python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 10 -a ' -a 3459 -l 10 ' -s datou_current_3459 -M 0 -S 0 -U 95,95,80 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 : 3277060 load datou : 3459 # 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 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 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : maybe we manage optionnal inputs ! 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 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 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 ? [ (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 : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5288, 'learn_papier_nantes_300421', 512, 512, 'learn_papier_nantes_300421', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 30, 17, 9, 41), datetime.datetime(2021, 4, 30, 17, 9, 41)) FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5309, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 16384, 25088, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 5, 10, 19, 20, 46), datetime.datetime(2021, 5, 10, 19, 20, 46)) load thcls load THCL from format json or kwargs add thcl : 2456 in CacheModelConfig load THCL from format json or kwargs add thcl : 2868 in CacheModelConfig load THCL from format json or kwargs add thcl : 2896 in CacheModelConfig load pdts add pdt : 4999 in CacheModelConfig add pdt : 5288 in CacheModelConfig add pdt : 5309 in CacheModelConfig Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec updating current state to 1 we have a portfolio with more photos than limit : 26>10 please execute split_portfolio.py -i 20475600 -l 10 size over we load limit photo not treated list_input_json: [] Current got : datou_id : 3459, datou_cur_ids : ['2579287'] with mtr_portfolio_ids : ['20475600'] and first list_photo_ids : [] new path : /proc/3277060/ 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 11449 mask_detect is not consistent : 3 used against 2 in the step definition ! Step 11452 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! Step 11452 crop_condition have less outputs used (2) than in the step definition (3) : some outputs may be not used ! Step 11453 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 11453 merge_mask_thcl_custom is not consistent : 4 used against 2 in the step definition ! WARNING : number of inputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11454 rle_unique_nms_with_priority is not consistent : 2 used against 1 in the step definition ! Step 11478 crop_condition have less inputs used (1) than in the step definition (2) : maybe we manage optionnal inputs ! WARNING : number of outputs for step 11478 crop_condition is not consistent : 4 used against 3 in the step definition ! WARNING : number of inputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! WARNING : number of outputs for step 11456 ventilate_hashtags_in_portfolio is not consistent : 2 used against 1 in the step definition ! Step 11455 final have less inputs used (2) than in the step definition (3) : maybe we manage optionnal inputs ! Step 11455 final have less outputs used (1) than in the step definition (2) : some outputs may be not used ! Step 11458 send_mail_cod have less inputs used (3) than in the step definition (5) : maybe we manage optionnal inputs ! 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 11449 doesn't seem to be define in the database( WARNING : type of input 2 of step 11452 doesn't seem to be define in the database( WARNING : output 1 of step 11449 have datatype=2 whereas input 1 of step 11453 have datatype=7 WARNING : type of output 2 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11454 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : type of output 3 of step 11453 doesn't seem to be define in the database( WARNING : type of input 1 of step 11456 doesn't seem to be define in the database( WARNING : type of output 1 of step 11456 doesn't seem to be define in the database( WARNING : type of input 3 of step 11455 doesn't seem to be define in the database( We ignore checkConsistencyTypeOutputInput for datou_step final ! We ignore checkConsistencyTypeOutputInput for datou_step final ! WARNING : output 0 of step 11456 have datatype=10 whereas input 3 of step 11458 have datatype=6 WARNING : type of input 5 of step 11458 doesn't seem to be define in the database( WARNING : output 0 of step 11477 have datatype=11 whereas input 5 of step 11458 have datatype=None WARNING : output 0 of step 11456 have datatype=10 whereas input 0 of step 11477 have datatype=18 WARNING : type of input 2 of step 11478 doesn't seem to be define in the database( WARNING : output 1 of step 11454 have datatype=7 whereas input 2 of step 11478 have datatype=None WARNING : type of output 3 of step 11478 doesn't seem to be define in the database( WARNING : type of input 2 of step 11456 doesn't seem to be define in the database( WARNING : output 0 of step 11453 have datatype=1 whereas input 0 of step 11454 have datatype=2 DataTypes for each output/input checked ! List Step Type Loaded in datou : mask_detect, 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 list_input_json : [] origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 10 ; length of list_pids : 10 ; length of list_args : 10 time to download the photos : 1.089125156402588 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 Wed Feb 12 12:06:27 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Beginning of datou step mask_detect ! save_polygon : True begin detect begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 3000 l 3632 free memory gpu now : 1265 wait 20 seconds l 3637 free memory