python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 8 -a ' -a 4741 -l 30 ' -s datou_current_4741 -M 0 -S 0 -U 95,95,120 import MySQLdb succeeded Import error (python version) ['/Users/moilerat/Documents/Fotonower/install/caffe/distribute/python', '/home/admin/workarea/git/Velours/python/prod', '/home/admin/workarea/install/caffe_cuda8_python3/python', '/home/admin/workarea/install/darknet', '/home/admin/workarea/git/Velours/python', '/home/admin/workarea/install/caffe_frcnn_python3/py-faster-rcnn/caffe-fast-rcnn/python', '/home/admin/mtr/.credentials', '/home/admin/workarea/install/caffe/python', '/home/admin/workarea/install/caffe_frcnn/py-faster-rcnn/tools', '/home/admin/workarea/git/fotonowerpip', '/home/admin/workarea/install/segment-anything', '/home/admin/workarea/git/pyfvs', '/usr/lib/python38.zip', '/usr/lib/python3.8', '/usr/lib/python3.8/lib-dynload', '/home/admin/.local/lib/python3.8/site-packages', '/usr/local/lib/python3.8/dist-packages', '/usr/lib/python3/dist-packages'] process id : 64911 load datou : 4741 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! Unexpected type for variable list_input_json ERROR or WARNING : can't parse json string Expecting value: line 1 column 1 (char 0) Tried to parse : chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? [(photo_id, hashtag_id, hashtag_type, x0, x1, y0, y1, score, seg_temp, polygons), ...] was removed should we ? chemin de la photo was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? donnée sous forme de texte was removed should we ? [ (photo_id, photo_id_loc, hashtag_type, x0, x1, y0, y1, score), ...] was removed should we ? [ (photo_id_loc, hashtag_id, hashtag_type, x0, x1, y0, y1, score, None), ...] was removed should we ? chemin de la photo was removed should we ? id de la photo (peut être local ou global) was removed should we ? chemin de la photo was removed should we ? (x0, y0, x1, y1) was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? id de la photo (peut être local ou global) was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de nombre was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? donnée sous forme de texte was removed should we ? None was removed should we ? donnée sous forme de texte was removed should we ? [ptf_id0,ptf_id1...] was removed should we ? FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5732, 'mask_refus_amiens_050123', 16384, 25088, 'mask_refus_amiens_050123', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 1, 5, 13, 23, 59), datetime.datetime(2023, 1, 5, 13, 23, 59)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) load thcls load THCL from format json or kwargs add thcl : 3453 in CacheModelConfig load THCL from format json or kwargs add thcl : 3783 in CacheModelConfig load pdts add pdt : 5732 in CacheModelConfig add pdt : 5972 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 list_input_json: [] Current got : datou_id : 4741, datou_cur_ids : ['2709756'] with mtr_portfolio_ids : ['21915585'] and first list_photo_ids : [] new path : /proc/64911/ Inside batchDatouExec : verbose : 0 # VR 17-11-17 : to create in DB ! Here we check the datou graph and we reorder steps ! Tree builded and cycle checked, now we need to re-order the steps ! We have currenlty an error because there is no dependence between the last step for the case tile - detect - glue We can either keep the depence of, it is better to keep an order compatible with the id of steps if we do not have sons, so a lexical order : (number_son, step_id) All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! All sons are already in current list ! DONE and to test : checkNoCycle ! Here we check the consistency of inputs/outputs number between the given ones and the db ! eke 1-6-18 : checkConsistencyNbInputNbOutput should be processed after step reordering ! WARNING : number of outputs for step 13156 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 13160 mask_detect have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 13160 mask_detect is not consistent : 3 used against 2 in the step definition ! WARNING : number of inputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 13158 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of inputs for step 13157 crop_condition is not consistent : 4 used against 2 in the step definition ! WARNING : number of outputs for step 13157 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of outputs for step 13161 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 13159 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 13159 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Number of inputs / outputs for each step checked ! Here we check the consistency of outputs/inputs types during steps connections eke 1-6-18 : checkConsistencyTypeOutputInput should be processed after checkConsistencyNbInputNbOutput ! WARNING : type of output 2 of step 13156 doesn't seem to be define in the database( WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 1 of step 