github博客传送门
csdn博客传送门
论文在此: Deep Residual Learning for Image Recognition
论文下载: https://arxiv.org/pdf/1512.03385.pdf
网络结构图:
Pytorch代码实现:
import torch.nn as nnimport mathdef conv3x3(in_planes, out_planes, stride=1): ???return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, ????????????????????padding=1, bias=False)class BasicBlock(nn.Module): ???expansion = 1 ???def __init__(self, inplanes, planes, stride=1, downsample=None): ???????super(BasicBlock, self).__init__() ???????self.conv1 = conv3x3(inplanes, planes, stride) ???????self.bn1 = nn.BatchNorm2d(planes) ???????self.relu = nn.ReLU(inplace=True) ???????self.conv2 = conv3x3(planes, planes) ???????self.bn2 = nn.BatchNorm2d(planes) ???????self.downsample = downsample ???????self.stride = stride ???def forward(self, x): ???????residual = x ???????out = self.conv1(x) ???????out = self.bn1(out) ???????out = self.relu(out) ???????out = self.conv2(out) ???????out = self.bn2(out) ???????if self.downsample is not None: ???????????residual = self.downsample(x) ???????out += residual ???????out = self.relu(out) ???????return outclass Bottleneck(nn.Module): ???expansion = 4 ???def __init__(self, inplanes, planes, stride=1, downsample=None): ???????super(Bottleneck, self).__init__() ???????self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) ???????self.bn1 = nn.BatchNorm2d(planes) ???????self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, ??????????????????????????????padding=1, bias=False) ???????self.bn2 = nn.BatchNorm2d(planes) ???????self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) ???????self.bn3 = nn.BatchNorm2d(planes * 4) ???????self.relu = nn.ReLU(inplace=True) ???????self.downsample = downsample ???????self.stride = stride ???def forward(self, x): ???????residual = x ???????out = self.conv1(x) ???????out = self.bn1(out) ???????out = self.relu(out) ???????out = self.conv2(out) ???????out = self.bn2(out) ???????out = self.relu(out) ???????out = self.conv3(out) ???????out = self.bn3(out) ???????if self.downsample is not None: ???????????residual = self.downsample(x) ???????out += residual ???????out = self.relu(out) ???????return outclass ResNet(nn.Module): ???def __init__(self, block, layers, num_classes=1000): ???????self.inplanes = 64 ???????super(ResNet, self).__init__() ???????self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, ??????????????????????????????bias=False) ???????self.bn1 = nn.BatchNorm2d(64) ???????self.relu = nn.ReLU(inplace=True) ???????self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) ???????self.layer1 = self._make_layer(block, 64, layers[0]) ???????self.layer2 = self._make_layer(block, 128, layers[1], stride=2) ???????self.layer3 = self._make_layer(block, 256, layers[2], stride=2) ???????self.layer4 = self._make_layer(block, 512, layers[3], stride=2) ???????self.avgpool = nn.AvgPool2d(7, stride=1) ???????self.fc = nn.Linear(512 * block.expansion, num_classes) ???????for m in self.modules(): ???????????if isinstance(m, nn.Conv2d): ???????????????n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels ???????????????m.weight.data.normal_(0, math.sqrt(2. / n)) ???????????elif isinstance(m, nn.BatchNorm2d): ???????????????m.weight.data.fill_(1) ???????????????m.bias.data.zero_() ???def _make_layer(self, block, planes, blocks, stride=1): ???????downsample = None ???????if stride != 1 or self.inplanes != planes * block.expansion: ???????????downsample = nn.Sequential( ???????????????nn.Conv2d(self.inplanes, planes * block.expansion, ?????????????????????????kernel_size=1, stride=stride, bias=False), ???????????????nn.BatchNorm2d(planes * block.expansion), ???????????) ???????layers = [] ???????layers.append(block(self.inplanes, planes, stride, downsample)) ???????self.inplanes = planes * block.expansion ???????for i in range(1, blocks): ???????????layers.append(block(self.inplanes, planes)) ???????return nn.Sequential(*layers) ???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.view(x.size(0), -1) ???????x = self.fc(x) ???????return xdef resnet18(**kwargs): ???model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs) ???return modeldef resnet34(**kwargs): ???model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs) ???return modeldef resnet50(**kwargs): ???model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs) ???return modeldef resnet101(**kwargs): ???model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs) ???return modeldef resnet152(**kwargs): ???model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs) ???return modelif __name__ == ‘__main__‘: ???# ‘ResNet‘, ‘resnet18‘, ‘resnet34‘, ‘resnet50‘, ‘resnet101‘, ‘resnet152‘ ???# Example ???net18 = resnet18() ???print(net18)ResNet(Pytroch实现)
原文地址：https://www.cnblogs.com/Mrzhang3389/p/10127223.html