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 -i 1390404834' -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 : 349155 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 : ['4121822'] with mtr_portfolio_ids : [] and first list_photo_ids : ['1390404834'] new path : /proc/349155/ 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 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 : 0.3052372932434082 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 14 step1:mask_detect Wed Nov 26 16:38:47 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Catched exception ! Connect or reconnect ! ERROR in select last photo from portfolio Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-11-26 16:38:50.475217: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-11-26 16:38:50.502421: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-11-26 16:38:50.504575: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f64c0000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:38:50.504632: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-11-26 16:38:50.508511: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-11-26 16:38:50.814853: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x256053f0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:38:50.814917: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-11-26 16:38:50.816420: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-11-26 16:38:50.816830: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:38:50.819973: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:38:50.825807: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:38:50.826206: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:38:50.829194: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:38:50.830525: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:38:50.835086: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:38:50.836516: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:38:50.836595: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:38:50.837337: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:38:50.837352: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:38:50.837360: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:38:50.838643: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-11-26 16:38:51.071400: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-11-26 16:38:51.071503: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:38:51.071522: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:38:51.071538: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:38:51.071553: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:38:51.071568: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:38:51.071583: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:38:51.071599: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:38:51.072989: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:38:51.074410: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-11-26 16:38:51.074502: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:38:51.074519: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:38:51.074534: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:38:51.074549: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:38:51.074563: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:38:51.074578: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:38:51.074592: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:38:51.075960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:38:51.076001: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:38:51.076012: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:38:51.076020: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:38:51.077329: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2486 thcls : [{'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5024 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5024, 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 16384, 25088, 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 12, 1, 0, 11, 4), datetime.datetime(2020, 12, 1, 0, 11, 4)) {'thcl': {'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}, 'list_hashtags': ['background', 'pet_clair', 'error', 'environment'], 'list_hashtags_csv': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'svm_hashtag_type_desc': 5024, 'photo_desc_type': 5024, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'pet_clair', 'error', 'environment'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error NUM_CLASSES 4 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-11-26 16:38:58.626749: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:38:58.776688: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error/mask_model.h5 size_local : 255899936 size in s3 : 255899936 create time local : 2021-08-11 01:29:18 create time in s3 : 2021-08-06 17:35:43 mask_model.h5 already exist and didn't need to update list_images length : 1 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 12) min: 0.00000 max: 3840.00000 nb d'objets trouves : 22 Detection mask done ! Trying to reset tf kernel 349252 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5706 tf kernel not reseted sub process len(results) : 1 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 1 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 10998 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2486 Catched exception ! Connect or reconnect ! thcls : [{'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2486, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_30112020_2692_pet_and_error', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3109, 'photo_desc_type': 5024, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5024 ['background', 'pet_clair', 'error', 'environment'] DEBUG bbox = [1422, 2118, 2160, 2958] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.02186870574951172 nb_pixel_total : 502967 time to create 1 rle with new method : 0.032324790954589844 length of segment : 701 DEBUG bbox = [24, 2340, 816, 3204] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.02026057243347168 nb_pixel_total : 542129 time to create 1 rle with new method : 0.03294205665588379 length of segment : 782 DEBUG bbox = [0, 0, 858, 978] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.05054211616516113 nb_pixel_total : 579942 time to create 1 rle with new method : 0.04139256477355957 length of segment : 887 DEBUG bbox = [1254, 18, 2160, 774] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007760763168334961 nb_pixel_total : 438929 time to create 1 rle with new method : 0.03811502456665039 length of segment : 927 DEBUG bbox = [1398, 1266, 2148, 2106] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.007845640182495117 nb_pixel_total : 527712 time to create 1 rle with new method : 0.03280329704284668 length of segment : 704 DEBUG bbox = [18, 912, 774, 1758] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008252143859863281 nb_pixel_total : 519022 time to create 1 rle with new method : 0.03278636932373047 length of segment : 703 DEBUG bbox = [18, 1710, 780, 2484] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006326198577880859 nb_pixel_total : 437999 time to create 1 rle with new method : 0.031135082244873047 length of segment : 686 DEBUG bbox = [660, 2268, 1470, 3090] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008289813995361328 nb_pixel_total : 485563 time to create 1 rle with new method : 0.038832902908325195 length of segment : 800 DEBUG bbox = [1332, 540, 2136, 1368] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.00824427604675293 nb_pixel_total : 520805 time to create 1 rle with new method : 0.03420448303222656 length of segment : 762 DEBUG bbox = [1374, 2856, 2160, 3738] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010251522064208984 nb_pixel_total : 501519 time to create 1 rle with new method : 0.08692502975463867 length of segment : 1174 DEBUG bbox = [0, 3060, 822, 3828] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.012212276458740234 nb_pixel_total : 482081 time to create 1 rle with new method : 0.0325162410736084 length of segment : 842 DEBUG bbox = [156, 0, 1332, 504] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009072065353393555 nb_pixel_total : 267957 time to create 1 rle with new method : 0.031389713287353516 length of segment : 1574 DEBUG bbox = [750, 2946, 1452, 3828] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008567571640014648 nb_pixel_total : 358606 time to create 1 rle with new method : 0.031181812286376953 length of segment : 795 DEBUG bbox = [582, 936, 1374, 1794] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.01204681396484375 nb_pixel_total : 465701 time to create 1 rle with new method : 0.034398555755615234 length of segment : 730 DEBUG bbox = [570, 1716, 1410, 2514] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010048389434814453 nb_pixel_total : 391015 time to create 1 rle with new method : 0.03524160385131836 length of segment : 750 DEBUG bbox = [624, 432, 1386, 1302] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.012580633163452148 nb_pixel_total : 373139 time to create 1 rle with new method : 0.027405738830566406 length of segment : 691 DEBUG bbox = [678, 2328, 912, 2514] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0003960132598876953 nb_pixel_total : 23247 time to create 1 rle with old method : 0.025561809539794922 length of segment : 226 DEBUG bbox = [1560, 2820, 1758, 2970] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0006744861602783203 nb_pixel_total : 15296 time to create 1 rle with old method : 0.01667499542236328 length of segment : 185 DEBUG bbox = [360, 1950, 552, 2124] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0006387233734130859 nb_pixel_total : 20186 time to create 1 rle with old method : 0.023180723190307617 length of segment : 189 DEBUG bbox = [1092, 450, 1524, 1200] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.002976655960083008 nb_pixel_total : 181606 time to create 1 rle with new method : 0.00810384750366211 length of segment : 348 DEBUG bbox = [1284, 2730, 1422, 3078] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.000701904296875 nb_pixel_total : 19802 time to create 1 rle with old method : 0.023646831512451172 length of segment : 123 DEBUG bbox = [12, 2466, 1494, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.015103578567504883 nb_pixel_total : 548412 time to create 1 rle with new method : 0.09130263328552246 length of segment : 1444 time spent for convertir_results : 3.811917543411255 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 51 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 16023 save missing photos in datou_result : time spend for datou_step_exec : 22.83087944984436 time spend to save output : 1.0722744464874268 total time spend for step 1 : 23.903153896331787 step2:mask_detect Wed Nov 26 16:39:11 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 Catched exception ! Connect or reconnect ! ERROR in select last photo from portfolio Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory l 3637 free memory gpu now : 10998 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-11-26 16:39:13.997111: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-11-26 16:39:14.022442: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2025-11-26 16:39:14.024360: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f64c4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:39:14.024405: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-11-26 16:39:14.027881: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-11-26 16:39:14.336839: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x25495a10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-11-26 16:39:14.336890: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-11-26 16:39:14.338206: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-11-26 16:39:14.338614: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:39:14.344910: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:39:14.347496: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:39:14.347879: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:39:14.350348: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:39:14.351600: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:39:14.356288: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:39:14.357646: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:39:14.357703: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:39:14.358468: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:39:14.358484: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:39:14.358493: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:39:14.359874: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) WARNING:tensorflow:From /home/admin/workarea/git/Velours/python/mtr/mask_rcnn/mask_detection.py:69: The name tf.keras.backend.set_session is deprecated. Please use tf.compat.v1.keras.backend.set_session instead. 