13161 doesn't seem to be define in the database( WARNING : type of input 3 of step 13159 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13163 have datatype=6 whereas input 2 of step 13157 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 0 of step 13162 have datatype=6 whereas input 2 of step 13157 have datatype=None We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 13161 have datatype=10 whereas input 3 of step 13164 have datatype=6 WARNING : output 0 of step 13161 have datatype=10 whereas input 0 of step 13166 have datatype=18 WARNING : type of input 5 of step 13164 doesn't seem to be define in the database( WARNING : output 0 of step 13166 have datatype=11 whereas input 5 of step 13164 have datatype=None WARNING : type of input 2 of step 13157 doesn't seem to be define in the database( WARNING : output 1 of step 13158 have datatype=7 whereas input 2 of step 13157 have datatype=None WARNING : type of output 3 of step 13157 doesn't seem to be define in the database( WARNING : type of input 3 of step 13161 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13163 doesn't seem to be define in the database( WARNING : type of output 2 of step 13160 doesn't seem to be define in the database( WARNING : type of input 1 of step 13162 doesn't seem to be define in the database( DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, mask_detect, blur_detection, brightness, rle_unique_nms_with_priority, crop_condition, ventilate_hashtags_in_portfolio, final, velours_tree, send_mail_cod, split_time_score list_input_json : [] origin We have 1 , BFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 8 ; length of list_pids : 8 ; length of list_args : 8 time to download the photos : 2.5923826694488525 About to test input to load we should then remove the video here, and this would fix the bug of datou_current ! Calling datou_exec Inside datou_exec : verbose : 0 number of steps : 11 step1:mask_detect Mon Mar 31 17:01:29 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 : 10593 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-03-31 17:01:32.742774: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-31 17:01:32.771111: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-31 17:01:32.773457: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f0f80000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-31 17:01:32.773527: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-31 17:01:32.778000: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-31 17:01:32.919615: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xb205b30 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-31 17:01:32.919687: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-31 17:01:32.920814: 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 2025-03-31 17:01:32.921201: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 17:01:32.923462: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 17:01:32.925715: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 17:01:32.926106: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 17:01:32.928399: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 17:01:32.929561: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 17:01:32.934052: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 17:01:32.935688: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 17:01:32.935788: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 17:01:32.936587: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-31 17:01:32.936605: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-31 17:01:32.936615: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-31 17:01:32.937979: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9671 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. 2025-03-31 17:01:33.224026: 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 2025-03-31 17:01:33.224151: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 17:01:33.224173: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 17:01:33.224192: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 17:01:33.224211: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 17:01:33.224229: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 17:01:33.224247: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 17:01:33.224265: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 17:01:33.225804: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 17:01:33.227219: 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 2025-03-31 17:01:33.227270: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-31 17:01:33.227289: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 17:01:33.227307: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-31 17:01:33.227341: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-31 17:01:33.227359: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-31 17:01:33.227376: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-31 17:01:33.227394: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-31 17:01:33.228918: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-31 17:01:33.228960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-31 17:01:33.228972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-31 17:01:33.228982: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-31 17:01:33.230572: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9671 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) Using TensorFlow backend. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:396: calling crop_and_resize_v1 (from tensorflow.python.ops.image_ops_impl) with box_ind is deprecated and will be removed in a future version. Instructions for updating: box_ind is deprecated, use box_indices instead WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:703: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. WARNING:tensorflow:From /home/admin/workarea/install/Mask_RCNN/model.py:729: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.cast` instead. Inside mask_sub_process Inside mask_detect About to load cache.load_thcl_param To do loadFromThcl(), then load ParamDescType : thcl3783 thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5972, 'learn_entrant_syctomXV_111023', 16384, 25088, 'learn_entrant_syctomXV_111023', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 10, 11, 15, 57, 35), datetime.datetime(2023, 10, 11, 15, 57, 35)) {'thcl': {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'], 'list_hashtags_csv': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'svm_hashtag_type_desc': 5972, 'photo_desc_type': 5972, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'] Configurations: BACKBONE resnet101 BACKBONE_SHAPES [[160 160] [ 80 80] [ 40 40] [ 20 20] [ 10 10]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.3 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 640 IMAGE_MIN_DIM 640 IMAGE_PADDING True IMAGE_SHAPE [640 640 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME learn_entrant_syctomXV_111023 NUM_CLASSES 11 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (16, 32, 64, 128, 256) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 model_param file didn't exist model_name : learn_entrant_syctomXV_111023 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-03-31 17:01:47.817319: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-31 17:01:48.039125: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 local folder : /data/models_weight/learn_entrant_syctomXV_111023 /data/models_weight/learn_entrant_syctomXV_111023/mask_model.h5 size_local : 256052544 size in s3 : 256052544 create time local : 2023-10-26 16:36:43 create time in s3 : 2023-10-11 13:57:17 mask_model.h5 already exist and didn't need to update list_images length : 8 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 16 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 13 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 7 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 12 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 8 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 17 NEW PHOTO Processing 1 images image shape: (4160, 3120, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 19) min: 0.00000 max: 4160.00000 nb d'objets trouves : 6 Detection mask done ! Trying to reset tf kernel 65371 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 5304 tf kernel not reseted sub process len(results) : 8 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 8 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 : 10593 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl3783 Catched exception ! Connect or reconnect ! thcls : [{'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 3783, 'mtr_user_id': 31, 'name': 'learn_entrant_syctomXV_111023', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,sac,textiles,verre,organique,dasri,masque,encombrant,autre_emballage,autre_non_emballage,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 4853, 'photo_desc_type': 5972, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5972 ['background', 'sac', 'textiles', 'verre', 'organique', 'dasri', 'masque', 'encombrant', 'autre_emballage', 'autre_non_emballage', 'environnement'] time for calcul the mask position with numpy : 0.001394033432006836 nb_pixel_total : 11915 time to create 1 rle with old method : 0.03229212760925293 length of segment : 224 time for calcul the mask position with numpy : 0.0025551319122314453 nb_pixel_total : 101391 time to create 1 rle with old method : 0.1134638786315918 length of segment : 415 time for calcul the mask position with numpy : 0.0017621517181396484 nb_pixel_total : 91080 time to create 1 rle with old method : 0.10587549209594727 length of segment : 281 time for calcul the mask position with numpy : 0.0011508464813232422 nb_pixel_total : 40940 time to create 1 rle with old method : 0.06599926948547363 length of segment : 307 time for calcul the mask position with numpy : 0.002846956253051758 nb_pixel_total : 112638 time to create 1 