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 : 430474 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 : ['4122124'] with mtr_portfolio_ids : ['28926786'] and first list_photo_ids : [] new path : /proc/430474/ 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 : 0.2257518768310547 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 17:26:52 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 : 3346 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-11-26 17:26:55.225494: 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 17:26:55.250575: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-11-26 17:26:55.252555: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fc530000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-11-26 17:26:55.252598: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-11-26 17:26:55.255975: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-11-26 17:26:55.475365: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x24db4c60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-11-26 17:26:55.475411: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-11-26 17:26:55.476445: 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 17:26:55.476812: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:26:55.483577: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:26:55.485982: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 17:26:55.486821: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 17:26:55.489106: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 17:26:55.490300: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 17:26:55.494883: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:26:55.495829: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 17:26:55.495884: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:26:55.496385: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 17:26:55.496400: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 17:26:55.496408: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 17:26:55.497256: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2894 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 17:26:55.745541: 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 17:26:55.745642: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:26:55.745674: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:26:55.745702: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 17:26:55.745730: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 17:26:55.745757: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 17:26:55.745783: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 17:26:55.745810: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:26:55.747095: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 17:26:55.747930: 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 17:26:55.747969: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:26:55.747985: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:26:55.747998: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 17:26:55.748012: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 17:26:55.748026: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 17:26:55.748040: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 17:26:55.748054: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:26:55.748863: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 17:26:55.748888: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 17:26:55.748896: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 17:26:55.748903: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 17:26:55.749708: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2894 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 17:27:03.428977: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:27:03.611953: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:27:04.918377: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.193405: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-11-26 17:27:05.240172: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.240222: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.241913: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.241944: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.243943: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.243963: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.244530: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.244545: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.269081: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.269123: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 564.38MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.269716: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.269733: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 564.38MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.271311: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.271333: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 290.15MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.271963: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.271980: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 290.15MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.277291: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.277334: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.277923: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.277938: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:05.279609: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.280226: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.285711: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.286309: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.287829: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.288416: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.315335: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.315974: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.316583: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.317200: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.320949: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.321580: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.337591: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.338231: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.338856: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.339482: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.351876: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.352513: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.353135: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.353743: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.358124: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.358782: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.363598: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.364249: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.376476: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.377113: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.381264: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.381885: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.382503: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.383118: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.383970: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.384585: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.395216: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.395860: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.396493: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.397101: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.397720: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.398345: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.413536: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.414122: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.433413: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.433473: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-11-26 17:27:05.434586: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.435740: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.443609: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.444274: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.444918: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.445548: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.453480: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.454120: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.470491: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.471415: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.472058: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.472640: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.476673: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.477252: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.477827: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.478424: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.479472: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.489557: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.490137: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.499137: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.499776: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.500402: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.500979: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.501564: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:05.502139: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 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 430516 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2153 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 : 3346 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 : 0.02276301383972168 nb_pixel_total : 502972 time to create 1 rle with new method : 0.030472278594970703 length of segment : 701 DEBUG bbox = [24, 2340, 816, 3204] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0531461238861084 nb_pixel_total : 542115 time to create 1 rle with new method : 0.033228397369384766 length of segment : 782 DEBUG bbox = [0, 0, 858, 978] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.023060083389282227 nb_pixel_total : 579998 time to create 1 rle with new method : 0.04037356376647949 length of segment : 887 DEBUG bbox = [1254, 18, 2160, 774] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006713390350341797 nb_pixel_total : 438893 time to create 1 rle with new method : 0.03213810920715332 length of segment : 927 DEBUG bbox = [1398, 1266, 2148, 2106] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007879972457885742 nb_pixel_total : 527724 time to create 1 rle with new method : 0.030467748641967773 length of segment : 704 DEBUG bbox = [18, 912, 774, 1758] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008172988891601562 nb_pixel_total : 518998 time to create 1 rle with new method : 0.031018495559692383 length of segment : 703 DEBUG bbox = [18, 1710, 780, 2484] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006430625915527344 nb_pixel_total : 438094 time to create 1 rle with new method : 0.02682781219482422 length of segment : 686 DEBUG bbox = [660, 2268, 1470, 3090] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008552789688110352 nb_pixel_total : 485581 time to create 1 rle with new method : 0.035588979721069336 length of segment : 800 DEBUG bbox = [1332, 540, 2136, 1368] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008039474487304688 nb_pixel_total : 520773 time to create 1 rle with new method : 0.03366446495056152 length of segment : 762 DEBUG bbox = [1374, 2856, 2160, 3738] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.011337995529174805 nb_pixel_total : 501554 time to create 1 rle with new method : 0.037447214126586914 length of segment : 1173 DEBUG bbox = [0, 3060, 822, 3828] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.011674880981445312 nb_pixel_total : 482103 time to create 1 rle with new method : 0.03293132781982422 length of segment : 842 DEBUG bbox = [156, 0, 1332, 504] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007524728775024414 nb_pixel_total : 267901 time to create 1 rle with new method : 0.030496835708618164 length of segment : 1574 DEBUG bbox = [750, 2946, 1452, 3828] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.005867719650268555 nb_pixel_total : 358592 time to create 1 rle with new method : 0.03200984001159668 length of segment : 795 DEBUG bbox = [582, 936, 1374, 1794] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009096622467041016 nb_pixel_total : 465713 time to create 1 rle with new method : 0.03591203689575195 length of segment : 730 DEBUG bbox = [570, 1716, 1410, 2514] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.019243955612182617 nb_pixel_total : 390993 time to create 1 rle with new method : 0.0279538631439209 length of segment : 749 DEBUG bbox = [624, 432, 1386, 