Open zhibeiyou135 opened 3 months ago
Hi, in the zero-shot setting, we use the test set of another dataset for training (this conforms to the principle that zero-shot learning cannot train on data of related objects). More details please refer to our technical report.
The train mode in dataset.py is written for the few-shot setting.
在train.py中: if args.dataset == 'mvtec': train_data = MVTecDataset(root=args.train_data_path, transform=preprocess, target_transform=transform, aug_rate=args.aug_rate) 并未设置mode='train',而 MVTecDataset中mode的默认值为 'test' 。下述代码: if mode == 'train':
如果模式是 'train'
无论是test.py还是train.py都不会执行 mode == 'train'。请问是应该将mode默认值设置为train,还是我理解的幼体,在train.py中mode就应该为test?