地址:
贴代码
- import torch.nn as nn
- import torch.utils.model_zoo as model_zoo
- __all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
- 'resnet152']
- model_urls = {
- 'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
- 'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
- 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
- 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
- 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
- }
- def conv3x3(in_planes, out_planes, stride=1):
- """3x3 convolution with padding"""
- return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
- padding=1, bias=False)
- 首先导入 torch.nn,pytorch 的网络模块多在此内, 然后导入 model_zoo, 作用是根据下面的 model_urls 里的地址加载网络预训练权重. 后面还对 conv2d 进行了一次封装, 个人觉得有些多余.
- 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 out
- 这里定义了最重要的残差模块, 这个是基础版, 由两个叠加的 3x3 卷积组成, 与之相对应的 bottleneck 模块在下面定义
- class 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 * self.expansion, kernel_size=1, bias=False)
- self.bn3 = nn.BatchNorm2d(planes * self.expansion)
- 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 out
- 与基础版的不同之处只在于这里是三个卷积, 分别是 1x1,3x3,1x1, 分别用来压缩维度, 卷积处理, 恢复维度, 这里我对 inplane,plane,expansion 的含义不甚明了, inplane 是输入的通道数, plane 是输出的通道数, expansion 是什么, 类似于 wide resnet 的宽度么? 接着就是网络主体了.
- class 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):
- nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
- elif isinstance(m, nn.BatchNorm2d):
- nn.init.constant_(m.weight, 1)
- nn.init.constant_(m.bias, 0)
- 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 x
- resnet 共有五个阶段, 其中第一阶段为一个 7x7 的卷积处理, stride 为 2, 然后经过池化处理, 此时特征图的尺寸已成为输入的 1/4, 接下来是四个阶段, 也就是代码中的 layer1,layer2,layer3,layer4. 这里用 make_layer 函数产生四个 layer, 需要用户输入每个 layer 的 block 数目 (即 layers 列表) 以及采用的 block 类型(基础版还是 bottleneck 版)
- 接下来就是 resnet18 等几个模型的类定义
- def resnet18(pretrained=False, **kwargs):
- """Constructs a ResNet-18 model.
- Args:
- pretrained (bool): If True, returns a model pre-trained on ImageNet
- """
- model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
- if pretrained:
- model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
- return model
- def resnet34(pretrained=False, **kwargs):
- """Constructs a ResNet-34 model.
- Args:
- pretrained (bool): If True, returns a model pre-trained on ImageNet
- """
- model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
- if pretrained:
- model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
- return model
- def resnet50(pretrained=False, **kwargs):
- """Constructs a ResNet-50 model.
- Args:
- pretrained (bool): If True, returns a model pre-trained on ImageNet
- """
- model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
- if pretrained:
- model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
- return model
- def resnet101(pretrained=False, **kwargs):
- """Constructs a ResNet-101 model.
- Args:
- pretrained (bool): If True, returns a model pre-trained on ImageNet
- """
- model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
- if pretrained:
- model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
- return model
- def resnet152(pretrained=False, **kwargs):
- """Constructs a ResNet-152 model.
- Args:
- pretrained (bool): If True, returns a model pre-trained on ImageNet
- """
- model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
- if pretrained:
- model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
- return model
这里比较简单, 就是调用上面 ResNet 对象, 输入 block 类型和 block 数目, 这里可以看到 resnet18 和 resnet34 用的是基础版 block, 因为此时网络还不深, 不太需要考虑模型的效率, 而当网络加深到 52,101,152 层时则有必要引入 bottleneck 结构, 方便模型的存储和计算. 另外是否加载预训练权重是可选的, 具体就是调用 model_zoo 加载指定链接地址的序列化文件, 反序列化为权重文件.
来源: http://www.bubuko.com/infodetail-2828092.html