1302] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008869171142578125 nb_pixel_total : 373124 time to create 1 rle with new method : 0.02597212791442871 length of segment : 692 DEBUG bbox = [678, 2328, 912, 2514] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004260540008544922 nb_pixel_total : 23244 time to create 1 rle with old method : 0.02427840232849121 length of segment : 226 DEBUG bbox = [1560, 2820, 1758, 2970] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0006237030029296875 nb_pixel_total : 15297 time to create 1 rle with old method : 0.017381906509399414 length of segment : 185 DEBUG bbox = [360, 1950, 552, 2124] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0007014274597167969 nb_pixel_total : 20186 time to create 1 rle with old method : 0.023079872131347656 length of segment : 189 DEBUG bbox = [1092, 450, 1524, 1200] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.003095865249633789 nb_pixel_total : 181600 time to create 1 rle with new method : 0.007964611053466797 length of segment : 349 DEBUG bbox = [1284, 2730, 1422, 3078] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0007264614105224609 nb_pixel_total : 19803 time to create 1 rle with old method : 0.020873069763183594 length of segment : 123 DEBUG bbox = [12, 2466, 1494, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.018695592880249023 nb_pixel_total : 548399 time to create 1 rle with new method : 0.19295716285705566 length of segment : 1444 time spent for convertir_results : 4.046386241912842 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 61 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 16023 save missing photos in datou_result : time spend for datou_step_exec : 22.28913640975952 time spend to save output : 1.0815303325653076 total time spend for step 1 : 23.37066674232483 step2:mask_detect Wed Nov 26 17:27:16 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 We 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 : 3346 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-11-26 17:27:18.719277: 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 17:27:18.746420: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-11-26 17:27:18.748579: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fc534000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-11-26 17:27:18.748634: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-11-26 17:27:18.752569: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-11-26 17:27:18.898701: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2615b9b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-11-26 17:27:18.898783: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-11-26 17:27:18.900080: 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 17:27:18.900930: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:27:18.905454: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:27:18.908931: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 17:27:18.909447: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 17:27:18.912994: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 17:27:18.914640: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 17:27:18.921214: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:27:18.922477: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 17:27:18.922601: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:27:18.923225: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 17:27:18.923245: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 17:27:18.923254: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 17:27:18.924170: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2894 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 17:27:19.089326: 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 17:27:19.089433: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:27:19.089471: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:27:19.089502: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 17:27:19.089530: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 17:27:19.089557: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 17:27:19.089590: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 17:27:19.089619: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:27:19.090995: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 17:27:19.092240: 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 17:27:19.092287: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 17:27:19.092321: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:27:19.092348: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 17:27:19.092374: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 17:27:19.092400: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 17:27:19.092426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 17:27:19.092453: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:27:19.093773: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 17:27:19.093811: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 17:27:19.093825: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 17:27:19.093838: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 17:27:19.095224: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2894 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 17:27:26.778222: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 17:27:26.959585: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 17:27:28.187136: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.460825: W tensorflow/core/common_runtime/bfc_allocator.cc:311] Garbage collection: deallocate free memory regions (i.e., allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently, you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature. 