多分类实践遇到的问题

1.不能导入pillow_version

Traceback (most recent call last):
  File "D:\code\pythonProject2023\pytorch\MulClass.py", line 3, in <module>
    from torchvision import transforms              # 图像原始处理的包
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torchvision\__init__.py", line 2, in <module>
    from torchvision import datasets
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torchvision\datasets\__init__.py", line 9, in <module>
    from .fakedata import FakeData
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torchvision\datasets\fakedata.py", line 3, in <module>
    from .. import transforms
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torchvision\transforms\__init__.py", line 1, in <module>
    from .transforms import *
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torchvision\transforms\transforms.py", line 17, in <module>
    from . import functional as F
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torchvision\transforms\functional.py", line 5, in <module>
    from PIL import Image, ImageOps, ImageEnhance, PILLOW_VERSION
ImportError: cannot import name 'PILLOW_VERSION' from 'PIL' (D:\install\anaconda\envs\pytorch\lib\site-packages\PIL\__init__.py)

原因：pillow版本过高
解决：修改模块文件（https://blog.csdn.net/BBJG_001/article/details/104369234）

from PIL import Image, ImageOps, ImageEnhance, __version__

在Pycharm中修改时会眺出警告，确认就能修改了

但是只有这样还是不够的，因为在下面的程序中用到的还是PILLOW_VERSION这个变量，然后我又做了这样一个操作

PILLOW_VERSION=__version__

注意这一句要放在所有用到PILLOW_VERSION变量的语句之前，我是把这句紧跟在了了所有导入操作之后

2.该张量含有多个（1个以上不含1个）boolean值，是不明确的，即无法比较

Traceback (most recent call last):
  File "D:\code\pythonProject2023\pytorch\MulClass.py", line 82, in <module>
    train(epoch)
  File "D:\code\pythonProject2023\pytorch\MulClass.py", line 59, in train
    loss = criterion(outputs, target)
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torch\nn\modules\loss.py", line 911, in __init__
    super(CrossEntropyLoss, self).__init__(weight, size_average, reduce, reduction)
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torch\nn\modules\loss.py", line 19, in __init__
    super(_WeightedLoss, self).__init__(size_average, reduce, reduction)
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torch\nn\modules\loss.py", line 12, in __init__
    self.reduction = _Reduction.legacy_get_string(size_average, reduce)
  File "D:\install\anaconda\envs\pytorch\lib\site-packages\torch\nn\_reduction.py", line 36, in legacy_get_string
    if size_average and reduce:
RuntimeError: bool value of Tensor with more than one value is ambiguous

原因：loss函数申明没有加括号
修改：criterion = torch.nn.CrossEntropyLoss()

3.整数型没有属性view
AttributeError: ‘int’ object has no attribute ‘view’
原因：不确定
修改：将测试从

for data in enumerate(train_loader, 0):

改为

for data in test_loader: