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291509_28-08-2025_14_18_17.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291509 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( 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`=26291509 AND mptpi.`type`=4855 To do Qualite : 0.5227519267425498 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26291510_28-08-2025_12_42_57.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26291510 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 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! 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 ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( 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`=26291510 AND mptpi.`type`=4855 To do NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'26082025': {'nb_upload': 4, '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 [1379844884, 1379844865, 1379844831, 1379844813] Looping around the photos to save general results len do output : 1 /26291504Didn'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 ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844884', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844865', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844831', None, None, None, None, None, '3623813') ('4741', None, None, None, None, None, None, None, '3623813') ('4741', '26291504', '1379844813', None, None, None, None, None, '3623813') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.013538837432861328 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.731194019317627 time spend to save output : 0.013874053955078125 total time spend for step 11 : 1.745068073272705 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 4 set_done_treatment 385.47user 155.20system 9:54.99elapsed 90%CPU (0avgtext+0avgdata 5905300maxresident)k 1153920inputs+371224outputs (11770major+28448186minor)pagefaults 0swaps