Closed acmername closed 6 months ago
Please use train_dataset, test_dataset = torch.utils.data.random_split(full_dataset, [train_size, test_size]) to split the dataset, and the random seed is the same as others.
Thank you for your timely recovery. Do you mean take half img and half labelcol from Train_Floder in the dataset file, subtract the corresponding data from train_text.xlsx and train?
Looking forward to your reply Thanks!