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 : 2186426 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 : ['3696150'] with mtr_portfolio_ids : ['26763391'] and first list_photo_ids : [] new path : /proc/2186426/ 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 , BFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 5 ; length of list_pids : 5 ; length of list_args : 5 time to download the photos : 1.1067540645599365 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 Sep 11 20:21:28 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 havn't enough memory gpu , need / 3000 l 3632 free memory gpu now : 1302 wait 20 seconds l 3637 free memory gpu now : 1302 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-09-11 20:21:54.347073: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-09-11 20:21:54.388840: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-09-11 20:21:54.391375: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f2b5c000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-09-11 20:21:54.391435: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-09-11 20:21:54.402036: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-09-11 20:21:54.703210: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3dd83150 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-09-11 20:21:54.703285: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-09-11 20:21:54.705359: 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 2025-09-11 20:21:54.710559: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:21:54.780370: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:21:54.828001: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-11 20:21:54.832545: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-11 20:21:54.953684: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-11 20:21:54.982099: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-11 20:21:55.065581: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-11 20:21:55.066670: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-11 20:21:55.067153: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:21:55.068664: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-11 20:21:55.068687: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-11 20:21:55.068698: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-11 20:21:55.071042: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 983 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. 2025-09-11 20:21:55.815471: 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 2025-09-11 20:21:55.815671: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:21:55.815699: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:21:55.815723: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-11 20:21:55.815747: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-11 20:21:55.815771: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-11 20:21:55.815798: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-11 20:21:55.815822: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-11 20:21:55.817652: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-11 20:21:55.820195: 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 2025-09-11 20:21:55.820304: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:21:55.820331: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:21:55.820397: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-11 20:21:55.820423: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-11 20:21:55.820447: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-11 20:21:55.820470: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-11 20:21:55.820493: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-11 20:21:55.822303: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-11 20:21:55.822369: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-11 20:21:55.822387: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-11 20:21:55.822401: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-11 20:21:55.824300: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 983 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 : [] 2025-09-11 20:22:07.837897: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:22:08.252990: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-11 20:22:10.484042: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.484725: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.492047: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.492170: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.553349: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.553498: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.599861: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.599935: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.09GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.653765: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-09-11 20:22:10.653812: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 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 : 5 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 18 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 9 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 16 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.63750 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 5 Detection mask done ! Trying to reset tf kernel 2187611 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 8701 tf kernel not reseted sub process len(results) : 5 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 5 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 : 10215 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 : 0.0019352436065673828 nb_pixel_total : 86481 time to create 1 rle with old method : 0.10701608657836914 length of segment : 197 time for calcul the mask position with numpy : 0.0003941059112548828 nb_pixel_total : 21213 time to create 1 rle with old method : 0.024611711502075195 length of segment : 199 time for calcul the mask position with numpy : 0.0007665157318115234 nb_pixel_total : 24134 time to create 1 rle with old method : 0.031035423278808594 length of segment : 217 time for calcul the mask position with numpy : 0.0007450580596923828 nb_pixel_total : 44732 time to create 1 rle with old method : 0.05080294609069824 length of segment : 270 time for calcul the mask position with numpy : 0.0003657341003417969 nb_pixel_total : 15844 time to create 1 rle with old method : 0.018464088439941406 length of segment : 236 time for calcul the mask position with numpy : 0.0003018379211425781 nb_pixel_total : 16049 time to create 1 rle with old method : 0.018961429595947266 length of segment : 111 time for calcul the mask position with numpy : 0.001079559326171875 nb_pixel_total : 74542 time to create 1 rle with old method : 0.08593201637268066 length of segment : 250 time for calcul the mask position with numpy : 0.003998279571533203 nb_pixel_total : 209875 time to create 1 rle with new method : 0.010846138000488281 length of segment : 329 time for calcul the mask position with numpy : 0.00044035911560058594 nb_pixel_total : 20723 time to create 1 rle with old method : 0.024725914001464844 length of segment : 146 time for calcul the mask position with numpy : 0.004912614822387695 nb_pixel_total : 194582 time to create 1 rle with new method : 0.09987473487854004 length of segment : 874 time for calcul the mask position with numpy : 0.007837533950805664 nb_pixel_total : 249553 time to create 1 rle with new method : 0.11547708511352539 length of segment : 710 time for calcul the mask position with numpy : 0.0011875629425048828 nb_pixel_total : 5264 time to create 1 rle with old method : 0.007348299026489258 length of segment : 99 time for calcul the mask position with numpy : 0.00046539306640625 nb_pixel_total : 21019 time to create 1 rle with old method : 0.027277231216430664 length of segment : 119 time for calcul the mask position with numpy : 0.0013153553009033203 nb_pixel_total : 89207 time to create 1 rle with old method : 0.13985776901245117 length of segment : 479 time for calcul the mask position with numpy : 0.0007092952728271484 nb_pixel_total : 19241 time to create 1 rle with old method : 0.0334925651550293 length of segment : 114 time for calcul the mask position with numpy : 0.0011970996856689453 nb_pixel_total : 87096 time to create 1 rle with old method : 0.10216331481933594 length of segment : 483 time for calcul the mask position with numpy : 0.0004458427429199219 nb_pixel_total : 12416 time to create 1 rle with old method : 0.014980554580688477 length of segment : 168 time for calcul the mask position with numpy : 0.0003628730773925781 nb_pixel_total : 18394 time to create 1 rle with old method : 0.021935701370239258 length of segment : 120 time for calcul the mask position with numpy : 0.0009026527404785156 nb_pixel_total : 55566 time to create 1 rle with old method : 0.0637516975402832 length of segment : 306 time for calcul the mask position with numpy : 0.0005002021789550781 nb_pixel_total : 29797 time to create 1 rle with old method : 0.03637838363647461 length of segment : 195 time for calcul the mask position with numpy : 0.0008828639984130859 nb_pixel_total : 50354 time to create 1 rle with old method : 0.05811619758605957 length of segment : 277 time for calcul the mask position with numpy : 0.0005669593811035156 nb_pixel_total : 43252 time to create 1 rle with old method : 0.049457550048828125 length of segment : 332 time for calcul the mask position with numpy : 0.0007901191711425781 nb_pixel_total : 41231 time to create 1 rle with old method : 0.04765629768371582 length of segment : 287 time for calcul the mask position with numpy : 0.0002968311309814453 nb_pixel_total : 15516 time to create 1 rle with old method : 0.018558979034423828 length of segment : 120 time for calcul the mask position with numpy : 0.0003974437713623047 nb_pixel_total : 18804 time to create 1 rle with old method : 0.02226853370666504 length of segment : 183 time for calcul the mask position with numpy : 0.0004329681396484375 nb_pixel_total : 28071 time to create 1 rle with old method : 0.03237032890319824 length of segment : 288 time for calcul the mask position with numpy : 0.0004646778106689453 nb_pixel_total : 29179 time to create 1 rle with old method : 0.033731937408447266 length of segment : 281 time for calcul the mask position with numpy : 0.004338502883911133 nb_pixel_total : 125586 time to create 1 rle with old method : 0.14315581321716309 length of segment : 398 time for calcul the mask position with numpy : 0.001300811767578125 nb_pixel_total : 32473 time to create 1 rle with old method : 0.03791999816894531 length of segment : 302 time for calcul the mask position with numpy : 0.07289624214172363 nb_pixel_total : 688854 time to create 1 rle with new method : 0.2714989185333252 length of segment : 825 time for calcul the mask position with numpy : 0.0008256435394287109 nb_pixel_total : 24067 time to create 1 rle with old method : 0.028198957443237305 length of segment : 197 time for calcul the mask position with numpy : 0.0021393299102783203 nb_pixel_total : 67678 time to create 1 rle with old method : 0.07894039154052734 length of segment : 514 time for calcul the mask position with numpy : 0.002948760986328125 nb_pixel_total : 104965 time to create 1 rle with old method : 0.1191415786743164 length of segment : 788 time for calcul the mask position with numpy : 0.0018410682678222656 nb_pixel_total : 44942 time to create 1 rle with old method : 0.05770421028137207 length of segment : 387 time for calcul the mask position with numpy : 0.003390789031982422 nb_pixel_total : 102693 time to create 1 rle with old method : 0.14994287490844727 length of segment : 425 time for calcul the mask position with numpy : 0.01928877830505371 nb_pixel_total : 649773 time to create 1 rle with new method : 0.07350397109985352 length of segment : 809 time for calcul the mask position with numpy : 0.001146554946899414 nb_pixel_total : 42101 time to create 1 rle with old method : 0.04804086685180664 length of segment : 285 time for calcul the mask position with numpy : 0.0009415149688720703 nb_pixel_total : 41947 time to create 1 rle with old method : 0.05253744125366211 length of segment : 325 time for calcul the mask position with numpy : 0.0008096694946289062 nb_pixel_total : 12635 time to create 1 rle with old method : 0.015093326568603516 length of segment : 159 time for calcul the mask position with numpy : 0.0004425048828125 nb_pixel_total : 5913 time to create 1 rle with old method : 0.007195711135864258 length of segment : 134 time for calcul the mask position with numpy : 0.0004639625549316406 nb_pixel_total : 23024 time to create 1 rle with old method : 0.028441667556762695 length of segment : 196 time for calcul the mask position with numpy : 0.001581430435180664 nb_pixel_total : 87838 time to create 1 rle with old method : 0.10072684288024902 length of segment : 491 time for calcul the mask position with numpy : 0.008917808532714844 nb_pixel_total : 297185 time to create 1 rle with new method : 0.05437612533569336 length of segment : 839 time for calcul the mask position with numpy : 0.0009322166442871094 nb_pixel_total : 32726 time to create 1 rle with old method : 0.03746199607849121 length of segment : 252 time for calcul the mask position with numpy : 0.001489400863647461 nb_pixel_total : 33356 time to create 1 rle with old method : 0.038507938385009766 length of segment : 511 time for calcul the mask position with numpy : 0.006196737289428711 nb_pixel_total : 283480 time to create 1 rle with new method : 0.013508081436157227 length of segment : 717 time for calcul the mask position with numpy : 0.016199588775634766 nb_pixel_total : 910001 time to create 1 rle with new method : 0.08685779571533203 length of segment : 1014 time for calcul the mask position with numpy : 0.0016374588012695312 nb_pixel_total : 34755 time to create 1 rle with old method : 0.03936290740966797 length of segment : 268 time for calcul the mask position with numpy : 0.0005376338958740234 nb_pixel_total : 23064 time to create 1 rle with old method : 0.027506351470947266 length of segment : 113 time for calcul the mask position with numpy : 0.0023348331451416016 nb_pixel_total : 96257 time to create 1 rle with old method : 0.1100928783416748 length of segment : 1026 time for calcul the mask position with numpy : 0.21984124183654785 nb_pixel_total : 3848343 time to create 1 rle with new method : 1.069582223892212 length of segment : 3597 time for calcul the mask position with numpy : 0.4212803840637207 nb_pixel_total : 2489634 time to create 1 rle with new method : 0.4311971664428711 length of segment : 1872 time for calcul the mask position with numpy : 0.3676629066467285 nb_pixel_total : 3986458 time to create 1 rle with new method : 0.6626176834106445 length of segment : 2349 time for calcul the mask position with numpy : 0.4969363212585449 nb_pixel_total : 4310373 time to create 1 rle with new method : 0.6520118713378906 length of segment : 3526 time for calcul the mask position with numpy : 0.0021910667419433594 nb_pixel_total : 97955 time to create 1 rle with old method : 0.11047816276550293 length of segment : 327 time spent for convertir_results : 17.01643681526184 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 55 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 87.73982429504395 time spend to save output : 0.15169358253479004 total time spend for step 1 : 87.89151787757874 step2:mask_detect Thu Sep 11 20:22:56 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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 : 6591 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-09-11 20:22:59.499625: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-09-11 20:22:59.528513: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3492910000 Hz 2025-09-11 20:22:59.530788: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f2b54000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-09-11 20:22:59.530850: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-09-11 20:22:59.535267: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-09-11 20:22:59.694910: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3e42b3d0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-09-11 20:22:59.695012: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-09-11 20:22:59.696537: 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 2025-09-11 20:22:59.697396: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:22:59.702211: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:22:59.706043: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-11 20:22:59.706512: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-11 20:22:59.710334: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-11 20:22:59.712082: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-11 20:22:59.718403: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-11 20:22:59.719860: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-11 20:22:59.719974: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:22:59.720787: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-11 20:22:59.720804: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-11 20:22:59.720813: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-11 20:22:59.722107: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6053 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. 