python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 8 -a ' --fifo -a 533 -l 100 ' -s datou_current_533 -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 : 2500795 load datou : 533 # 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 ! 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 ! 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 ! 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_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? [ (photo_id, hashtag_id_0, score_0), (photo_id, hashtag_id_1, score_1), ...] was removed should we ? (photo_id, hashtag_id, score_max) was removed should we ? chemin de la photo was removed should we ? load thcls load pdts Running datou job : batch_current TODO datou_current to load to do maybe to take outside batchDatouExec no input labels no input values updating current state to 1 we have a portfolio with more photos than limit : 8700>100 please execute split_portfolio.py -i 21319675 -l 100 size over we load limit photo not treated list_input_json: {} Current got : datou_id : 533, datou_cur_ids : ['2660215'] with mtr_portfolio_ids : ['21319675'] and first list_photo_ids : [] new path : /proc/2500795/ 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 ! 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 ! 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 ! DataTypes for each output/input checked ! List Step Type Loaded in datou : tfhub_classification2, argmax list_input_json : {} origin We have 1 , WARNING: data may be incomplete, need to offset and complete ! BFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFBFwe have missing 0 photos in the step downloads : photo missing : [] try to delete the photos missing in DB length of list_filenames : 36 ; length of list_pids : 36 ; length of list_args : 36 time to download the photos : 4.2974536418914795 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 : 2 step1:tfhub_classification2 Sun Mar 30 11:28:33 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 TFHub with tf2 ! nombre de thcls : 3 we are using the classfication for multi_thcl [3513, 3379, 3847] begin to check gpu status inside check gpu memory 2025-03-30 11:28:35.952020: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2025-03-30 11:28:35.988842: 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 2025-03-30 11:28:35.989126: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-30 11:28:35.991313: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-30 11:28:35.993344: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-30 11:28:35.993668: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-30 11:28:35.995811: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-30 11:28:35.996889: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-30 11:28:36.001175: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-30 11:28:36.002288: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-30 11:28:36.002792: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2025-03-30 11:28:36.010770: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493065000 Hz 2025-03-30 11:28:36.012371: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f5fdc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2025-03-30 11:28:36.012420: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2025-03-30 11:28:36.231917: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xfffd490 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2025-03-30 11:28:36.231996: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2025-03-30 11:28:36.233465: 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 2025-03-30 11:28:36.233668: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-30 11:28:36.233725: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-30 11:28:36.233774: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2025-03-30 11:28:36.233826: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2025-03-30 11:28:36.233876: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2025-03-30 11:28:36.233924: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2025-03-30 11:28:36.233969: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-30 11:28:36.235686: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2025-03-30 11:28:36.235800: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2025-03-30 