2025-11-26 17:27:28.508385: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.508443: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.509112: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.509130: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.511223: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.511243: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.511877: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.511892: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.536409: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.536433: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 564.38MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.537024: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.537056: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 564.38MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.538596: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.538617: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 290.15MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.539250: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.539266: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 290.15MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.544592: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.544611: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.545198: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.545213: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.08GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-11-26 17:27:28.546905: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.547545: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.553008: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.553607: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.555176: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.555781: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.581345: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.581942: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.582555: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.583192: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.595848: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.596499: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.611876: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.612527: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.613202: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.613842: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.626059: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.626692: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.627331: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.627928: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.632206: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.632819: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.637437: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.638033: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.650160: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.650809: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.655069: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.655699: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.656288: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.656875: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.657625: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.658221: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.668822: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.669474: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.670125: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.670777: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.671414: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.672049: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.687517: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.688549: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.731366: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.732424: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.733466: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.734496: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.742572: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.743244: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.759331: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.760222: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.761112: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.761983: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.766374: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.767186: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.767906: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.768488: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.769550: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.769568: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-11-26 17:27:28.779688: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.780331: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.789244: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.789890: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.790550: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.791188: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.791831: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-11-26 17:27:28.792466: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 2.33G (2499674112 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 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 431286 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 2153 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 : 3346 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 : 0.01440119743347168 nb_pixel_total : 615203 time to create 1 rle with new method : 0.03639101982116699 length of segment : 888 DEBUG bbox = [1278, 2862, 2160, 3780] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008905649185180664 nb_pixel_total : 629000 time to create 1 rle with new method : 0.4317474365234375 length of segment : 945 DEBUG bbox = [1392, 2076, 2130, 3024] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008835077285766602 nb_pixel_total : 491155 time to create 1 rle with new method : 0.03741097450256348 length of segment : 675 DEBUG bbox = [1224, 0, 2160, 810] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0063245296478271484 nb_pixel_total : 420706 time to create 1 rle with new method : 0.017351388931274414 length of segment : 907 DEBUG bbox = [42, 1836, 318, 2202] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0009369850158691406 nb_pixel_total : 47409 time to create 1 rle with old method : 0.05049633979797363 length of segment : 258 DEBUG bbox = [0, 3090, 900, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006829261779785156 nb_pixel_total : 486658 time to create 1 rle with new method : 0.015183448791503906 length of segment : 1063 DEBUG bbox = [600, 2970, 1464, 3810] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006577968597412109 nb_pixel_total : 447772 time to create 1 rle with new method : 0.01923537254333496 length of segment : 864 DEBUG bbox = [24, 0, 