2025-09-11 20:22:59.966568: 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 2025-09-11 20:22:59.966673: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:22:59.966800: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:22:59.966818: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-11 20:22:59.966835: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-11 20:22:59.966852: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-11 20:22:59.966868: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-11 20:22:59.966884: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-11 20:22:59.967960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-11 20:22:59.969221: 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 2025-09-11 20:22:59.969315: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-09-11 20:22:59.969349: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:22:59.969373: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-09-11 20:22:59.969390: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-09-11 20:22:59.969406: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-09-11 20:22:59.969422: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-09-11 20:22:59.969438: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-09-11 20:22:59.970497: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-09-11 20:22:59.970532: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-09-11 20:22:59.970541: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-09-11 20:22:59.970549: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-09-11 20:22:59.971743: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6053 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 : [] 2025-09-11 20:23:12.343888: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-09-11 20:23:12.546648: 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 : 5 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 59 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 81 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 65 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 132.63750 image_metas shape: (1, 17) min: 0.00000 max: 4160.00000 nb d'objets trouves : 20 NEW PHOTO Processing 1 images image shape: (4160, 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: 4160.00000 nb d'objets trouves : 8 Detection mask done ! Trying to reset tf kernel 2190344 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5079 tf kernel not reseted sub process len(results) : 5 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 5 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 : 10368 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 : 0.005636930465698242 nb_pixel_total : 111462 time to create 1 rle with old method : 0.153916597366333 length of segment : 340 time for calcul the mask position with numpy : 0.0015664100646972656 nb_pixel_total : 43032 time to create 1 rle with old method : 0.06951212882995605 length of segment : 230 time for calcul the mask position with numpy : 0.023606061935424805 nb_pixel_total : 1088066 time to create 1 rle with new method : 0.09451484680175781 length of segment : 1244 time for calcul the mask position with numpy : 0.0008034706115722656 nb_pixel_total : 30634 time to create 1 rle with old method : 0.03537917137145996 length of segment : 186 time for calcul the mask position with numpy : 0.0012135505676269531 nb_pixel_total : 54641 time to create 1 rle with old method : 0.0639333724975586 length of segment : 211 time for calcul the mask position with numpy : 0.013552188873291016 nb_pixel_total : 589203 time to create 1 rle with new method : 0.06687116622924805 length of segment : 1229 time for calcul the mask position with numpy : 0.012405633926391602 nb_pixel_total : 638943 time to create 1 rle with new method : 0.02835369110107422 length of segment : 859 time for calcul the mask position with numpy : 0.004393100738525391 nb_pixel_total : 273488 time to create 1 rle with new method : 0.01224827766418457 length of segment : 1078 time for calcul the mask position with numpy : 0.00046896934509277344 nb_pixel_total : 14197 time to create 1 rle with old method : 0.016830921173095703 length of segment : 93 time for calcul the mask position with numpy : 0.003993034362792969 nb_pixel_total : 193647 time to create 1 rle with new method : 0.009994983673095703 length of segment : 505 time for calcul the mask position with numpy : 0.013967037200927734 nb_pixel_total : 668690 time to create 1 rle with new method : 0.04225921630859375 length of segment : 857 time for calcul the mask position with numpy : 0.002575397491455078 nb_pixel_total : 113918 time to create 1 rle with old method : 0.13086628913879395 length of segment : 340 time for calcul the mask position with numpy : 0.002293109893798828 nb_pixel_total : 109672 time to create 1 rle with old method : 0.12499570846557617 length of segment : 463 time for calcul the mask position with numpy : 0.0012094974517822266 nb_pixel_total : 37995 time to create 1 rle with old method : 0.04501223564147949 length of segment : 256 time for calcul the mask position with numpy : 0.003885030746459961 nb_pixel_total : 140278 time to create 1 rle with old method : 0.1580963134765625 length of segment : 630 time for calcul the mask position with numpy : 0.001384735107421875 nb_pixel_total : 64944 time to create 1 rle with old method : 0.07431221008300781 length of segment : 244 time for calcul the mask position with numpy : 0.007931232452392578 nb_pixel_total : 371775 time to create 1 rle with new method : 0.03607463836669922 length of segment : 732 time for calcul the mask position with numpy : 0.002808809280395508 nb_pixel_total : 139282 time to create 1 rle with old method : 0.15962910652160645 length of segment : 502 time for calcul the mask position with numpy : 0.006941318511962891 nb_pixel_total : 38122 time to create 1 rle with old method : 0.06055116653442383 length of segment : 197 time for calcul the mask position with numpy : 0.0026853084564208984 nb_pixel_total : 78104 time to create 1 rle with old method : 0.14337491989135742 length of segment : 292 time for calcul the mask position with numpy : 0.0007467269897460938 nb_pixel_total : 16667 time to create 1 rle with old method : 0.030930757522583008 length of segment : 171 time for calcul the mask position with numpy : 0.004439353942871094 nb_pixel_total : 94558 time to create 1 rle with old method : 0.17824673652648926 length of segment : 245 time for calcul the mask position with numpy : 0.0073833465576171875 nb_pixel_total : 252184 time to create 1 rle with new method : 0.01537632942199707 length of segment : 570 time for calcul the mask position with numpy : 0.0026450157165527344 nb_pixel_total : 75266 time to create 1 rle with old method : 0.13631677627563477 length of segment : 384 time for calcul the mask position with numpy : 0.001556396484375 nb_pixel_total : 73514 time to create 1 rle with old method : 0.09108805656433105 length of segment : 270 time for calcul the mask position with numpy : 0.012494087219238281 nb_pixel_total : 303685 time to create 1 rle with new method : 0.0268709659576416 length of segment : 1029 time for calcul the mask position with numpy : 0.006638526916503906 nb_pixel_total : 237471 time to create 1 rle with new method : 0.01945018768310547 length of segment : 1260 time for calcul the mask position with numpy : 0.004318952560424805 nb_pixel_total : 219826 time to create 1 rle with new method : 0.012190580368041992 length of segment : 662 time for calcul the mask position with numpy : 0.0025861263275146484 nb_pixel_total : 154580 time to create 1 rle with new method : 0.006334543228149414 length of segment : 377 time for calcul the mask position with numpy : 0.0019135475158691406 nb_pixel_total : 97439 time to create 1 rle with old method : 0.11609745025634766 length of segment : 526 time for calcul the mask position with numpy : 0.0016791820526123047 nb_pixel_total : 100497 time to create 1 rle with old method : 0.11291909217834473 length of segment : 346 time for calcul the mask position with numpy : 0.011861801147460938 nb_pixel_total : 453094 time to create 1 rle with new method : 0.04062962532043457 length of segment : 675 time for calcul the mask position with numpy : 0.001966238021850586 nb_pixel_total : 102662 time to create 1 rle with old method : 0.11461353302001953 length of segment : 517 time for calcul the mask position with numpy : 0.0014188289642333984 nb_pixel_total : 75612 time to create 1 rle with old method : 0.08564162254333496 length of segment : 234 time for calcul the mask position with numpy : 0.0007953643798828125 nb_pixel_total : 24326 time to create 1 rle with old method : 0.03234219551086426 length of segment : 234 time for calcul the mask position with numpy : 0.0008361339569091797 nb_pixel_total : 30743 time to create 1 rle with old method : 0.04122209548950195 length of segment : 228 time for calcul the mask position with numpy : 0.0009312629699707031 nb_pixel_total : 32003 time to create 1 rle with old method : 0.037317752838134766 length of segment : 191 time for calcul the mask position with numpy : 0.0034224987030029297 nb_pixel_total : 144000 time to create 1 rle with old method : 0.17009902000427246 length of segment : 574 time for calcul the mask position with numpy : 0.0018105506896972656 nb_pixel_total : 82905 time to create 1 rle with old method : 0.09492683410644531 length of segment : 376 time for calcul the mask position with numpy : 0.000993967056274414 nb_pixel_total : 48704 time to create 1 rle with old method : 0.055864572525024414 length of segment : 205 time for calcul the mask position with numpy : 0.021700620651245117 nb_pixel_total : 1089528 time to create 1 rle with new method : 0.10989856719970703 length of segment : 1449 time for calcul the mask position with numpy : 0.0007395744323730469 nb_pixel_total : 35553 time to create 1 rle with old method : 0.039385318756103516 length of segment : 218 time for calcul the mask position with numpy : 0.003674745559692383 nb_pixel_total : 154854 time to create 1 rle with new method : 0.011241912841796875 length of segment : 571 time for calcul the mask position with numpy : 0.0018930435180664062 nb_pixel_total : 72492 time to create 1 rle with old method : 0.08055830001831055 length of segment : 365 time for calcul the mask position with numpy : 0.0033881664276123047 nb_pixel_total : 145750 time to create 1 rle with old method : 0.15978789329528809 length of segment : 443 time for calcul the mask position with numpy : 0.0015430450439453125 nb_pixel_total : 76875 time to create 1 rle with old method : 0.08163833618164062 length of segment : 405 time for calcul the mask position with numpy : 0.002559661865234375 nb_pixel_total : 115527 time to create 1 rle with old method : 0.12703895568847656 length of segment : 521 time for calcul the mask position with numpy : 0.0039052963256835938 nb_pixel_total : 161494 time to create 1 rle with new method : 0.011137008666992188 length of segment : 497 time for calcul the mask position with numpy : 0.00805974006652832 nb_pixel_total : 390873 time to create 1 rle with new method : 0.16441607475280762 length of segment : 981 time for calcul the mask position with numpy : 0.00512385368347168 nb_pixel_total : 266472 time to create 1 rle with new method : 0.014408111572265625 length of segment : 465 time for calcul the mask position with numpy : 0.001424551010131836 nb_pixel_total : 79340 time to create 1 rle with old method : 0.08641767501831055 length of segment : 238 time for calcul the mask position with numpy : 0.004849433898925781 nb_pixel_total : 201594 time to create 1 rle with new method : 0.014265775680541992 length of segment : 662 time for calcul the mask position with numpy : 0.001775503158569336 nb_pixel_total : 86424 time to create 1 rle with old method : 0.09534549713134766 length of segment : 425 time for calcul the mask position with numpy : 0.001954793930053711 nb_pixel_total : 111165 time to create 1 rle with old method : 0.12391471862792969 length of segment : 257 time for calcul the mask position with numpy : 0.002417325973510742 nb_pixel_total : 51576 time to create 1 rle with old method : 0.06945180892944336 length of segment : 327 time for calcul the mask position with numpy : 0.006606340408325195 nb_pixel_total : 263360 time to create 1 rle with new method : 0.018259763717651367 length of segment : 606 time for calcul the mask position with numpy : 0.005354881286621094 nb_pixel_total : 254821 time to create 1 rle with new method : 0.016476869583129883 length of segment : 897 time for calcul the mask position with numpy : 0.004145622253417969 nb_pixel_total : 150355 time to create 1 rle with new method : 0.012746095657348633 length of segment : 549 time for calcul the mask position with numpy : 0.007143259048461914 nb_pixel_total : 434514 time to create 1 rle with new method : 0.017794132232666016 length of segment : 698 time for calcul the mask position with numpy : 0.0013713836669921875 nb_pixel_total : 60243 time to create 1 rle with old method : 0.08676266670227051 length of segment : 327 time for calcul the mask position with numpy : 0.0013644695281982422 nb_pixel_total : 52441 time to create 1 rle with old method : 0.0676107406616211 length of segment : 398 time for calcul the mask position with numpy : 0.0015070438385009766 nb_pixel_total : 56851 time to create 1 rle with old method : 0.06373476982116699 length of segment : 327 time for calcul the mask position with numpy : 0.0013616085052490234 nb_pixel_total : 49252 time to create 1 rle with old method : 0.05513787269592285 length of segment : 272 time for calcul the mask position with numpy : 0.0010552406311035156 nb_pixel_total : 43375 time to create 1 rle with old method : 0.04888653755187988 length of segment : 297 time for calcul the mask position with numpy : 0.0011358261108398438 nb_pixel_total : 29957 time to create 1 rle with old method : 0.03437924385070801 length of segment : 328 time for calcul the mask position with numpy : 0.0031931400299072266 nb_pixel_total : 125651 time to create 1 rle with old method : 0.13867926597595215 length of segment : 471 time for calcul the mask position with numpy : 0.004184246063232422 nb_pixel_total : 185688 time to create 1 rle with new method : 0.012115001678466797 length of segment : 569 time for calcul the mask position with numpy : 0.0022783279418945312 nb_pixel_total : 70713 time to create 1 rle with old method : 0.0793912410736084 length of segment : 358 time for calcul the mask position with numpy : 0.0015094280242919922 nb_pixel_total : 52107 time to create 1 rle with old method : 0.07046914100646973 length of segment : 303 time for calcul the mask position with numpy : 0.007357120513916016 nb_pixel_total : 265088 time to create 1 rle with new method : 0.0216062068939209 length of segment : 568 time for calcul the mask position with numpy : 0.0007672309875488281 nb_pixel_total : 20595 time to create 1 rle with old method : 0.02375960350036621 length of segment : 169 time for calcul the mask position with numpy : 0.0012671947479248047 nb_pixel_total : 29533 time to create 1 rle with old method : 0.033715009689331055 length of segment : 512 time for calcul the mask position with numpy : 0.0004572868347167969 nb_pixel_total : 18065 time to create 1 rle with old method : 0.02117466926574707 length of segment : 139 time for calcul the mask position with numpy : 0.0025572776794433594 nb_pixel_total : 123109 time to create 1 rle with old method : 0.14130258560180664 length of segment : 442 time for calcul the mask position with numpy : 0.0007655620574951172 nb_pixel_total : 26891 time to create 1 rle with old method : 0.03038954734802246 length of segment : 215 time for calcul the mask position with numpy : 0.0037355422973632812 nb_pixel_total : 144893 time to create 1 rle with old method : 0.15901708602905273 length of segment : 427 time for calcul the mask position with numpy : 0.0010602474212646484 nb_pixel_total : 47612 time to create 1 rle with old method : 0.05240797996520996 length of segment : 243 time for calcul the mask position with numpy : 0.0013849735260009766 nb_pixel_total : 57859 time to create 1 rle with old method : 0.06307697296142578 length of segment : 290 time for calcul the