11:28:36.236730: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2025-03-30 11:28:36.236758: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2025-03-30 11:28:36.236775: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2025-03-30 11:28:36.238457: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3096 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 2080 Ti, pci bus id: 0000:41:00.0, compute capability: 7.5) l 3637 free memory gpu now : 3165 max_wait_temp : 1 max_wait : 5 1 Physical GPUs, 1 Logical GPUs tagging for thcl : 3513 To do loadFromThcl(), then load ParamDescType : thcl3513 thcls : [{'id': 3513, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2_tf', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 4557, 'photo_desc_type': 5767, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'}] thcl {'id': 3513, 'mtr_user_id': 31, 'name': 'Rungis_amount_dechets_fall_2018_v2_tf', 'pb_hashtag_id': 0, 'live': b'\x00', 'list_hashtags': '05102018_Papier_non_papier_dense,05102018_Papier_non_papier_peu_dense,05102018_Papier_non_papier_presque_vide,05102018_Papier_non_papier_tres_dense,05102018_Papier_non_papier_tres_peu_dense', 'svm_portfolios_learning': '1108385,1108386,1108388,1108384,1108387', 'photo_hashtag_type': 4557, 'photo_desc_type': 5767, 'type_classification': 'tf_classification2', 'hashtag_id_list': '2107751013,2107751014,2107751015,2107751016,2107751017'} Update svm_hashtag_type_desc : 5767 FOUND : 1 Here is data_from_sql_as_vec to set the ParamDescriptorType : (5767, 'Rungis_amount_dechets_fall_2018_v2_tf', 2048, 2048, 'Rungis_amount_dechets_fall_2018_v2_tf', 'pool5', 10.0, None, None, 256, None, 0, None, 8, None, None, -1000.0, 3, datetime.datetime(2023, 3, 16, 15, 52, 10), datetime.datetime(2023, 3, 16, 15, 52, 10)) model_name : Rungis_amount_dechets_fall_2018_v2_tf model_param file didn't exist model_name : Rungis_amount_dechets_fall_2018_v2_tf model_type : tf_classification2 list file need : ['Confusion_Matrix.png', 'Precision_Recall_05102018_Papier_non_papier_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00001', 'model_checkpoint.ckpt.data-00000-of-00002', 'model_checkpoint.ckpt.data-00001-of-00002', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file exist in s3 : ['Confusion_Matrix.png', 'Precision_Recall_05102018_Papier_non_papier_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg', 'Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg', 'Result_Summary.txt', 'checkpoint', 'model_checkpoint.ckpt.data-00000-of-00001', 'model_checkpoint.ckpt.data-00000-of-00002', 'model_checkpoint.ckpt.data-00001-of-00002', 'model_checkpoint.ckpt.index', 'model_weights.h5'] file manque in s3 : [] 2025-03-30 11:28:42.831796: I tensorflow/stream_executor/cuda/cuda_driver.cc:763] failed to allocate 3.02G (3246391296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory local folder : /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Confusion_Matrix.png size_local : 67810 size in s3 : 67810 create time local : 2023-10-30 16:21:37 create time in s3 : 2023-10-30 14:09:29 Confusion_Matrix.png already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_dense.jpg size_local : 73949 size in s3 : 73949 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:30 Precision_Recall_05102018_Papier_non_papier_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg size_local : 85572 size in s3 : 85572 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:39 Precision_Recall_05102018_Papier_non_papier_peu_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg size_local : 72361 size in s3 : 72361 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:37 Precision_Recall_05102018_Papier_non_papier_presque_vide.