Pytorch | 报错The given NumPy array is not writeable,and PyTorch does not support non-writeable tensor

Pytorch | 报错 The given NumPy array is not writeable,and PyTorch does not support non-writeable tensor

    • 1. 报错
    • 2. 解决方案
      • 2.1 查找 mnist.py 文件
      • 2.2 修改 mnist.py 文件
      • 2.3 问题解决

1. 报错

/home/dong/anaconda3/lib/python3.8/site-packages/torchvision/datasets/mnist.py:498: 
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  /pytorch/torch/csrc/utils/tensor_numpy.cpp:180.)
  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)

在这里插入图片描述

2. 解决方案

2.1 查找 mnist.py 文件

\qquad 根据报错:

/home/dong/anaconda3/lib/python3.8/site-packages/torchvision/datasets/mnist.py:498: 

可以知道mnist.py文件所在位置为/home/dong/anaconda3/lib/python3.8/site-packages/torchvision/datasets/
Pytorch | 报错The given NumPy array is not writeable,and PyTorch does not support non-writeable tensor_第1张图片

2.2 修改 mnist.py 文件

\qquad 修改mnist.py文件的第 498 498 498 行,删除copy=False
在这里插入图片描述

2.3 问题解决

Pytorch | 报错The given NumPy array is not writeable,and PyTorch does not support non-writeable tensor_第2张图片

你可能感兴趣的:(pytorch,pytorch,深度学习,python)