pytorch实现ResNet50模型（小白学习，详细讲解）

参考资料

作为新手学习难免会有很多不懂的地方，以下是我参考的一些资料：
ResNet源码：https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
源码讲解：https://www.jianshu.com/p/ec0967460d08
ResNet论文：https://arxiv.org/pdf/1512.03385.pdf
ResNet50复现：https://note.youdao.com/ynoteshare1/index.html?id=5a7dbe1a71713c317062ddeedd97d98e&type=note
ResNet50复现讲解：https://www.bilibili.com/video/BV1154y1S7WC?from=search&seid=8328821625196427671

代码实现

import torch
from torch import nn
class Bottleneck(nn.Module):
    #每个stage维度中扩展的倍数
    extention=4
    def __init__(self,inplanes,planes,stride,downsample=None):
        '''

        :param inplanes: 输入block的之前的通道数
        :param planes: 在block中间处理的时候的通道数
                planes*self.extention:输出的维度
        :param stride:
        :param downsample:
        '''
        super(Bottleneck, self).__init__()

        self.conv1=nn.Conv2d(inplanes,planes,kernel_size=1,stride=stride,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.conv3=nn.Conv2d(planes,planes*self.extention,kernel_size=1,stride=1,bias=False)
        self.bn3=nn.BatchNorm2d(planes*self.extention)

        self.relu=nn.ReLU(inplace=True)

        #判断残差有没有卷积
        self.downsample=downsample
        self.stride=stride

    def forward(self,x):
        #参差数据
        residual=x

        #卷积操作
        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=self.relu(out)

        #是否直连（如果Indentity blobk就是直连；如果Conv2 Block就需要对残差边就行卷积，改变通道数和size
        if self.downsample is not None:
            residual=self.downsample(x)

        #将残差部分和卷积部分相加
        out+=residual
        out=self.relu(out)

        return out


class ResNet(nn.Module):
    def __init__(self,block,layers,num_class):
        #inplane=当前的fm的通道数
        self.inplane=64
        super(ResNet, self).__init__()

        #参数
        self.block=block
        self.layers=layers

        #stem的网络层
        self.conv1=nn.Conv2d(3,self.inplane,kernel_size=7,stride=2,padding=3,bias=False)
        self.bn1=nn.BatchNorm2d(self.inplane)
        self.relu=nn.ReLU()
        self.maxpool=nn.MaxPool2d(kernel_size=3,stride=2,padding=1)

        #64,128,256,512指的是扩大4倍之前的维度，即Identity Block中间的维度
        self.stage1=self.make_layer(self.block,64,layers[0],stride=1)
        self.stage2=self.make_layer(self.block,128,layers[1],stride=2)
        self.stage3=self.make_layer(self.block,256,layers[2],stride=2)
        self.stage4=self.make_layer(self.block,512,layers[3],stride=2)

        #后续的网络
        self.avgpool=nn.AvgPool2d(7)
        self.fc=nn.Linear(512*block.extention,num_class)

    def forward(self,x):
        #stem部分：conv+bn+maxpool
        out=self.conv1(x)
        out=self.bn1(out)
        out=self.relu(out)
        out=self.maxpool(out)

        #block部分
        out=self.stage1(out)
        out=self.stage2(out)
        out=self.stage3(out)
        out=self.stage4(out)

        #分类
        out=self.avgpool(out)
        out=torch.flatten(out,1)
        out=self.fc(out)

        return out

    def make_layer(self,block,plane,block_num,stride=1):
        '''
        :param block: block模板
        :param plane: 每个模块中间运算的维度，一般等于输出维度/4
        :param block_num: 重复次数
        :param stride: 步长
        :return:
        '''
        block_list=[]
        #先计算要不要加downsample
        downsample=None
        if(stride!=1 or self.inplane!=plane*block.extention):
            downsample=nn.Sequential(
                nn.Conv2d(self.inplane,plane*block.extention,stride=stride,kernel_size=1,bias=False),
                nn.BatchNorm2d(plane*block.extention)
            )

        # Conv Block输入和输出的维度（通道数和size）是不一样的，所以不能连续串联，他的作用是改变网络的维度
        # Identity Block 输入维度和输出（通道数和size）相同，可以直接串联，用于加深网络
        #Conv_block
        conv_block=block(self.inplane,plane,stride=stride,downsample=downsample)
        block_list.append(conv_block)
        self.inplane=plane*block.extention

        #Identity Block
        for i in range(1,block_num):
            block_list.append(block(self.inplane,plane,stride=1))

        return nn.Sequential(*block_list)




resnet=ResNet(Bottleneck,[3,4,6,3],1000)
x=torch.randn(64,3,224,224)
X=resnet(x)
print(X.shape)

输出结果

torch.Size([64, 1000])

