python /home/admin/mtr/script_for_cron.py -j default -m 20 -a 'python3 ~/workarea/git/Velours/python/prod/datou.py -j batch_current -a 3804 -P 28926786' -s traitement_sts -M 0 -S 0 -U 100,80,95 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/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', '/home/admin/workarea/git/apy', '/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 : 378884 load datou : 3804 # 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 ! 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 11560 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11567 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11567 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 11563 crop_condition is not consistent : 4 used against 2 in the step definition ! Step 11563 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11564 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11564 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11565 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11565 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11573 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11573 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11568 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11568 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11566 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11566 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 11560 doesn't seem to be define in the database( WARNING : type of input 2 of step 11563 doesn't seem to be define in the database( WARNING : output 1 of step 11560 have datatype=2 whereas input 1 of step 11564 have datatype=7 WARNING : type of output 2 of step 11564 doesn't seem to be define in the database( WARNING : type of input 1 of step 11565 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 2 of step 11567 doesn't seem to be define in the database( WARNING : type of input 3 of step 11563 doesn't seem to be define in the database( WARNING : type of output 3 of step 11564 doesn't seem to be define in the database( WARNING : type of input 1 of step 11568 doesn't seem to be define in the database( WARNING : type of output 1 of step 11568 doesn't seem to be define in the database( WARNING : type of input 3 of step 11566 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11563 doesn't seem to be define in the database( WARNING : output 0 of step 11570 have datatype=6 whereas input 2 of step 11563 have datatype=None WARNING : type of input 2 of step 11563 doesn't seem to be define in the database( WARNING : output 0 of step 11569 have datatype=6 whereas input 2 of step 11563 have datatype=None WARNING : type of output 2 of step 11560 doesn't seem to be define in the database( WARNING : type of input 1 of step 11570 doesn't seem to be define in the database( WARNING : type of output 2 of step 11560 doesn't seem to be define in the database( WARNING : type of input 1 of step 11569 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11568 have datatype=10 whereas input 3 of step 11571 have datatype=6 WARNING : type of input 2 of step 11573 doesn't seem to be define in the database( WARNING : output 1 of step 11565 have datatype=7 whereas input 2 of step 11573 have datatype=None WARNING : type of output 3 of step 11573 doesn't seem to be define in the database( WARNING : type of input 3 of step 11568 doesn't seem to be define in the database( WARNING : output 0 of step 11568 have datatype=10 whereas input 0 of step 11587 have datatype=18 WARNING : type of input 5 of step 11571 doesn't seem to be define in the database( WARNING : output 0 of step 11587 have datatype=11 whereas input 5 of step 11571 have datatype=None WARNING : output 0 of step 11564 have datatype=1 whereas input 0 of step 11565 have datatype=2 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 ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? chemin de la photo was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? output optionnel thcl was removed should we ? id de la photo (peut être local ou global) was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? id de la photo (peut être local ou global) was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] 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 : (5024, 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 16384, 25088, 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 12, 1, 0, 11, 4), datetime.datetime(2020, 12, 1, 0, 11, 4)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5035, 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 16384, 25088, 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 12, 5, 18, 56, 33), datetime.datetime(2020, 12, 5, 18, 56, 33)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5722, 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 2048, 2048, 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2022, 10, 27, 14, 43, 34), datetime.datetime(2022, 10, 27, 14, 43, 34)) load thcls load THCL from format json or kwargs add thcl : 2486 in CacheModelConfig load THCL from format json or kwargs add thcl : 2499 in CacheModelConfig load THCL from format json or kwargs add thcl : 3441 in CacheModelConfig load pdts add pdt : 5024 in CacheModelConfig add pdt : 5035 in CacheModelConfig add pdt : 5722 in CacheModelConfig Running datou job : batch_current updating current state to 1 list_input_json: [] Current got : datou_id : 3804, datou_cur_ids : ['4121914'] with mtr_portfolio_ids : ['28926786'] and first list_photo_ids : [] new path : /proc/378884/ 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 ! 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 11560 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11567 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11567 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 11563 crop_condition is not consistent : 4 used against 2 in the step definition ! Step 11563 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11564 merge_mask_thcl_custom have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11564 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11565 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11565 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11573 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11573 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11568 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11568 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11566 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11566 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 11560 doesn't seem to be define in the database( WARNING : type of input 2 of step 11563 doesn't seem to be define in the database( WARNING : output 1 of step 11560 have datatype=2 whereas input 1 of step 11564 have datatype=7 WARNING : type of output 2 of step 11564 doesn't seem to be define in the database( WARNING : type of input 1 of step 11565 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 2 of step 11567 doesn't seem to be define in the database( WARNING : type of input 3 of step 11563 doesn't seem to be define in the database( WARNING : type of output 3 of step 11564 doesn't seem to be define in the database( WARNING : type of input 1 of step 11568 doesn't seem to be define in the database( WARNING : type of output 1 of step 11568 doesn't seem to be define in the database( WARNING : type of input 3 of step 11566 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 11563 doesn't seem to be define in the database( WARNING : output 0 of step 11570 have datatype=6 whereas input 2 of step 11563 have datatype=None WARNING : type of input 2 of step 11563 doesn't seem to be define in the database( WARNING : output 0 of step 11569 have datatype=6 whereas input 2 of step 11563 have datatype=None WARNING : type of output 2 of step 11560 doesn't seem to be define in the database( WARNING : type of input 1 of step 11570 doesn't seem to be define in the database( WARNING : type of output 2 of step 11560 doesn't seem to be