本文共 648 字，大约阅读时间需要 2 分钟。

报错如下：

File “/home/muli/anaconda3/lib/python3.5/site-packages/torchvision/transforms/functional.py”, line 158, in normalize raise TypeError(‘tensor is not a torch image.’) TypeError: tensor is not a torch image.

解决办法：

transforms.ToTensor()操作要在transforms.Normalize(mean=[0.56391764, 0.43714827, 0.4107524], std=[0.22986116, 0.21178758, 0.20076773])操作的前面

trainTransform = transforms.Compose([         transforms.RandomResizedCrop(224), # 随机裁剪,         transforms.RandomHorizontalFlip(), # 随机水平翻转         transforms.ToTensor(),         transforms.Normalize(mean=[0.56391764, 0.43714827, 0.4107524], std=[0.22986116, 0.21178758, 0.20076773]) # 正则化    ])

转载地址：http://jjfxf.baihongyu.com/