1002, 1032] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010172367095947266 nb_pixel_total : 522563 time to create 1 rle with new method : 0.0358123779296875 length of segment : 834 DEBUG bbox = [612, 0, 1608, 714] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006304502487182617 nb_pixel_total : 320756 time to create 1 rle with new method : 0.03635740280151367 length of segment : 1252 DEBUG bbox = [1302, 1488, 2136, 2358] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007791996002197266 nb_pixel_total : 449479 time to create 1 rle with new method : 0.020577430725097656 length of segment : 795 DEBUG bbox = [744, 1698, 1044, 1962] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0008096694946289062 nb_pixel_total : 30909 time to create 1 rle with old method : 0.03299379348754883 length of segment : 239 DEBUG bbox = [18, 2376, 948, 3294] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010070085525512695 nb_pixel_total : 570400 time to create 1 rle with new method : 0.03184771537780762 length of segment : 924 DEBUG bbox = [30, 12, 252, 186] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004913806915283203 nb_pixel_total : 24380 time to create 1 rle with old method : 0.02620410919189453 length of segment : 281 DEBUG bbox = [702, 2328, 1482, 3096] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.014015436172485352 nb_pixel_total : 350017 time to create 1 rle with new method : 0.035920143127441406 length of segment : 671 DEBUG bbox = [684, 1674, 1500, 2598] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.011615514755249023 nb_pixel_total : 374608 time to create 1 rle with new method : 0.23857426643371582 length of segment : 722 DEBUG bbox = [174, 1098, 1068, 1998] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.011818170547485352 nb_pixel_total : 474006 time to create 1 rle with new method : 0.02216815948486328 length of segment : 930 DEBUG bbox = [0, 1722, 846, 2556] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009307622909545898 nb_pixel_total : 409603 time to create 1 rle with new method : 0.03342700004577637 length of segment : 848 DEBUG bbox = [828, 1524, 1068, 1764] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0006194114685058594 nb_pixel_total : 38106 time to create 1 rle with old method : 0.042885780334472656 length of segment : 208 DEBUG bbox = [666, 2334, 924, 2520] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0005180835723876953 nb_pixel_total : 28338 time to create 1 rle with old method : 0.03207540512084961 length of segment : 237 DEBUG bbox = [1266, 2736, 1422, 3096] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004646778106689453 nb_pixel_total : 23827 time to create 1 rle with old method : 0.027259111404418945 length of segment : 130 DEBUG bbox = [858, 1284, 1764, 2142] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009443044662475586 nb_pixel_total : 419763 time to create 1 rle with new method : 0.0182034969329834 length of segment : 866 DEBUG bbox = [690, 2244, 2094, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0233461856842041 nb_pixel_total : 206221 time to create 1 rle with new method : 0.206345796585083 length of segment : 626 DEBUG bbox = [882, 2466, 1092, 2694] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004410743713378906 nb_pixel_total : 19070 time to create 1 rle with old method : 0.021416425704956055 length of segment : 154 DEBUG bbox = [1188, 1986, 1410, 2166] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004239082336425781 nb_pixel_total : 31123 time to create 1 rle with old method : 0.03379178047180176 length of segment : 218 DEBUG bbox = [1152, 606, 1368, 840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0008957386016845703 nb_pixel_total : 13064 time to create 1 rle with old method : 0.014926671981811523 length of segment : 129 DEBUG bbox = [726, 366, 1602, 1368] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.012412071228027344 nb_pixel_total : 467151 time to create 1 rle with new method : 0.02408623695373535 length of segment : 767 DEBUG bbox = [1152, 2508, 2046, 3306] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.005063056945800781 nb_pixel_total : 235766 time to create 1 rle with new method : 0.01565694808959961 length of segment : 803 time spent for convertir_results : 4.792445421218872 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 61 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 17234 save missing photos in datou_result : time spend for datou_step_exec : 23.02273917198181 time spend to save output : 1.2280018329620361 total time spend for step 2 : 24.250741004943848 step3:blur_detection Wed Nov 26 17:27:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 0.011744260787963867 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 : 0.011725902557373047 save missing photos in datou_result : time spend for datou_step_exec : 0.031943321228027344 time spend to save output : 0.029402732849121094 total time spend for step 3 : 0.06134605407714844 step4:brightness Wed Nov 26 17:27:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! 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 : 0.009794473648071289 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 : 0.01099705696105957 save missing photos in datou_result : time spend for datou_step_exec : 0.03388500213623047 time spend to save output : 0.025902986526489258 total time spend for step 4 : 0.05978798866271973 step5:crop_condition Wed Nov 26 17:27:40 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure Loading chi in step crop with photo_hashtag_type : 3132 Loading chi in step crop for list_pids : 1 ! batch 1 Loaded 61 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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 31 time used for this insertion : 0.0461733341217041 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.0959420204162598 time spend to save output : 0.04663968086242676 total time spend for step 5 : 2.1425817012786865 step6:thcl Wed Nov 26 17:27:42 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 : 0.005196809768676758 time to convert the images to numpy array : 0.007831096649169922 time to import caffe and check if the image exist : 0.005250692367553711 time to convert the images to numpy array : 0.008022069931030273 time to import caffe and check if the image exist : 0.0067555904388427734 time to convert the images to numpy array : 0.006573200225830078 time to import caffe and check if the image exist : 0.0068280696868896484 