请问有大佬可以帮忙解释一下P188页model.train(False)和model.train(True)的区别及这样设置的原因吗？感激

你好, P173, 使用github上的代码, 依然报错:

images, labels = next(iter(data_loader_train))

File “/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py”, line 615, in next
batch = self.collatefn([self.dataset[i] for i in indices])
File “/usr/local/lib/python2.7/dist-packages/torchvision/datasets/mnist.py”, line 95, in getitem
img = self.transform(img)
File “/usr/local/lib/python2.7/dist-packages/torchvision/transforms/transforms.py”, line 60, in call
img = t(img)
File “/usr/local/lib/python2.7/dist-packages/torchvision/transforms/transforms.py”, line 163, in call
return F.normalize(tensor, self.mean, self.std, self.inplace)
File “/usr/local/lib/python2.7/dist-packages/torchvision/transforms/functional.py”, line 208, in normalize
tensor.sub(mean[:, None, None]).div_(std[:, None, None])
RuntimeError: output with shape [1, 28, 28] doesn’t match the broadcast shape [3, 28, 28]

你好, 在P173页, “images, labels = next(iter(data_loader_train))” 会报错, 请问该怎么解决

File “./ch6.4.1.py”, line 67, in <module>
images, labels = next(iter(dataloadertrain))
File “/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py”, line 615, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File “/usr/local/lib/python2.7/dist-packages/torchvision/datasets/mnist.py”, line 95, in __getitem
img = self.transform(img)
TypeError: ‘module’ object is not callable

勘误 p145 语法不推荐了

a = torch.range(1, 20, 1)
print(a)

UserWarning: torch.range is deprecated in f**or of torch.arange and will be removed in 0.5. Note that arange generates values in [start; end), not [start; end].
  """Entry point for launching an IPython kernel.

p126 勘误提交

print("Matrix2: a * b =", c)
# alter
print("Matrix2: a * b =", d)