define in the database( WARNING : type of input 1 of step 11569 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11568 have datatype=10 whereas input 3 of step 11571 have datatype=6 WARNING : type of input 2 of step 11573 doesn't seem to be define in the database( WARNING : output 1 of step 11565 have datatype=7 whereas input 2 of step 11573 have datatype=None WARNING : type of output 3 of step 11573 doesn't seem to be define in the database( WARNING : type of input 3 of step 11568 doesn't seem to be define in the database( WARNING : output 0 of step 11568 have datatype=10 whereas input 0 of step 11587 have datatype=18 WARNING : type of input 5 of step 11571 doesn't seem to be define in the database( WARNING : output 0 of step 11587 have datatype=11 whereas input 5 of step 11571 have datatype=None WARNING : output 0 of step 11564 have datatype=1 whereas input 0 of step 11565 have datatype=2 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, mask_detect, blur_detection, brightness, crop_condition, thcl, merge_mask_thcl_custom, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score over limit max, limiting to limit_max 25 list_input_json : [] origin We have 1 , BFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 1 ; length of list_pids : 1 ; length of list_args : 1 time to download the photos : 0.3100285530090332 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 : 14 step1:mask_detect Wed Nov 26 16:57:52 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-11-26 16:57:55.008026: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-11-26 16:57:55.034412: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-11-26 16:57:55.036219: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f6290000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:57:55.036269: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-11-26 16:57:55.038775: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-11-26 16:57:55.313428: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x16a00190 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:57:55.313484: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-11-26 16:57:55.314753: 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 2025-11-26 16:57:55.315164: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:57:55.318303: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:57:55.321246: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:57:55.321742: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:57:55.324565: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:57:55.325576: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:57:55.330041: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:57:55.331589: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:57:55.331663: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:57:55.332410: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:57:55.332424: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:57:55.332433: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:57:55.333715: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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. 2025-11-26 16:57:55.578635: 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 2025-11-26 16:57:55.578740: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:57:55.578763: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:57:55.578785: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:57:55.578805: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:57:55.578826: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:57:55.578846: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:57:55.578866: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:57:55.580490: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:57:55.581911: 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 2025-11-26 16:57:55.581996: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:57:55.582017: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:57:55.582034: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:57:55.582052: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:57:55.582069: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:57:55.582086: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:57:55.582104: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:57:55.583731: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:57:55.583774: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:57:55.583786: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:57:55.583796: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:57:55.585540: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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 : thcl2486 thcls : [{'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5024 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5024, 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 16384, 25088, 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 12, 1, 0, 11, 4), datetime.datetime(2020, 12, 1, 0, 11, 4)) {'thcl': {'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}, 'list_hashtags': ['background', 'pet_clair', 'error', 'environment'], 'list_hashtags_csv': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'svm_hashtag_type_desc': 5024, 'photo_desc_type': 5024, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'pet_clair', 'error', 'environment'] 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_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error NUM_CLASSES 4 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_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-11-26 16:58:05.345957: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:58:05.518661: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error/mask_model.h5 size_local : 255899936 size in s3 : 255899936 create time local : 2021-08-11 01:29:18 create time in s3 : 2021-08-06 17:35:43 mask_model.h5 already exist and didn't need to update list_images length : 1 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 12) min: 0.00000 max: 3840.00000 nb d'objets trouves : 22 Detection mask done ! Trying to reset tf kernel 378951 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5706 tf kernel not reseted sub process len(results) : 1 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 1 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 : 10998 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2486 Catched exception ! Connect or reconnect ! thcls : [{'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5024 ['background', 'pet_clair', 'error', 'environment'] DEBUG bbox = [1422, 2118, 2160, 2958] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.017768383026123047 nb_pixel_total : 502969 time to create 1 rle with new method : 0.023401737213134766 length of segment : 701 DEBUG bbox = [24, 2340, 816, 3204] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.017282724380493164 nb_pixel_total : 542113 time to create 1 rle with new method : 0.027278900146484375 length of segment : 782 DEBUG bbox = [0, 0, 858, 978] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.24437475204467773 nb_pixel_total : 579928 time to create 1 rle with new method : 0.03394126892089844 length of segment : 887 DEBUG bbox = [1254, 18, 2160, 774] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0070726871490478516 nb_pixel_total : 438886 time to create 1 rle with new method : 0.03775334358215332 length of segment : 927 DEBUG bbox = [1398, 1266, 2148, 2106] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.00860905647277832 nb_pixel_total : 527736 time to create 1 rle with new method : 0.029927968978881836 length of segment : 703 DEBUG bbox = [18, 912, 774, 1758] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008646726608276367 nb_pixel_total : 519059 time to create 1 rle with new method : 0.03526163101196289 length of segment : 703 DEBUG bbox = [18, 1710, 780, 2484] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006810903549194336 nb_pixel_total : 438056 time to create 1 rle