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg size_local : 83567 size in s3 : 83567 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:48 Precision_Recall_05102018_Papier_non_papier_tres_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg size_local : 71611 size in s3 : 71611 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:29 Precision_Recall_05102018_Papier_non_papier_tres_peu_dense.jpg already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/Result_Summary.txt size_local : 1058 size in s3 : 1058 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:30 Result_Summary.txt already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/checkpoint size_local : 99 size in s3 : 99 create time local : 2023-10-30 16:21:38 create time in s3 : 2023-10-30 14:09:36 checkpoint already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.data-00000-of-00001 size_local : 188538519 size in s3 : 188538519 create time local : 2023-10-30 16:21:41 create time in s3 : 2023-10-30 14:09:40 model_checkpoint.ckpt.data-00000-of-00001 already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.data-00000-of-00002 size_local : 216572 size in s3 : 216572 create time local : 2023-10-30 16:21:41 create time in s3 : 2023-03-16 14:52:09 model_checkpoint.ckpt.data-00000-of-00002 already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.data-00001-of-00002 size_local : 32279708 size in s3 : 32279708 create time local : 2023-10-30 16:21:42 create time in s3 : 2023-03-16 14:52:07 model_checkpoint.ckpt.data-00001-of-00002 already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_checkpoint.ckpt.index size_local : 28001 size in s3 : 28001 create time local : 2023-10-30 16:21:42 create time in s3 : 2023-10-30 14:09:30 model_checkpoint.ckpt.index already exist and didn't need to update /data/models_weight/Rungis_amount_dechets_fall_2018_v2_tf/model_weights.h5 size_local : 94501976 size in s3 : 94501976 create time local : 2023-10-30 16:21:44 create time in s3 : 2023-10-30 14:09:37 model_weights.h5 already exist and didn't need to update desc size : 2048 Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= module (KerasLayer) (None, 2048) 23561152 _________________________________________________________________ Rungis_amount_dechets_fall_2 (None, 5) 10245 ================================================================= Total params: 23,571,397 Trainable params: 10,245 Non-trainable params: 23,561,152 _________________________________________________________________ Loading Weights... time used to create the model : 7.657862186431885 time used to load_weights : 0.1872718334197998 0it [00:00, ?it/s] 36it [00:00, 3409.39it/s]2025-03-30 11:28:46.111763: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2025-03-30 11:28:46.312403: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2025-03-30 11:28:46.386077: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2025-03-30 11:28:46.436510: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR temp/1743326908_2500795_1348831735_7997557447042e02b0e5acd95e771ae9.jpg temp/1743326908_2500795_1348831731_14a6b23a4a5ca57e1ca7881abe5d0cd0.jpg temp/1743326908_2500795_1348831729_f8c55eebd2f46726a7718bb5de25aa24.jpg temp/1743326908_2500795_1348831703_20d7e8bcf8792ec27674cc22f31655fa.jpg temp/1743326908_2500795_1348831701_a2e151a7111ee9aa6325671fd901b382.jpg temp/1743326908_2500795_1348831699_562de603dab576c2356176a5ad67091c.jpg temp/1743326908_2500795_1348831691_cf9a8c26da4178bb4a98529ff38ad061.jpg temp/1743326908_2500795_1348831689_d0a781a5c8480e60983919e78b6959ce.jpg temp/1743326908_2500795_1348831687_7f97e1136f2f87bc5a1c691aae5cf714.jpg temp/1743326908_2500795_1348831685_3e93b16bd86ccf5fde82a549eaba37d8.jpg temp/1743326908_2500795_1348831684_ebea8cca7b0cdaf2e12a2d0bf204901b.jpg temp/1743326908_2500795_1348831682_74db8c92351f046d9af6222c8df3780c.jpg temp/1743326908_2500795_1348831675_1947731286f0c88d660e45b3a13e1717.jpg temp/1743326908_2500795_1348831673_6f3761009bba5afb40836d0a08de82a1.jpg temp/1743326908_2500795_1348831671_dc3235a1f8fdaf0a7ae564fcf23e97f9.jpg temp/1743326908_2500795_1348831668_b4a042cb861c639b405fd083c1565b7e.jpg temp/1743326908_2500795_1348831665_dc98d3644e30a7409e256d8577ff6596.jpg temp/1743326908_2500795_1348831662_75674aea1f8ef2b53b98ada51823782e.jpg temp/1743326908_2500795_1348831650_5d4b9fb4cc6c8edc22a3d916bc7e3e72.jpg temp/1743326908_2500795_1348831647_e9df0f41c8f1c3e4c8648e24ff27e02f.jpg temp/1743326908_2500795_1348831646_81ab788d66080b2fa243fc9ab1ab45c5.jpg temp/1743326908_2500795_1348831643_ea0a2e73e310c9cccf181de5d7aa5b65.jpg temp/1743326908_2500795_1348831640_5d2f375110c2229ead6587d8be7759d6.jpg temp/1743326908_2500795_1348831637_5f0434e28ea6f2094a0dc1fa556de758.jpg temp/1743326908_2500795_1348831632_23f7ebed859e569101da79282ba83021.jpg temp/1743326908_2500795_1348831628_3aea4e8f9f286b8eec674a0b588d805a.jpg temp/1743326908_2500795_1348831625_b636f75fcd24a0dc57ae1743d1e68290.jpg