python /home/admin/mtr/script_for_cron.py -j datou_current3 -m 12 -a ' -a 533 -l 200 --rand=1 ' -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 : 2406560 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 list_input_json: {} Date 2026-06-15 11:10:29.923795 Current got : datou_id : 533, datou_cur_ids : ['4385730'] with mtr_portfolio_ids : ['31157000'] and first list_photo_ids : [] new path : /proc/2406560/ 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 , 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 : 8.315143823623657 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 Mon Jun 15 11:10:38 2026 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 2026-06-15 11:10:41.190243: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2026-06-15 11:10:41.198668: 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 2026-06-15 11:10:41.198898: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2026-06-15 11:10:41.200545: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2026-06-15 11:10:41.202120: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2026-06-15 11:10:41.202413: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2026-06-15 11:10:41.204295: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2026-06-15 11:10:41.205253: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2026-06-15 11:10:41.208966: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2026-06-15 11:10:41.210046: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2026-06-15 11:10:41.210436: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2026-06-15 11:10:41.217656: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3493010000 Hz 2026-06-15 11:10:41.218947: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fa494000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2026-06-15 11:10:41.218979: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2026-06-15 11:10:41.436531: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x153f47b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2026-06-15 11:10:41.436578: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 2080 Ti, Compute Capability 7.5 2026-06-15 11:10:41.437628: 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 2026-06-15 11:10:41.437704: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2026-06-15 11:10:41.437748: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2026-06-15 11:10:41.437777: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10 2026-06-15 11:10:41.437804: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10 2026-06-15 11:10:41.437830: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10 2026-06-15 11:10:41.437856: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10 2026-06-15 11:10:41.437883: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2026-06-15 11:10:41.439290: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0 2026-06-15 11:10:41.439356: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1 2026-06-15 11:10:41.440209: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix: 2026-06-15 11:10:41.440234: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108] 0 2026-06-15 11:10:41.440248: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0: N 2026-06-15 11:10:41.441705: 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 : 3897 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 : [] 2026-06-15 11:10:48.047093: 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:14 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:15 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:15 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:16 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:16 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:16 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:17 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 : 2026-03-04 13:31:58 create time in s3 : 2026-03-04 12:24:17 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 : 2026-03-04 13:32:01 create time in s3 : 2026-03-04 12:24:27 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 : 2026-03-04 13:32:01 create time in s3 : 2026-03-04 12:24:28 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 : 2026-03-04 13:32:02 create time in s3 : 2026-03-04 12:24:31 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 : 2026-03-04 13:32:02 create time in s3 : 2026-03-04 12:24:31 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 : 2026-03-04 13:32:04 create time in s3 : 2026-03-04 12:24:36 