使用torchvision.datasets.Imagefolder将数据分为训练集和测试集

orig_set = torchvision.datasets.Imagefolder(...)  # your dataset
n = len(orig_set)  # total number of examples
n_test = int(0.1 * n)  # take ~10% for test
test_set = torch.utils.data.Subset(orig_set, range(n_test))  # take first 10%
train_set = torch.utils.data.Subset(orig_set, range(n_test, n))  # take the rest   

注: 英文标签不影响标签问题、最终都会按照字母排序转换为数字标签