mask position with numpy : 0.0021789073944091797 nb_pixel_total : 117512 time to create 1 rle with old method : 0.12764215469360352 length of segment : 654 time for calcul the mask position with numpy : 0.0055751800537109375 nb_pixel_total : 239809 time to create 1 rle with new method : 0.016637802124023438 length of segment : 635 time for calcul the mask position with numpy : 0.011929512023925781 nb_pixel_total : 476774 time to create 1 rle with new method : 0.0304262638092041 length of segment : 1172 time for calcul the mask position with numpy : 0.005244255065917969 nb_pixel_total : 218929 time to create 1 rle with new method : 0.01488351821899414 length of segment : 802 time for calcul the mask position with numpy : 0.0006117820739746094 nb_pixel_total : 28342 time to create 1 rle with old method : 0.031453609466552734 length of segment : 252 time for calcul the mask position with numpy : 0.004760026931762695 nb_pixel_total : 227410 time to create 1 rle with new method : 0.01296234130859375 length of segment : 523 time for calcul the mask position with numpy : 0.002529621124267578 nb_pixel_total : 103496 time to create 1 rle with old method : 0.11332249641418457 length of segment : 431 time for calcul the mask position with numpy : 0.000865936279296875 nb_pixel_total : 39928 time to create 1 rle with old method : 0.044632673263549805 length of segment : 273 time for calcul the mask position with numpy : 0.001428365707397461 nb_pixel_total : 54076 time to create 1 rle with old method : 0.05989956855773926 length of segment : 373 time for calcul the mask position with numpy : 0.005307435989379883 nb_pixel_total : 257320 time to create 1 rle with new method : 0.014351129531860352 length of segment : 694 time for calcul the mask position with numpy : 0.0031070709228515625 nb_pixel_total : 100249 time to create 1 rle with old method : 0.1114339828491211 length of segment : 516 time for calcul the mask position with numpy : 0.0031359195709228516 nb_pixel_total : 136275 time to create 1 rle with old method : 0.15133905410766602 length of segment : 347 time for calcul the mask position with numpy : 0.0014548301696777344 nb_pixel_total : 66340 time to create 1 rle with old method : 0.07492899894714355 length of segment : 183 time for calcul the mask position with numpy : 0.0011925697326660156 nb_pixel_total : 50648 time to create 1 rle with old method : 0.05711650848388672 length of segment : 250 time for calcul the mask position with numpy : 0.002153635025024414 nb_pixel_total : 65392 time to create 1 rle with old method : 0.07466554641723633 length of segment : 301 time for calcul the mask position with numpy : 0.0006237030029296875 nb_pixel_total : 17416 time to create 1 rle with old method : 0.027896881103515625 length of segment : 139 time for calcul the mask position with numpy : 0.0020246505737304688 nb_pixel_total : 80625 time to create 1 rle with old method : 0.09090065956115723 length of segment : 474 time for calcul the mask position with numpy : 0.0005564689636230469 nb_pixel_total : 19367 time to create 1 rle with old method : 0.02199721336364746 length of segment : 153 time for calcul the mask position with numpy : 0.0005240440368652344 nb_pixel_total : 18780 time to create 1 rle with old method : 0.021706104278564453 length of segment : 143 time for calcul the mask position with numpy : 0.009525537490844727 nb_pixel_total : 402815 time to create 1 rle with new method : 0.026944637298583984 length of segment : 1075 time for calcul the mask position with numpy : 0.019110918045043945 nb_pixel_total : 904669 time to create 1 rle with new method : 0.2889096736907959 length of segment : 1593 time for calcul the mask position with numpy : 0.001722097396850586 nb_pixel_total : 77429 time to create 1 rle with old method : 0.08625602722167969 length of segment : 339 time for calcul the mask position with numpy : 0.005744457244873047 nb_pixel_total : 196811 time to create 1 rle with new method : 0.018897294998168945 length of segment : 797 time for calcul the mask position with numpy : 0.0033257007598876953 nb_pixel_total : 88128 time to create 1 rle with old method : 0.10803747177124023 length of segment : 521 time for calcul the mask position with numpy : 0.004157543182373047 nb_pixel_total : 112326 time to create 1 rle with old method : 0.1479947566986084 length of segment : 582 time for calcul the mask position with numpy : 0.002286672592163086 nb_pixel_total : 89930 time to create 1 rle with old method : 0.1014096736907959 length of segment : 346 time for calcul the mask position with numpy : 0.002292156219482422 nb_pixel_total : 76188 time to create 1 rle with old method : 0.08493638038635254 length of segment : 292 time for calcul the mask position with numpy : 0.00035858154296875 nb_pixel_total : 12290 time to create 1 rle with old method : 0.014175891876220703 length of segment : 127 time for calcul the mask position with numpy : 0.0006017684936523438 nb_pixel_total : 22240 time to create 1 rle with old method : 0.024520158767700195 length of segment : 193 time for calcul the mask position with numpy : 0.01301717758178711 nb_pixel_total : 564518 time to create 1 rle with new method : 0.09546804428100586 length of segment : 777 time for calcul the mask position with numpy : 0.017864704132080078 nb_pixel_total : 402620 time to create 1 rle with new method : 0.0987539291381836 length of segment : 1324 time for calcul the mask position with numpy : 0.003618955612182617 nb_pixel_total : 176716 time to create 1 rle with new method : 0.009527206420898438 length of segment : 527 time for calcul the mask position with numpy : 0.002800464630126953 nb_pixel_total : 146954 time to create 1 rle with old method : 0.15438604354858398 length of segment : 579 time for calcul the mask position with numpy : 0.0007519721984863281 nb_pixel_total : 30370 time to create 1 rle with old method : 0.03395891189575195 length of segment : 191 time for calcul the mask position with numpy : 0.004500389099121094 nb_pixel_total : 155347 time to create 1 rle with new method : 0.014205217361450195 length of segment : 607 time for calcul the mask position with numpy : 0.0024077892303466797 nb_pixel_total : 127983 time to create 1 rle with old method : 0.1367788314819336 length of segment : 445 time for calcul the mask position with numpy : 0.0015320777893066406 nb_pixel_total : 68195 time to create 1 rle with old method : 0.07487201690673828 length of segment : 371 time for calcul the mask position with numpy : 0.0012917518615722656 nb_pixel_total : 59545 time to create 1 rle with old method : 0.06595516204833984 length of segment : 440 time for calcul the mask position with numpy : 0.00494384765625 nb_pixel_total : 221148 time to create 1 rle with new method : 0.014540910720825195 length of segment : 1037 time for calcul the mask position with numpy : 0.0009386539459228516 nb_pixel_total : 43096 time to create 1 rle with old method : 0.04625678062438965 length of segment : 321 time for calcul the mask position with numpy : 0.004433155059814453 nb_pixel_total : 132245 time to create 1 rle with old method : 0.13982129096984863 length of segment : 549 time for calcul the mask position with numpy : 0.0061855316162109375 nb_pixel_total : 309229 time to create 1 rle with new method : 0.018206119537353516 length of segment : 1366 time for calcul the mask position with numpy : 0.001779794692993164 nb_pixel_total : 79486 time to create 1 rle with old method : 0.08501362800598145 length of segment : 370 time for calcul the mask position with numpy : 0.0036346912384033203 nb_pixel_total : 147199 time to create 1 rle with old method : 0.15982484817504883 length of segment : 762 time for calcul the mask position with numpy : 0.0007052421569824219 nb_pixel_total : 28513 time to create 1 rle with old method : 0.031641483306884766 length of segment : 230 time for calcul the mask position with numpy : 0.002554178237915039 nb_pixel_total : 93844 time to create 1 rle with old method : 0.10742807388305664 length of segment : 374 time for calcul the mask position with numpy : 0.0036275386810302734 nb_pixel_total : 148422 time to create 1 rle with old method : 0.1660628318786621 length of segment : 450 time for calcul the mask position with numpy : 0.002193450927734375 nb_pixel_total : 97531 time to create 1 rle with old method : 0.1085355281829834 length of segment : 436 time for calcul the mask position with numpy : 0.0018813610076904297 nb_pixel_total : 60129 time to create 1 rle with old method : 0.07085514068603516 length of segment : 349 time for calcul the mask position with numpy : 0.0024771690368652344 nb_pixel_total : 128155 time to create 1 rle with old method : 0.13697052001953125 length of segment : 337 time for calcul the mask position with numpy : 0.003985404968261719 nb_pixel_total : 171019 time to create 1 rle with new method : 0.01178598403930664 length of segment : 593 time for calcul the mask position with numpy : 0.01872849464416504 nb_pixel_total : 405265 time to create 1 rle with new method : 0.37717604637145996 length of segment : 1292 time for calcul the mask position with numpy : 0.020691633224487305 nb_pixel_total : 173702 time to create 1 rle with new method : 0.15183305740356445 length of segment : 524 time for calcul the mask position with numpy : 0.0021255016326904297 nb_pixel_total : 110278 time to create 1 rle with old method : 0.1256241798400879 length of segment : 357 time for calcul the mask position with numpy : 0.0013773441314697266 nb_pixel_total : 59880 time to create 1 rle with old method : 0.06717967987060547 length of segment : 332 time for calcul the mask position with numpy : 0.0030105113983154297 nb_pixel_total : 132758 time to create 1 rle with old method : 0.15162420272827148 length of segment : 509 time for calcul the mask position with numpy : 0.0013387203216552734 nb_pixel_total : 58112 time to create 1 rle with old method : 0.06481766700744629 length of segment : 356 time for calcul the mask position with numpy : 0.0026979446411132812 nb_pixel_total : 119879 time to create 1 rle with old method : 0.13523125648498535 length of segment : 445 time for calcul the mask position with numpy : 0.004618644714355469 nb_pixel_total : 221248 time to create 1 rle with new method : 0.014441251754760742 length of segment : 753 time for calcul the mask position with numpy : 0.002317190170288086 nb_pixel_total : 115340 time to create 1 rle with old method : 0.1271800994873047 length of segment : 450 time for calcul the mask position with numpy : 0.0025644302368164062 nb_pixel_total : 146260 time to create 1 rle with old method : 0.16103172302246094 length of segment : 571 time for calcul the mask position with numpy : 0.001092672348022461 nb_pixel_total : 49904 time to create 1 rle with old method : 0.0569310188293457 length of segment : 364 time for calcul the mask position with numpy : 0.0019648075103759766 nb_pixel_total : 63848 time to create 1 rle with old method : 0.07669639587402344 length of segment : 313 time for calcul the mask position with numpy : 0.0054836273193359375 nb_pixel_total : 248715 time to create 1 rle with new method : 0.014688253402709961 length of segment : 734 time for calcul the mask position with numpy : 0.0008871555328369141 nb_pixel_total : 41649 time to create 1 rle with old method : 0.046295881271362305 length of segment : 293 time for calcul the mask position with numpy : 0.0015690326690673828 nb_pixel_total : 75893 time to create 1 rle with old method : 0.09130573272705078 length of segment : 337 time for calcul the mask position with numpy : 0.010040998458862305 nb_pixel_total : 403827 time to create 1 rle with new method : 0.02074432373046875 length of segment : 836 time for calcul the mask position with numpy : 0.0009942054748535156 nb_pixel_total : 47943 time to create 1 rle with old method : 0.0532379150390625 length of segment : 290 time for calcul the mask position with numpy : 0.0015294551849365234 nb_pixel_total : 59155 time to create 1 rle with old method : 0.0662088394165039 length of segment : 295 time for calcul the mask position with numpy : 0.01678466796875 nb_pixel_total : 702738 time to create 1 rle with new method : 0.07337212562561035 length of segment : 982 time for calcul the mask position with numpy : 0.0019068717956542969 nb_pixel_total : 46621 time to create 1 rle with old method : 0.05643916130065918 length of segment : 233 time for calcul the mask position with numpy : 0.0010848045349121094 nb_pixel_total : 42201 time to create 1 rle with old method : 0.05091357231140137 length of segment : 340 time for calcul the mask position with numpy : 0.003836393356323242 nb_pixel_total : 163842 time to create 1 rle with new method : 0.010410547256469727 length of segment : 615 time for calcul the mask position with numpy : 0.0026023387908935547 nb_pixel_total : 92953 time to create 1 rle with old method : 0.10021519660949707 length of segment : 379 time for calcul the mask position with numpy : 0.009129524230957031 nb_pixel_total : 369421 time to create 1 rle with new method : 0.1926560401916504 length of segment : 1065 time for calcul the mask position with numpy : 0.004006147384643555 nb_pixel_total : 227508 time to create 1 rle with new method : 0.009679555892944336 length of segment : 635 time for calcul the mask position with numpy : 0.010469198226928711 nb_pixel_total : 383772 time to create 1 rle with new method : 0.02628350257873535 length of segment : 957 time for calcul the mask position with numpy : 0.0016601085662841797 nb_pixel_total : 46858 time to create 1 rle with old method : 0.05144762992858887 length of segment : 475 time for calcul the mask position with numpy : 0.0009188652038574219 nb_pixel_total : 45055 time to create 1 rle with old method : 0.04924345016479492 length of segment : 348 time for calcul the mask position with numpy : 0.0003814697265625 nb_pixel_total : 16283 time to create 1 rle with old method : 0.01783919334411621 length of segment : 260 time for calcul the mask position with numpy : 0.0029578208923339844 nb_pixel_total : 105367 time to create 1 rle with old method : 0.11472177505493164 length of segment : 634 time for calcul the mask position with numpy : 0.00394129753112793 nb_pixel_total : 189004 time to create 1 rle with new method : 0.010238170623779297 length of segment : 563 time for calcul the mask position with numpy : 0.0007085800170898438 nb_pixel_total : 27026 time to create 1 rle with old method : 0.029744863510131836 length of segment : 145 time for calcul the mask position with numpy : 0.0008172988891601562 nb_pixel_total : 20958 time to create 1 rle with old method : 0.023489713668823242 length of segment : 325 time for calcul the mask position with numpy : 0.002023458480834961 nb_pixel_total : 119816 time to create 1 rle with old method : 0.13668537139892578 length of segment : 462 time for calcul the mask position with numpy : 0.0010657310485839844 nb_pixel_total : 45738 time to create 1 rle with old method : 0.05346322059631348 length of segment : 232 time for calcul the mask position with numpy : 0.028405189514160156 nb_pixel_total : 956538 time to create 1 rle with new method : 0.34282946586608887 length of segment : 2218 time for calcul the mask position with numpy : 0.001245737075805664 nb_pixel_total : 38548 time to create 1 rle with old method : 0.04156041145324707 length of segment : 298 time for calcul the mask position with numpy : 0.0009949207305908203 nb_pixel_total : 60206 time to create 1 rle with old method : 0.06468701362609863 length of segment : 322 time for calcul the mask position with numpy : 0.004357099533081055 nb_pixel_total : 173658 time to create 1 rle with new method : 0.01314854621887207 length of segment : 885 time for calcul the mask position with numpy : 0.01931023597717285 nb_pixel_total : 524173 time to create 1 rle with new method : 0.2630007266998291 length of segment : 1654 time for calcul the mask position with numpy : 0.0010406970977783203 nb_pixel_total : 18128 time to create 1 rle with old method : 0.02070784568786621 length of segment : 197 time for calcul the mask position with numpy : 0.003962993621826172 nb_pixel_total : 190104 time to create 1 rle with new method : 0.011831045150756836 length of segment : 828 time for calcul the mask position with numpy : 0.0020186901092529297 nb_pixel_total : 91453 time to create 1 rle with old method : 0.10104775428771973 length of segment : 246 time for calcul the mask position with numpy : 0.004460334777832031 nb_pixel_total : 172338 time to create 1 rle with new method : 0.011414051055908203 length of segment : 387 time for calcul the mask position with numpy : 0.0023615360260009766 nb_pixel_total : 58147 time to create 1 rle with old method : 0.06457066535949707 length of segment : 507 time for calcul the mask position with numpy : 0.003936052322387695 nb_pixel_total : 117418 time to create 1 rle with old method : 0.12824296951293945 length of segment : 523 time for calcul the mask position with numpy : 0.001251220703125 nb_pixel_total : 64608 time to create 1 rle with old method : 0.07087516784667969 length of segment : 327 time for calcul the mask position with numpy : 0.0006923675537109375 nb_pixel_total : 22372 time to create 1 rle with old method : 0.02475881576538086 length of segment : 162 time for calcul the mask position with numpy : 0.0012793540954589844 nb_pixel_total : 69638 time to create 1 rle with old method : 0.07581806182861328 length of segment : 407 time for calcul the mask position with numpy : 0.004938364028930664 nb_pixel_total : 319123 time to create 1 rle with new method : 0.012728452682495117 length of segment : 756 time for calcul the mask position with numpy : 0.010008811950683594 nb_pixel_total : 477909 time to create 1 rle with new method : 0.04693126678466797 length of segment : 946 time for calcul the mask position with numpy : 0.005365133285522461 nb_pixel_total : 313221 time to create 1 rle with new method : 0.015787601470947266 length of segment : 736 time for calcul the mask position with numpy : 0.006506919860839844 nb_pixel_total : 294333 time to create 1 rle with new method : 0.016573429107666016 length of segment : 895 time for calcul the mask position with numpy : 0.0028197765350341797 nb_pixel_total : 148511 time to create 1 rle with old method : 0.16762137413024902 length of segment : 505 time for calcul the mask position with numpy : 0.013614177703857422 nb_pixel_total : 571708 time to create 1 rle with new method : 0.0530397891998291 length of segment : 1174 time for calcul the mask position with numpy : 0.006446123123168945 nb_pixel_total : 327541 time to create 1 rle with new method : 0.19290637969970703 length of segment : 969 time for calcul the mask position with numpy : 0.0031533241271972656 nb_pixel_total : 141375 time to create 1 rle with old method : 0.18185806274414062 length of segment : 399 time for calcul the mask position with numpy : 0.004457950592041016 nb_pixel_total : 183303 time to create 1 rle with new method : 0.011847496032714844 length of segment : 691 time for calcul the mask position with numpy : 0.004355430603027344 nb_pixel_total : 121386 time to create 1 rle with old method : 0.15155315399169922 length of segment : 304 time for calcul the mask position with numpy : 0.0035240650177001953 nb_pixel_total : 175739 time to create 1 rle with new method : 0.00995016098022461 length of segment : 653 time for calcul the mask position with numpy : 0.0010094642639160156 nb_pixel_total : 26985 time to create 1 rle with old method : 0.03046703338623047 length of segment : 196 time for calcul the mask position with numpy : 0.0008370876312255859 nb_pixel_total : 37562 time to create 1 rle with old method : 0.04134654998779297 length of segment : 235 time for calcul the mask position with numpy : 0.002190828323364258 nb_pixel_total : 93929 time to create 1 rle with old method : 0.10396909713745117 length of segment : 410 time for calcul the mask position with numpy : 0.002215862274169922 nb_pixel_total : 138854 time to create 1 rle with old method : 0.153947114944458 length of segment : 588 time for calcul the mask position with numpy : 0.0011017322540283203 nb_pixel_total : 44673 time to create 1 rle with old method : 0.04884624481201172 length of segment : 361 time for calcul the mask position with numpy : 0.0009565353393554688 nb_pixel_total : 59489 time to create 1 rle with old method : 0.06610107421875 length of segment : 398 time for calcul the mask position with numpy : 0.0011219978332519531 nb_pixel_total : 55941 time to create 1 rle with old method : 0.06155753135681152 length of segment : 439 time for calcul the mask position with numpy : 0.0006730556488037109 nb_pixel_total : 32715 time to create 1 rle with old method : 0.0369112491607666 length of segment : 192 time for calcul the mask position with numpy : 0.002508878707885742 nb_pixel_total : 121652 time to create 1 rle with old method : 0.1492915153503418 length of segment : 405 time for calcul the mask position with numpy : 0.0028693675994873047 nb_pixel_total : 158033 time to create 1 rle with new method : 0.009102821350097656 length of segment : 444 time for calcul the mask position with numpy : 0.0011065006256103516 nb_pixel_total : 27853 time to create 1 rle with old method : 0.031075239181518555 length of segment : 318 time for calcul the mask position with numpy : 0.002827882766723633 nb_pixel_total : 152528 time to create 1 rle with new method : 0.008440256118774414 length of segment : 614 time for calcul the mask position with numpy : 0.0024099349975585938 nb_pixel_total : 139050 time to create 1 rle with old method : 0.17402148246765137 length of segment : 610 time for calcul the mask position with numpy : 0.0008282661437988281 nb_pixel_total : 39716 time to create 1 rle with old method : 0.043807268142700195 length of segment : 262 time for calcul the mask position with numpy : 0.0005869865417480469 nb_pixel_total : 38362 time to create 1 rle with old method : 0.04198408126831055 length of segment : 247 time for calcul the mask position with numpy : 0.0055196285247802734 nb_pixel_total : 252143 time to create 1 rle with new method : 0.01712799072265625 length of segment : 1119 time for calcul the mask position with numpy : 0.0646822452545166 nb_pixel_total : 1813853 time to create 1 rle with new method : 0.5057113170623779 length of segment : 1788 time for calcul the mask position with numpy : 0.01727914810180664 nb_pixel_total : 1247375 time to create 1 rle with new method : 0.1943967342376709 length of segment : 1343 time for calcul the mask position with numpy : 0.0034008026123046875 nb_pixel_total : 268672 time to create 1 rle with new method : 0.008123397827148438 length of segment : 352 time for calcul the mask position with numpy : 0.0005633831024169922 nb_pixel_total : 31348 time to create 1 rle with old method : 0.03543353080749512 length of segment : 257 time for calcul the mask position with numpy : 0.0009822845458984375 nb_pixel_total : 62539 time to create 1 rle with old method : 0.07239508628845215 length of segment : 259 time for calcul the mask position with numpy : 0.0002872943878173828 nb_pixel_total : 15141 time to create 1 rle with old method : 0.01729106903076172 length of segment : 84 time for calcul the mask position with numpy : 0.0002548694610595703 nb_pixel_total : 10877 time to create 1 rle with old method : 0.012457847595214844 length of segment : 101 time for calcul the mask position with numpy : 0.0016422271728515625 nb_pixel_total : 85265 time to create 1 rle with old method : 0.09420657157897949 length of segment : 672 time for calcul the mask position with numpy : 0.001230478286743164 nb_pixel_total : 91641 time to create 1 rle with old method : 0.09975075721740723 length of segment : 489 time for calcul the mask position with numpy : 0.0018646717071533203 nb_pixel_total : 147710 time to create 1 rle with old method : 0.15686273574829102 length of segment : 382 time for calcul the mask position with numpy : 0.0001659393310546875 nb_pixel_total : 9093 time to create 1 rle with old method : 0.010469198226928711 length of segment : 82 time for calcul the mask position with numpy : 0.005239248275756836 nb_pixel_total : 358599 time to create 1 rle with new method : 0.014798402786254883 length of segment : 583 time for calcul the mask position with numpy : 0.0010447502136230469 nb_pixel_total : 51054 time to create 1 rle with old method : 0.05546736717224121 length of segment : 484 time for calcul the mask position with numpy : 0.002161264419555664 nb_pixel_total : 126947 time to create 1 rle with old method : 0.16843414306640625 length of segment : 258 time for calcul the mask position with numpy : 0.16027545928955078 nb_pixel_total : 1890057 time to create 1 rle with new method : 0.28166913986206055 length of segment : 2026 time for calcul the mask position with numpy : 0.007040262222290039 nb_pixel_total : 477758 time to create 1 rle with new method : 0.022120237350463867 length of segment : 877 time for calcul the mask position with numpy : 0.021656513214111328 nb_pixel_total : 746272 time to create 1 rle with new method : 0.38712334632873535 length of segment : 1061 time for calcul the mask position with numpy : 0.051048994064331055 nb_pixel_total : 1881742 time to create 1 rle with new method : 0.33495354652404785 length of segment : 3014 time for calcul the mask position with numpy : 0.027920246124267578 nb_pixel_total : 2010667 time to create 1 rle with new method : 0.33128857612609863 length of segment : 2045 time for calcul the mask position with numpy : 0.01994156837463379 nb_pixel_total : 1480524 time to create 1 rle with new method : 0.17331194877624512 length of segment : 2054 time for calcul the mask position with numpy : 0.4398233890533447 nb_pixel_total : 7332587 time to create 1 rle with new method : 1.027653455734253 length of segment : 4515 time for calcul the mask position with numpy : 0.018330097198486328 nb_pixel_total : 1488813 time to create 1 rle with new method : 0.09956693649291992 length of segment : 682 time for calcul the mask position with numpy : 0.0017156600952148438 nb_pixel_total : 129523 time to create 1 rle with old method : 0.15126943588256836 length of segment : 334 time for calcul the mask position with numpy : 0.0016024112701416016 nb_pixel_total : 117354 time to create 1 rle with old method : 0.16095805168151855 length of segment : 368 time for calcul the mask position with numpy : 0.02072620391845703 nb_pixel_total : 981419 time to create 1 rle with new method : 0.1702098846435547 length of segment : 1725 time for calcul the mask position with numpy : 0.0004863739013671875 nb_pixel_total : 27958 time to create 1 rle with old method : 0.03273582458496094 length of segment : 148 time for calcul the mask position with numpy : 0.000751495361328125 nb_pixel_total : 28465 time to create 1 rle with old method : 0.046605825424194336 length of segment : 150 time for calcul the mask position with numpy : 0.022077560424804688 nb_pixel_total : 1574056 time to create 1 rle with new method : 0.12519001960754395 length of segment : 756 time spent for convertir_results : 49.008912563323975 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 288 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 135.03579878807068 time spend to save output : 0.44879984855651855 total time spend for step 2 : 135.4845986366272 step3:blur_detection Thu Sep 11 20:25:12 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 (4160, 3120) 1598.3682959729708 (4160, 3120) 2582.2747456307966 (4160, 3120) 1631.178744633392 (4160, 3120) 269.11710001819137 (4160, 3120) 236.44734648850695 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 : 5 time used for this insertion : 0.036116838455200195 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.032533884048461914 save missing photos in datou_result : time spend for datou_step_exec : 2.2880451679229736 time spend to save output : 0.08529973030090332 total time spend for step 3 : 2.373344898223877 step4:brightness Thu Sep 11 20:25:14 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/1757614887_2186426_1383289782_115c254d72943fbf075f5740d0dbd1d0.jpg treat image : temp/1757614887_2186426_1383289779_e84d693edc6911bfa35d5a410401e716.jpg treat image : temp/1757614887_2186426_1383289776_9afe5914b67512e084287321ec1037ad.jpg treat image : temp/1757614887_2186426_1383289773_32dc1528ac24953fe84a7d1b07ce320a.jpg treat image : temp/1757614887_2186426_1383289770_acbcce911c1ffd34415b79a70e05e15b.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 : 5 time used for this insertion : 0.03652071952819824 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 5 time used for this insertion : 0.03905630111694336 save missing photos in datou_result : time spend for datou_step_exec : 7.995859622955322 time spend to save output : 0.09276938438415527 total time spend for step 4 : 8.088629007339478 step5:rle_unique_nms_with_priority Thu Sep 11 20:25:22 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 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 288 chid ids of type : 4854 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++nb_obj : 72 nb_hashtags : 9 time to prepare the origin masks : 72.61326050758362 time for calcul the mask position with numpy : 0.47025585174560547 nb_pixel_total : 4056457 time to create 1 rle with new method : 1.2346885204315186 time for calcul the mask position with numpy : 0.05246376991271973 nb_pixel_total : 2815 time to create 1 rle with old method : 0.003354787826538086 time for calcul the mask position with numpy : 0.05195188522338867 nb_pixel_total : 93946 time to create 1 rle with old method : 0.10539603233337402 time for calcul the mask position with numpy : 0.05445361137390137 nb_pixel_total : 73728 time to create 1 rle with old method : 0.08398818969726562 time for calcul the mask position with numpy : 0.05451178550720215 nb_pixel_total : 14092 time to create 1 rle with old method : 0.016123294830322266 time for calcul the mask position with numpy : 0.05415940284729004 nb_pixel_total : 2574 time to create 1 rle with old method : 0.003268003463745117 time for calcul the mask position with numpy : 0.05515575408935547 nb_pixel_total : 86276 time to create 1 rle with old method : 0.09654498100280762 time for calcul the mask position with numpy : 0.05427408218383789 nb_pixel_total : 4450 time to create 1 rle with old method : 0.00606536865234375 time for calcul the mask position with numpy : 0.054137229919433594 nb_pixel_total : 2654 time to create 1 rle with old method : 0.0032172203063964844 time for calcul the mask position with numpy : 0.053716421127319336 nb_pixel_total : 42796 time to create 1 rle with old method : 0.04732346534729004 time for calcul the mask position with numpy : 0.054778099060058594 nb_pixel_total : 1027 time to create 1 rle with old method : 0.0016160011291503906 time for calcul the mask position with numpy : 0.05480241775512695 nb_pixel_total : 139912 time to create 1 rle with old method : 0.1532127857208252 time for calcul the mask position with numpy : 0.05517578125 nb_pixel_total : 216293 time to create 1 rle with new method : 1.355696439743042 time for calcul the mask position with numpy : 0.05736374855041504 nb_pixel_total : 2850 time to create 1 rle with old method : 0.004908084869384766 time for calcul the mask position with numpy : 0.060613393783569336 nb_pixel_total : 153927 time to create 1 rle with new method : 1.1597552299499512 time for calcul the mask position with numpy : 0.05313277244567871 nb_pixel_total : 251573 time to create 1 rle with new method : 0.9853122234344482 time for calcul the mask position with numpy : 0.05565977096557617 nb_pixel_total : 23079 time to create 1 rle with old method : 0.027415990829467773 time for calcul the mask position with numpy : 0.058417558670043945 nb_pixel_total : 216072 time to create 1 rle with new method : 1.1630935668945312 time for calcul the mask position with numpy : 0.05211186408996582 nb_pixel_total : 37857 time to create 1 rle with old method : 0.04366636276245117 time for calcul the mask position with numpy : 0.05244183540344238 nb_pixel_total : 1225 time to create 1 rle with old method : 0.00177764892578125 time for calcul the mask position with numpy : 0.05317211151123047 nb_pixel_total : 6606 time to create 1 rle with old method : 0.007898330688476562 time for calcul the mask position with numpy : 0.0543673038482666 nb_pixel_total : 22 time to create 1 rle with old method : 0.00019431114196777344 time for calcul the mask position with numpy : 0.06362533569335938 nb_pixel_total : 113657 time to create 1 rle with old method : 0.12904095649719238 time for calcul the mask position with numpy : 0.05353045463562012 nb_pixel_total : 193483 time to create 1 rle with new method : 1.163384199142456 time for calcul the mask position with numpy : 0.051085710525512695 nb_pixel_total : 37989 time to create 1 rle with old method : 0.041396379470825195 time for calcul the mask position with numpy : 0.053148746490478516 nb_pixel_total : 24292 time to create 1 rle with old method : 0.02700638771057129 time for calcul the mask position with numpy : 0.053322553634643555 nb_pixel_total : 73419 time to create 1 rle with old method : 0.07898950576782227 time for calcul the mask position with numpy : 0.05241870880126953 nb_pixel_total : 76845 time to create 1 rle with old method : 0.08144450187683105 time for calcul the mask position with numpy : 0.05156087875366211 nb_pixel_total : 199240 time to create 1 rle with new method : 0.9361748695373535 time for calcul the mask position with numpy : 0.05278491973876953 nb_pixel_total : 21149 time to create 1 rle with old method : 0.023383378982543945 time for calcul the mask position with numpy : 