with new method : 0.02799844741821289 length of segment : 686 DEBUG bbox = [660, 2268, 1470, 3090] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.00834798812866211 nb_pixel_total : 485588 time to create 1 rle with new method : 0.14865636825561523 length of segment : 800 DEBUG bbox = [1332, 540, 2136, 1368] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008518695831298828 nb_pixel_total : 520762 time to create 1 rle with new method : 0.03441977500915527 length of segment : 762 DEBUG bbox = [1374, 2856, 2160, 3738] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008031129837036133 nb_pixel_total : 501532 time to create 1 rle with new method : 0.035629987716674805 length of segment : 1174 DEBUG bbox = [0, 3060, 822, 3828] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.011261701583862305 nb_pixel_total : 482092 time to create 1 rle with new method : 0.124969482421875 length of segment : 841 DEBUG bbox = [156, 0, 1332, 504] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007793903350830078 nb_pixel_total : 267873 time to create 1 rle with new method : 0.0307619571685791 length of segment : 1574 DEBUG bbox = [750, 2946, 1452, 3828] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006198883056640625 nb_pixel_total : 358571 time to create 1 rle with new method : 0.04005002975463867 length of segment : 794 DEBUG bbox = [582, 936, 1374, 1794] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010471343994140625 nb_pixel_total : 465591 time to create 1 rle with new method : 0.028605222702026367 length of segment : 730 DEBUG bbox = [570, 1716, 1410, 2514] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007695198059082031 nb_pixel_total : 390968 time to create 1 rle with new method : 0.026732683181762695 length of segment : 750 DEBUG bbox = [624, 432, 1386, 1302] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.00676417350769043 nb_pixel_total : 373083 time to create 1 rle with new method : 0.027904987335205078 length of segment : 693 DEBUG bbox = [678, 2328, 912, 2514] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0003924369812011719 nb_pixel_total : 23243 time to create 1 rle with old method : 0.02527475357055664 length of segment : 227 DEBUG bbox = [1560, 2820, 1758, 2970] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0006489753723144531 nb_pixel_total : 15299 time to create 1 rle with old method : 0.016650676727294922 length of segment : 185 DEBUG bbox = [360, 1950, 552, 2124] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0006861686706542969 nb_pixel_total : 20188 time to create 1 rle with old method : 0.02280116081237793 length of segment : 189 DEBUG bbox = [1092, 450, 1524, 1200] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0031685829162597656 nb_pixel_total : 181629 time to create 1 rle with new method : 0.008373737335205078 length of segment : 346 DEBUG bbox = [1284, 2730, 1422, 3078] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0005612373352050781 nb_pixel_total : 19786 time to create 1 rle with old method : 0.022604703903198242 length of segment : 123 DEBUG bbox = [12, 2466, 1494, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.015226125717163086 nb_pixel_total : 548117 time to create 1 rle with new method : 0.08953571319580078 length of segment : 1445 time spent for convertir_results : 4.322486162185669 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 51 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 16022 save missing photos in datou_result : time spend for datou_step_exec : 26.303088903427124 time spend to save output : 1.0779950618743896 total time spend for step 1 : 27.381083965301514 step2:mask_detect Wed Nov 26 16:58:19 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 : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-11-26 16:58:22.225457: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-11-26 16:58:22.250620: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-11-26 16:58:22.252786: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f6294000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:58:22.252843: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-11-26 16:58:22.256787: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-11-26 16:58:22.571416: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x16d56080 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:58:22.571486: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-11-26 16:58:22.573020: 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 2025-11-26 16:58:22.573495: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:58:22.576864: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:58:22.579876: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:58:22.580212: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:58:22.582521: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:58:22.583668: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:58:22.588685: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:58:22.590165: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:58:22.590251: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:58:22.591077: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:58:22.591095: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:58:22.591104: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:58:22.592458: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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. 2025-11-26 16:58:22.814053: 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 2025-11-26 16:58:22.814147: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:58:22.814170: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:58:22.814191: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:58:22.814211: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:58:22.814245: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:58:22.814266: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:58:22.814301: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:58:22.815905: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:58:22.817294: 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 2025-11-26 16:58:22.817332: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:58:22.817353: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:58:22.817372: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:58:22.817392: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:58:22.817411: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:58:22.817430: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:58:22.817450: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:58:22.819073: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:58:22.819115: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:58:22.819126: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:58:22.819136: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:58:22.820598: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 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 : thcl2499 thcls : [{'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5035 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5035, 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 16384, 25088, 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 12, 5, 18, 56, 33), datetime.datetime(2020, 12, 5, 18, 56, 33)) {'thcl': {'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}, 'list_hashtags': ['background', 'pet_clair', 'error', 'environment'], 'list_hashtags_csv': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'svm_hashtag_type_desc': 5035, 'photo_desc_type': 5035, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'pet_clair', 'error', 'environment'] 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_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug NUM_CLASSES 4 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_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-11-26 16:58:31.749883: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:58:31.920797: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug/mask_model.h5 