rle with old method : 0.12813973426818848 length of segment : 621 time for calcul the mask position with numpy : 0.002711057662963867 nb_pixel_total : 92569 time to create 1 rle with old method : 0.12202000617980957 length of segment : 327 time for calcul the mask position with numpy : 0.00040221214294433594 nb_pixel_total : 9698 time to create 1 rle with old method : 0.011775016784667969 length of segment : 126 time for calcul the mask position with numpy : 0.0013120174407958984 nb_pixel_total : 31044 time to create 1 rle with old method : 0.05132269859313965 length of segment : 294 time for calcul the mask position with numpy : 0.002572298049926758 nb_pixel_total : 86421 time to create 1 rle with old method : 0.1230778694152832 length of segment : 567 time for calcul the mask position with numpy : 0.0033872127532958984 nb_pixel_total : 147433 time to create 1 rle with old method : 0.17889952659606934 length of segment : 456 time for calcul the mask position with numpy : 0.001401662826538086 nb_pixel_total : 25622 time to create 1 rle with old method : 0.030060529708862305 length of segment : 233 time for calcul the mask position with numpy : 0.0029621124267578125 nb_pixel_total : 110531 time to create 1 rle with old method : 0.1327803134918213 length of segment : 525 time for calcul the mask position with numpy : 0.00044989585876464844 nb_pixel_total : 11430 time to create 1 rle with old method : 0.013582468032836914 length of segment : 163 time for calcul the mask position with numpy : 0.0006737709045410156 nb_pixel_total : 21303 time to create 1 rle with old method : 0.024813175201416016 length of segment : 224 time for calcul the mask position with numpy : 0.0024251937866210938 nb_pixel_total : 87106 time to create 1 rle with old method : 0.10293149948120117 length of segment : 300 time for calcul the mask position with numpy : 0.0011563301086425781 nb_pixel_total : 31933 time to create 1 rle with old method : 0.04030799865722656 length of segment : 251 time for calcul the mask position with numpy : 0.0007600784301757812 nb_pixel_total : 25258 time to create 1 rle with old method : 0.04347681999206543 length of segment : 224 time for calcul the mask position with numpy : 0.001268148422241211 nb_pixel_total : 52421 time to create 1 rle with old method : 0.10867428779602051 length of segment : 243 time for calcul the mask position with numpy : 0.002382040023803711 nb_pixel_total : 72553 time to create 1 rle with old method : 0.09993648529052734 length of segment : 533 time for calcul the mask position with numpy : 0.0009663105010986328 nb_pixel_total : 15626 time to create 1 rle with old method : 0.01930546760559082 length of segment : 149 time for calcul the mask position with numpy : 0.0030303001403808594 nb_pixel_total : 102694 time to create 1 rle with old method : 0.12237048149108887 length of segment : 551 time for calcul the mask position with numpy : 0.0015017986297607422 nb_pixel_total : 69220 time to create 1 rle with old method : 0.09332895278930664 length of segment : 446 time for calcul the mask position with numpy : 0.001077890396118164 nb_pixel_total : 46893 time to create 1 rle with old method : 0.06170797348022461 length of segment : 222 time for calcul the mask position with numpy : 0.0024302005767822266 nb_pixel_total : 149469 time to create 1 rle with old method : 0.21184468269348145 length of segment : 498 time for calcul the mask position with numpy : 0.0009634494781494141 nb_pixel_total : 35378 time to create 1 rle with old method : 0.057244062423706055 length of segment : 316 time for calcul the mask position with numpy : 0.0021462440490722656 nb_pixel_total : 111969 time to create 1 rle with old method : 0.15736603736877441 length of segment : 569 time for calcul the mask position with numpy : 0.002642393112182617 nb_pixel_total : 64797 time to create 1 rle with old method : 0.0921781063079834 length of segment : 433 time for calcul the mask position with numpy : 0.002942800521850586 nb_pixel_total : 98531 time to create 1 rle with old method : 0.11090397834777832 length of segment : 426 time for calcul the mask position with numpy : 0.002039670944213867 nb_pixel_total : 47672 time to create 1 rle with old method : 0.08325719833374023 length of segment : 277 time for calcul the mask position with numpy : 0.0010035037994384766 nb_pixel_total : 10780 time to create 1 rle with old method : 0.013070106506347656 length of segment : 256 time for calcul the mask position with numpy : 0.010576248168945312 nb_pixel_total : 43019 time to create 1 rle with old method : 0.05007791519165039 length of segment : 435 time for calcul the mask position with numpy : 0.003041982650756836 nb_pixel_total : 113817 time to create 1 rle with old method : 0.12816762924194336 length of segment : 491 time for calcul the mask position with numpy : 0.001337289810180664 nb_pixel_total : 37937 time to create 1 rle with old method : 0.04359626770019531 length of segment : 211 time for calcul the mask position with