2025-11-26 16:39:14.516264: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-11-26 16:39:14.516349: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:39:14.516372: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:39:14.516393: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:39:14.516426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:39:14.516448: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:39:14.516468: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:39:14.516488: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:39:14.518087: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:39:14.519488: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties: pciBusID: 0000:41:00.0 name: NVIDIA GeForce RTX 2080 Ti computeCapability: 7.5 coreClock: 1.545GHz coreCount: 68 deviceMemorySize: 10.76GiB deviceMemoryBandwidth: 573.69GiB/s 2025-11-26 16:39:14.519526: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-11-26 16:39:14.519547: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:39:14.519567: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-11-26 16:39:14.519586: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-11-26 16:39:14.519606: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-11-26 16:39:14.519625: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-11-26 16:39:14.519644: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-11-26 16:39:14.521230: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-11-26 16:39:14.521267: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-11-26 16:39:14.521278: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-11-26 16:39:14.521287: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-11-26 16:39:14.522965: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10193 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl2499 thcls : [{'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5035 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5035, 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 16384, 25088, 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 12, 5, 18, 56, 33), datetime.datetime(2020, 12, 5, 18, 56, 33)) {'thcl': {'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}, 'list_hashtags': ['background', 'pet_clair', 'error', 'environment'], 'list_hashtags_csv': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'svm_hashtag_type_desc': 5035, 'photo_desc_type': 5035, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'pet_clair', 'error', 'environment'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug NUM_CLASSES 4 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-11-26 16:39:22.728518: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-11-26 16:39:22.899694: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug /data/models_weight/Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug/mask_model.h5 size_local : 255899936 size in s3 : 255899936 create time local : 2021-08-11 01:32:04 create time in s3 : 2021-08-06 17:27:07 mask_model.h5 already exist and didn't need to update list_images length : 1 NEW PHOTO Processing 1 images image shape: (2160, 3840, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 12) min: 0.00000 max: 3840.00000 nb d'objets trouves : 27 Detection mask done ! Trying to reset tf kernel 349871 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5706 tf kernel not reseted sub process len(results) : 1 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 1 len(list_Values) 0 process is alive finish correctly or not : True after detect begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 10998 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2499 Catched exception ! Connect or reconnect ! thcls : [{'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'}] thcl {'id': 2499, 'mtr_user_id': 31, 'name': 'Mask_dechet_Plastique_Clair_Rubbia_051220_2692_pet_and_error_limeil_all_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,pet_clair,error,environment', 'svm_portfolios_learning': '0,0,0,0', 'photo_hashtag_type': 3126, 'photo_desc_type': 5035, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0'} Update svm_hashtag_type_desc : 5035 ['background', 'pet_clair', 'error', 'environment'] DEBUG bbox = [1248, 420, 2142, 1374] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.015054941177368164 nb_pixel_total : 615202 time to create 1 rle with new method : 0.03927755355834961 length of segment : 888 DEBUG bbox = [1278, 2862, 2160, 3780] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009996175765991211 nb_pixel_total : 628968 time to create 1 rle with new method : 0.0741124153137207 length of segment : 945 DEBUG bbox = [1392, 2076, 2130, 3024] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009458780288696289 nb_pixel_total : 491118 time to create 1 rle with new method : 0.03067183494567871 length of segment : 675 DEBUG bbox = [1224, 0, 2160, 810] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010532140731811523 nb_pixel_total : 420712 time to create 1 rle with new method : 0.015212059020996094 length of segment : 907 DEBUG bbox = [42, 1836, 318, 2202] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.001753091812133789 nb_pixel_total : 47405 time to create 1 rle with old method : 0.05270576477050781 length of segment : 258 DEBUG bbox = [0, 3090, 900, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010945558547973633 nb_pixel_total : 486689 time to create 1 rle with new method : 0.01392984390258789 length of segment : 1062 DEBUG bbox = [600, 2970, 1464, 3810] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008101940155029297 nb_pixel_total : 447870 time to create 1 rle with new method : 0.013978004455566406 length of segment : 864 DEBUG bbox = [24, 0, 1002, 1032] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.01360177993774414 nb_pixel_total : 522488 time to create 1 rle with new method : 0.030152082443237305 length of segment : 834 DEBUG bbox = [612, 0, 1608, 714] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006469249725341797 nb_pixel_total : 320797 time to create 1 rle with new method : 0.03436112403869629 length of segment : 1253 DEBUG bbox = [1302, 1488, 2136, 2358] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.009370803833007812 nb_pixel_total : 449497 time to create 1 rle with new method : 0.015478849411010742 length of segment : 796 DEBUG bbox = [744, 1698, 1044, 1962] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.001361846923828125 