size_local : 255899936 size in s3 : 255899936 create time local : 2021-08-11 01:32:04 create time in s3 : 2021-08-06 17:27:07 mask_model.h5 already exist and didn't need to update list_images length : 1 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 12) min: 0.00000 max: 3840.00000 nb d'objets trouves : 27 Detection mask done ! Trying to reset tf kernel 379751 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5706 tf kernel not reseted sub process len(results) : 1 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 1 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 : 10998 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2499 Catched exception ! Connect or reconnect ! thcls : [{'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5035 ['background', 'pet_clair', 'error', 'environment'] DEBUG bbox = [1248, 420, 2142, 1374] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.013819456100463867 nb_pixel_total : 615179 time to create 1 rle with new method : 0.25583362579345703 length of segment : 888 DEBUG bbox = [1278, 2862, 2160, 3780] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008336544036865234 nb_pixel_total : 628966 time to create 1 rle with new method : 0.03423905372619629 length of segment : 943 DEBUG bbox = [1398, 2070, 2130, 3024] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006307125091552734 nb_pixel_total : 495366 time to create 1 rle with new method : 0.027878522872924805 length of segment : 672 DEBUG bbox = [1224, 0, 2160, 810] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.005896329879760742 nb_pixel_total : 420689 time to create 1 rle with new method : 0.015122413635253906 length of segment : 908 DEBUG bbox = [42, 1836, 318, 2202] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0008380413055419922 nb_pixel_total : 47412 time to create 1 rle with old method : 0.050566673278808594 length of segment : 258 DEBUG bbox = [0, 3090, 900, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007741451263427734 nb_pixel_total : 486740 time to create 1 rle with new method : 0.015665769577026367 length of segment : 1062 DEBUG bbox = [600, 2970, 1464, 3810] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006239652633666992 nb_pixel_total : 447559 time to create 1 rle with new method : 0.015070915222167969 length of segment : 866 DEBUG bbox = [24, 0, 1002, 1032] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009065866470336914 nb_pixel_total : 522441 time to create 1 rle with new method : 0.03258991241455078 length of segment : 834 DEBUG bbox = [612, 0, 1608, 714] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.005674839019775391 nb_pixel_total : 320763 time to create 1 rle with new method : 0.19414258003234863 length of segment : 1253 DEBUG bbox = [1308, 1476, 2136, 2352] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006249189376831055 nb_pixel_total : 447518 time to create 1 rle with new method : 0.015493631362915039 length of segment : 793 DEBUG bbox = [744, 1698, 1044, 1962] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0006918907165527344 nb_pixel_total : 30906 time to create 1 rle with old method : 0.034982919692993164 length of segment : 240 DEBUG bbox = [18, 2382, 948, 3294] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.00838613510131836 nb_pixel_total : 566339 time to create 1 rle with new method : 0.025035858154296875 length of segment : 924 DEBUG bbox = [30, 12, 252, 186] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.000446319580078125 nb_pixel_total : 24406 time to create 1 rle with old method : 0.027402400970458984 length of segment : 282 DEBUG bbox = [702, 2334, 1482, 3096] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.005110502243041992 nb_pixel_total : 347062 time to create 1 rle with new method : 0.026972055435180664 length of segment : 671 DEBUG bbox = [684, 1674, 1500, 2598] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006284236907958984 nb_pixel_total : 375764 time to create 1 rle with new method : 0.09510254859924316 length of segment : 726 DEBUG bbox = [174, 1098, 1068, 1998] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008403539657592773 nb_pixel_total : 473999 time to create 1 rle with new method : 0.022906064987182617 length of segment : 930 DEBUG bbox = [0, 1722, 846, 2556] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006785869598388672 nb_pixel_total : 409528 time to create 1 rle with new method : 0.033882856369018555 length of segment : 848 DEBUG bbox = [828, 1524, 1068, 1764] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0005881786346435547 nb_pixel_total : 38102 time to create 1 rle with old method : 0.04013419151306152 length of segment : 208 DEBUG bbox = [666, 2334, 924, 2520] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004379749298095703 nb_pixel_total : 28339 time to create 1 rle with old method : 0.031080245971679688 length of segment : 237 DEBUG bbox = [1266, 2736, 1422, 3096] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.00045037269592285156 nb_pixel_total : 23703 time to create 1 rle with old method : 0.027054309844970703 length of segment : 128 DEBUG bbox = [858, 1284, 1764, 2148] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006387233734130859 nb_pixel_total : 425969 time to create 1 rle with new method : 0.01771068572998047 length of segment : 871 DEBUG bbox = [690, 2244, 2094, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.011294364929199219 nb_pixel_total : 205120 time to create 1 rle with new method : 0.669036865234375 length of segment : 626 DEBUG bbox = [882, 2466, 1092, 2694] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004401206970214844 nb_pixel_total : 19065 time to create 1 rle with old method : 0.021921157836914062 length of segment : 152 DEBUG bbox = [1188, 1986, 1410, 2166] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0005123615264892578 nb_pixel_total : 31177 time to create 1 rle with old method : 0.035065650939941406 length of segment : 217 DEBUG bbox = [1152, 606, 1368, 840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.00039649009704589844 nb_pixel_total : 13064 time to create 1 rle with old method : 0.014881372451782227 length of segment : 129 DEBUG bbox = [726, 366, 1602, 1368] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006937503814697266 nb_pixel_total : 467124 time to create 1 rle with new method : 0.021593332290649414 length of segment : 768 DEBUG bbox = [1152, 2508, 2040, 3300] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.004992961883544922 nb_pixel_total : 227844 time to create 1 rle with new method : 0.014816045761108398 length of segment : 789 time spent for convertir_results : 5.043483018875122 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 57 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 17223 save missing photos in datou_result : time spend for datou_step_exec : 26.17206120491028 time spend to save output : 1.2266530990600586 total time spend for step 2 : 27.398714303970337 step3:blur_detection Wed Nov 26 16:58:47 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 toutes les photos sont déjà traitées, on saute les calculs 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 : 1 time used for this insertion : 0.009894609451293945 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.009821653366088867 save missing photos in datou_result : time spend for datou_step_exec : 0.026318788528442383 time spend to save output : 0.024759292602539062 total time spend for step 3 : 0.051078081130981445 step4:brightness Wed Nov 26 16:58:47 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 toutes les photos sont déjà traitées, on saute les calculs 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 : 1 time used for this insertion : 0.009811162948608398 begin to insert list_values into photo_hahstag_ids : length of list_valuse in save_photo_hashtag_id_type : 1 time used for this insertion : 0.009980916976928711 save missing photos in datou_result : time spend for datou_step_exec : 0.030119657516479492 time spend