numpy : 0.002175569534301758 nb_pixel_total : 74514 time to create 1 rle with old method : 0.08501195907592773 length of segment : 278 time for calcul the mask position with numpy : 0.00048065185546875 nb_pixel_total : 8342 time to create 1 rle with old method : 0.009716272354125977 length of segment : 139 time for calcul the mask position with numpy : 0.0012197494506835938 nb_pixel_total : 47803 time to create 1 rle with old method : 0.07080984115600586 length of segment : 203 time for calcul the mask position with numpy : 0.0005166530609130859 nb_pixel_total : 18725 time to create 1 rle with old method : 0.021557331085205078 length of segment : 185 time for calcul the mask position with numpy : 0.0017540454864501953 nb_pixel_total : 68718 time to create 1 rle with old method : 0.07874655723571777 length of segment : 453 time for calcul the mask position with numpy : 0.003560304641723633 nb_pixel_total : 171553 time to create 1 rle with new method : 0.011987686157226562 length of segment : 753 time for calcul the mask position with numpy : 0.0010330677032470703 nb_pixel_total : 54384 time to create 1 rle with old method : 0.06690120697021484 length of segment : 161 time for calcul the mask position with numpy : 0.0014927387237548828 nb_pixel_total : 65060 time to create 1 rle with old method : 0.07935500144958496 length of segment : 317 time for calcul the mask position with numpy : 0.0008759498596191406 nb_pixel_total : 29840 time to create 1 rle with old method : 0.034116268157958984 length of segment : 257 time for calcul the mask position with numpy : 0.0020732879638671875 nb_pixel_total : 133779 time to create 1 rle with old method : 0.1513504981994629 length of segment : 388 time for calcul the mask position with numpy : 0.0035784244537353516 nb_pixel_total : 223034 time to create 1 rle with new method : 0.009584188461303711 length of segment : 691 time for calcul the mask position with numpy : 0.0016651153564453125 nb_pixel_total : 113799 time to create 1 rle with old method : 0.12917494773864746 length of segment : 394 time for calcul the mask position with numpy : 0.0018887519836425781 nb_pixel_total : 73664 time to create 1 rle with old method : 0.10366964340209961 length of segment : 364 time for calcul the mask position with numpy : 0.0015573501586914062 nb_pixel_total : 39449 time to create 1 rle with old method : 0.06282424926757812 length of segment : 353 time for calcul the mask position with numpy : 0.0003514289855957031 nb_pixel_total : 12156 time to create 1 rle with old method : 0.017286300659179688 length of segment : 124 time for calcul the mask position with numpy : 0.00032973289489746094 nb_pixel_total : 16075 time to create 1 rle with old method : 0.018862247467041016 length of segment : 143 time for calcul the mask position with numpy : 0.00046706199645996094 nb_pixel_total : 27896 time to create 1 rle with old method : 0.032370805740356445 length of segment : 154 time for calcul the mask position with numpy : 0.0003211498260498047 nb_pixel_total : 10219 time to create 1 rle with old method : 0.012704133987426758 length of segment : 137 time for calcul the mask position with numpy : 0.0002415180206298828 nb_pixel_total : 11982 time to create 1 rle with old method : 0.013998746871948242 length of segment : 122 time for calcul the mask position with numpy : 0.003174304962158203 nb_pixel_total : 193001 time to create 1 rle with new method : 0.0068395137786865234 length of segment : 493 time for calcul the mask position with numpy : 0.0035505294799804688 nb_pixel_total : 191899 time to create 1 rle with new method : 0.006450176239013672 length of segment : 479 time for calcul the mask position with numpy : 0.0007526874542236328 nb_pixel_total : 10990 time to create 1 rle with old method : 0.012764215469360352 length of segment : 184 time for calcul the mask position with numpy : 0.00683140754699707 nb_pixel_total : 291458 time to create 1 rle with new method : 0.02056884765625 length of segment : 762 time for calcul the mask position with numpy : 0.0034520626068115234 nb_pixel_total : 133382 time to create 1 rle with old method : 0.15518569946289062 length of segment : 478 time for calcul the mask position with numpy : 0.0009000301361083984 nb_pixel_total : 35634 time to create 1 rle with old method : 0.041091203689575195 length of segment : 272 time for calcul the mask position with numpy : 0.0005257129669189453 nb_pixel_total : 19128 time to create 1 rle with old method : 0.022220134735107422 length of segment : 106 time for calcul the mask position with numpy : 0.009522676467895508 nb_pixel_total : 401809 time to create 1 rle with new method : 0.1137080192565918 length of segment : 660 time for calcul the mask position with numpy : 0.0010790824890136719 nb_pixel_total : 58969 time to create 1 rle with old method : 0.08498549461364746 length of segment : 176 time for calcul the mask position with numpy : 0.000675201416015625 nb_pixel_total : 20548 time to create 1 rle with old method : 