gpu now : 1265 max_wait_temp : 1 max_wait : 0 gpu_flag : 0 2025-02-12 12:06:51.333871: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-02-12 12:06:51.367283: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-02-12 12:06:51.369783: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f09cc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-02-12 12:06:51.369861: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-02-12 12:06:51.376187: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-02-12 12:06:51.709868: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x35f17d40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-02-12 12:06:51.709972: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-02-12 12:06:51.711467: 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 2025-02-12 12:06:51.713087: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:06:51.724920: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:06:51.744712: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 12:06:51.747251: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 12:06:51.771629: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 12:06:51.775782: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 12:06:51.823491: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:06:51.824898: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 12:06:51.825436: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:06:51.826122: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 12:06:51.826144: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 12:06:51.826156: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 12:06:51.827615: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 886 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. 2025-02-12 12:06:52.316201: 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 2025-02-12 12:06:52.316356: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:06:52.316379: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:06:52.316398: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 12:06:52.316416: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 12:06:52.316433: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 12:06:52.316450: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 12:06:52.316473: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:06:52.317339: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 12:06:52.318455: 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 2025-02-12 12:06:52.318495: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-02-12 12:06:52.318513: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:06:52.318530: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-02-12 12:06:52.318546: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-02-12 12:06:52.318563: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-02-12 12:06:52.318579: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-02-12 12:06:52.318595: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:06:52.319473: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-02-12 12:06:52.319528: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-02-12 12:06:52.319539: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-02-12 12:06:52.319549: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-02-12 12:06:52.320488: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 886 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 : thcl2896 thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5309, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 16384, 25088, 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 5, 10, 19, 20, 46), datetime.datetime(2021, 5, 10, 19, 20, 46)) {'thcl': {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}, 'list_hashtags': ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'], 'list_hashtags_csv': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'svm_hashtag_type_desc': 5309, 'photo_desc_type': 5309, 'pb_hashtag_id_or_classifier': 0} list_class_names : ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', '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_convoyeur_qualipapia_nantes_poly_100521_1 NUM_CLASSES 10 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_convoyeur_qualipapia_nantes_poly_100521_1 model_type : mask_rcnn list file need : ['mask_model.h5'] file exist in s3 : ['mask_model.h5'] file manque in s3 : [] 2025-02-12 12:06:57.534143: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 51380224 exceeds 10% of free system memory. 2025-02-12 12:07:02.483109: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-02-12 12:07:02.844588: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-02-12 12:07:04.907656: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.908089: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.914583: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.914605: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.920612: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.920635: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 466.56MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.950787: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.950813: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.06GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.957135: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:04.957629: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 338.29M (354720256 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:04.958101: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 304.46M (319248384 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:04.958571: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 