normalize = tvtsf.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
img = normalize(t.from_numpy(img))
在这段代码运行后，会出现RuntimeError: expected Double tensor (got Float tensor)
bug message并不清晰，这里是pytorch issues的解答。
normalize()需要的数据类型是torch.float类型，所以改为以下代码：
normalize = tvtsf.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
img = normalize(t.from_numpy(img).float())