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 : 7.993424415588379 time used to load_weights : 0.3110816478729248 0it [00:00, ?it/s] 5it [00:00, 49.63it/s] 11it [00:00, 53.75it/s] 17it [00:00, 47.51it/s] 22it [00:00, 45.66it/s] 28it [00:00, 47.74it/s] 33it [00:00, 46.84it/s] 36it [00:00, 45.85it/s]2026-06-15 11:10:52.972426: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2026-06-15 11:10:52.982572: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_NOT_INITIALIZED 2026-06-15 11:10:53.238307: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2026-06-15 11:10:53.248447: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2026-06-15 11:10:53.251593: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR temp/1781514630_2406560_1418778650_9eb355d6ad6b89eabee0cff2a76ce48c.jpg temp/1781514630_2406560_1418778649_354a13a1e12e0f252510fe14b4224467.jpg temp/1781514630_2406560_1418778648_71244233df6e47395445df0d7bbe67e5.jpg temp/1781514630_2406560_1418778647_37df746498fa15fde86d95b9bb26938d.jpg temp/1781514630_2406560_1418778646_434b3fb552751bd8dd736a32da0ccb1d.jpg temp/1781514630_2406560_1418778645_b1702e3467a8a1fc6d1337271d1d76f7.jpg temp/1781514630_2406560_1418778144_b0647d13a488e1c90318a8d3150bdc42.jpg temp/1781514630_2406560_1418778143_57e7d5e44b86961c66dfb47a0eaa69e1.jpg temp/1781514630_2406560_1418778142_c6d75f14eb55218428165bc2ba62f4a9.jpg temp/1781514630_2406560_1418778141_def9bfc8011a4a6cc9310a1053bb5a72.jpg temp/1781514630_2406560_1418778140_1313ffa2a3d5e14545f88263feb3d553.jpg temp/1781514630_2406560_1418778139_a03189bc3093e2b85c68f8d88cc6c2f9.jpg temp/1781514630_2406560_1418775615_ff50ac30f9f34fdfa17f9d2449792b62.jpg temp/1781514630_2406560_1418775614_6175059ce10287a132484cf72b96e845.jpg temp/1781514630_2406560_1418775613_a124c9a33e71a57de884467f7cac5346.jpg temp/1781514630_2406560_1418775612_29fda4976c904954f1074a84182dc670.jpg temp/1781514630_2406560_1418775611_b3c0cccff63b83d804f6f8b0f3638fca.jpg temp/1781514630_2406560_1418775609_2c179281ef5e4432630f1d4d4c4aa436.jpg temp/1781514630_2406560_1418775059_460065302d7c615c7245cd90aee2b086.jpg temp/1781514630_2406560_1418775058_6343fabc5efb5d3e4b0d966bb4653222.jpg temp/1781514630_2406560_1418775057_39c55586c882021663edc68f3fad4a2b.jpg temp/1781514630_2406560_1418775056_41ad76e9a83ed6e4672fc83a53fcaa00.jpg temp/1781514630_2406560_1418775055_f61d15301111984c433b14447b156c5e.jpg temp/1781514630_2406560_1418775054_0d8e9a039569a3ec182562458ae94f2e.jpg temp/1781514630_2406560_1418774312_6cef1b86c0fc7ded68a7ee4c5c4b6e09.jpg temp/1781514630_2406560_1418774311_821abf606db091629e75122ec6eb945e.jpg temp/1781514630_2406560_1418774310_2d24ba97e99aec4ca0c676390cad41ac.jpg temp/1781514630_2406560_1418774309_9700836030f4e604b7ab163a97c6a87c.jpg temp/1781514630_2406560_1418774308_82e6c2e37ebdcf1f8cc4446204badb44.jpg temp/1781514630_2406560_1418774307_d4455af63a7025316f1c135614ec58e1.jpg temp/1781514630_2406560_1418773310_ffec763f48a64cfee5708492ff29910e.jpg temp/1781514630_2406560_1418773309_18f559082450661f7f9a4c890dd70b51.jpg temp/1781514630_2406560_1418773308_bf26c6ff695bd154be9b88a49a0f5d92.jpg temp/1781514630_2406560_1418773307_405c3675da0c8e9524474bda5acc080d.jpg temp/1781514630_2406560_1418773306_656f0c9a490ca70727374be95624d5d9.jpg temp/1781514630_2406560_1418773305_3a5a7d48a6298fd2fe621f3baf7aa3f8.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 2340, 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 2534, 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 3171, 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, [1418778650, 1418778649, 1418778648, 1418778647, 1418778646, 1418778645, 1418778144, 1418778143, 1418778142, 1418778141, 1418778140, 1418778139, 1418775615, 1418775614, 1418775613, 1418775612, 1418775611, 1418775609, 1418775059, 1418775058, 1418775057, 1418775056, 1418775055, 1418775054, 1418774312, 1418774311, 1418774310, 1418774309, 1418774308, 1418774307, 1418773310, 1418773309, 1418773308, 1418773307, 1418773306, 1418773305] begin to insert list_values into mtr_datou_result : length of list_values in save_final : 36 time used for this insertion : 0.06377816200256348 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 : 14.820690631866455 time spend to save output : 0.07424807548522949 total time spend for step 0 : 14.894938707351685 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 ! 13.20user 5.17system 0:29.82elapsed 61%CPU (0avgtext+0avgdata 1782172maxresident)k 980208inputs+1017800outputs (354major+530787minor)pagefaults 0swaps