to save output : 0.02483844757080078 total time spend for step 4 : 0.05495810508728027 step5:crop_condition Wed Nov 26 16:58:47 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 Loading chi in step crop with photo_hashtag_type : 3132 Loading chi in step crop for list_pids : 1 ! batch 1 Loaded 57 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : error param for this class : {'min_score': 0.3} filtre for class : error hashtag_id of this class : 501120777 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 10 About to insert : list_path_to_insert length 10 new photo from crops ! we have finished the crop for the class : error delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1390404834] Looping around the photos to save general results len do output : 10 /-4009041074Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009041079Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009041066Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009034719Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009041085Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009034717Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009041080Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009034721Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009041081Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-4009034718Didn'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 ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 31 time used for this insertion : 0.021502256393432617 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.1520652770996094 time spend to save output : 0.0220489501953125 total time spend for step 5 : 2.174114227294922 step6:thcl Wed Nov 26 16:58:49 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step Thcl ! nombre de thcls : 1 we are using the classfication for multi_thcl [3441] time to import caffe and check if the image exist : 0.006269216537475586 time to convert the images to numpy array : 0.007781505584716797 time to import caffe and check if the image exist : 0.006547212600708008 time to convert the images to numpy array : 0.007474660873413086 time to import caffe and check if the image exist : 0.006581783294677734 time to convert the images to numpy array : 0.007783412933349609 time to import caffe and check if the image exist : 0.0069658756256103516 time to convert the images to numpy array : 0.009695053100585938 time to import caffe and check if the image exist : 0.0071904659271240234 time to convert the images to numpy array : 0.009018898010253906 time to import caffe and check if the image exist : 0.005283355712890625 time to convert the images to numpy array : 0.012444019317626953 time to import caffe and check if the image exist : 0.007123470306396484 time to convert the images to numpy array : 0.009923696517944336 time to import caffe and check if the image exist : 0.005214691162109375 time to convert the images to numpy array : 0.013702869415283203 time to import caffe and check if the image exist : 0.007781505584716797 time to convert the images to numpy array : 0.01071476936340332 time to import caffe and check if the image exist : 0.006272077560424805 time to convert the images to numpy array : 0.014369726181030273 total time to convert the images to numpy array : 0.19944190979003906 list photo_ids error: [] list photo_ids correct : [-4009041074, -4009034717, -4009034718, -4009034719, -4009041081, -4009041085, -4009034721, -4009041079, -4009041080, -4009041066] number of photos to traite : 10 try to delete the photos incorrect in DB tagging for thcl : 3441 To do loadFromThcl(), then load ParamDescType : thcl3441 thcls : [{'id': 3441, 'mtr_user_id': 31, 'name': 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'autre,barquette_avec_film,bouchon,carton,environnement,etiquette,metal,papier,pehd,pet_clair,pet_fonce', 'svm_portfolios_learning': '3309139,3309056,3309252,3309141,7554268,3309137,3312281,3309184,3309073,3309053,3309070', 'photo_hashtag_type': 4456, 'photo_desc_type': 5722, 'type_classification': 'caffe', 'hashtag_id_list': '494826614,2107756859,492645504,492774966,493012381,492636447,492628673,492668766,628944319,2107755846,2107755900'}] thcl {'id': 3441, 'mtr_user_id': 31, 'name': 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'autre,barquette_avec_film,bouchon,carton,environnement,etiquette,metal,papier,pehd,pet_clair,pet_fonce', 'svm_portfolios_learning': '3309139,3309056,3309252,3309141,7554268,3309137,3312281,3309184,3309073,3309053,3309070', 'photo_hashtag_type': 4456, 'photo_desc_type': 5722, 'type_classification': 'caffe', 'hashtag_id_list': '494826614,2107756859,492645504,492774966,493012381,492636447,492628673,492668766,628944319,2107755846,2107755900'} Update svm_hashtag_type_desc : 5722 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5722, 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 2048, 2048, 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2022, 10, 27, 14, 43, 34), datetime.datetime(2022, 10, 27, 14, 43, 34)) To loadFromThcl() : net_5722 begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10998 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5722, 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 2048, 2048, 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2022, 10, 27, 14, 43, 34), datetime.datetime(2022, 10, 27, 14, 43, 34)) None mean_file_type : mean_file_path : prototxt_file_path : model : sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4 /data/models_weight/sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4/caffemodel size_local : 94358554 size in s3 : 94358554 create time local : 2022-10-30 01:36:46 create time in s3 : 2022-10-27 12:43:29 caffemodel already exist and didn't need to update /data/models_weight/sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4/deploy.prototxt size_local : 32544 size in s3 : 32544 create time local : 2022-10-30 01:36:46 create time in s3 : 2022-10-27 12:43:33 deploy.prototxt already exist and didn't need to update /data/models_weight/sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2022-10-30 01:36:46 create time in s3 : 2022-10-27 12:43:34 mean.npy already exist and didn't need to update /data/models_weight/sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4/synset_words.txt size_local : 346 size in s3 : 346 create time local : 2022-10-30 01:36:46 create time in s3 : 2022-10-27 12:43:33 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /home/admin/workarea/install/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/:/home/admin/workarea/git/apy/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4/deploy.prototxt caffemodel_filename : /data/models_weight/sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_261022_4/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10776 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 0.1157064437866211 time used to do the prediction : 0.09644699096679688 save descriptor for thcl : 3441 time to traite the descriptors : 0.053160667419433594 storage_type for insertDescriptorsMulti : 3 Missing photo l117 : -4009041074 Missing photo l117 : -4009034717 Missing photo l117 : -4009034718 Missing photo l117 : -4009034719 Missing photo l117 : -4009041081 Missing photo l117 : -4009041085 Missing photo l117 : -4009034721 Missing photo l117 : -4009041079 Missing photo l117 : -4009041080 Missing photo l117 : -4009041066 To insert : -4009041074 Missing photo l134 : -4009041074 To insert : -4009034717 Missing photo l134 : -4009034717 To insert : -4009034718 Missing photo l134 : -4009034718 To insert : -4009034719 Missing photo l134 : -4009034719 To insert : -4009041081 Missing photo l134 : -4009041081 To insert : -4009041085 Missing photo l134 : -4009041085 To insert : -4009034721 Missing photo l134 : -4009034721 To insert : -4009041079 Missing photo l134 : -4009041079 To insert : -4009041080 Missing photo l134 : -4009041080 To insert : -4009041066 Missing photo l134 : -4009041066 time to insert the descriptors : 1.829455852508545 Inside saveOutput : final : False verbose : 0 time used to find the portfolios of the photos test new format of the output of the step_thcl begin to insert list_values into class_photo_scores : length of list_valuse in save_photo_hashtag_id_thcl_score : 0 time used for this insertion : 2.86102294921875e-06 save missing photos in datou_result : time spend for datou_step_exec : 6.059002637863159 time spend to save output : 0.0001811981201171875 total time spend for step 6 : 6.059183835983276 step7:merge_mask_thcl_custom Wed Nov 26 16:58:55 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 1 Inconsistent number of input and output, step which parrallelize and manage error in input by avoiding sending an output for this data can't be used in tree dependencies of input and output complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step merge_mask_thcl_custom batch 1 Loaded 57 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++As expected we have just one thcl present End of step merge_mask_thcl_custom Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : merge_mask_thcl_custom we use saveGeneral [1390404834] Looping around the photos to save general results len do output : 1 /1390404834Didn'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 : Managing all output in save final without adding information in the mtr_datou_result ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.016213417053222656 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.10681343078613281 time spend to save output : 0.016376018524169922 total time spend for step 7 : 0.12318944931030273 step8:rle_unique_nms_with_priority Wed Nov 26 16:58:55 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Begin step rle-unique-nms nb_obj : 55 nb_hashtags : 3 time to prepare the origin masks : 23.017901182174683 time for calcul the mask position with numpy : 0.030273914337158203 nb_pixel_total : 415305 time to create 1 rle with new method : 0.9551947116851807 time for calcul the mask position with numpy : 0.03337669372558594 nb_pixel_total : 479108 time to create 1 rle with new method : 0.7374439239501953 time for calcul the mask position with numpy : 0.03344297409057617 nb_pixel_total : 4599 time to create 1 rle with old method : 0.007909297943115234 time for calcul the mask position with numpy : 0.040773868560791016 nb_pixel_total : 509428 time to create 1 rle with new method : 0.623507022857666 time for calcul the mask position with numpy : 0.03181862831115723 nb_pixel_total : 339043 time to create 1 rle with new method : 0.6865239143371582 time for calcul the mask position with numpy : 0.03315544128417969 nb_pixel_total : 554783 time to create 1 rle with new method : 0.7374849319458008 time for calcul the mask position with numpy : 0.03282785415649414 nb_pixel_total : 565 time to create 1 rle with old method : 0.0009484291076660156 time for calcul the mask position with numpy : 0.031177282333374023 nb_pixel_total : 11743 time to create 1 rle with old method : 0.012937068939208984 time for calcul the mask position with numpy : 0.033898353576660156 nb_pixel_total : 541612 time to create 1 rle with new method : 0.6898677349090576 time for calcul the mask position with numpy : 0.03201866149902344 nb_pixel_total : 28125 time to create 1 rle with old method : 0.030074357986450195 time for calcul the mask position with numpy : 0.030916452407836914 nb_pixel_total : 24290 time to create 1 rle with old method : 0.0256807804107666 time for calcul the mask position with numpy : 0.03197956085205078 nb_pixel_total : 47254 time to create 1 rle with old method : 0.04804515838623047 time for calcul the mask position with numpy : 0.030802011489868164 nb_pixel_total : 38126 time to create 1 rle with old method : 0.038910627365112305 time for calcul the mask position with numpy : 0.032248735427856445 nb_pixel_total : 251699 time to create 1 rle with new method : 0.7137248516082764 time for calcul the mask position with numpy : 0.03338742256164551 nb_pixel_total : 20140 time to create 1 rle with old method : 0.022193193435668945 time for calcul the mask position with numpy : 0.03523993492126465 nb_pixel_total : 6593 time to create 1 rle with old method : 0.010114192962646484 time for calcul the mask position with numpy : 0.03542351722717285 nb_pixel_total : 22028 time to create 1 rle with old method : 0.024213790893554688 time for calcul the mask position with numpy : 0.03462934494018555 nb_pixel_total : 214686 time to create 1 rle with new method : 0.4303090572357178 time for calcul the mask position with numpy : 0.03474235534667969 nb_pixel_total : 309173 time to create 1 rle with new method : 0.8951983451843262 time for calcul the mask position with numpy : 0.03130316734313965 nb_pixel_total : 1805 time to create 1 rle with old method : 0.002518892288208008 time for calcul the mask position with numpy : 0.03233051300048828 nb_pixel_total : 400487 time to create 1 rle with new method : 0.7287611961364746 time for calcul the mask position with numpy : 0.03396415710449219 nb_pixel_total : 409729 time to create 1 rle with new method : 0.6214687824249268 time for calcul the mask position with numpy : 0.03235793113708496 nb_pixel_total : 28316 time to create 1 rle with old method : 0.028590679168701172 time for calcul the mask position with numpy : 0.030814170837402344 nb_pixel_total : 802 time to create 1 rle with old method : 0.0009465217590332031 time for calcul the mask position with numpy : 0.03158283233642578 nb_pixel_total : 50479 time to create 1 rle with old method : 0.05178999900817871 time for calcul the mask position with numpy : 0.0306243896484375 nb_pixel_total : 11744 time to create 1 rle with old method : 0.011925935745239258 time for calcul the mask position with numpy : 0.03228116035461426 nb_pixel_total : 336119 time to create 1 rle with new method : 0.4678614139556885 time for calcul the mask position with numpy : 0.03300952911376953 nb_pixel_total : 111328 time to create 1 rle with old method : 0.11510205268859863 time for calcul the mask position with numpy : 0.03228473663330078 nb_pixel_total : 37984 time to create 1 rle with old method : 0.0392146110534668 time for calcul the mask position with numpy : 0.03168964385986328 nb_pixel_total : 11 time to create 1 rle with old method : 3.5762786865234375e-05 time for calcul the mask position with numpy : 0.030807971954345703 nb_pixel_total : 11 time to create 1 rle with old method : 3.361701965332031e-05 time for calcul the mask position with numpy : 0.03083038330078125 nb_pixel_total : 6860 time to create 1 rle with old method : 0.007604122161865234 time for calcul the mask position with numpy : 0.030487060546875 nb_pixel_total : 42 time to create 1 rle with old method : 0.000400543212890625 time for calcul the mask position with numpy : 0.03116607666015625 nb_pixel_total : 72803 time to create 1 rle with old method : 0.07391500473022461 time for calcul the mask position with numpy : 0.03239774703979492 nb_pixel_total : 64688 time to create 1 rle with old method : 0.0659487247467041 time for calcul the mask position with numpy : 0.03291010856628418 nb_pixel_total : 41105 time to create 1 rle with old method : 0.04372119903564453 time for calcul the mask position with numpy : 0.03156757354736328 nb_pixel_total : 31107 time to create 1 rle with old method : 0.03185677528381348 time for calcul the mask position with numpy : 0.0355677604675293 nb_pixel_total : 579986 time to create 1 rle with new method : 0.6130623817443848 time for calcul the mask position with numpy : 0.032196998596191406 nb_pixel_total : 1364 time to create 1 rle with old method : 0.0018260478973388672 time for calcul the mask position with numpy : 0.03198385238647461 nb_pixel_total : 23628 time to create 1 rle with old method : 0.024552345275878906 time for calcul the mask position with numpy : 0.03197336196899414 nb_pixel_total : 15627 time to create 1 rle with old method : 0.01635456085205078 time for calcul the mask position with numpy : 0.03157186508178711 nb_pixel_total : 39833 time to create 1 rle with old method : 0.04081225395202637 time