nb_pixel_total : 30908 time to create 1 rle with old method : 0.03441190719604492 length of segment : 239 DEBUG bbox = [18, 2376, 948, 3294] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.011066198348999023 nb_pixel_total : 570331 time to create 1 rle with new method : 0.024025678634643555 length of segment : 924 DEBUG bbox = [30, 12, 252, 186] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0003943443298339844 nb_pixel_total : 24392 time to create 1 rle with old method : 0.027692556381225586 length of segment : 281 DEBUG bbox = [702, 2328, 1482, 3096] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006834506988525391 nb_pixel_total : 349999 time to create 1 rle with new method : 0.21067571640014648 length of segment : 672 DEBUG bbox = [684, 1674, 1500, 2598] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0072650909423828125 nb_pixel_total : 374598 time to create 1 rle with new method : 0.023137807846069336 length of segment : 722 DEBUG bbox = [174, 1098, 1068, 1998] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010047435760498047 nb_pixel_total : 473985 time to create 1 rle with new method : 0.01683497428894043 length of segment : 930 DEBUG bbox = [0, 1722, 846, 2556] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.006403684616088867 nb_pixel_total : 409578 time to create 1 rle with new method : 0.029097318649291992 length of segment : 848 DEBUG bbox = [828, 1524, 1068, 1764] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0005207061767578125 nb_pixel_total : 38107 time to create 1 rle with old method : 0.043512821197509766 length of segment : 208 DEBUG bbox = [666, 2334, 924, 2520] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004622936248779297 nb_pixel_total : 28339 time to create 1 rle with old method : 0.03252911567687988 length of segment : 237 DEBUG bbox = [1266, 2736, 1422, 3096] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004487037658691406 nb_pixel_total : 23827 time to create 1 rle with old method : 0.028400659561157227 length of segment : 130 DEBUG bbox = [858, 1284, 1764, 2142] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0067975521087646484 nb_pixel_total : 419739 time to create 1 rle with new method : 0.018538951873779297 length of segment : 866 DEBUG bbox = [690, 2244, 2094, 3840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.010823965072631836 nb_pixel_total : 206107 time to create 1 rle with new method : 0.23640108108520508 length of segment : 626 DEBUG bbox = [882, 2466, 1092, 2694] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0003821849822998047 nb_pixel_total : 19075 time to create 1 rle with old method : 0.021722793579101562 length of segment : 153 DEBUG bbox = [1188, 1986, 1410, 2166] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004417896270751953 nb_pixel_total : 31123 time to create 1 rle with old method : 0.03627157211303711 length of segment : 218 DEBUG bbox = [1152, 606, 1368, 840] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.0004801750183105469 nb_pixel_total : 13065 time to create 1 rle with old method : 0.01519775390625 length of segment : 129 DEBUG bbox = [726, 366, 1602, 1368] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.008040189743041992 nb_pixel_total : 467135 time to create 1 rle with new method : 0.018433332443237305 length of segment : 767 DEBUG bbox = [1152, 2508, 2046, 3306] DEBUG masks shape = (2160, 3840) time for calcul the mask position with numpy : 0.004948139190673828 nb_pixel_total : 235741 time to create 1 rle with new method : 0.014761686325073242 length of segment : 803 time spent for convertir_results : 4.342635631561279 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 51 chid ids of type : 3132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++Number RLEs to save : 17235 save missing photos in datou_result : time spend for datou_step_exec : 24.103598594665527 time spend to save output : 1.1983413696289062 total time spend for step 2 : 25.301939964294434 step3:blur_detection Wed Nov 26 16:39:36 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 Catched exception ! Connect or reconnect ! ERROR in select last photo from portfolio 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 : 0.010077714920043945 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 : 0.009983539581298828 save missing photos in datou_result : time spend for datou_step_exec : 0.13233304023742676 time spend to save output : 0.024934768676757812 total time spend for step 3 : 0.15726780891418457 step4:brightness Wed Nov 26 16:39:36 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 Catched exception ! Connect or reconnect ! ERROR in select last photo from portfolio 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 : 0.009970903396606445 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 : 0.010918140411376953 save missing photos in datou_result : time spend for datou_step_exec : 0.14360833168029785 time spend to save output : 0.02624654769897461 total time spend for step 4 : 0.16985487937927246 step5:crop_condition Wed Nov 26 16:39:37 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 Catched exception ! Connect or reconnect ! ERROR in select last photo from portfolio ERROR in datou_step_exec, will save and exit ! list index out of range File "/home/admin/workarea/git/Velours/python/mtr/datou/datou_lib.py", line 2339, in datou_exec output = datou_step_exec(sNext, args, cache, context, map_info, verbose, mtr_user_id) File "/home/admin/workarea/git/Velours/python/mtr/datou/datou_lib.py", line 2517, in datou_step_exec return post_process.datou_step_exec_crop_condition(param, json_param, args, cache, context, map_info, verbose) File "/home/admin/workarea/git/Velours/python/mtr/datou/lib_step_exec/lib_step_post_processing.py", line 395, in datou_step_exec_crop_condition mtr_user_id = context.pq.select_user_from_port(list(map_info["map_portfolio_photo"].keys())[0]) [1390404834] begin to insert list_values into mtr_datou_result : length of list_values in save_final : 1 time used for this insertion : 0.01793980598449707 save_final ERROR in last step crop_condition, list index out of range time spend for datou_step_exec : 0.11113524436950684 time spend to save output : 0.02309441566467285 total time spend for step 4 : 0.1342296600341797 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 27.82user 21.96system 0:54.06elapsed 92%CPU (0avgtext+0avgdata 3080300maxresident)k 1576inputs+2744outputs (40major+2543915minor)pagefaults 0swaps