PyTorch从零开始实现ResNet

代码实现

本文实现 ResNet原论文 Deep Residual Learning for Image Recognition 中的50层，101层和152层残差连接。

代码中使用基础残差块这个概念，这里的基础残差块指的是上图中红色矩形圈出的内容：从上到下分别使用3, 4, 6, 3个基础残差块，每个基础残差块由三个卷积层组成，核大小分别为1x1, 3x3, 1x1 。

残差连接的结构

复现代码如下：

import torch
import torch.nn as nn# 基础残差块，后面ResNet要多次重复使用该块
class block(nn.Module):def __init__(self, in_channels, out_channels, identity_downsample=None, stride=1):super(block, self).__init__()self.expansion = 4  self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)self.bn1 = nn.BatchNorm2d(out_channels)self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride, padding=1)self.bn2 = nn.BatchNorm2d(out_channels)self.conv3 = nn.Conv2d(out_channels, out_channels*self.expansion, kernel_size=1, stride=1, padding=0)self.bn3 = nn.BatchNorm2d(out_channels*self.expansion)self.relu = nn.ReLU()self.identity_downsample = identity_downsampledef forward(self, x):identity = xx = self.conv1(x)x = self.bn1(x)x = self.relu(x)x = self.conv2(x)x = self.bn2(x)x = self.relu(x)x = self.conv3(x)x = self.bn3(x)if self.identity_downsample is not None:identity = self.identity_downsample(identity)x += identityx = self.relu(x)return xclass ResNet(nn.Module):def __init__(self, block, layers, image_channels, num_classes):super(ResNet, self).__init__()# 初始化的层self.in_channels = 64self.conv1 = nn.Conv2d(image_channels, 64, kernel_size=7, stride=2, padding=3)self.bn1 = nn.BatchNorm2d(64)self.relu = nn.ReLU()self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)# ResNet layersself.layer1 = self._make_layer(block, layers[0], out_channels=64, stride=1)self.layer2 = self._make_layer(block, layers[1], out_channels=128, stride=2)self.layer3 = self._make_layer(block, layers[2], out_channels=256, stride=2)self.layer4 = self._make_layer(block, layers[3], out_channels=512, stride=2)self.avgpool = nn.AdaptiveAvgPool2d((1, 1))self.fc = nn.Linear(512*4, num_classes)def forward(self, x):x = self.conv1(x)x = self.bn1(x)x = self.relu(x)x = self.maxpool(x)x = self.layer1(x)x = self.layer2(x)x = self.layer3(x)x = self.layer4(x)x = self.avgpool(x)x = x.reshape(x.shape[0], -1)x = self.fc(x)return x# 核心函数：调用block基础残差块，构造ResNet的每一层def _make_layer(self, block, num_residual_blocks, out_channels, stride):identity_downsample = Nonelayers = []if stride != 1 or self.in_channels != out_channels * 4:identity_downsample = nn.Sequential(nn.Conv2d(self.in_channels, out_channels*4, kernel_size=1,stride=stride),                                               nn.BatchNorm2d(out_channels*4))layers.append(block(self.in_channels, out_channels, identity_downsample, stride))self.in_channels = out_channels * 4for i in range(num_residual_blocks - 1):layers.append(block(self.in_channels, out_channels)) # 256 -> 64, 64*4(256) againreturn nn.Sequential(*layers)# 构造ResNet50层：默认图像通道3，分类类别为1000
def resnet50(img_channels=3, num_classes=1000):return ResNet(block, [3, 4, 6, 3], img_channels, num_classes)# 构造ResNet101层  
def resnet101(img_channels=3, num_classes=1000):return ResNet(block, [3, 4, 23, 3], img_channels, num_classes)# 构造ResNet152层  
def resnet152(img_channels=3, num_classes=1000):return ResNet(block, [3, 8, 36, 3], img_channels, num_classes)# 测试输出y的形状是否满足1000类
def test():net = resnet152()x = torch.randn(2, 3, 224, 224)y = net(x)print(y.shape) # [2, 1000]test()

参考

[1] Deep Residual Learning for Image Recognition
[2] https://www.youtube.com/watch?v=DkNIBBBvcPs&list=PLhhyoLH6IjfxeoooqP9rhU3HJIAVAJ3Vz&index=19