0.05188393592834473 nb_pixel_total : 39017 time to create 1 rle with old method : 0.04367971420288086 time for calcul the mask position with numpy : 0.052922964096069336 nb_pixel_total : 151919 time to create 1 rle with new method : 1.151057481765747 time for calcul the mask position with numpy : 0.05361294746398926 nb_pixel_total : 72220 time to create 1 rle with old method : 0.08186149597167969 time for calcul the mask position with numpy : 0.07229995727539062 nb_pixel_total : 667862 time to create 1 rle with new method : 0.8659152984619141 time for calcul the mask position with numpy : 0.05506277084350586 nb_pixel_total : 30666 time to create 1 rle with old method : 0.03448343276977539 time for calcul the mask position with numpy : 0.054987192153930664 nb_pixel_total : 23595 time to create 1 rle with old method : 0.027003765106201172 time for calcul the mask position with numpy : 0.0544893741607666 nb_pixel_total : 102640 time to create 1 rle with old method : 0.11511540412902832 time for calcul the mask position with numpy : 0.05414271354675293 nb_pixel_total : 44637 time to create 1 rle with old method : 0.07099699974060059 time for calcul the mask position with numpy : 0.05769801139831543 nb_pixel_total : 31882 time to create 1 rle with old method : 0.05181002616882324 time for calcul the mask position with numpy : 0.05450177192687988 nb_pixel_total : 77960 time to create 1 rle with old method : 0.10100984573364258 time for calcul the mask position with numpy : 0.05979108810424805 nb_pixel_total : 109425 time to create 1 rle with old method : 0.1279449462890625 time for calcul the mask position with numpy : 0.054113149642944336 nb_pixel_total : 54397 time to create 1 rle with old method : 0.06035327911376953 time for calcul the mask position with numpy : 0.052580833435058594 nb_pixel_total : 368 time to create 1 rle with old method : 0.0004436969757080078 time for calcul the mask position with numpy : 0.0562434196472168 nb_pixel_total : 80972 time to create 1 rle with old method : 0.08764052391052246 time for calcul the mask position with numpy : 0.05350184440612793 nb_pixel_total : 370342 time to create 1 rle with new method : 1.559180736541748 time for calcul the mask position with numpy : 0.05546283721923828 nb_pixel_total : 97425 time to create 1 rle with old method : 0.11057043075561523 time for calcul the mask position with numpy : 0.05601954460144043 nb_pixel_total : 143908 time to create 1 rle with old method : 0.15709185600280762 time for calcul the mask position with numpy : 0.05255746841430664 nb_pixel_total : 48598 time to create 1 rle with old method : 0.05213618278503418 time for calcul the mask position with numpy : 0.05323433876037598 nb_pixel_total : 16389 time to create 1 rle with old method : 0.020052433013916016 time for calcul the mask position with numpy : 0.05230522155761719 nb_pixel_total : 687 time to create 1 rle with old method : 0.0013930797576904297 time for calcul the mask position with numpy : 0.05659127235412598 nb_pixel_total : 588946 time to create 1 rle with new method : 0.9529645442962646 time for calcul the mask position with numpy : 0.05400705337524414 nb_pixel_total : 17797 time to create 1 rle with old method : 0.0213775634765625 time for calcul the mask position with numpy : 0.0696556568145752 nb_pixel_total : 1087998 time to create 1 rle with new method : 1.344954013824463 time for calcul the mask position with numpy : 0.0547637939453125 nb_pixel_total : 138664 time to create 1 rle with old method : 0.15677523612976074 time for calcul the mask position with numpy : 0.05403590202331543 nb_pixel_total : 20654 time to create 1 rle with old method : 0.022975921630859375 time for calcul the mask position with numpy : 0.059778690338134766 nb_pixel_total : 637789 time to create 1 rle with new method : 0.9958539009094238 time for calcul the mask position with numpy : 0.05275154113769531 nb_pixel_total : 2518 time to create 1 rle with old method : 0.0035064220428466797 time for calcul the mask position with numpy : 0.053008079528808594 nb_pixel_total : 143814 time to create 1 rle with old method : 0.15814661979675293 time for calcul the mask position with numpy : 0.05296015739440918 nb_pixel_total : 3632 time to create 1 rle with old method : 0.004085540771484375 time for calcul the mask position with numpy : 0.053202152252197266 nb_pixel_total : 219097 time to create 1 rle with new method : 1.079050064086914 time for calcul the mask position with numpy : 0.05553007125854492 nb_pixel_total : 106466 time to create 1 rle with old method : 0.12102031707763672 time for calcul the mask position with numpy : 0.055284976959228516 nb_pixel_total : 23890 time to create 1 rle with old method : 0.027038097381591797 time for calcul the mask position with numpy : 0.053926944732666016 nb_pixel_total : 22925 time to create 1 rle with old method : 0.026590824127197266 time for calcul the mask position with numpy : 0.05864548683166504 nb_pixel_total : 646619 time to create 1 rle with new method : 1.0760397911071777 time for calcul the mask position with numpy : 0.061766862869262695 nb_pixel_total : 100218 time to create 1 rle with old method : 0.11277937889099121 time for calcul the mask position with numpy : 0.06065011024475098 nb_pixel_total : 449432 time to create 1 rle with new method : 0.8400478363037109 time for calcul the mask position with numpy : 0.053167104721069336 nb_pixel_total : 3601 time to create 1 rle with old method : 0.004551410675048828 time for calcul the mask position with numpy : 0.05392646789550781 nb_pixel_total : 273115 time to create 1 rle with new method : 1.4412264823913574 time for calcul the mask position with numpy : 0.056691884994506836 nb_pixel_total : 1824 time to create 1 rle with old method : 0.003523111343383789 time for calcul the mask position with numpy : 0.053476572036743164 nb_pixel_total : 27 time to create 1 rle with old method : 5.698204040527344e-05 time for calcul the mask position with numpy : 0.05742835998535156 nb_pixel_total : 111088 time to create 1 rle with old method : 0.1213228702545166 time for calcul the mask position with numpy : 0.05272960662841797 nb_pixel_total : 13403 time to create 1 rle with old method : 0.014645099639892578 time for calcul the mask position with numpy : 0.05395698547363281 nb_pixel_total : 30469 time to create 1 rle with old method : 0.03599691390991211 create new chi : 27.49728298187256 time to delete rle : 0.08709716796875 batch 1 Loaded 73 chid ids of type : 4855 Number RLEs to save : 53632 TO DO : save crop sub photo not yet done ! save time : 4.095738649368286 nb_obj : 90 nb_hashtags : 10 time to prepare the origin masks : 64.37633681297302 time for calcul the mask position with numpy : 0.629274845123291 nb_pixel_total : 5035667 time to create 1 rle with new method : 2.1854350566864014 time for calcul the mask position with numpy : 0.05413246154785156 nb_pixel_total : 8785 time to create 1 rle with old method : 0.010504961013793945 time for calcul the mask position with numpy : 0.055150508880615234 nb_pixel_total : 60046 time to create 1 rle with old method : 0.06732416152954102 time for calcul the mask position with numpy : 0.05450081825256348 nb_pixel_total : 52463 time to create 1 rle with old method : 0.05664515495300293 time for calcul the mask position with numpy : 0.051856040954589844 nb_pixel_total : 135888 time to create 1 rle with old method : 0.144287109375 time for calcul the mask position with numpy : 0.052341461181640625 nb_pixel_total : 29714 time to create 1 rle with old method : 0.033278465270996094 time for calcul the mask position with numpy : 0.05408167839050293 nb_pixel_total : 97330 time to create 1 rle with old method : 0.1030573844909668 time for calcul the mask position with numpy : 0.05377006530761719 nb_pixel_total : 1292 time to create 1 rle with old method : 0.0015239715576171875 time for calcul the mask position with numpy : 0.0614926815032959 nb_pixel_total : 401247 time to create 1 rle with new method : 1.034285306930542 time for calcul the mask position with numpy : 0.054457902908325195 nb_pixel_total : 120618 time to create 1 rle with old method : 0.13214635848999023 time for calcul the mask position with numpy : 0.057500600814819336 nb_pixel_total : 185459 time to create 1 rle with new method : 1.0312466621398926 time for calcul the mask position with numpy : 0.0518951416015625 nb_pixel_total : 482 time to create 1 rle with old method : 0.00052642822265625 time for calcul the mask position with numpy : 0.05290818214416504 nb_pixel_total : 144192 time to create 1 rle with old method : 0.15483498573303223 time for calcul the mask position with numpy : 0.0521998405456543 nb_pixel_total : 13488 time to create 1 rle with old method : 0.014588594436645508 time for calcul the mask position with numpy : 0.054225921630859375 nb_pixel_total : 125425 time to create 1 rle with old method : 0.13557028770446777 time for calcul the mask position with numpy : 0.0528104305267334 nb_pixel_total : 39889 time to create 1 rle with old method : 0.04378795623779297 time for calcul the mask position with numpy : 0.05281543731689453 nb_pixel_total : 18144 time to create 1 rle with old method : 0.020389080047607422 time for calcul the mask position with numpy : 0.05393266677856445 nb_pixel_total : 99879 time to create 1 rle with old method : 0.11232638359069824 time for calcul the mask position with numpy : 0.05456066131591797 nb_pixel_total : 3840 time to create 1 rle with old method : 0.005786895751953125 time for calcul the mask position with numpy : 0.06415724754333496 nb_pixel_total : 255675 time to create 1 rle with new method : 1.1884026527404785 time for calcul the mask position with numpy : 0.05269813537597656 nb_pixel_total : 22214 time to create 1 rle with old method : 0.024149417877197266 time for calcul the mask position with numpy : 0.05384087562561035 nb_pixel_total : 146822 time to create 1 rle with old method : 0.15724992752075195 time for calcul the mask position with numpy : 0.05151510238647461 nb_pixel_total : 2489 time to create 1 rle with old method : 0.002830982208251953 time for calcul the mask position with numpy : 0.05150771141052246 nb_pixel_total : 75004 time to create 1 rle with old method : 0.08157849311828613 time for calcul the mask position with numpy : 0.05294537544250488 nb_pixel_total : 55857 time to create 1 rle with old method : 0.060480356216430664 time for calcul the mask position with numpy : 0.052152156829833984 nb_pixel_total : 57824 time to create 1 rle with old method : 0.06186819076538086 time for calcul the mask position with numpy : 0.05289459228515625 nb_pixel_total : 226859 time to create 1 rle with new method : 1.0245296955108643 time for calcul the mask position with numpy : 0.056406259536743164 nb_pixel_total : 239085 time to create 1 rle with new method : 1.2769863605499268 time for calcul the mask position with numpy : 0.05271315574645996 nb_pixel_total : 1895 time to create 1 rle with old method : 0.002328634262084961 time for calcul the mask position with numpy : 0.05260729789733887 nb_pixel_total : 27961 time to create 1 rle with old method : 0.037581443786621094 time for calcul the mask position with numpy : 0.06124424934387207 nb_pixel_total : 29791 time to create 1 rle with old method : 0.033830881118774414 time for calcul the mask position with numpy : 0.05381321907043457 nb_pixel_total : 20548 time to create 1 rle with old method : 0.023389816284179688 time for calcul the mask position with numpy : 0.061285972595214844 nb_pixel_total : 282580 time to create 1 rle with new method : 2.2866532802581787 time for calcul the mask position with numpy : 0.05502462387084961 nb_pixel_total : 16557 time to create 1 rle with old method : 0.01877140998840332 time for calcul the mask position with numpy : 0.05409359931945801 nb_pixel_total : 1455 time to create 1 rle with old method : 0.001878976821899414 time for calcul the mask position with numpy : 0.05489540100097656 nb_pixel_total : 196672 time to create 1 rle with new method : 1.0637083053588867 time for calcul the mask position with numpy : 0.05721330642700195 nb_pixel_total : 3873 time to create 1 rle with old method : 0.004769802093505859 time for calcul the mask position with numpy : 0.05833292007446289 nb_pixel_total : 160625 time to create 1 rle with new method : 1.5173060894012451 time for calcul the mask position with numpy : 0.05448794364929199 nb_pixel_total : 59548 time to create 1 rle with old method : 0.06696820259094238 time for calcul the mask position with numpy : 0.05861544609069824 nb_pixel_total : 65149 time to create 1 rle with old method : 0.07326269149780273 time for calcul the mask position with numpy : 0.054128408432006836 nb_pixel_total : 8244 time to create 1 rle with old method : 0.00976419448852539 time for calcul the mask position with numpy : 0.0539393424987793 nb_pixel_total : 33707 time to create 1 rle with old method : 0.04155254364013672 time for calcul the mask position with numpy : 0.06312227249145508 nb_pixel_total : 67873 time to create 1 rle with old method : 0.08472132682800293 time for calcul the mask position with numpy : 0.05369687080383301 nb_pixel_total : 28330 time to create 1 rle with old method : 0.03183579444885254 time for calcul the mask position with numpy : 0.055196285247802734 nb_pixel_total : 26822 time to create 1 rle with old method : 0.029486656188964844 time for calcul the mask position with numpy : 0.059591054916381836 nb_pixel_total : 163863 time to create 1 rle with new method : 0.9351153373718262 time for calcul the mask position with numpy : 0.054563283920288086 nb_pixel_total : 6047 time to create 1 rle with old method : 0.007475137710571289 time for calcul the mask position with numpy : 0.05355381965637207 nb_pixel_total : 569 time to create 1 rle with old method : 0.0008723735809326172 time for calcul the mask position with numpy : 0.05512714385986328 nb_pixel_total : 122778 time to create 1 rle with old method : 0.14642548561096191 time for calcul the mask position with numpy : 0.05713629722595215 nb_pixel_total : 44703 time to create 1 rle with old method : 0.06552362442016602 time for calcul the mask position with numpy : 0.060658931732177734 nb_pixel_total : 50571 time to create 1 rle with old method : 0.05872941017150879 time for calcul the mask position with numpy : 0.0565335750579834 nb_pixel_total : 126790 time to create 1 rle with old method : 0.13924336433410645 time for calcul the mask position with numpy : 0.057160377502441406 nb_pixel_total : 11991 time to create 1 rle with old method : 0.019216537475585938 time for calcul the mask position with numpy : 0.057711124420166016 nb_pixel_total : 15062 time to create 1 rle with old method : 0.017250537872314453 time for calcul the mask position with numpy : 0.05304241180419922 nb_pixel_total : 15461 time to create 1 rle with old method : 0.01705002784729004 time for calcul the mask position with numpy : 0.05377769470214844 nb_pixel_total : 55533 time to create 1 rle with old method : 0.06133008003234863 time for calcul the mask position with numpy : 0.05483126640319824 nb_pixel_total : 264404 time to create 1 rle with new method : 0.88421630859375 time for calcul the mask position with numpy : 0.05428934097290039 nb_pixel_total : 10389 time to create 1 rle with old method : 0.011967182159423828 time for calcul the mask position with numpy : 0.055795907974243164 nb_pixel_total : 18715 time to create 1 rle with old method : 0.031157970428466797 time for calcul the mask position with numpy : 0.06545233726501465 nb_pixel_total : 113907 time to create 1 rle with old method : 0.1267549991607666 time for calcul the mask position with numpy : 0.07300972938537598 nb_pixel_total : 906840 time to create 1 rle with new method : 0.649289608001709 time for calcul the mask position with numpy : 0.05380105972290039 nb_pixel_total : 115098 time to create 1 rle with old method : 0.1535322666168213 time for calcul the mask position with numpy : 0.05375814437866211 nb_pixel_total : 43340 time to create 1 rle with old method : 0.048630714416503906 time for calcul the mask position with numpy : 0.05459141731262207 nb_pixel_total : 56795 time to create 1 rle with old method : 0.06334567070007324 time for calcul the mask position with numpy : 0.05760526657104492 nb_pixel_total : 475764 time to create 1 rle with new method : 0.8232421875 time for calcul the mask position with numpy : 0.054886579513549805 nb_pixel_total : 50250 time to create 1 rle with old method : 0.056825876235961914 time for calcul the mask position with numpy : 0.05502009391784668 nb_pixel_total : 83324 time to create 1 rle with old method : 0.0933370590209961 time for calcul the mask position with numpy : 0.054639577865600586 nb_pixel_total : 43333 time to create 1 rle with old method : 0.048566341400146484 time for calcul the mask position with numpy : 0.05373811721801758 