Created by: liu824

DALI is not installed, you can improve performance if use DALI [INFO: train.py: 254]: Namespace(batch_size=None, config='./configs/bmn.yaml', epoch=None, fix_random_seed=False, is_profiler=0, learning_rate=None, log_interval=10, model_name='BMN', no_memory_optimize=False, pretrain='data/dataset/bmn/BMN.pdparams', profiler_path='./', resume=None, save_dir='./data/checkpoints', use_gpu=True, valid_interval=1) [INFO: config_utils.py: 70]: ---------------- Train Arguments ---------------- [INFO: config_utils.py: 72]: MODEL: [INFO: config_utils.py: 74]: name:BMN [INFO: config_utils.py: 74]: tscale:100 [INFO: config_utils.py: 74]: dscale:100 [INFO: config_utils.py: 74]: feat_dim:400 [INFO: config_utils.py: 74]: prop_boundary_ratio:0.5 [INFO: config_utils.py: 74]: num_sample:32 [INFO: config_utils.py: 74]: num_sample_perbin:3 [INFO: config_utils.py: 74]: anno_file:data/dataset/bmn/trainlabel.json [INFO: config_utils.py: 74]: feat_path:data/dataset/bmn/videofeature [INFO: config_utils.py: 72]: TRAIN: [INFO: config_utils.py: 74]: subset:train [INFO: config_utils.py: 74]: epoch:10 [INFO: config_utils.py: 74]: batch_size:8 [INFO: config_utils.py: 74]: num_threads:8 [INFO: config_utils.py: 74]: use_gpu:True [INFO: config_utils.py: 74]: num_gpus:1 [INFO: config_utils.py: 74]: learning_rate:0.001 [INFO: config_utils.py: 74]: learning_rate_decay:0.1 [INFO: config_utils.py: 74]: lr_decay_iter:4200 [INFO: config_utils.py: 74]: l2_weight_decay:0.0001 [INFO: config_utils.py: 72]: VALID: [INFO: config_utils.py: 74]: subset:validation [INFO: config_utils.py: 74]: batch_size:8 [INFO: config_utils.py: 74]: num_threads:8 [INFO: config_utils.py: 74]: use_gpu:True [INFO: config_utils.py: 74]: num_gpus:1 [INFO: config_utils.py: 72]: TEST: [INFO: config_utils.py: 74]: subset:validation [INFO: config_utils.py: 74]: batch_size:1 [INFO: config_utils.py: 74]: num_threads:1 [INFO: config_utils.py: 74]: snms_alpha:0.001 [INFO: config_utils.py: 74]: snms_t1:0.5 [INFO: config_utils.py: 74]: snms_t2:0.9 [INFO: config_utils.py: 74]: output_path:data/output/EVAL/BMN_results [INFO: config_utils.py: 74]: result_path:data/evaluate_results [INFO: config_utils.py: 72]: INFER: [INFO: config_utils.py: 74]: subset:test [INFO: config_utils.py: 74]: batch_size:1 [INFO: config_utils.py: 74]: num_threads:1 [INFO: config_utils.py: 74]: snms_alpha:0.4 [INFO: config_utils.py: 74]: snms_t1:0.5 [INFO: config_utils.py: 74]: snms_t2:0.9 [INFO: config_utils.py: 74]: filelist:data/dataset/bmn/infer1.list [INFO: config_utils.py: 74]: output_path:data/output/INFER/BMN_results [INFO: config_utils.py: 74]: result_path:data/predict_results [INFO: config_utils.py: 75]: ------------------------------------------------- W0713 13:21:17.239037 25735 device_context.cc:252] Please NOTE: device: 0, CUDA Capability: 70, Driver API Version: 9.2, Runtime API Version: 9.0 W0713 13:21:17.242261 25735 device_context.cc:260] device: 0, cuDNN Version: 7.3. [INFO: model.py: 152]: Load pretrain weights from data/dataset/bmn/BMN.pdparams Traceback (most recent call last): File "train.py", line 259, in train(args) File "train.py", line 174, in train train_model.load_pretrain_params(exe, pretrain, train_prog, place) File "/home/aistudio/models-release-1.8/PaddleCV/video/models/model.py", line 154, in load_pretrain_params fluid.set_program_state(prog, state_dict) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/io.py", line 1967, in set_program_state .format(orig_para_np.shape, para.name, new_para_np.shape) AssertionError: Parameter's shape does not match, the Program requires a parameter with the shape of ((100, 32, 100, 100)), while the loaded parameter (namely [ sample_mask ]) has a shape of ((100, 320000)).