### ResNet18架构详解
#### 基本模块定义
ResNet通过引入残差块解决了深层神经网络训练困难的问题。对于ResNet18而言，其基础构建单元由两个卷积层组成，每个卷积层后面跟着批量归一化(Batch Normalization)操作和ReLU激活函数[^1]。
```python
import torch.nn as nn
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = nn.ReLU()(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = nn.ReLU()(out)
return out
```
#### 整体网络结构描述
整个ResNet18由四个阶段构成，每个阶段包含多个相同的残差块。输入图片经过初始的7×7卷积核处理后进入这些阶段，在最后一个全连接层之前还有一层全局平均池化(Global Average Pooling)[^3]。
- 初始层：采用较大的步幅(stride=2)，并设置padding使得输出大小减半。
- 阶段1至4：分别含有两次、两次、两次、两次迭代的基本block；其中除了第一个stage外其他stages的第一个block会改变feature map size (stride=2).
```python
class ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=10):
super(ResNet, self).__init__()
self.in_planes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.linear = nn.Linear(512 * block.expansion, num_classes)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride))
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def ResNet18():
return ResNet(BasicBlock, [2, 2, 2, 2])
```
#### 工作流程概述
当一张RGB三通道彩色图像作为输入传入到ResNet18时，该图像会被逐步缩小尺寸的同时增加特征维度直到最终被映射成固定长度向量表示形式用于分类或其他下游任务预测[^2].
扫一扫
6078
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
