ResNet及其Pytorch实现

由于梯度消失问题，导致神经网络深度加深之后更难训练以及性能下降。

# KeyPoint

* 引入 identity shortcut connection

最有名的结构：

![resnet](https://leanote.com/api/file/getImage?fileId=5d80e4d7ab64417b54003485)

* 有论文提到说，将resnet的一个块改为如下架构能够在上千层深的网络中，得到更好的训练效果。

![title](https://leanote.com/api/file/getImage?fileId=5d80e809ab64417956003490)

* 基于resnet基础上，有了ResNeXt，并联了多个块。

![title](https://leanote.com/api/file/getImage?fileId=5d80e841ab6441795600349e)

* DenseNet，多个跨层链接，但这样的多个跨层链接多了效果并不好，于是分成多个块。

![title](https://leanote.com/api/file/getImage?fileId=5d80e887ab64417b5400354a)

![title](https://leanote.com/api/file/getImage?fileId=5d80e8ddab64417b54003558)

* ResNet训练时间较长，按一定概率训练时直接drop掉一个块，会得到更少性能和使用更少时间。

![title](https://leanote.com/api/file/getImage?fileId=5d80e920ab644179560034c6)

* 有实验表明，ResNet 中不同路径的集合有类似集成的行为。有实验表示101层的ResNet大多数贡献来自于长度为 9 到 18 的路径，但它们只占所有路径的一小部分。表明 ResNet 并没有解决长路径的梯度消失问题，而是通过缩短有效路径的长度训练非常深层的 ResNet 网络。

# 代码

```python
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)
                     
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

class Bottleneck(nn.Module): # 残差块
    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)# 这样放大有什么用呢
        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
        
        
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
```

wuvin

导航

最近发表

友情链接