PyTorch 笔记（三）

Deep Learning with PyTorch: A 60 Minute Blitz

书接上回，了解了PyTorch的自动求导（autograd）过程后，尝试搭建简单的卷积神经网络；

这里直接摆上tutorials的CNN代码，并对其中一些点进行强调和补充；

import torch
import torch.nn as nn
import torch.nn.functional as F

1. torch.nn

torch.nn包中汇集了神经网络中常用的层模块：

---

卷积层(torch.nn.Conv2d)

CLASS  torch.nn.Conv2d

(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros')

Parameters

in_channels (int) – Number of channels in the input image

out_channels (int) – Number of channels produced by the convolution

kernel_size (int or tuple) – Size of the convolving kernel

stride (int or tuple, optional) – Stride of the convolution. Default: 1

padding (int or tuple, optional) – Zero-padding added to both sides of the input. Default: 0

padding_mode (string, optional) – zeros

dilation (int or