274.01M (287323648 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:04.959052: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 246.61M (258591488 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:04.959086: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.959576: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:04.959592: W tensorflow/core/common_runtime/bfc_allocator.cc:245] Allocator (GPU_0_bfc) ran out of memory trying to allocate 243.25MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2025-02-12 12:07:04.995636: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:04.996209: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.068683: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.069165: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.080721: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.081214: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.109058: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.109564: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.113016: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.113495: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.128962: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.129442: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.160643: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.161134: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.165189: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.165650: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.166285: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.166745: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.177541: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.178002: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.178472: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.178941: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.218761: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.218824: W tensorflow/core/kernels/gpu_utils.cc:49] Failed to allocate memory for convolution redzone checking; skipping this check. This is benign and only means that we won't check cudnn for out-of-bounds reads and writes. This message will only be printed once. 2025-02-12 12:07:05.219707: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.220567: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.228018: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.228693: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.252649: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.253289: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.253938: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.254545: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.258978: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.259590: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.261118: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.279948: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.280641: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.281186: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.281692: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.282196: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory 2025-02-12 12:07:05.282713: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 375.88M (394133504 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1 /data/models_weight/learn_convoyeur_qualipapia_nantes_poly_100521_1/mask_model.h5 size_local : 256031040 size in s3 : 256031040 create time local : 2021-08-09 05:45:48 create time in s3 : 2021-08-06 18:59:51 mask_model.h5 already exist and didn't need to update list_images length : 10 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 2 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 4 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 4 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 6 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 4 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 9 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 4 NEW PHOTO Processing 1 images image shape: (1080, 1920, 3) min: 0.00000 max: 255.00000 molded_images shape: (1, 640, 640, 3) min: -123.70000 max: 151.10000 image_metas shape: (1, 18) min: 0.00000 max: 1920.00000 nb d'objets trouves : 5 Detection mask done ! Trying to reset tf kernel 3278505 begin to check gpu status inside check gpu memory l 3610 free memory gpu now : 70 tf kernel not reseted sub process len(results) : 10 len(list_Values) 0 None max_time_sub_proc : 3600 parent process len(results) : 10 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 : 1263 list_Values should be empty [] To do loadFromThcl(), then load ParamDescType : thcl2896 Catched exception ! Connect or reconnect ! thcls : [{'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'}] thcl {'id': 2896, 'mtr_user_id': 31, 'name': 'learn_convoyeur_qualipapia_nantes_poly_100521_1', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'background,carton_brun,carton_gris,cartonnette,kraft,autre_refus,metal,plastique,teint_dans_la_masse,environnement', 'svm_portfolios_learning': '0,0,0,0,0,0,0,0,0,0', 'photo_hashtag_type': 3663, 'photo_desc_type': 5309, 'type_classification': 'mask_rcnn', 'hashtag_id_list': '0,0,0,0,0,0,0,0,0,0'} Update svm_hashtag_type_desc : 5309 ['background', 'carton_brun', 'carton_gris', 'cartonnette', 'kraft', 'autre_refus', 'metal', 'plastique', 'teint_dans_la_masse', 'environnement'] time for calcul the mask position with numpy : 0.6939163208007812 nb_pixel_total : 1405983 time to create 1 rle with new method : 0.09719300270080566 length of segment : 1164 time for calcul