nb_pixel_total : 3751 time to create 1 rle with old method : 0.004557132720947266 time for calcul the mask position with numpy : 0.054384469985961914 nb_pixel_total : 59816 time to create 1 rle with old method : 0.06725716590881348 time for calcul the mask position with numpy : 0.05417943000793457 nb_pixel_total : 19298 time to create 1 rle with old method : 0.021811962127685547 time for calcul the mask position with numpy : 0.054833412170410156 nb_pixel_total : 49162 time to create 1 rle with old method : 0.05560040473937988 time for calcul the mask position with numpy : 0.05414843559265137 nb_pixel_total : 30307 time to create 1 rle with old method : 0.034193992614746094 time for calcul the mask position with numpy : 0.054620981216430664 nb_pixel_total : 103208 time to create 1 rle with old method : 0.11611461639404297 time for calcul the mask position with numpy : 0.053774356842041016 nb_pixel_total : 2229 time to create 1 rle with old method : 0.0028634071350097656 time for calcul the mask position with numpy : 0.0587925910949707 nb_pixel_total : 219132 time to create 1 rle with new method : 0.7824547290802002 time for calcul the mask position with numpy : 0.05224800109863281 nb_pixel_total : 17249 time to create 1 rle with old method : 0.022397518157958984 time for calcul the mask position with numpy : 0.05204653739929199 nb_pixel_total : 4962 time to create 1 rle with old method : 0.0055446624755859375 time for calcul the mask position with numpy : 0.053316593170166016 nb_pixel_total : 67195 time to create 1 rle with old method : 0.07440710067749023 time for calcul the mask position with numpy : 0.05369853973388672 nb_pixel_total : 1172 time to create 1 rle with old method : 0.0015759468078613281 time for calcul the mask position with numpy : 0.0536954402923584 nb_pixel_total : 40542 time to create 1 rle with old method : 0.04548001289367676 time for calcul the mask position with numpy : 0.053923606872558594 nb_pixel_total : 1774 time to create 1 rle with old method : 0.0021772384643554688 time for calcul the mask position with numpy : 0.05929160118103027 nb_pixel_total : 545611 time to create 1 rle with new method : 1.0982625484466553 time for calcul the mask position with numpy : 0.05435347557067871 nb_pixel_total : 52042 time to create 1 rle with old method : 0.05858349800109863 time for calcul the mask position with numpy : 0.05399751663208008 nb_pixel_total : 17334 time to create 1 rle with old method : 0.023815393447875977 time for calcul the mask position with numpy : 0.06846475601196289 nb_pixel_total : 125431 time to create 1 rle with old method : 0.17270326614379883 time for calcul the mask position with numpy : 0.0540308952331543 nb_pixel_total : 29485 time to create 1 rle with old method : 0.03476905822753906 time for calcul the mask position with numpy : 0.054175615310668945 nb_pixel_total : 66147 time to create 1 rle with old method : 0.07601809501647949 time for calcul the mask position with numpy : 0.05473971366882324 nb_pixel_total : 7481 time to create 1 rle with old method : 0.008984565734863281 time for calcul the mask position with numpy : 0.053800344467163086 nb_pixel_total : 18048 time to create 1 rle with old method : 0.022022724151611328 time for calcul the mask position with numpy : 0.05370187759399414 nb_pixel_total : 14990 time to create 1 rle with old method : 0.01894974708557129 create new chi : 28.022857904434204 time to delete rle : 0.008237361907958984 batch 1 Loaded 91 chid ids of type : 4855 Number RLEs to save : 66814 TO DO : save crop sub photo not yet done ! save time : 6.65126371383667 nb_obj : 79 nb_hashtags : 10 time to prepare the origin masks : 60.21593713760376 time for calcul the mask position with numpy : 0.5066211223602295 nb_pixel_total : 4466935 time to create 1 rle with new method : 1.0081901550292969 time for calcul the mask position with numpy : 0.05249929428100586 nb_pixel_total : 26865 time to create 1 rle with old method : 0.030205965042114258 time for calcul the mask position with numpy : 0.05730700492858887 nb_pixel_total : 12473 time to create 1 rle with old method : 0.014142274856567383 time for calcul the mask position with numpy : 0.06064486503601074 nb_pixel_total : 286371 time to create 1 rle with new method : 0.841294527053833 time for calcul the mask position with numpy : 0.05387234687805176 nb_pixel_total : 14264 time to create 1 rle with old method : 0.016195058822631836 time for calcul the mask position with numpy : 0.05506730079650879 nb_pixel_total : 358750 time to create 1 rle with new method : 0.9483504295349121 time for calcul the mask position with numpy : 0.05353116989135742 nb_pixel_total : 163532 time to create 1 rle with new method : 0.945659875869751 time for calcul the mask position with numpy : 0.05214190483093262 nb_pixel_total : 58863 time to create 1 rle with old method : 0.06421160697937012 time for calcul the mask position with numpy : 0.05261802673339844 nb_pixel_total : 32451 time to create 1 rle with old method : 0.03522443771362305 time for calcul the mask position with numpy : 0.051958560943603516 nb_pixel_total : 183270 time to create 1 rle with new method : 0.8876118659973145 time for calcul the mask position with numpy : 0.051996707916259766 nb_pixel_total : 2046 time to create 1 rle with old method : 0.0025167465209960938 time for calcul the mask position with numpy : 0.05196547508239746 nb_pixel_total : 30916 time to create 1 rle with old method : 0.03485536575317383 time for calcul the mask position with numpy : 0.056180715560913086 nb_pixel_total : 22189 time to create 1 rle with old method : 0.02441096305847168 time for calcul the mask position with numpy : 0.0536799430847168 nb_pixel_total : 100502 time to create 1 rle with old method : 0.118316650390625 time for calcul the mask position with numpy : 0.053473711013793945 nb_pixel_total : 50293 time to create 1 rle with old method : 0.054370880126953125 time for calcul the mask position with numpy : 0.051610708236694336 nb_pixel_total : 47810 time to create 1 rle with old method : 0.052075862884521484 time for calcul the mask position with numpy : 0.05136513710021973 nb_pixel_total : 50953 time to create 1 rle with old method : 0.055655717849731445 time for calcul the mask position with numpy : 0.05369210243225098 nb_pixel_total : 125487 time to create 1 rle with old method : 0.13555479049682617 time for calcul the mask position with numpy : 0.05264115333557129 nb_pixel_total : 26858 time to create 1 rle with old method : 0.02922368049621582 time for calcul the mask position with numpy : 0.053169965744018555 nb_pixel_total : 45446 time to create 1 rle with old method : 0.050991058349609375 time for calcul the mask position with numpy : 0.05389881134033203 nb_pixel_total : 81662 time to create 1 rle with old method : 0.09123015403747559 time for calcul the mask position with numpy : 0.05385780334472656 nb_pixel_total : 38434 time to create 1 rle with old method : 0.043320417404174805 time for calcul the mask position with numpy : 0.060285091400146484 nb_pixel_total : 318028 time to create 1 rle with new method : 1.5821866989135742 time for calcul the mask position with numpy : 0.05241513252258301 nb_pixel_total : 98957 time to create 1 rle with old method : 0.10722136497497559 time for calcul the mask position with numpy : 0.05377674102783203 nb_pixel_total : 93502 time to create 1 rle with old method : 0.10140371322631836 time for calcul the mask position with numpy : 0.05192065238952637 nb_pixel_total : 173092 time to create 1 rle with new method : 1.8080265522003174 time for calcul the mask position with numpy : 0.052514076232910156 nb_pixel_total : 55850 time to create 1 rle with old method : 0.06129717826843262 time for calcul the mask position with numpy : 0.05230832099914551 nb_pixel_total : 44818 time to create 1 rle with old method : 0.05005478858947754 time for calcul the mask position with numpy : 0.053772687911987305 nb_pixel_total : 63718 time to create 1 rle with old method : 0.06949996948242188 time for calcul the mask position with numpy : 0.055552005767822266 nb_pixel_total : 248249 time to create 1 rle with new method : 1.137237548828125 time for calcul the mask position with numpy : 0.051502227783203125 nb_pixel_total : 283 time to create 1 rle with old method : 0.0005283355712890625 time for calcul the mask position with numpy : 0.05395984649658203 nb_pixel_total : 382849 time to create 1 rle with new method : 1.5690851211547852 time for calcul the mask position with numpy : 0.05460834503173828 nb_pixel_total : 188248 time to create 1 rle with new method : 0.931938648223877 time for calcul the mask position with numpy : 0.05397796630859375 nb_pixel_total : 37468 time to create 1 rle with old method : 0.04194927215576172 time for calcul the mask position with numpy : 0.0533750057220459 nb_pixel_total : 4043 time to create 1 rle with old method : 0.004979133605957031 time for calcul the mask position with numpy : 0.053736209869384766 nb_pixel_total : 29832 time to create 1 rle with old method : 0.03338479995727539 time for calcul the mask position with numpy : 0.0554351806640625 nb_pixel_total : 32666 time to create 1 rle with old method : 0.03502964973449707 time for calcul the mask position with numpy : 0.052239179611206055 nb_pixel_total : 67510 time to create 1 rle with old method : 0.07704019546508789 time for calcul the mask position with numpy : 0.05503344535827637 nb_pixel_total : 31947 time to create 1 rle with old method : 0.03524327278137207 time for calcul the mask position with numpy : 0.05221152305603027 nb_pixel_total : 64272 time to create 1 rle with old method : 0.06958913803100586 time for calcul the mask position with numpy : 0.05336356163024902 nb_pixel_total : 24026 time to create 1 rle with old method : 0.026345491409301758 time for calcul the mask position with numpy : 0.06812429428100586 nb_pixel_total : 907610 time to create 1 rle with new method : 0.9022243022918701 time for calcul the mask position with numpy : 0.05445218086242676 nb_pixel_total : 2557 time to create 1 rle with old method : 0.002990245819091797 time for calcul the mask position with numpy : 0.05292820930480957 nb_pixel_total : 41594 time to create 1 rle with old method : 0.045435428619384766 time for calcul the mask position with numpy : 0.05498909950256348 nb_pixel_total : 2041 time to create 1 rle with old method : 0.002451181411743164 time for calcul the mask position with numpy : 0.05364561080932617 nb_pixel_total : 39590 time to create 1 rle with old method : 0.04370760917663574 time for calcul the mask position with numpy : 0.0526580810546875 nb_pixel_total : 211 time to create 1 rle with old method : 0.00040078163146972656 time for calcul the mask position with numpy : 0.05426836013793945 nb_pixel_total : 185030 time to create 1 rle with new method : 0.9701516628265381 time for calcul the mask position with numpy : 0.058118581771850586 nb_pixel_total : 505263 time to create 1 rle with new method : 0.9231040477752686 time for calcul the mask position with numpy : 0.052396535873413086 nb_pixel_total : 14792 time to create 1 rle with old method : 0.016668081283569336 time for calcul the mask position with numpy : 0.053313493728637695 nb_pixel_total : 10898 time to create 1 rle with old method : 0.012038230895996094 time for calcul the mask position with numpy : 0.0534977912902832 nb_pixel_total : 18345 time to create 1 rle with old method : 0.021126508712768555 time for calcul the mask position with numpy : 0.05388617515563965 nb_pixel_total : 92703 time to create 1 rle with old method : 0.10181951522827148 time for calcul the mask position with numpy : 0.06238269805908203 nb_pixel_total : 89501 time to create 1 rle with old method : 0.09933710098266602 time for calcul the mask position with numpy : 0.05398106575012207 nb_pixel_total : 528 time to create 1 rle with old method : 0.0009012222290039062 time for calcul the mask position with numpy : 0.057799339294433594 nb_pixel_total : 403548 time to create 1 rle with new method : 1.0645594596862793 time for calcul the mask position with numpy : 0.05514025688171387 nb_pixel_total : 138460 time to create 1 rle with old method : 0.15819239616394043 time for calcul the mask position with numpy : 0.054512977600097656 nb_pixel_total : 2789 time to create 1 rle with old method : 0.0034508705139160156 time for calcul the mask position with numpy : 0.0543665885925293 nb_pixel_total : 247383 time to create 1 rle with new method : 0.8165953159332275 time for calcul the mask position with numpy : 0.05382084846496582 nb_pixel_total : 105372 time to create 1 rle with old method : 0.1142430305480957 time for calcul the mask position with numpy : 0.052506446838378906 nb_pixel_total : 4425 time to create 1 rle with old method : 0.00510859489440918 time for calcul the mask position with numpy : 0.053066253662109375 nb_pixel_total : 10526 time to create 1 rle with old method : 0.011726140975952148 time for calcul the mask position with numpy : 0.0556941032409668 nb_pixel_total : 251134 time to create 1 rle with new method : 0.8712954521179199 time for calcul the mask position with numpy : 0.05326437950134277 nb_pixel_total : 58844 time to create 1 rle with old method : 0.06395888328552246 time for calcul the mask position with numpy : 0.05287289619445801 nb_pixel_total : 19538 time to create 1 rle with old method : 0.022021770477294922 time for calcul the mask position with numpy : 0.054239749908447266 nb_pixel_total : 20872 time to create 1 rle with old method : 0.023513317108154297 time for calcul the mask position with numpy : 0.05587506294250488 nb_pixel_total : 115994 time to create 1 rle with old method : 0.12866640090942383 time for calcul the mask position with numpy : 0.05422234535217285 nb_pixel_total : 69478 time to create 1 rle with old method : 0.0760340690612793 time for calcul the mask position with numpy : 0.05511212348937988 nb_pixel_total : 227062 time to create 1 rle with new method : 0.9198379516601562 time for calcul the mask position with numpy : 0.05351400375366211 nb_pixel_total : 95958 time to create 1 rle with old method : 0.1041572093963623 time for calcul the mask position with numpy : 0.05299544334411621 nb_pixel_total : 45000 time to create 1 rle with old method : 0.04911231994628906 time for calcul the mask position with numpy : 0.0531919002532959 nb_pixel_total : 3200 time to create 1 rle with old method : 0.004389524459838867 time for calcul the mask position with numpy : 0.060486555099487305 nb_pixel_total : 687032 time to create 1 rle with new method : 0.899369478225708 time for calcul the mask position with numpy : 0.0522916316986084 nb_pixel_total : 51373 time to create 1 rle with old method : 0.058910369873046875 time for calcul the mask position with numpy : 0.052059173583984375 nb_pixel_total : 18019 time to create 1 rle with old method : 0.019615650177001953 time for calcul the mask position with numpy : 0.05732250213623047 nb_pixel_total : 28114 time to create 1 rle with old method : 0.0323939323425293 time for calcul the mask position with numpy : 0.05300617218017578 nb_pixel_total : 75644 time to create 1 rle with old method : 0.08220458030700684 time for calcul the mask position with numpy : 0.05224204063415527 nb_pixel_total : 147713 time to create 1 rle with old method : 0.16062140464782715 time for calcul the mask position with numpy : 0.05312681198120117 nb_pixel_total : 16252 time to create 1 rle with old method : 0.01790904998779297 time for calcul the mask position with numpy : 0.05303621292114258 nb_pixel_total : 39079 time to create 1 rle with old method : 0.043909549713134766 create new chi : 27.70647883415222 time to delete rle : 0.009437084197998047 batch 1 Loaded 80 chid ids of type : 4855 Number RLEs to save : 70141 TO DO : save crop sub photo not yet done ! save time : 6.657925367355347 nb_obj : 27 nb_hashtags : 7 time to prepare the origin masks : 28.928335189819336 time for calcul the mask position with numpy : 0.2157294750213623 nb_pixel_total : 4394868 time to create 1 rle with new method : 0.5769498348236084 time for calcul the mask position with numpy : 0.051757097244262695 nb_pixel_total : 7937 time to create 1 rle with old method : 0.008991718292236328 time for calcul the mask position with numpy : 0.22821736335754395 nb_pixel_total : 268260 time to create 1 rle with new method : 0.5229635238647461 time for calcul the mask position with numpy : 0.054250240325927734 nb_pixel_total : 3285 time to create 1 rle with old method : 0.0038962364196777344 time for calcul the mask position with numpy : 0.053415775299072266 nb_pixel_total : 10819 time to create 1 rle with old method : 0.012550830841064453 time for calcul the mask position with numpy : 0.05248308181762695 nb_pixel_total : 15070 time to create 1 rle with old method : 0.017224550247192383 time for calcul the mask position with numpy : 0.05269598960876465 