for calcul the mask position with numpy : 0.033673763275146484 nb_pixel_total : 147384 time to create 1 rle with old method : 0.15256285667419434 time for calcul the mask position with numpy : 0.03065323829650879 nb_pixel_total : 873 time to create 1 rle with old method : 0.0011000633239746094 time for calcul the mask position with numpy : 0.035440921783447266 nb_pixel_total : 438426 time to create 1 rle with new method : 0.6043410301208496 time for calcul the mask position with numpy : 0.031123876571655273 nb_pixel_total : 90 time to create 1 rle with old method : 0.0003981590270996094 time for calcul the mask position with numpy : 0.03168439865112305 nb_pixel_total : 59357 time to create 1 rle with old method : 0.061125755310058594 time for calcul the mask position with numpy : 0.03134965896606445 nb_pixel_total : 618 time to create 1 rle with old method : 0.0010101795196533203 time for calcul the mask position with numpy : 0.03542160987854004 nb_pixel_total : 499478 time to create 1 rle with new method : 0.593801736831665 time for calcul the mask position with numpy : 0.03493070602416992 nb_pixel_total : 527333 time to create 1 rle with new method : 0.5702939033508301 time for calcul the mask position with numpy : 0.0344691276550293 nb_pixel_total : 488050 time to create 1 rle with new method : 0.46956324577331543 time for calcul the mask position with numpy : 0.0312650203704834 nb_pixel_total : 8284 time to create 1 rle with old method : 0.00879049301147461 time for calcul the mask position with numpy : 0.031494140625 nb_pixel_total : 381 time to create 1 rle with old method : 0.001027822494506836 time for calcul the mask position with numpy : 0.03130292892456055 nb_pixel_total : 20219 time to create 1 rle with old method : 0.022043466567993164 time for calcul the mask position with numpy : 0.03256702423095703 nb_pixel_total : 15265 time to create 1 rle with old method : 0.015899181365966797 time for calcul the mask position with numpy : 0.03206610679626465 nb_pixel_total : 4484 time to create 1 rle with old method : 0.0054645538330078125 create new chi : 14.4206862449646 time to delete rle : 0.058858633041381836 batch 1 Loaded 69 chid ids of type : 3327 Number RLEs to save : 37878 TO DO : save crop sub photo not yet done ! save time : 2.335662603378296 map_output_result : {1390404834: (0.0, 'Should be the crop_list due to order', 0.0)} End step rle-unique-nms Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : rle_unique_nms_with_priority we use saveGeneral [1390404834] Looping around the photos to save general results len do output : 1 /1390404834.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 ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.014048337936401367 save_final save missing photos in datou_result : time spend for datou_step_exec : 40.050934076309204 time spend to save output : 0.014289617538452148 total time spend for step 8 : 40.065223693847656 step9:crop_condition Wed Nov 26 16:59:35 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 : 3327 Loading chi in step crop for list_pids : 1 ! batch 1 Loaded 69 chid ids of type : 3327 begin to crop the class : pet_clair param for this class : {'min_score': 0.5} filtre for class : pet_clair hashtag_id of this class : 2107755846 Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! Next one ! map_result returned by crop_photo_return_map_crop : length : 13 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/1764172794_378884 INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049567_0.png', 0, 958, 811, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049594_0.png', 0, 854, 880, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049578_0.png', 0, 601, 638, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049565_0.png', 0, 816, 705, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049580_0.png', 0, 797, 702, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049604_0.png', 0, 825, 702, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049566_0.png', 0, 705, 684, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4046250090_0.png', 0, 616, 705, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049605_0.png', 0, 824, 696, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049581_0.png', 0, 766, 757, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049576_0.png', 0, 115, 137, 0, 1764172796,'0',0) batch_size : 0, verbose : False, strat_bulk_insert : ignore_different_from_first This is a hack ! INSERT INTO MTRBack.photos (`timeStamp`, `latitude`, `longitude`, `right_categories`, `tags`, `speed`, `size`, `text`, `altitude`, `width`, `height`, `score`, `created_at`,`source_id`,`place_id`) VALUES (FROM_UNIXTIME(1764172796), 0.0, 0.0, 14, '', 0, 0, '1764172672_378884_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049569_0.png', 0, 836, 781, 0, 1764172796,'0',0) 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 : 3.4949231147766113 we have finished the crop for the class : pet_clair begin to crop the class : etiquette param for this class : {'min_score': 0.5} filtre for class : etiquette hashtag_id of this class : 492636447 begin to crop the class : bouchon param for this class : {'min_score': 0.5} filtre for class : bouchon hashtag_id of this class : 492645504 begin to crop the class : pet_fonce param for this class : {'min_score': 0.5} filtre for class : pet_fonce hashtag_id of this class : 2107755900 begin to crop the class : pehd param for this class : {'min_score': 0.5} filtre for class : pehd hashtag_id of this class : 628944319 begin to crop the class : barquette_avec_film param for this class : {'min_score': 0.5} filtre for class : barquette_avec_film hashtag_id of this class : 2107756859 begin to crop the class : papier param for this class : {'min_score': 0.5} filtre for class : papier hashtag_id of this class : 492668766 begin to crop the class : carton param for this class : {'min_score': 0.5} filtre for class : carton hashtag_id of this class : 492774966 begin to crop the class : verre param for this class : {'min_score': 0.5} filtre for class : verre hashtag_id of this class : 492631919 begin to crop the class : metal param for this class : {'min_score': 0.5} filtre for class : metal hashtag_id of this class : 492628673 begin to crop the class : autre param for this class : {'min_score': 0.5} filtre for class : autre hashtag_id of this class : 494826614 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1390404834] Looping around the photos to save general results len do output : 13 /1396266652Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266653Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266654Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266655Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266656Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266657Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266659Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393124098Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396266663Didn'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 ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 40 time used for this insertion : 0.023491859436035156 save_final save missing photos in datou_result : time spend for datou_step_exec : 22.279011011123657 time spend to save output : 0.02421879768371582 total time spend for step 9 : 22.303229808807373 step10:ventilate_hashtags_in_portfolio Wed Nov 26 16:59:57 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 ! To do loadFromThcl(), then load ParamDescType : thcl2547 thcls : [{'id': 2547, 'mtr_user_id': 31, 'name': 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_2212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'autre,barquette_avec_film,bouchon,carton,environnement,etiquette,metal,papier,pehd,pet_clair,pet_fonce', 'svm_portfolios_learning': '3309139,3309056,3309252,3309141,3309086,3309137,3312281,3309184,3309073,3309053,3309070', 'photo_hashtag_type': 3200, 'photo_desc_type': 5072, 'type_classification': 'caffe', 'hashtag_id_list': '494826614,2107756859,492645504,492774966,493012381,492636447,492628673,492668766,628944319,2107755846,2107755900'}] thcl {'id': 2547, 'mtr_user_id': 31, 'name': 'sur_classifieur_rubbia_pet_clair_10_classes_finetune_aug_2212', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'autre,barquette_avec_film,bouchon,carton,environnement,etiquette,metal,papier,pehd,pet_clair,pet_fonce', 'svm_portfolios_learning': '3309139,3309056,3309252,3309141,3309086,3309137,3312281,3309184,3309073,3309053,3309070', 'photo_hashtag_type': 3200, 'photo_desc_type': 5072, 'type_classification': 'caffe', 'hashtag_id_list': '494826614,2107756859,492645504,492774966,493012381,492636447,492628673,492668766,628944319,2107755846,2107755900'} Update svm_hashtag_type_desc : 5072 Iterating over portfolio : 28926786 get user id for portfolio 28926786 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`=28926786 AND mptpi.