与ResNet18 和 34不一样的是，50，101和152使用了bottleneck结构而不是basic block。在bottleneck中，对channel进行了缩放。
具体的图解可以参考ResNet50网络结构图及结构详解，在这篇文章中，BTNK1对应代码中 bottleneck downsampling = True的情况，BTNK2对应downsampling = False的情况。
import torch
import torch.nn as nn
import torchvision
import numpy as np
from torchsummary import summary
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
__all__ = ['ResNet50', 'ResNet101', 'ResNet152']
def Conv1(in_planes, places, stride=2):
return nn.Sequential(
nn.Conv2d(in_channels=in_planes, out_channels=places, kernel_size=7, stride=stride, padding=3, bias=False),
nn.BatchNorm2d(places),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
)
class Bottleneck(nn.Module):
def __init__(self, in_places, places, stride=1, downsampling=False, expansion=4):
super(Bottleneck, self).__init__()
self.expansion = expansion
self.downsampling = downsampling
self.bottleneck = nn.Sequential(
nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False),
nn.BatchNorm2d(places),
nn.ReLU(inplace=True),
nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
nn.BatchNorm2d(places),
nn.ReLU(inplace=True),
nn.Conv2d(in_channels=places, out_channels=places*self.expansion, kernel_size=1, stride=1, bias=False),
nn.BatchNorm2d(places*self.expansion)
)
if self.downsampling:
self.downsample = nn.Sequential(
nn.Conv2d(in_channels=in_places, out_channels=places*self.expansion, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(places*self.expansion)
)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
residual = x
out = self.bottleneck(x)
if self.downsampling:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, blocks, num_classes = 1000, expansion = 4):
super(ResNet, self).__init__()
self.expansion = expansion
self.conv1 = Conv1(in_planes=3, places=64)
self.layer1 = self.make_layer(in_places=64, places=64, block=blocks[0], stride=1)
self.layer2 = self.make_layer(in_places=256, places=128, block=blocks[1], stride=2)
self.layer3 = self.make_layer(in_places=512, places=256, block=blocks[2], stride=2)
self.layer4 = self.make_layer(in_places=1024, places=512, block=blocks[3], stride=2)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.fc = nn.Linear(2048, 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, in_places, places, block, stride):
layers = []
layers.append(Bottleneck(in_places, places, stride, downsampling=True))
for i in range(1, block):
layers.append(Bottleneck(in_places=places*self.expansion, places=places))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(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
def ResNet50():
return ResNet([3,4,6,3])
def ResNet101():
return ResNet([3,4,23,3])
def ResNet152():
return ResNet([3,8,36,3])
if __name__=='__main__':
device = torch.device("cuda" if torch.cuda.is_available() else 'cpu')
model = ResNet50()
model = model.to(device)
summary(model, (3,224,224))
input = torch.randn(1,3,224,224).cuda()
out = model(input)
print(out.shape)
使用torchsummary打印网络，对于ResNet-50:
================================================================
Total params: 25,557,032
Trainable params: 25,557,032
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 286.56
Params size (MB): 97.49
Estimated Total Size (MB): 384.62
----------------------------------------------------------------