the mask position with numpy : 0.0051419734954833984 nb_pixel_total : 306766 time to create 1 rle with new method : 0.011485815048217773 length of segment : 969 time for calcul the mask position with numpy : 0.03897356986999512 nb_pixel_total : 1224551 time to create 1 rle with new method : 0.6249446868896484 length of segment : 1675 time for calcul the mask position with numpy : 0.0003230571746826172 nb_pixel_total : 9018 time to create 1 rle with old method : 0.018326282501220703 length of segment : 72 time for calcul the mask position with numpy : 0.004354715347290039 nb_pixel_total : 246164 time to create 1 rle with new method : 0.009245157241821289 length of segment : 646 time for calcul the mask position with numpy : 0.0054073333740234375 nb_pixel_total : 301462 time to create 1 rle with new method : 0.009384870529174805 length of segment : 969 time for calcul the mask position with numpy : 0.0009791851043701172 nb_pixel_total : 37329 time to create 1 rle with old method : 0.04315996170043945 length of segment : 209 time for calcul the mask position with numpy : 0.0036590099334716797 nb_pixel_total : 151873 time to create 1 rle with new method : 0.006929159164428711 length of segment : 701 time for calcul the mask position with numpy : 0.014253616333007812 nb_pixel_total : 652054 time to create 1 rle with new method : 0.07283234596252441 length of segment : 1447 time for calcul the mask position with numpy : 0.00014090538024902344 nb_pixel_total : 743 time to create 1 rle with old method : 0.0009214878082275391 length of segment : 79 time for calcul the mask position with numpy : 0.00016379356384277344 nb_pixel_total : 4376 time to create 1 rle with old method : 0.005183219909667969 length of segment : 52 time for calcul the mask position with numpy : 0.0010535717010498047 nb_pixel_total : 69774 time to create 1 rle with old method : 0.08307743072509766 length of segment : 268 time for calcul the mask position with numpy : 0.0006933212280273438 nb_pixel_total : 31784 time to create 1 rle with old method : 0.035700082778930664 length of segment : 201 time for calcul the mask position with numpy : 0.001416921615600586 nb_pixel_total : 42647 time to create 1 rle with old method : 0.04630637168884277 length of segment : 667 time for calcul the mask position with numpy : 0.015778779983520508 nb_pixel_total : 820647 time to create 1 rle with new method : 0.09592008590698242 length of segment : 1174 time for calcul the mask position with numpy : 0.0006358623504638672 nb_pixel_total : 16556 time to create 1 rle with old method : 0.019044876098632812 length of segment : 167 time for calcul the mask position with numpy : 0.007114887237548828 nb_pixel_total : 315947 time to create 1 rle with new method : 0.020355224609375 length of segment : 1027 time for calcul the mask position with numpy : 0.0001914501190185547 nb_pixel_total : 840 time to create 1 rle with old method : 0.0012159347534179688 length of segment : 38 time for calcul the mask position with numpy : 0.0006239414215087891 nb_pixel_total : 17646 time to create 1 rle with old method : 0.020986318588256836 length of segment : 195 time for calcul the mask position with numpy : 0.010861396789550781 nb_pixel_total : 588649 time to create 1 rle with new method : 0.171738862991333 length of segment : 1534 time for calcul the mask position with numpy : 0.0003631114959716797 nb_pixel_total : 6640 time to create 1 rle with old method : 0.00806570053100586 length of segment : 157 time for calcul the mask position with numpy : 0.0002295970916748047 nb_pixel_total : 6164 time to create 1 rle with old method : 0.008510828018188477 length of segment : 74 time for calcul the mask position with numpy : 0.0008144378662109375 nb_pixel_total : 32181 time to create 1 rle with old method : 0.03526949882507324 length of segment : 290 time for calcul the mask position with numpy : 0.0002200603485107422 nb_pixel_total : 4809 time to create 1 rle with old method : 0.005850791931152344 length of segment : 87 time for calcul the mask position with numpy : 0.0006694793701171875 nb_pixel_total : 39207 time to create 1 rle with old method : 0.04358673095703125 length of segment : 292 time for calcul the mask position with numpy : 0.0008873939514160156 nb_pixel_total : 29531 time to create 1 rle with old method : 0.03376936912536621 length of segment : 178 time for calcul the mask position with numpy : 0.0007882118225097656 nb_pixel_total : 15519 time to create 1 rle with old method : 0.01850748062133789 length of segment : 274 time for calcul the mask position with numpy : 0.0004429817199707031 nb_pixel_total : 11583 time to create 1 rle with old method : 0.013164520263671875 length of segment : 211 time for calcul the mask position with numpy : 0.008051633834838867 nb_pixel_total : 365838 time to create 1 rle with new method : 0.0173184871673584 length of segment : 1836 time for calcul the mask position with numpy : 0.0008914470672607422 nb_pixel_total : 62086 time to create 1 rle with old method : 0.07011938095092773 length of segment : 379 time for calcul the mask position with numpy : 0.0016489028930664062 nb_pixel_total : 79240 time to create 1 rle with old method : 0.09067773818969727 length of segment : 199 time for calcul the mask position with numpy : 0.009812116622924805 nb_pixel_total : 340313 time to create 1 rle with new method : 0.0196993350982666 length of segment : 1280 time for calcul the mask position with numpy : 0.0001125335693359375 nb_pixel_total : 2544 time to create 1 rle with old method : 0.0031397342681884766 length of segment : 82 time for calcul the mask position with numpy : 5.245208740234375e-05 