`type`=3327 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('verre','environnement','pet_clair','pet_fonce','mal_croppe','barquette_avec_film','etiquette','carton','pehd','metal','flou','bouchon','autre','papier')) AND mptpi.`min_score`=0.5 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") 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`=28926786 AND mptpi.`type`=3327 AND mptpi.`hashtag_id` in (select hashtag_id FROM MTRBack.hashtags where hashtag in ('verre','environnement','pet_clair','pet_fonce','mal_croppe','barquette_avec_film','etiquette','carton','pehd','metal','flou','bouchon','autre','papier')) AND mptpi.`min_score`=0.5 To do lien utilise dans velours : https://marlene.fotonower.com/velours/28926915,28926916,28926917,28926918,28926919,28926920,28926921,28926922,28926923,28926924,28926925,28926926,28926927,28926928?tags=metal,carton,pet_clair,etiquette,pehd,flou,papier,autre,bouchon,mal_croppe,pet_fonce,barquette_avec_film,verre,environnement Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : ventilate_hashtags_in_portfolio we use saveGeneral [1390404834] Looping around the photos to save general results len do output : 1 /28926786. 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 ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.01781439781188965 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.183791399002075 time spend to save output : 0.01800394058227539 total time spend for step 10 : 2.2017953395843506 step11:final Wed Nov 26 17:00:00 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 ! apple list_material_ratio_1 [('28926786', '3327', '494826614', '0.0'), ('28926786', '3327', '492774966', '0.0'), ('28926786', '3327', '492628673', '0.0'), ('28926786', '3327', '492668766', '0.0'), ('28926786', '3327', '628944319', '0.0'), ('28926786', '3327', '2107755900', '0.0'), ('28926786', '3327', '2107755846', '0.9265458741404441'), ('28926786', '3327', '492645504', '0.0'), ('28926786', '3327', '492636447', '0.0'), ('28926786', '3327', '2107756859', '0.0'), ('28926786', '3327', '493061979', '0.07345412585955594')] 0.07345412585955594 0.9265458741404441 list_material_ratio_3 [('28926786', '3327', '494826614', '0.0'), ('28926786', '3327', '492774966', '0.0'), ('28926786', '3327', '492628673', '0.0'), ('28926786', '3327', '492668766', '0.0'), ('28926786', '3327', '628944319', '0.0'), ('28926786', '3327', '2107755900', '0.0'), ('28926786', '3327', '2107755846', '1.0'), ('28926786', '3327', '492645504', '0.0'), ('28926786', '3327', '492636447', '0.0'), ('28926786', '3327', '2107756859', '0.0')] Inside saveOutput : final : False verbose : 0 original output for save of step final : {1390404834: ('0.0',)} new output for save of step final : {1390404834: ('0.0',)} [1390404834] Looping around the photos to save general results len do output : 1 /1390404834.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 ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.018251895904541016 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.14769649505615234 time spend to save output : 0.01841568946838379 total time spend for step 11 : 0.16611218452453613 step12:velours_tree Wed Nov 26 17:00:00 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 : 0.03317761421203613 time spend to save output : 3.0517578125e-05 total time spend for step 12 : 0.03320813179016113 step13:send_mail_cod Wed Nov 26 17:00:00 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 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 in order to get the selector url, please entre the license of selector results_Auto_P28926786_26-11-2025_17_00_00.pdf 28926915 imagette289269151764172800 28926916 imagette289269161764172800 28926918 imagette289269181764172800 28926919 imagette289269191764172800 28926920 imagette289269201764172800 28926921 imagette289269211764172800 28926922 imagette289269221764172800 28926923 imagette289269231764172800 28926924 imagette289269241764172800 28926925 imagette289269251764172800 28926926 imagette289269261764172800 28926927 imagette289269271764172800 SELECT h.hashtag,pcr.value FROM MTRUser.portfolio_carac_ratio pcr, MTRBack.hashtags h where pcr.portfolio_id=28926786 and hashtag_type = 3327 and pcr.hashtag_id = h.hashtag_id; velour_link : https://marlene.fotonower.com/velours/28926915,28926916,28926917,28926918,28926919,28926920,28926921,28926922,28926923,28926924,28926925,28926926,28926927,28926928?tags=metal,carton,pet_clair,etiquette,pehd,flou,papier,autre,bouchon,mal_croppe,pet_fonce,barquette_avec_film,verre,environnement your option no_mail is active, we will not send the real mail to your client args[1390404834] : ((1390404834, -6.186561832478863, 492609224), (1390404834, -0.4382390890556738, 496442774), '0.0') We are sending mail with results at report@fotonower.com refus_total : 0.0 2022-04-13 10:29:59 0 SELECT ph.photo_id,ph.url,ph.username,ph.uploaded_at,ph.text FROM MTRBack.photos_view ph, MTRUser.mtr_portfolio_photos mpp WHERE ph.photo_id=mpp.mtr_photo_id AND mpp.mtr_portfolio_id=28926786 AND mpp.hide_status=0 ORDER BY mpp.order LIMIT 0, 1000 start upload file to ovh https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28926786_26-11-2025_17_00_00.pdf results_Auto_P28926786_26-11-2025_17_00_00.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28926786_26-11-2025_17_00_00.pdf start insert file to database insert into MTRUser.mtr_files (mtd_id,mtr_portfolio_id,text,url,format,tags,file_size,value) values ('3804','28926786','results_Auto_P28926786_26-11-2025_17_00_00.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28926786_26-11-2025_17_00_00.pdf','pdf','','0.06','0.0') Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : send_mail_cod we use saveGeneral [1390404834] 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 ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.015096664428710938 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.9590842723846436 time spend to save output : 0.015225887298583984 total time spend for step 13 : 0.9743101596832275 step14:split_time_score Wed Nov 26 17:00:01 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 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 ! Dont find camara_place_name for portfolio_id : 28926786 Inside saveOutput : final : True verbose : 0 saveOutput not yet implemented for datou_step.type : split_time_score we use saveGeneral [1390404834] Looping around the photos to save general results len do output : 0 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 ('3804', None, None, None, None, None, None, None, '4121914') ('3804', '28926786', '1390404834', None, None, None, None, None, '4121914') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.016868114471435547 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12450194358825684 time spend to save output : 0.016991615295410156 total time spend for step 14 : 0.141493558883667 caffe_path_current : About to save ! 2 After save, about to update current ! ret : 2 len(input) + len(total_photo_id_missing) : 1 set_done_treatment 75.58user 46.66system 2:11.40elapsed 93%CPU (0avgtext+0avgdata 3070164maxresident)k 48inputs+60512outputs (1major+6208700minor)pagefaults 0swaps