nb_pixel_total : 2772 time to create 1 rle with old method : 0.003242969512939453 time for calcul the mask position with numpy : 0.05293536186218262 nb_pixel_total : 1350 time to create 1 rle with old method : 0.0016872882843017578 time for calcul the mask position with numpy : 0.05316591262817383 nb_pixel_total : 32697 time to create 1 rle with old method : 0.036333560943603516 time for calcul the mask position with numpy : 0.13745880126953125 nb_pixel_total : 1831147 time to create 1 rle with new method : 0.7667722702026367 time for calcul the mask position with numpy : 0.05584883689880371 nb_pixel_total : 110662 time to create 1 rle with old method : 0.12023162841796875 time for calcul the mask position with numpy : 0.05495333671569824 nb_pixel_total : 84812 time to create 1 rle with old method : 0.09127473831176758 time for calcul the mask position with numpy : 0.0774834156036377 nb_pixel_total : 1621629 time to create 1 rle with new method : 0.9001057147979736 time for calcul the mask position with numpy : 0.05335664749145508 nb_pixel_total : 22792 time to create 1 rle with old method : 0.024901866912841797 time for calcul the mask position with numpy : 0.0532526969909668 nb_pixel_total : 251534 time to create 1 rle with new method : 0.8437068462371826 time for calcul the mask position with numpy : 0.054079532623291016 nb_pixel_total : 147284 time to create 1 rle with old method : 0.16166472434997559 time for calcul the mask position with numpy : 0.054997920989990234 nb_pixel_total : 202932 time to create 1 rle with new method : 0.7771944999694824 time for calcul the mask position with numpy : 0.05538296699523926 nb_pixel_total : 17916 time to create 1 rle with old method : 0.02070021629333496 time for calcul the mask position with numpy : 0.054201602935791016 nb_pixel_total : 33199 time to create 1 rle with old method : 0.035393714904785156 time for calcul the mask position with numpy : 0.05666089057922363 nb_pixel_total : 349870 time to create 1 rle with new method : 0.7399604320526123 time for calcul the mask position with numpy : 0.05873227119445801 nb_pixel_total : 283055 time to create 1 rle with new method : 1.0825695991516113 time for calcul the mask position with numpy : 0.05591583251953125 nb_pixel_total : 62397 time to create 1 rle with old method : 0.06992673873901367 time for calcul the mask position with numpy : 0.0717768669128418 nb_pixel_total : 1245147 time to create 1 rle with new method : 0.8617849349975586 time for calcul the mask position with numpy : 0.05265021324157715 nb_pixel_total : 4724 time to create 1 rle with old method : 0.005319356918334961 time for calcul the mask position with numpy : 0.05534934997558594 nb_pixel_total : 62195 time to create 1 rle with old method : 0.0683906078338623 time for calcul the mask position with numpy : 0.07601094245910645 nb_pixel_total : 1810396 time to create 1 rle with new method : 0.660839319229126 time for calcul the mask position with numpy : 0.05339169502258301 nb_pixel_total : 91400 time to create 1 rle with old method : 0.09823250770568848 time for calcul the mask position with numpy : 0.05435919761657715 nb_pixel_total : 9051 time to create 1 rle with old method : 0.009986162185668945 create new chi : 10.97544813156128 time to delete rle : 0.0033333301544189453 batch 1 Loaded 28 chid ids of type : 4855 Number RLEs to save : 36710 TO DO : save crop sub photo not yet done ! save time : 3.2364087104797363 nb_obj : 9 nb_hashtags : 3 time to prepare the origin masks : 24.764225482940674 time for calcul the mask position with numpy : 0.09627175331115723 nb_pixel_total : 1033089 time to create 1 rle with new method : 1.319676160812378 time for calcul the mask position with numpy : 0.07875704765319824 nb_pixel_total : 9915 time to create 1 rle with old method : 0.010909318923950195 time for calcul the mask position with numpy : 0.07322001457214355 nb_pixel_total : 100970 time to create 1 rle with old method : 0.11091375350952148 time for calcul the mask position with numpy : 0.07919812202453613 nb_pixel_total : 2236480 time to create 1 rle with new method : 1.0174753665924072 time for calcul the mask position with numpy : 0.06154036521911621 nb_pixel_total : 662292 time to create 1 rle with new method : 1.1724674701690674 time for calcul the mask position with numpy : 0.04834556579589844 nb_pixel_total : 501603 time to create 1 rle with new method : 1.1004931926727295 time for calcul the mask position with numpy : 0.04361605644226074 nb_pixel_total : 38362 time to create 1 rle with old method : 0.04234647750854492 time for calcul the mask position with numpy : 0.04913973808288574 nb_pixel_total : 92666 time to create 1 rle with old method : 0.09656810760498047 time for calcul the mask position with numpy : 0.052552223205566406 nb_pixel_total : 890042 time to create 1 rle with new method : 1.3799669742584229 time for calcul the mask position with numpy : 0.9439475536346436 nb_pixel_total : 7413781 time to create 1 rle with new method : 1.7648167610168457 create new chi : 9.921418905258179 time to delete rle : 0.0039081573486328125 batch 1 Loaded 10 chid ids of type : 4855 Number RLEs to save : 25031 TO DO : save crop sub photo not yet done ! save time : 2.1205012798309326 map_output_result : {1383289782: (0.4971304553968302, 'Should be the crop_list due to order', 0.4198686975534639), 1383289779: (0.4971304553968302, 'Should be the crop_list due to order', 0.4601747647963612), 1383289776: (0.4971304553968302, 'Should be the crop_list due to order', 0.5211819152723389), 1383289773: (0.4971304553968302, 'Should be the crop_list due to order', 0.08442689936198707), 1383289770: (0.4971304553968302, '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 [1383289782, 1383289779, 1383289776, 1383289773, 1383289770] Looping around the photos to save general results len do output : 5 /1383289782.Didn't retrieve data . /1383289779.Didn't retrieve data . /1383289776.Didn't retrieve data . /1383289773.Didn't retrieve data . /1383289770.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, '3696150') ('4741', '26763391', '1383289782', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289779', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289776', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289773', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289770', None, None, None, None, None, '3696150') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.03568148612976074 save_final save missing photos in datou_result : time spend for datou_step_exec : 380.97722125053406 time spend to save output : 0.6130633354187012 total time spend for step 5 : 381.59028458595276 step6:crop_condition Thu Sep 11 20:31:44 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 5 ! batch 1 Loaded 282 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 ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 28 About to insert : list_path_to_insert length 28 new photo from crops ! About to upload 28 photos upload in portfolio : 3015255 init cache_photo without model_param we have 28 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757615545_2186426 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 28 photos in the portfolio 3015255 time of upload the photos Elapsed time : 9.187677383422852 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 ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! 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 : 53 About to insert : list_path_to_insert length 53 new photo from crops ! About to upload 53 photos upload in portfolio : 3015255 init cache_photo without model_param we have 53 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757615597_2186426 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 ! 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 53 photos in the portfolio 3015255 time of upload the photos Elapsed time : 18.000450134277344 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 ! Next one ! Next one ! 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/1757615623_2186426 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 : 7.004766464233398 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 ! 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/1757615635_2186426 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 : 2.7862067222595215 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 map_result returned by crop_photo_return_map_crop : length : 0 About to insert : list_path_to_insert length 0 new photo from crops ! About to upload 0 photos WARNING : list_path_to_insert is empty, cannot upload ! 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/1757615643_2186426 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 : 0.7494518756866455 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 ! map_result returned by crop_photo_return_map_crop : length : 12 About to insert : list_path_to_insert length 12 new photo from crops ! About to upload 12 photos upload in portfolio : 3015255 init cache_photo without model_param we have 12 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757615652_2186426 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 12 photos in the portfolio 3015255 time of upload the photos Elapsed time : 4.31214714050293 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 ! map_result returned by crop_photo_return_map_crop : length : 4 About to insert : list_path_to_insert length 4 new photo from crops ! About to upload 4 photos upload in portfolio : 3015255 init cache_photo without model_param we have 4 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757615659_2186426 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 4 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.873633623123169 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 ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 37 About to insert : list_path_to_insert length 37 new photo from crops ! About to upload 37 photos upload in portfolio : 3015255 init cache_photo without model_param we have 37 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757615703_2186426 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 ! 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 37 photos in the portfolio 3015255 time of upload the photos Elapsed time : 12.65854024887085 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 Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! About to upload 2 photos upload in portfolio : 3015255 init cache_photo without model_param we have 2 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757615728_2186426 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 2 photos in the portfolio 3015255 time of upload the photos Elapsed time : 1.335279941558838 we have finished the crop for the class : autre_emballage 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 ! 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/1757615735_2186426 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 : 3.2204532623291016 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 ! map_result returned by crop_photo_return_map_crop : length : 26 About to insert : list_path_to_insert length 26 new photo from crops ! About to upload 26 photos upload in portfolio : 3015255 init cache_photo without model_param we have 26 photo to upload uploaded to storage server : ovh folder_temporaire : temp/1757615861_2186426 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 26 photos in the portfolio 3015255 time of upload the photos Elapsed time : 9.826220273971558 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 [1383289782, 1383289779, 1383289776, 1383289773, 1383289770] Looping around the photos to save general results len do output : 198 /1383291068Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291069Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291070Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291071Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291072Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291073Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291075Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291076Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291077Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291078Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291082Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291083Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291084Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291086Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291087Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291088Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291089Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291090Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291091Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291093Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291094Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291095Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291097Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291159Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291160Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291161Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291163Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291164Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291165Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291166Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291167Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291168Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291169Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291170Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291171Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291172Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291173Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291174Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291175Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291176Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291177Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291178Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291179Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291180Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291181Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291182Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291184Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291185Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291186Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291187Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291188Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291189Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291190Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291191Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291192Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291193Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291194Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291195Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291197Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291198Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291199Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291200Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291201Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291202Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291203Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291205Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291206Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291207Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291208Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291209Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291210Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291211Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291212Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291213Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291214Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291215Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291225Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291226Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291227Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291228Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291229Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291230Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291231Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291232Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291233Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291234Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291235Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291236Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291237Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291238Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291240Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291242Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291243Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291244Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291245Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291249Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291250Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291251Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291252Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291253Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291254Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291255Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291256Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291260Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291270Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291271Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291272Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291273Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291274Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291275Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291276Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291277Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291278Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291279Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291280Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291281Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291283Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291284Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291285Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291286Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291307Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291308Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291309Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291310Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291311Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291312Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291313Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291314Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291315Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291316Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291317Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291318Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291319Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291320Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291321Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291322Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291323Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291324Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291325Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291326Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291327Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291328Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291329Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291330Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291331Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291332Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291333Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291334Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291335Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291336Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291337Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291338Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291339Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291340Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291341Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291342Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291343Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291361Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291362Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291366Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291367Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291368Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291369Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291370Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291371Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291372Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291373Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291428Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291429Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291432Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291434Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291435Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291436Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291437Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291440Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291441Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291442Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291443Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291444Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291445Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291446Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291448Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291452Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291453Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1383291454Didn'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, '3696150') ('4741', '26763391', '1383289782', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289779', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289776', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289773', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289770', None, None, None, None, None, '3696150') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 599 time used for this insertion : 0.08848047256469727 save_final save missing photos in datou_result : time spend for datou_step_exec : 369.6213700771332 time spend to save output : 0.09455180168151855 total time spend for step 6 : 369.7159218788147 step7:ventilate_hashtags_in_portfolio Thu Sep 11 20:37:53 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 : 26763391 get user id for portfolio 26763391 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`=26763391 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`=26763391 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`=26763391 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`=26763391 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://marlene.fotonower.com/velours/26764124,26764125,26764126,26764127,26764128,26764133,26764135,26764136,26764137,26764138,26764139,26764140,26764142,26764143,26764144,26764145,26764146,26764147,26764148,26764149?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=26763391 Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1383289782, 1383289779, 1383289776, 1383289773, 1383289770] Looping around the photos to save general results len do output : 1 /26763391. 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, '3696150') ('4741', '26763391', '1383289782', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289779', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289776', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289773', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289770', None, None, None, None, None, '3696150') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.02778172492980957 save_final save missing photos in datou_result : time spend for datou_step_exec : 9.254222631454468 time spend to save output : 0.028025388717651367 total time spend for step 7 : 9.28224802017212 step8:final Thu Sep 11 20:38:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : {1383289782: ('0.40952757973689263',), 1383289779: ('0.40952757973689263',), 1383289776: ('0.40952757973689263',), 1383289773: ('0.40952757973689263',), 1383289770: ('0.40952757973689263',)} new output for save of step final : {1383289782: ('0.40952757973689263',), 1383289779: ('0.40952757973689263',), 1383289776: ('0.40952757973689263',), 1383289773: ('0.40952757973689263',), 1383289770: ('0.40952757973689263',)} [1383289782, 1383289779, 1383289776, 1383289773, 1383289770] Looping around the photos to save general results len do output : 5 /1383289782.Didn't retrieve data . /1383289779.Didn't retrieve data . /1383289776.Didn't retrieve data . /1383289773.Didn't retrieve data . /1383289770.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, '3696150') ('4741', '26763391', '1383289782', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289779', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289776', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289773', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289770', None, None, None, None, None, '3696150') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 15 time used for this insertion : 0.025709152221679688 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.2525005340576172 time spend to save output : 0.02625417709350586 total time spend for step 8 : 0.27875471115112305 step9:velours_tree Thu Sep 11 20:38:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure 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 : 0.16562771797180176 time spend to save output : 4.124641418457031e-05 total time spend for step 9 : 0.16566896438598633 step10:send_mail_cod Thu Sep 11 20:38:03 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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_P26763391_11-09-2025_20_38_03.pdf 26764095 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 .imagette267640951757615883 26764096 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 .imagette267640961757615885 26764097 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 .imagette267640971757615887 26764098 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 .imagette267640981757615888 26764099 imagette267640991757615889 26764101 change filename to text .imagette267641011757615889 26764102 imagette267641021757615889 26764103 imagette267641031757615889 26764104 imagette267641041757615889 26764105 imagette267641051757615889 26764106 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 .imagette267641061757615889 26764107 change filename to text .change filename to text .change filename to text .change filename to text .imagette267641071757615890 26764108 imagette267641081757615890 26764109 imagette267641091757615891 26764110 imagette267641101757615891 26764111 imagette267641111757615891 26764112 imagette267641121757615891 26764113 change filename to text .change filename to text .imagette267641131757615891 26764114 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 .imagette267641141757615891 26764116 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 .imagette267641161757615891 26764117 imagette267641171757615893 26764118 imagette267641181757615894 26764119 imagette267641191757615894 26764120 imagette267641201757615894 26764121 imagette267641211757615894 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=26763391 and hashtag_type = 4855 and pcr.hashtag_id = h.hashtag_id; velour_link : https://marlene.fotonower.com/velours/26764124,26764125,26764126,26764127,26764128,26764133,26764135,26764136,26764137,26764138,26764139,26764140,26764142,26764143,26764144,26764145,26764146,26764147,26764148,26764149?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=26763391 your option no_mail is active, we will not send the real mail to your client args[1383289782] : ((1383289782, 1598.3682959729708, 2107751945), (1383289782, -0.2787853879333064, 496442774), '0.40952757973689263') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1383289779] : ((1383289779, 2582.2747456307966, 492609224), (1383289779, -0.3530677615487111, 496442774), '0.40952757973689263') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1383289776] : ((1383289776, 1631.178744633392, 2107751945), (1383289776, -0.34511417710159487, 496442774), '0.40952757973689263') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1383289773] : ((1383289773, 269.11710001819137, 492688767), (1383289773, -0.28672465470784114, 496442774), '0.40952757973689263') We are sending mail with results at report@fotonower.com,cod@fotonower.com args[1383289770] : ((1383289770, 236.44734648850695, 492688767), (1383289770, -0.91122615449762, 501862349), '0.40952757973689263') We are sending mail with results at report@fotonower.com,cod@fotonower.com refus_total : 0.40952757973689263 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_P26763391_11-09-2025_20_38_03.pdf results_Auto_P26763391_11-09-2025_20_38_03.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26763391_11-09-2025_20_38_03.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','26763391','results_Auto_P26763391_11-09-2025_20_38_03.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26763391_11-09-2025_20_38_03.pdf','pdf','','2.58','0.40952757973689263') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1383289782, 1383289779, 1383289776, 1383289773, 1383289770] 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, '3696150') ('4741', '26763391', '1383289782', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289779', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289776', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289773', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289770', None, None, None, None, None, '3696150') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 5 time used for this insertion : 0.012662410736083984 save_final save missing photos in datou_result : time spend for datou_step_exec : 14.238472938537598 time spend to save output : 0.013009309768676758 total time spend for step 10 : 14.251482248306274 step11:split_time_score Thu Sep 11 20:38:17 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 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'}] (('56', 5),) ERROR counted https://github.com/fotonower/Velours/issues/663#issuecomment-421136223 {} 11092025 26763391 Nombre de photos uploadées : 5 / 23040 (0%) 11092025 26763391 Nombre de photos taguées (types de déchets): 0 / 5 (0%) 11092025 26763391 Nombre de photos taguées (volume) : 0 / 5 (0%) elapsed_time : load_data_split_time_score 1.6927719116210938e-05 elapsed_time : order_list_meta_photo_and_scores 1.9311904907226562e-05 ????? elapsed_time : fill_and_build_computed_from_old_data 0.0004611015319824219 Catched exception ! Connect or reconnect ! Catched exception ! Connect or reconnect ! elapsed_time : insert_dashboard_record_day_entry 0.6848797798156738 We will return after consolidate but for now we need the day, how to get it, for now depending on the previous heavy steps find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26763389 order by id desc limit 1 Qualite : 0.40952757973689263 find url: https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P26763391_11-09-2025_20_38_03.pdf select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26763391 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`=26763391 AND mptpi.`type`=4855 To do find url: select completion_json, dashboard_run_id from MTRPhoto.dashboard_results where mtr_portfolio_id = 26763392 order by id desc limit 1 NUMBER BATCH : 0 # DISPLAY ALL COLLECTED DATA : {'11092025': {'nb_upload': 5, '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 [1383289782, 1383289779, 1383289776, 1383289773, 1383289770] Looping around the photos to save general results len do output : 1 /26763391Didn'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, '3696150') ('4741', '26763391', '1383289782', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289779', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289776', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289773', None, None, None, None, None, '3696150') ('4741', None, None, None, None, None, None, None, '3696150') ('4741', '26763391', '1383289770', None, None, None, None, None, '3696150') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 6 time used for this insertion : 0.025612354278564453 save_final save missing photos in datou_result : time spend for datou_step_exec : 3.7153403759002686 time spend to save output : 0.025925636291503906 total time spend for step 11 : 3.7412660121917725 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 1 len(input) + len(total_photo_id_missing) : 5 set_done_treatment 609.98user 299.14system 16:57.14elapsed 89%CPU (0avgtext+0avgdata 7328044maxresident)k 3243976inputs+693728outputs (22751major+47676635minor)pagefaults 0swaps