time to convert the images to numpy array : 0.0064678192138671875 time to import caffe and check if the image exist : 0.0069732666015625 time to convert the images to numpy array : 0.0056951045989990234 time to import caffe and check if the image exist : 0.005534648895263672 time to convert the images to numpy array : 0.008728742599487305 time to import caffe and check if the image exist : 0.005502939224243164 time to convert the images to numpy array : 0.011062145233154297 time to import caffe and check if the image exist : 0.006773710250854492 time to convert the images to numpy array : 0.010326385498046875 time to import caffe and check if the image exist : 0.0066378116607666016 time to convert the images to numpy array : 0.010564804077148438 time to import caffe and check if the image exist : 0.004485368728637695 time to convert the images to numpy array : 0.01401972770690918 total time to convert the images to numpy array : 0.2228996753692627 list photo_ids error: [] list photo_ids correct : [-4009034719, -4009041080, -4009034721, -4009041081, -4009034718, -4009041074, -4009041079, -4009041085, -4009034717, -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 : 3346 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 : 3127 max_wait_temp : 1 max_wait : 0 dict_keys(['pool5', 'prob']) time used to do the prepocess of the images : 0.10246419906616211 time used to do the prediction : 0.1555624008178711 save descriptor for thcl : 3441 time to traite the descriptors : 0.07580709457397461 storage_type for insertDescriptorsMulti : 3 Missing photo l117 : -4009034719 Missing photo l117 : -4009041080 Missing photo l117 : -4009034721 Missing photo l117 : -4009041081 Missing photo l117 : -4009034718 Missing photo l117 : -4009041074 Missing photo l117 : -4009041079 Missing photo l117 : -4009041085 Missing photo l117 : -4009034717 Missing photo l117 : -4009041066 To insert : -4009034719 Missing photo l134 : -4009034719 To insert : -4009041080 Missing photo l134 : -4009041080 To insert : -4009034721 Missing photo l134 : -4009034721 To insert : -4009041081 Missing photo l134 : -4009041081 To insert : -4009034718 Missing photo l134 : -4009034718 To insert : -4009041074 Missing photo l134 : -4009041074 To insert : -4009041079 Missing photo l134 : -4009041079 To insert : -4009041085 Missing photo l134 : -4009041085 To insert : -4009034717 Missing photo l134 : -4009034717 To insert : -4009041066 Missing photo l134 : -4009041066 time to insert the descriptors : 2.075009822845459 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 : 3.5762786865234375e-06 save missing photos in datou_result : time spend for datou_step_exec : 6.4118492603302 time spend to save output : 0.0002391338348388672 total time spend for step 6 : 6.412088394165039 step7:merge_mask_thcl_custom Wed Nov 26 17:27:48 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 61 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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.013479232788085938 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.13659143447875977 time spend to save output : 0.0136871337890625 total time spend for step 7 : 0.15027856826782227 step8:rle_unique_nms_with_priority Wed Nov 26 17:27:49 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 Begin step rle-unique-nms nb_obj : 59 nb_hashtags : 3 time to prepare the origin masks : 24.12393021583557 time for calcul the mask position with numpy : 0.03375601768493652 nb_pixel_total : 414980 time to create 1 rle with new method : 0.6347002983093262 time for calcul the mask position with numpy : 0.03591799736022949 nb_pixel_total : 479108 time to create 1 rle with new method : 0.5080838203430176 time for calcul the mask position with numpy : 0.03237271308898926 nb_pixel_total : 4599 time to create 1 rle with old method : 0.005059957504272461 time for calcul the mask position with numpy : 0.03539848327636719 nb_pixel_total : 509428 time to create 1 rle with new method : 0.3266925811767578 time for calcul the mask position with numpy : 0.03498673439025879 nb_pixel_total : 339043 time to create 1 rle with new method : 0.31316161155700684 time for calcul the mask position with numpy : 0.0364232063293457 nb_pixel_total : 554783 time to create 1 rle with new method : 0.5548720359802246 time for calcul the mask position with numpy : 0.033388614654541016 nb_pixel_total : 565 time to create 1 rle with old method : 0.0010411739349365234 time for calcul the mask position with numpy : 0.03264904022216797 nb_pixel_total : 11743 time to create 1 rle with old method : 0.014678478240966797 time for calcul the mask position with numpy : 0.03614974021911621 nb_pixel_total : 541612 time to create 1 rle with new method : 0.3650369644165039 time for calcul the mask position with numpy : 0.033132314682006836 nb_pixel_total : 28125 time to create 1 rle with old method : 0.029815673828125 time for calcul the mask position with numpy : 0.0326993465423584 nb_pixel_total : 24290 time to create 1 rle with old method : 0.026421308517456055 time for calcul the mask position with numpy : 0.03231334686279297 nb_pixel_total : 47254 time to create 1 rle with old method : 0.04943513870239258 time for calcul the mask position with numpy : 0.03258037567138672 nb_pixel_total : 38126 time to create 1 rle with old method : 0.038643836975097656 time for calcul the mask position with numpy : 0.03452897071838379 nb_pixel_total : 251699 time to create 1 rle with new method : 0.3418614864349365 time for calcul the mask position with numpy : 0.03323054313659668 nb_pixel_total : 20140 time to create 1 rle with old method : 0.02213454246520996 time for calcul the mask position with numpy : 0.03379654884338379 nb_pixel_total : 6593 time to create 1 rle with old method : 0.0072231292724609375 time for calcul the mask position with numpy : 0.0340876579284668 nb_pixel_total : 22028 time to create 1 rle with old method : 0.02379465103149414 time for calcul the mask position with numpy : 0.0323793888092041 nb_pixel_total : 867 time to create 1 rle with old method : 0.0014638900756835938 time for calcul the mask position with numpy : 0.03457021713256836 nb_pixel_total : 214239 time to create 1 rle with new method : 0.3140740394592285 time for calcul the mask position with numpy : 0.03624916076660156 nb_pixel_total : 332478 time to create 1 rle with new method : 0.39000487327575684 time for calcul the mask position with numpy : 0.03424334526062012 nb_pixel_total : 1805 time to create 1 rle with