temp/1743326908_2500795_1348831622_6abf4be53b6e03dd050f6f879fe318e8.jpg temp/1743326908_2500795_1348831619_7ee8ff13c7e9b09c3af4630189cb8f66.jpg temp/1743326908_2500795_1348831616_5deed2d23a0fe5118f3f7615066a26ae.jpg temp/1743326908_2500795_1348831610_2d6d307f5848084794b8454b78ccc573.jpg temp/1743326908_2500795_1348831606_d32f4cd2a4063c709eeae3fbb730e7cc.jpg temp/1743326908_2500795_1348831601_20b70b256f629d0e65ac68308d78441d.jpg temp/1743326908_2500795_1348831594_e96feed0a0f725e916e245f1af5bbb06.jpg temp/1743326908_2500795_1348831589_5d7a6fd602f2ba8f7e3e82272511dd72.jpg temp/1743326908_2500795_1348831583_c9ade4148c2f47db0c5fd8bdfc037806.jpg Found 36 images belonging to 1 classes. begin to do the prediction : ERROR in datou_step_exec, will save and exit ! Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[{{node model/module/StatefulPartitionedCall/StatefulPartitionedCall/StatefulPartitionedCall/conv1/StatefulPartitionedCall/Conv2D}}]] [Op:__inference_predict_function_34490] Function call stack: predict_function File "/home/admin/workarea/git/Velours/python/mtr/datou/datou_lib.py", line 2329, in datou_exec output = datou_step_exec(sNext, args, cache, context, map_info, verbose, mtr_user_id) File "/home/admin/workarea/git/Velours/python/mtr/datou/datou_lib.py", line 2523, in datou_step_exec return lib_process.datou_step_tfhub2(param, json_param, args, cache, context, map_info, verbose) File "/home/admin/workarea/git/Velours/python/mtr/datou/lib_step_exec/lib_step_process.py", line 3146, in datou_step_tfhub2 classes, outputs, features = this_model.predict_image_paths(list_paths, keep_aspect_ratio=keep_aspect_ratio, File "/home/admin/workarea/git/Velours/python/mtr/tfhub2/evaluate.py", line 288, in predict_image_paths Y_pred, F_pred = self.model.predict(valid_generator, validation_steps) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/engine/training.py", line 88, in _method_wrapper return method(self, *args, **kwargs) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/engine/training.py", line 1268, in predict tmp_batch_outputs = predict_function(iterator) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/eager/def_function.py", line 580, in __call__ result = self._call(*args, **kwds) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/eager/def_function.py", line 650, in _call return self._concrete_stateful_fn._filtered_call(canon_args, canon_kwds) # pylint: disable=protected-access File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/eager/function.py", line 1661, in _filtered_call return self._call_flat( File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/eager/function.py", line 1745, in _call_flat return self._build_call_outputs(self._inference_function.call( File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/eager/function.py", line 593, in call outputs = execute.execute( File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/eager/execute.py", line 59, in quick_execute tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name, [1348831735, 1348831731, 1348831729, 1348831703, 1348831701, 1348831699, 1348831691, 1348831689, 1348831687, 1348831685, 1348831684, 1348831682, 1348831675, 1348831673, 1348831671, 1348831668, 1348831665, 1348831662, 1348831650, 1348831647, 1348831646, 1348831643, 1348831640, 1348831637, 1348831632, 1348831628, 1348831625, 1348831622, 1348831619, 1348831616, 1348831610, 1348831606, 1348831601, 1348831594, 1348831589, 1348831583] begin to insert list_values into mtr_datou_result : length of list_values in save_final : 36 time used for this insertion : 0.02654743194580078 save_final ERROR in last step tfhub_classification2, Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[{{node model/module/StatefulPartitionedCall/StatefulPartitionedCall/StatefulPartitionedCall/conv1/StatefulPartitionedCall/Conv2D}}]] [Op:__inference_predict_function_34490] Function call stack: predict_function time spend for datou_step_exec : 13.267427682876587 time spend to save output : 0.0358119010925293 total time spend for step 0 : 13.303239583969116 need to delete datou_research and reload, so keep current state 1 caffe_path_current : About to save ! 2 After save, about to update current ! 12.70user 3.66system 0:22.70elapsed 72%CPU (0avgtext+0avgdata 1959544maxresident)k 25520inputs+29384outputs (84major+473901minor)pagefaults 0swaps