nb_pixel_total : 701 time to create 1 rle with old method : 0.0009603500366210938 length of segment : 41 time for calcul the mask position with numpy : 0.0002453327178955078 nb_pixel_total : 11972 time to create 1 rle with old method : 0.013765573501586914 length of segment : 140 time for calcul the mask position with numpy : 0.000133514404296875 nb_pixel_total : 1090 time to create 1 rle with old method : 0.0021631717681884766 length of segment : 34 time for calcul the mask position with numpy : 9.059906005859375e-05 nb_pixel_total : 1883 time to create 1 rle with old method : 0.002557039260864258 length of segment : 40 time for calcul the mask position with numpy : 0.004259586334228516 nb_pixel_total : 312839 time to create 1 rle with new method : 0.01020193099975586 length of segment : 1069 time for calcul the mask position with numpy : 0.0023305416107177734 nb_pixel_total : 146313 time to create 1 rle with old method : 0.1667470932006836 length of segment : 311 time for calcul the mask position with numpy : 0.02362370491027832 nb_pixel_total : 1326061 time to create 1 rle with new method : 0.21875357627868652 length of segment : 1734 time for calcul the mask position with numpy : 0.004770755767822266 nb_pixel_total : 289975 time to create 1 rle with new method : 0.010442972183227539 length of segment : 787 time for calcul the mask position with numpy : 0.00429081916809082 nb_pixel_total : 320158 time to create 1 rle with new method : 0.011646270751953125 length of segment : 1200 time for calcul the mask position with numpy : 0.00022745132446289062 nb_pixel_total : 3734 time to create 1 rle with old method : 0.004868268966674805 length of segment : 77 time for calcul the mask position with numpy : 0.0013349056243896484 nb_pixel_total : 34797 time to create 1 rle with old method : 0.039385318756103516 length of segment : 588 time for calcul the mask position with numpy : 0.0035746097564697266 nb_pixel_total : 191756 time to create 1 rle with new method : 0.006632089614868164 length of segment : 1056 time for calcul the mask position with numpy : 0.005053281784057617 nb_pixel_total : 364379 time to create 1 rle with new method : 0.008963346481323242 length of segment : 982 time for calcul the mask position with numpy : 0.004059791564941406 nb_pixel_total : 269959 time to create 1 rle with new method : 0.01116800308227539 length of segment : 1398 time spent for convertir_results : 7.4644176959991455 Inside saveOutput : final : False verbose : 0 eke 12-6-18 : saveMask need to be cleaned for new output ! Number saved : None batch 1 Loaded 47 chid ids of type : 3663 Number RLEs to save : 28050 save missing photos in datou_result : time spend for datou_step_exec : 55.79066038131714 time spend to save output : 1.6416165828704834 total time spend for step 1 : 57.43227696418762 step2:crop_condition Wed Feb 12 12:07:24 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! We should have FATAL ERROR but same_nb_input_output==True : this should be an optionnal input ! VR 22-3-18 : For now we do not clean correctly the datou structure Loading chi in step crop with photo_hashtag_type : 3663 Loading chi in step crop for list_pids : 10 ! batch 1 Loaded 47 chid ids of type : 3663 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ begin to crop the class : teint_dans_la_masse param for this class : {'min_score': 0.7} filtre for class : teint_dans_la_masse hashtag_id of this class : 2107752385 we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 11 About to insert : list_path_to_insert length 11 new photo from crops ! we have finished the crop for the class : teint_dans_la_masse begin to crop the class : autre_refus param for this class : {'min_score': 0.5} filtre for class : autre_refus hashtag_id of this class : 2107752406 we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 1 About to insert : list_path_to_insert length 1 new photo from crops ! we have finished the crop for the class : autre_refus begin to crop the class : carton_gris param for this class : {'min_score': 0.5} filtre for class : carton_gris hashtag_id of this class : 2107753020 begin to crop the class : cartonnette param for this class : {'min_score': 0.5} filtre for class : cartonnette hashtag_id of this class : 702398920 we have both polygon and rles Next one ! we have both polygon and rles Next one ! map_result returned by crop_photo_return_map_crop : length : 2 About to insert : list_path_to_insert length 2 new photo from crops ! we have finished the crop for the class : cartonnette begin to crop the class : carton_brun param for this class : {'min_score': 0.7} filtre for class : carton_brun hashtag_id of this class : 2107753024 begin to crop the class : plastique param for this class : {'min_score': 0.5} filtre for class : plastique hashtag_id of this class : 492725882 begin to crop the class : kraft param for this class : {'min_score': 0.5} filtre for class : kraft hashtag_id of this class : 493202403 begin to crop the class : metal param for this class : {'min_score': 0.5} filtre for class : metal hashtag_id of this class : 492628673 delete rles for these photos Inside saveOutput : final : False verbose : 0 saveOutput not yet implemented for datou_step.type : crop_condition we use saveGeneral [1337080176, 1337079856, 1337079701, 1337079699, 1337079672, 1337079660, 1337079613, 1337079475, 1337079426, 1337079169] Looping around the photos to save general results len do output : 14 /-3671645430Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645431Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645433Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645439Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645449Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645447Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645450Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645461Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645465Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645472Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645471Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645438Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645451Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . /-3671645456Didn't retrieve data .Didn't retrieve data .Didn't retrieve data . before output type Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Here is an output not treated by saveGeneral : Managing all output in save final without adding information in the mtr_datou_result ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337080176', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079856', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079701', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079699', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079672', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079660', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079613', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079475', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079426', None, None, None, None, None, '2579287') ('3459', None, None, None, None, None, None, None, '2579287') ('3459', '20475600', '1337079169', None, None, None, None, None, '2579287') begin to insert list_values into mtr_datou_result : length of list_values in save_final : 52 time used for this insertion : 0.020735502243041992 save_final save missing photos in datou_result : time spend for datou_step_exec : 6.638596534729004 time spend to save output : 0.021787166595458984 total time spend for step 2 : 6.660383701324463 step3:thcl Wed Feb 12 12:07:31 2025 VR 17-11-17 : now, only for linear exec dependencies tree, some output goes to fill the input of the next VR 22-3-18 : now we test the dependencies tree, but keep two separate code for datou_prepare_output_input until the code is correctly tested, clean and works in both case VR 22-3-18 : but we use the first code for the first step id = -1, build in the code of datou_exec VR 22-3-18 : we should manage here the case when we are at the first step instead of building this step before datou_exec Currently we do not manage missing dependencies information, that could maybe be correctly interpreted with default behavior Some of the step done at execution of the step could be done before when the tree of execution is build and the dependencies of different step analysed complete output_args for input 0 VR 22-3-18 : For now we do not clean correctly the datou structure Beginning of datou step Thcl ! nombre de thcls : 2 we are using the classfication for multi_thcl [2456, 2868] time to import caffe and check if the image exist : 0.009289264678955078 time to convert the images to numpy array : 2.6226043701171875e-06 time to import caffe and check if the image exist : 0.009708404541015625 time to convert the images to numpy array : 2.384185791015625e-06 time to import caffe and check if the image exist : 0.01034855842590332 time to convert the images to numpy array : 2.1457672119140625e-06 time to import caffe and check if the image exist : 0.011447906494140625 time to convert the images to numpy array : 0.007025003433227539 time to import caffe and check if the image exist : 0.012065410614013672 time to convert the images to numpy array : 0.0072650909423828125 time to import caffe and check if the image exist : 0.010368585586547852 time to convert the images to numpy array : 0.012511730194091797 time to import caffe and check if the image exist : 0.013422966003417969 time to convert the images to numpy array : 0.015317678451538086 time to import caffe and check if the image exist : 0.013907909393310547 time to convert the images to numpy array : 0.10729670524597168 time to import caffe and check if the image exist : 0.009772777557373047 time to convert the images to numpy array : 0.4153444766998291 time to import caffe and check if the image exist : 0.01118016242980957 time to convert the images to numpy array : 0.4191579818725586 total time to convert the images to numpy array : 0.8869438171386719 list photo_ids error: [] list photo_ids correct : [-3671645450, -3671645461, -3671645449, -3671645447, -3671645433, -3671645439, -3671645451, -3671645456, -3671645471, -3671645438, -3671645430, -3671645431, -3671645465, -3671645472] number of photos to traite : 14 try to delete the photos incorrect in DB tagging for thcl : 2456 To do loadFromThcl(), then load ParamDescType : thcl2456 thcls : [{'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'}] thcl {'id': 2456, 'mtr_user_id': 31, 'name': 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'papier,refus', 'svm_portfolios_learning': '3028087,3028251', 'photo_hashtag_type': 3049, 'photo_desc_type': 4999, 'type_classification': 'caffe', 'hashtag_id_list': '492668766,538914404'} Update svm_hashtag_type_desc : 4999 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) To loadFromThcl() : net_4999 begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 1263 wait 20 seconds l 3637 free memory gpu now : 1263 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (4999, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 16384, 25088, 'learn_qualipapia_papier_refus_from_vlg_data_aug', 'res5b', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2020, 10, 23, 14, 27, 22), datetime.datetime(2020, 10, 23, 14, 27, 