old method : 0.0029926300048828125 time for calcul the mask position with numpy : 0.03770041465759277 nb_pixel_total : 400487 time to create 1 rle with new method : 0.3650996685028076 time for calcul the mask position with numpy : 0.03605365753173828 nb_pixel_total : 409729 time to create 1 rle with new method : 0.35923218727111816 time for calcul the mask position with numpy : 0.03383994102478027 nb_pixel_total : 28316 time to create 1 rle with old method : 0.03143143653869629 time for calcul the mask position with numpy : 0.032894134521484375 nb_pixel_total : 802 time to create 1 rle with old method : 0.0009453296661376953 time for calcul the mask position with numpy : 0.0343630313873291 nb_pixel_total : 50479 time to create 1 rle with old method : 0.05446124076843262 time for calcul the mask position with numpy : 0.032059669494628906 nb_pixel_total : 11744 time to create 1 rle with old method : 0.01260519027709961 time for calcul the mask position with numpy : 0.03518223762512207 nb_pixel_total : 336119 time to create 1 rle with new method : 0.3656649589538574 time for calcul the mask position with numpy : 0.035465240478515625 nb_pixel_total : 111211 time to create 1 rle with old method : 0.12235164642333984 time for calcul the mask position with numpy : 0.034165382385253906 nb_pixel_total : 37984 time to create 1 rle with old method : 0.04178738594055176 time for calcul the mask position with numpy : 0.033396244049072266 nb_pixel_total : 11 time to create 1 rle with old method : 4.100799560546875e-05 time for calcul the mask position with numpy : 0.0334925651550293 nb_pixel_total : 11 time to create 1 rle with old method : 3.170967102050781e-05 time for calcul the mask position with numpy : 0.03815603256225586 nb_pixel_total : 6766 time to create 1 rle with old method : 0.008206605911254883 time for calcul the mask position with numpy : 0.03392195701599121 nb_pixel_total : 42 time to create 1 rle with old method : 0.0004067420959472656 time for calcul the mask position with numpy : 0.03267621994018555 nb_pixel_total : 72789 time to create 1 rle with old method : 0.07991933822631836 time for calcul the mask position with numpy : 0.034624576568603516 nb_pixel_total : 64688 time to create 1 rle with old method : 0.06960320472717285 time for calcul the mask position with numpy : 0.03310537338256836 nb_pixel_total : 40828 time to create 1 rle with old method : 0.0443425178527832 time for calcul the mask position with numpy : 0.0386500358581543 nb_pixel_total : 579942 time to create 1 rle with new method : 0.3038206100463867 time for calcul the mask position with numpy : 0.03282952308654785 nb_pixel_total : 1364 time to create 1 rle with old method : 0.001996278762817383 time for calcul the mask position with numpy : 0.034963130950927734 nb_pixel_total : 23628 time to create 1 rle with old method : 0.026344776153564453 time for calcul the mask position with numpy : 0.03433680534362793 nb_pixel_total : 15415 time to create 1 rle with old method : 0.017031431198120117 time for calcul the mask position with numpy : 0.03455853462219238 nb_pixel_total : 39833 time to create 1 rle with old method : 0.044179439544677734 time for calcul the mask position with numpy : 0.03606986999511719 nb_pixel_total : 147384 time to create 1 rle with old method : 0.1615619659423828 time for calcul the mask position with numpy : 0.03353309631347656 nb_pixel_total : 873 time to create 1 rle with old method : 0.001215219497680664 time for calcul the mask position with numpy : 0.03493165969848633 nb_pixel_total : 1824 time to create 1 rle with old method : 0.002738475799560547 time for calcul the mask position with numpy : 0.036605119705200195 nb_pixel_total : 437171 time to create 1 rle with new method : 0.32281947135925293 time for calcul the mask position with numpy : 0.03385591506958008 nb_pixel_total : 6151 time to create 1 rle with old method : 0.2045743465423584 time for calcul the mask position with numpy : 0.034393310546875 nb_pixel_total : 60772 time to create 1 rle with old method : 0.06713485717773438 time for calcul the mask position with numpy : 0.034209489822387695 nb_pixel_total : 90 time to create 1 rle with old method : 0.0004494190216064453 time for calcul the mask position with numpy : 0.03423762321472168 nb_pixel_total : 619 time to create 1 rle with old method : 0.0011048316955566406 time for calcul the mask position with numpy : 0.03879880905151367 nb_pixel_total : 499478 time to create 1 rle with new method : 0.4210090637207031 time for calcul the mask position with numpy : 0.032834768295288086 nb_pixel_total : 314 time to create 1 rle with old method : 0.0009644031524658203 time for calcul the mask position with numpy : 0.03805732727050781 nb_pixel_total : 527333 time to create 1 rle with new method : 0.3403787612915039 time for calcul the mask position with numpy : 0.04021048545837402 nb_pixel_total : 488050 time to create 1 rle with new method : 0.3855917453765869 time for calcul the mask position with numpy : 0.03787827491760254 nb_pixel_total : 8284 time to create 1 rle with old method : 0.011868715286254883 time for calcul the mask position with numpy : 0.036194562911987305 nb_pixel_total : 381 time to create 1 rle with old method : 0.0011172294616699219 time for calcul the mask position with numpy : 0.035506486892700195 nb_pixel_total : 20210 time to create 1 rle with old method : 0.0245058536529541 time for calcul the mask position with numpy : 0.03563690185546875 nb_pixel_total : 15265 time to create 1 rle with old method : 0.01661992073059082 time for calcul the mask position with numpy : 0.03486299514770508 nb_pixel_total : 4502 time to create 1 rle with old method : 0.005576133728027344 time for calcul the mask position with numpy : 0.03903770446777344 nb_pixel_total : 6 time to create 1 rle with old method : 3.838539123535156e-05 create new chi : 10.39810585975647 time to delete rle : 0.06036043167114258 batch 1 Loaded 75 chid ids of type : 3327 Number RLEs to save : 38857 TO DO : save crop sub photo not yet done ! save time : 2.286971092224121 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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.01654791831970215 save_final save missing photos in datou_result : time spend for datou_step_exec : 37.085686922073364 time spend to save output : 0.016807079315185547 total time spend for step 8 : 37.10249400138855 step9:crop_condition Wed Nov 26 17:28:26 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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 