首先我们需要了解ResNet的原理和ResNet50的构造，如果参考我所上传的资料，完全可以搞懂。

代码讲解

这段代码是这个结构的复现。

self.conv1=nn.Conv2d(inplanes,planes,kernel_size=1,stride=stride,bias=False)
self.bn1=nn.BatchNorm2d(planes)

self.conv2=nn.Conv2d(planes,planes,kernel_size=3,stride=1,padding=1,bias=False)
elf.bn2=nn.BatchNorm2d(planes)

self.conv3=nn.Conv2d(planes,planes*self.extention,kernel_size=1,stride=1,bias=False)
self.bn3=nn.BatchNorm2d(planes*self.extention)

self.relu=nn.ReLU(inplace=True)

这是ResNet最核心的地方：

downsample是用来将残差数据和卷积数据的shape变的相同，可以直接进行相加操作。

 if self.downsample is not None:
            residual=self.downsample(x)

        #将残差部分和卷积部分相加
        out+=residual
        out=self.relu(out)

ResNet

总体结构

class ResNet(nn.Module):
    def __init__(self,block,layers,num_class):
        #inplane=当前的fm的通道数
        self.inplane=64
        super(ResNet, self).__init__()

        #参数
        self.block=block
        self.layers=layers

        #stem的网络层
        self.conv1=nn.Conv2d(3,self.inplane,kernel_size=7,stride=2,padding=3,bias=False)
        self.bn1=nn.BatchNorm2d(self.inplane)
        self.relu=nn.ReLU()
        self.maxpool=nn.MaxPool2d(kernel_size=3,stride=2,padding=1)

        #64,128,256,512指的是扩大4倍之前的维度，即Identity Block中间的维度
        self.stage1=self.make_layer(self.block,64,layers[0],stride=1)
        self.stage2=self.make_layer(self.block,128,layers[1],stride=2)
        self.stage3=self.make_layer(self.block,256,layers[2],stride=2)
        self.stage4=self.make_layer(self.block,512,layers[3],stride=2)

        #后续的网络
        self.avgpool=nn.AvgPool2d(7)
        self.fc=nn.Linear(512*block.extention,num_class)

    def forward(self,x):
        #stem部分：conv+bn+maxpool
        out=self.conv1(x)
        out=self.bn1(out)
        out=self.relu(out)
        out=self.maxpool(out)

        #block部分
        out=self.stage1(out)
        out=self.stage2(out)
        out=self.stage3(out)
        out=self.stage4(out)

        #分类
        out=self.avgpool(out)
        out=torch.flatten(out,1)
        out=self.fc(out)

        return out

    def make_layer(self,block,plane,block_num,stride=1):
        '''
        :param block: block模板
        :param plane: 每个模块中间运算的维度，一般等于输出维度/4
        :param block_num: 重复次数
        :param stride: 步长
        :return:
        '''
        block_list=[]
        #先计算要不要加downsample
        downsample=None
        if(stride!=1 or self.inplane!=plane*block.extention):
            downsample=nn.Sequential(
                nn.Conv2d(self.inplane,plane*block.extention,stride=stride,kernel_size=1,bias=False),
                nn.BatchNorm2d(plane*block.extention)
            )

        # Conv Block输入和输出的维度（通道数和size）是不一样的，所以不能连续串联，他的作用是改变网络的维度
        # Identity Block 输入维度和输出（通道数和size）相同，可以直接串联，用于加深网络
        #Conv_block
        conv_block=block(self.inplane,plane,stride=stride,downsample=downsample)
        block_list.append(conv_block)
        self.inplane=plane*block.extention

        #Identity Block
        for i in range(1,block_num):
            block_list.append(block(self.inplane,plane,stride=1))

        return nn.Sequential(*block_list)

这段代码实现了

 self.conv1=nn.Conv2d(3,self.inplane,kernel_size=7,stride=2,padding=3,bias=False)
        self.bn1=nn.BatchNorm2d(self.inplane)
        self.relu=nn.ReLU()
        self.maxpool=nn.MaxPool2d(kernel_size=3,stride=2,padding=1)

这段代码实现了

 #64,128,256,512指的是扩大4倍之前的维度，即Identity Block中间的维度
        self.stage1=self.make_layer(self.block,64,layers[0],stride=1)
        self.stage2=self.make_layer(self.block,128,layers[1],stride=2)
        self.stage3=self.make_layer(self.block,256,layers[2],stride=2)
        self.stage4=self.make_layer(self.block,512,layers[3],stride=2)

这段代码实现了

 self.avgpool=nn.AvgPool2d(7)
 self.fc=nn.Linear(512*block.extention,num_class)

make_layer
downsample是残差是否进行卷积的标识。

 downsample=None

 #残差进行卷积的条件
if(stride!=1 or self.inplane!=plane*block.extention):
	 downsample=nn.Sequential(
        nn.Conv2d(self.inplane,plane*block.extention,stride=stride,kernel_size=1,bias=False),
        nn.BatchNorm2d(plane*block.extention)
        )

Conv Block输入和输出的维度（通道数和size）是不一样的，所以不能连续串联，他的作用是改变网络的维度

conv_block=block(self.inplane,plane,stride=stride,downsample=downsample)

Identity Block 输入维度和输出（通道数和size）相同，可以直接串联，用于加深网络

#Identity Block
        for i in range(1,block_num):
            block_list.append(block(self.inplane,plane,stride=1))

网络结构