RuntimeError: mat1 dim 1 must match mat2 dim 0

[wys2929]

when i try:python main.py pretrain_crossclr_3views --config config/CrosSCLR/crossclr_3views_xview.yaml
out:RuntimeError: mat1 dim 1 must match mat2 dim 0
Parameters:
{'work_dir': 'work_dir/crossclr_3views/1_xview_frame50_channel16_epoch300_cross150', 'config': 'config/CrosSCLR/crossclr_3views_xview.yaml', 'phase': 'train', 'save_result': False, 'start_epoch': 0, 'num_epoch': 50, 'use_gpu': True, 'device': [0, 1], 'log_interval': 100, 'save_interval': 5, 'eval_interval': -1, 'save_log': True, 'print_log': True, 'pavi_log': False, 'train_feeder': 'feeder.ntu_feeder.Feeder_dual', 'test_feeder': 'feeder.feeder', 'num_worker': 4, 'train_feeder_args': {'data_path': 'data/NTU60_frame50/xview/train_position.npy', 'label_path': 'data/NTU-RGB-D/xview/train_label.pkl', 'shear_amplitude': 0.5, 'temperal_padding_ratio': 6, 'mmap': True}, 'test_feeder_args': {}, 'batch_size': 64, 'test_batch_size': 64, 'debug': False, 'model': 'net.crossclr_3views.CrosSCLR', 'model_args': {'base_encoder': 'net.st_gcn.Model', 'pretrain': True, 'feature_dim': 128, 'queue_size': 32768, 'momentum': 0.999, 'Temperature': 0.07, 'mlp': True, 'in_channels': 3, 'hidden_channels': 16, 'hidden_dim': 256, 'num_class': 60, 'dropout': 0.5, 'graph_args': {'layout': 'ntu-rgb+d', 'strategy': 'spatial'}, 'edge_importance_weighting': True}, 'weights': None, 'ignore_weights': [], 'base_lr': 0.1, 'step': [250], 'optimizer': 'SGD', 'nesterov': False, 'weight_decay': 0.0001, 'view': 'all', 'cross_epoch': 25, 'context': True, 'topk': 1}

Can you please help me to see what is the problem, thanks a lot

[wys2929]

After I modify the device to 0, it will be fine after running it again

[wys2929]

but i don't know why