pytorch笔记

目录

• 参考资料
  • 文档
  • 视频
• 一些坑
  • 1、加载Mnist数据集的坑
  • 2、

参考资料

文档

https://github.com/jcjohnson/pytorch-examples

https://pytorch.org/docs/stable/index.html

（pytorch中文官方文档）https://pytorch-cn.readthedocs.io/zh/latest/package_references/torch-optim/

视频

https://www.bilibili.com/video/BV1tk4y1q7Jv/?spm_id_from=333.788&vd_source=3f409e335d99edd58fc22f4c59f6ae9e

一些坑

1、加载Mnist数据集的坑

print("下载训练集中...")
train_set = torchvision.datasets.MNIST(".\data", train=True, download=True, transform=pipeline)
print("下载测试集中...")
test_set = torchvision.datasets.MNIST(".\data", train=False, download=True, transform=pipeline)

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)

解决方法：直接定位到错误的地方，删掉, copy=False，就正常了

2、