一、介绍
残差网络(ResNet)是由何凯明等人提出的一种深层神经网络。ResNet在网络加深的同时,可以解决由梯度消失或爆炸而导致的精度下降问题。其中resnet34是ResNet中比较简单的一个版本,只有34层深度。ResNet34在计算机视觉领域应用广泛,如图像分类、物体检测和分割等。
二、原理
ResNet的主要思想是通过引入残差模块(residual block)来加深网络,残差模块和普通的卷积模块相比,其主要区别在于在每一个卷积层之后都有直接的连接(shortcut connection)来 bypass 原本的卷积输出。
这种直接连接可以理解为是一条跨层连接的捷径,保证了网络的信息流畅性。用公式表示如下:
其中H(X)代表residual block输出,F(X)代表输入经过两个卷积之后的结果,W是权重,b是偏差(bias),后面的权重是可学习的。 X+H(X) 是shortcut connection。
ResNet 使用的 residual block 是基于两个 3x3 卷积层和一个跨层连接的模块,我们称之为 Residual Unit 。如下图所示:
其中的 shortcut connection,即跨层连接,可以有两种形式:addition 和 projection shortcut。
addition shortcut 如图:
而 projection shortcut 如图:
三、代码实现
下面是使用PyTorch实现resnet34的代码。首先要导入必要的库:
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
import torch.nn.functional as F
import torch
__all__ = ['ResNet', 'resnet34']
model_urls = {
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.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)
def conv1x1(in_planes, out_planes, stride=1):
"1x1 convolution"
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, 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):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
# 判断是否需要downsample操作
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False):
super(ResNet, self).__init__()
self.inplanes = 64
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.AdaptiveAvgPool2d((1, 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.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# 零初始化最后一层的权重
if zero_init_residual:
for m in self.modules():
if isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
elif isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ 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 = torch.flatten(x, 1)
x = self.fc(x)
return x
def _resnet(arch, block, layers, pretrained, progress, **kwargs):
model = ResNet(block, layers, **kwargs)
if pretrained:
state_dict = model_zoo.load_url(model_urls[arch], progress=progress)
model.load_state_dict(state_dict)
return model
def resnet34(pretrained=False, progress=True, **kwargs):
return _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress, **kwargs)
四、应用与拓展
ResNet的应用非常广泛,除了在计算机视觉领域,也被用作自然语言处理和语音识别等其他领域。除了resnet34,还有resnet50、resnet101等版本,可以根据任务的复杂度选择适合的版本。在实际应用中,可以通过fine-tuning、数据增强等方法对ResNet进行拓展,提高其在特定任务上的表现。