ResNet34之pytorch实现

我的实现：

import torch
from torch import nn
#因为ResNet34包含重复的单元，故用ResidualBlock类来简化代码
class ResidualBlock(nn.Module):
def __init__(self,inchannel,outchannel,stride,shortcut=None):
super(ResidualBlock,self).__init__()
self.basic = nn.Sequential(
nn.Conv2d(inchannel,outchannel,3,stride,1,bias=False),#要采样的话在这里改变stride
nn.BatchNorm2d(outchannel),#批处理正则化
nn.ReLU(inplace=True),#激活
nn.Conv2d(outchannel,outchannel,3,1,1,bias=False),#采样之后注意保持feature map的大小不变
nn.BatchNorm2d(outchannel),
)
self.shortcut = shortcut

def forward(self,x):
out = self.basic(x)
residual = x if self.shortcut is None else self.shortcut(x)#计算残差
out += residual
return nn.ReLU(inplace=True)(out)#注意激活
#ResNet类
class ResNet(nn.Module):
def __init__(self):
super(ResNet,self).__init__()
self.pre = nn.Sequential(
nn.Conv2d(3,64,7,2,3,bias=False),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True),
nn.MaxPool2d(3,2,1),
)#开始的部分
self.body = self.makelayers([3,4,6,3])#具有重复模块的部分
self.classifier = nn.Linear(512,1000)#末尾的部分

def makelayers(self,blocklist):#注意传入列表而不是解列表
self.layers = []
for index,blocknum in enumerate(blocklist):
if index != 0:
shortcut = nn.Sequential(
nn.Conv2d(64*2**(index-1),64*2**index,1,2,bias=False),
nn.BatchNorm2d(64*2**index)
)#使得输入输出通道数调整为一致
self.layers.append(ResidualBlock(64*2**(index-1),64*2**index,2,shortcut))#每次变化通道数时进行下采样
for i in range(0 if index==0 else 1,blocknum):
self.layers.append(ResidualBlock(64*2**index,64*2**index,1))
return nn.Sequential(*self.layers)

def forward(self,x):
x = self.pre(x)
x = self.body(x)
x = nn.AvgPool2d(7)(x)#kernel_size为7是因为经过多次下采样之后feature map的大小为7*7，即224->112->56->28->14->7
x = x.view(x.size(0),-1)
x = self.classifier(x)
return x

net = ResNet()
print(net)

input = torch.autograd.Variable(t.randn(1,3,224,224))
print(net(input))

输出：

ResNet(
(pre): Sequential(
(0): Conv2d (3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): MaxPool2d(kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1))
)
(body): Sequential(
(0): ResidualBlock(
(basic): Sequential(
(0): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
)
)
(1): ResidualBlock(
(basic): Sequential(
(0): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
)
)
(2): ResidualBlock(
(basic): Sequential(
(0): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
)
)
(3): ResidualBlock(
(basic): Sequential(
(0): Conv2d (64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
(shortcut): Sequential(
(0): Conv2d (64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
)
(4): ResidualBlock(
(basic): Sequential(
(0): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
)
(5): ResidualBlock(
(basic): Sequential(
(0): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
)
(6): ResidualBlock(
(basic): Sequential(
(0): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
)
(7): ResidualBlock(
(basic): Sequential(
(0): Conv2d (128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
(shortcut): Sequential(
(0): Conv2d (128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
)
(8): ResidualBlock(
(basic): Sequential(
(0): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
)
(9): ResidualBlock(
(basic): Sequential(
(0): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
)
(10): ResidualBlock(
(basic): Sequential(
(0): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
)
(11): ResidualBlock(
(basic): Sequential(
(0): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
)
(12): ResidualBlock(
(basic): Sequential(
(0): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)

4000
)
(13): ResidualBlock(
(basic): Sequential(
(0): Conv2d (256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
)
(shortcut): Sequential(
(0): Conv2d (256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
)
)
(14): ResidualBlock(
(basic): Sequential(
(0): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
)
)
(15): ResidualBlock(
(basic): Sequential(
(0): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
(2): ReLU(inplace)
(3): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
)
)
)
(classifier): Linear(in_features=512, out_features=1000)
)
Variable containing:
-0.3515 -0.2473  0.1059  ...  -0.0547 -0.3626  0.5740
[torch.FloatTensor of size 1x1000]

源码实现：

from torchvision import models
print(models.resnet34())

输出：

ResNet(
(conv1): Conv2d (3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(maxpool): MaxPool2d(kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), dilation=(1, 1))
(layer1): Sequential(
(0): BasicBlock(
(conv1): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
)
(1): BasicBlock(
(conv1): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
)
(2): BasicBlock(
(conv1): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)
)
)
(layer2): Sequential(
(0): BasicBlock(
(conv1): Conv2d (64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(downsample): Sequential(
(0): Conv2d (64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
)
(1): BasicBlock(
(conv1): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
(2): BasicBlock(
(conv1): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
(3): BasicBlock(
(conv1): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)
)
)
(layer3): Sequential(
(0): BasicBlock(
(conv1): Conv2d (128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(downsample): Sequential(
(0): Conv2d (128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
)
(1): BasicBlock(
(conv1): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
(2): BasicBlock(
(conv1): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
(3): BasicBlock(
(conv1): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
(4): BasicBlock(
(conv1): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
(5): BasicBlock(
(conv1): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True)
)
)
(layer4): Sequential(
(0): BasicBlock(
(conv1): Conv2d (256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
(downsample): Sequential(
(0): Conv2d (256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
)
)
(1): BasicBlock(
(conv1): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
)
(2): BasicBlock(
(conv1): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
(relu): ReLU(inplace)
(conv2): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True)
)
)
(avgpool): AvgPool2d(kernel_size=7, stride=1, padding=0, ceil_mode=False, count_include_pad=True)
(fc): Linear(in_features=512, out_features=1000)
)