pytorch复现ResNet
import torch
from torch import nn
# layer 18 & 34
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channel)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channel)
self.downsample = downsample
def forward(self, x):
identity = x
if self.downsample is not None:
identity = self.downsample(x)
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out += identity
out = self.relu(out)
return out
# layer: 50 & 101 & 152
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, in_channel, out_channel, stride=1, downsample=None):
super(Bottleneck,self).__init__()
self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
kernel_size=1, stride=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channel)
self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
kernel_size=3,stride=stride,bias=False)
self.bn2= nn.BatchNorm2d(out_channel)
self.conv3 = nn.Conv2d(in_channels=out_channel,out_channels=out_channel*self.expansion,
kernel_size=1, stride=1, bias=False)
self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
self.relu = nn.ReLU()
self.downsample = downsample
def forward(self, x):
identity = x
if self.downsample is not None:
identity = self.downsample(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)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, block_num, num_classes=1000, include_top=True):
super(ResNet, self).__init__()
self.in_channel = 64
self.block = block
self.block_num = block_num
self.include_top = include_top
#3 代表RGB初始图像的通道为3
self.conv1 = nn.Conv2d(3,self.in_channel, kernel_size=7, stride=2,
padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(self.in_channel)
self.relu = nn.ReLU()
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, block_num[0], stride=1)
self.layer2 = self._make_layer(block, 128, block_num[1], stride=2)
self.layer3 = self._make_layer(block, 256, block_num[2], stride=2)
self.layer4 = self._make_layer(block, 512, block_num[3], stride=2)
if self.include_top:
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')
def _make_layer(self, block, channel, block_num, stride=1):
#18 & 34
downsample = None
#50 & 101 & 152 :对block中的identity进行操作
if stride != 1 or self.in_channel != channel*block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.in_channel, channel*block.expansion, stride=stride,
kernel_size=1, bias=False),
nn.BatchNorm2d(channel*block.expansion))
layers = []
conv_block = block(self.in_channel, channel,stride=stride, downsample=downsample)
layers.append(conv_block)
self.in_channel = channel * block.expansion
for _ in range(1,block_num):
layers.append(block(self.in_channel, channel))
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)
if self.include_top:
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
def resnet34(num_classes=1000, include_top=True):
return ResNet(BasicBlock, [3,4,6,3], num_classes=num_classes, include_top=True)
def resnet101(num_classes=1000, include_top=True):
return ResNet(Bottleneck, [3,4,23,3], num_classes=num_classes, include_top=True)
测试
resnet=ResNet(BasicBlock,[3,4,6,3],1000)
x=torch.randn(64,3,224,224)
X=resnet(x)
print(X.shape)