22)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_qualipapia_papier_refus_from_vlg_data_aug Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_qualipapia_papier_refus_from_vlg_data_aug model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel size_local : 44972172 size in s3 : 44972172 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 caffemodel already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt size_local : 17311 size in s3 : 17311 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:51 mean.npy already exist and didn't need to update /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/synset_words.txt size_local : 57 size in s3 : 57 create time local : 2021-08-09 05:55:48 create time in s3 : 2021-08-06 19:28:49 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /home/admin/workarea/install/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/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/deploy.prototxt caffemodel_filename : /data/models_weight/learn_qualipapia_papier_refus_from_vlg_data_aug/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 1044 wait 20 seconds l 3637 free memory gpu now : 1044 max_wait_temp : 1 max_wait : 0 dict_keys(['prob']) time used to do the prepocess of the images : 0.20663690567016602 time used to do the prediction : 0.14151430130004883 we don't save the descriptors for this thcl 2456 tagging for thcl : 2868 To do loadFromThcl(), then load ParamDescType : thcl2868 thcls : [{'id': 2868, 'mtr_user_id': 31, 'name': 'learn_papier_nantes_300421', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton_brun,Carton_gris,Teint_Dans_La_Masse,autre_refus,cartonnette,environnement,kraft,metal,papier,plastique', 'svm_portfolios_learning': '3752117,3752118,3752123,3752106,3752116,3752124,3752119,3581575,3486029,3752122', 'photo_hashtag_type': 3632, 'photo_desc_type': 5288, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'}] thcl {'id': 2868, 'mtr_user_id': 31, 'name': 'learn_papier_nantes_300421', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': 'Carton_brun,Carton_gris,Teint_Dans_La_Masse,autre_refus,cartonnette,environnement,kraft,metal,papier,plastique', 'svm_portfolios_learning': '3752117,3752118,3752123,3752106,3752116,3752124,3752119,3581575,3486029,3752122', 'photo_hashtag_type': 3632, 'photo_desc_type': 5288, 'type_classification': 'caffe', 'hashtag_id_list': '2107753024,2107753020,2107752385,2107752406,702398920,493012381,493202403,492628673,492668766,492725882'} Update svm_hashtag_type_desc : 5288 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5288, 'learn_papier_nantes_300421', 512, 512, 'learn_papier_nantes_300421', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 30, 17, 9, 41), datetime.datetime(2021, 4, 30, 17, 9, 41)) To loadFromThcl() : net_5288 begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 1042 wait 20 seconds l 3637 free memory gpu now : 1042 max_wait_temp : 1 max_wait : 0 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5288, 'learn_papier_nantes_300421', 512, 512, 'learn_papier_nantes_300421', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 1, datetime.datetime(2021, 4, 30, 17, 9, 41), datetime.datetime(2021, 4, 30, 17, 9, 41)) None mean_file_type : mean_file_path : prototxt_file_path : model : learn_papier_nantes_300421 Inside get_net Inside get_net before cache_data_model model_param file didn't exist Inside get_net before CDM.load_model_par_type model_name : learn_papier_nantes_300421 model_type : caffe list file need : ['caffemodel', 'deploy_conv_normal.prototxt', 'deploy_fc.prototxt', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file exist in s3 : ['caffemodel', 'deploy.prototxt', 'mean.npy', 'synset_words.txt'] file manque in s3 : ['deploy_conv_normal.prototxt', 'deploy_fc.prototxt'] local folder : /data/models_weight/learn_papier_nantes_300421 /data/models_weight/learn_papier_nantes_300421/caffemodel size_local : 44791983 size in s3 : 44791983 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:13 caffemodel already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/deploy.prototxt size_local : 17255 size in s3 : 17255 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:12 deploy.prototxt already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/mean.npy size_local : 1572992 size in s3 : 1572992 create time local : 2021-08-09 05:55:59 create time in s3 : 2021-08-06 19:22:14 mean.npy already exist and didn't need to update /data/models_weight/learn_papier_nantes_300421/synset_words.txt size_local : 331 size in s3 : 331 create time local : 2021-08-09 05:56:00 create time in s3 : 2021-08-06 19:22:12 synset_words.txt already exist and didn't need to update Inside get_net after CDM.load_model_par_type After if not only_with_local_cache: /home/admin/workarea/install/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/ Here before set mode gpu Doing nothing but we could set mode gpu after set mode gpu prototxt_filename : /data/models_weight/learn_papier_nantes_300421/deploy.prototxt caffemodel_filename : /data/models_weight/learn_papier_nantes_300421/caffemodel now we set caffe to gpu mode before predict begin to check gpu status inside check gpu memory havn't enough memory gpu , need / 2500 l 3632 free memory gpu now : 1042 wait 20 seconds WARNING: Logging before InitGoogleLogging() is written to STDERR F0212 12:09:00.207566 3277060 syncedmem.cpp:71] Check failed: error == cudaSuccess (2 vs. 0) out of memory *** Check failure stack trace: *** Command terminated by signal 6 28.05user 25.66system 2:37.25elapsed 34%CPU (0avgtext+0avgdata 2289588maxresident)k 2061744inputs+9008outputs (7970major+1357293minor)pagefaults 0swaps