0.02333354949951172 length of segment : 252 time for calcul the mask position with numpy : 0.0004210472106933594 nb_pixel_total : 20573 time to create 1 rle with old method : 0.023773670196533203 length of segment : 185 time for calcul the mask position with numpy : 0.0009746551513671875 nb_pixel_total : 31570 time to create 1 rle with old method : 0.03595447540283203 length of segment : 241 time for calcul the mask position with numpy : 0.00045943260192871094 nb_pixel_total : 19455 time to create 1 rle with old method : 0.024425506591796875 length of segment : 89 time for calcul the mask position with numpy : 0.008557558059692383 nb_pixel_total : 9253 time to create 1 rle with old method : 0.012851715087890625 length of segment : 277 time for calcul the mask position with numpy : 0.0012354850769042969 nb_pixel_total : 44156 time to create 1 rle with old method : 0.050484657287597656 length of segment : 182 time for calcul the mask position with numpy : 0.004907131195068359 nb_pixel_total : 257765 time to create 1 rle with new method : 0.009836673736572266 length of segment : 626 time for calcul the mask position with numpy : 0.0004038810729980469 nb_pixel_total : 11912 time to create 1 rle with old method : 0.014081716537475586 length of segment : 134 time for calcul the mask position with numpy : 0.0008089542388916016 nb_pixel_total : 13091 time to create 1 rle with old method : 0.017038822174072266 length of segment : 242 time for calcul the mask position with numpy : 0.0013875961303710938 nb_pixel_total : 49401 time to create 1 rle with old method : 0.05558013916015625 length of segment : 269 time for calcul the mask position with numpy : 0.0005817413330078125 nb_pixel_total : 21588 time to create 1 rle with old method : 0.02475571632385254 length of segment : 182 time for calcul the mask position with numpy : 0.0010225772857666016 nb_pixel_total : 33579 time to create 1 rle with old method : 0.03920340538024902 length of segment : 213 time for calcul the mask position with numpy : 0.0035560131072998047 nb_pixel_total : 113451 time to create 1 rle with old method : 0.1300654411315918 length of segment : 462 time for calcul the mask position with numpy : 0.0008378028869628906 nb_pixel_total : 23208 time to create 1 rle with old method : 0.02729177474975586 length of segment : 233 time for calcul the mask position with numpy : 0.00023698806762695312 nb_pixel_total : 2929 time to create 1 rle with old method : 0.0038344860076904297 length of segment : 38 time for calcul the mask position with numpy : 0.0008084774017333984 nb_pixel_total : 31188 time to create 1 rle with old method : 0.036828041076660156 length of segment : 179 time for calcul the mask position with numpy : 0.0005731582641601562 nb_pixel_total : 14787 time to create 1 rle with old method : 0.0214693546295166 length of segment : 117 time for calcul the mask position with numpy : 0.0009260177612304688 nb_pixel_total : 40570 time to create 1 rle with old method : 0.046973228454589844 length of segment : 236 time for calcul the mask position with numpy : 0.0005803108215332031 nb_pixel_total : 33272 time to create 1 rle with old method : 0.05740666389465332 length of segment : 188 time for calcul the mask position with numpy : 0.00034737586975097656 nb_pixel_total : 6679 time to create 1 rle with old method : 0.008918523788452148 length of segment : 101 time for calcul the mask position with numpy : 0.14918136596679688 nb_pixel_total : 1265537 time to create 1 rle with new method : 0.3231043815612793 length of segment : 1351 time for calcul the mask position with numpy : 0.17470216751098633 nb_pixel_total : 3067816 time to create 1 rle with new method : 0.49669408798217773 length of segment : 2733 time for calcul the mask position with numpy : 0.3465585708618164 nb_pixel_total : 5471909 time to create 1 rle with new method : 0.6144106388092041 length of segment : 3304 time for calcul the mask position with numpy : 0.005190610885620117 nb_pixel_total : 321218 time to create 1 rle with new method : 0.013108253479003906 length of segment : 1165 time for calcul the mask position with numpy : 0.0045282840728759766 nb_pixel_total : 333404 time to create 1 rle with new method : 0.010939598083496094 length of segment : 267 time spent for convertir_results : 15.044353485107422 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 86 chid ids of type : 4854 Number RLEs to save : 0 save missing photos in datou_result : time spend for datou_step_exec : 68.71718311309814 time spend to save output : 0.1131429672241211 total time spend for step 1 : 68.83032608032227 step2:mask_detect Mon Mar 31 17:02:38 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 new photo added, this last batch is non a complet batch, should exit and reload photo caffe_path_current : About to save ! 2 After save, about to update current ! 32.60user 42.04system 1:14.24elapsed 100%CPU (0avgtext+0avgdata 4462144maxresident)k 509872inputs+61064outputs (788major+5124629minor)pagefaults 0swaps