75 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 : 14 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/1764174526_430474 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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049567_0.png', 0, 958, 811, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049594_0.png', 0, 854, 880, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4046255156_0.png', 0, 596, 637, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049565_0.png', 0, 816, 705, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049580_0.png', 0, 797, 702, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049604_0.png', 0, 825, 702, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049566_0.png', 0, 705, 684, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049579_0.png', 0, 616, 708, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049605_0.png', 0, 824, 696, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049581_0.png', 0, 766, 757, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049576_0.png', 0, 115, 137, 0, 1764174528,'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(1764174528), 0.0, 0.0, 14, '', 0, 0, '1764174412_430474_1390404834_21d8b3022193ceb2def5c87914a3f088_18581028_rle_crop_4009049569_0.png', 0, 836, 781, 0, 1764174528,'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 : 3.4757184982299805 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 : 14 /1396268658Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268660Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1393124092Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268661Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268662Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268664Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268665Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268666Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396267100Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268668Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268669Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268670Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268672Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /1396268673Didn'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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 43 time used for this insertion : 0.027276277542114258 save_final save missing photos in datou_result : time spend for datou_step_exec : 23.633675813674927 time spend to save output : 0.02802276611328125 total time spend for step 9 : 23.661698579788208 step10:ventilate_hashtags_in_portfolio Wed Nov 26 17:28:49 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 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','etiquette','pet_clair','environnement','barquette_avec_film','autre','pet_fonce','mal_croppe','flou','papier','bouchon','pehd','metal','carton')) 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','etiquette','pet_clair','environnement','barquette_avec_film','autre','pet_fonce','mal_croppe','flou','papier','bouchon','pehd','metal','carton')) 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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 2 time used for this insertion : 0.014341592788696289 save_final save missing photos in datou_result : time spend for datou_step_exec : 2.0790863037109375 time spend to save output : 0.01451873779296875 total time spend for step 10 : 2.0936050415039062 step11:final Wed Nov 26 17:28:51 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! complete output_args for input 2 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step final ! Catched exception ! Connect or reconnect ! Inside saveOutput : final : False verbose : 0 original output for save of step final : {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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 3 time used for this insertion : 0.016308069229125977 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.13965654373168945 time spend to save output : 0.016460418701171875 total time spend for step 11 : 0.15611696243286133 step12:velours_tree Wed Nov 26 17:28:52 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 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 : 0.05327796936035156 time spend to save output : 3.695487976074219e-05 total time spend for step 12 : 0.053314924240112305 step13:send_mail_cod Wed Nov 26 17:28:52 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 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_28_52.pdf 28926915 imagette289269151764174532 28926916 imagette289269161764174532 28926918 imagette289269181764174532 28926919 imagette289269191764174532 28926920 imagette289269201764174532 28926921 imagette289269211764174532 28926922 imagette289269221764174532 28926923 imagette289269231764174532 28926924 imagette289269241764174532 28926925 imagette289269251764174532 28926926 imagette289269261764174532 28926927 imagette289269271764174532 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_28_52.pdf results_Auto_P28926786_26-11-2025_17_28_52.pdf uploaded to url https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28926786_26-11-2025_17_28_52.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_28_52.pdf','https://storage.sbg.cloud.ovh.net/v1/AUTH_3b171620e76e4af496c5fd050759c9f0/media.fotonower.com/results_Auto_P28926786_26-11-2025_17_28_52.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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.01887035369873047 save_final save missing photos in datou_result : time spend for datou_step_exec : 1.0383307933807373 time spend to save output : 0.019008874893188477 total time spend for step 13 : 1.0573396682739258 step14:split_time_score Wed Nov 26 17:28:53 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed 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, '4122124') ('3804', '28926786', '1390404834', None, None, None, None, None, '4122124') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.013950586318969727 save_final save missing photos in datou_result : time spend for datou_step_exec : 0.12312126159667969 time spend to save output : 0.014065980911254883 total time spend for step 14 : 0.13718724250793457 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 76.78user 35.57system 2:04.65elapsed 90%CPU (0avgtext+0avgdata 2939464maxresident)k 317928inputs+61544outputs (2846major+6390480minor)pagefaults 0swaps