The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors.

导入MNIST数据集时出错

UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  ..\torch\csrc\utils\tensor_numpy.cpp:180.)
  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)

解决办法:

找到torchvision包的位置,然后在torchvision/datasets/MNIST.py里找到

return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)

这一行,把其中的copy=False删掉,得到

return torch.from_numpy(parsed.astype(m[2])).view(*s)

源解决方法链接:https://github.com/pytorch/vision/pull/4184

你可能感兴趣的:(深度学习,计算机视觉,pytorch,深度学习)