首先我們先來(lái)看看resnet34的模型圖

不同深度的ResNet.jpg

詳細(xì)的resnet34模型

resnet34詳細(xì)結(jié)構(gòu)

import torch.nn as nn
import torch
from torch.autograd import Variable as V

# 定義最基本的殘差模塊
class ResidualBlock(nn.Module):

    def __init__(self, in_channel, out_channel, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel, kernel_size=3,
                               stride=stride, padding=1)
        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
        # downsample定義的是否是虛線的殘差模塊冗荸，如果是那么在x = F(x) + x時(shí)覆致，
        # 輸入的x的維度和輸出的F(x)的維度就不相等，需要對(duì)輸入的x進(jìn)行下采樣操作望抽。
        if self.downsample is not None:
            identity = self.downsample(x)
        # 第一次卷積操作
        out = self.conv1(x)
        out = self.bn1(out)  # 批歸一化
        out = self.relu(out)  # 激活函數(shù)
        # 第二次卷積操作
        out = self.conv2(out)
        out = self.bn2(out)
        # 輸出的模型加上輸入的模型加矛，
        out += identity
        out = self.relu(out)
        return out

class ResNet34(nn.Module):
    def __init__(self,num_classes=1000):
        super(ResNet34,self).__init__()
        #對(duì)輸入的rgb三維的圖像進(jìn)行卷積
        self.conv1 = nn.Conv2d(in_channels=3,out_channels=64,kernel_size=7,stride=2,
                               padding=3,bias=False)

        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.max_pool = nn.MaxPool2d(kernel_size=3,stride=2,padding=1)

        # 定義各層的殘差結(jié)構(gòu)
        self.layer1 = self.make_layer(in_channel=64, out_channel=64,num_block=3,stride=1)
        self.layer2 = self.make_layer(in_channel=64, out_channel=128,num_block=4,stride=2)
        self.layer3 = self.make_layer(in_channel=128, out_channel=256,num_block=6,stride=2)
        self.layer4 = self.make_layer(in_channel=256, out_channel=512,num_block=3,stride=2)

        #上面輸出的結(jié)果是7x7x512的向量，對(duì)這個(gè)向量進(jìn)行平均池化的得到1x512的向量
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        # 定義線性層煤篙，讓512維的向量映射到1000維的維度上斟览。
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self,in_channel, out_channel,num_block,stride=1):
        downsample = None
        if stride==2:
            downsample = nn.Sequential(
                nn.Conv2d(in_channels=in_channel,out_channels=out_channel,
                          kernel_size=1,stride=2,bias=False),
                nn.BatchNorm2d(out_channel)
            )
        layers=[]
        # 每一層的第一個(gè)殘差模塊定義，需要定義downsample來(lái)確定是否需要對(duì)輸入做變換
        layers.append(ResidualBlock(in_channel=in_channel,out_channel=out_channel,
                                    downsample=downsample,stride=stride))
        #當(dāng)前層的后面幾個(gè)殘差模塊的輸入和輸出就是一樣的舰蟆。
        for i in range(1,num_block):
            layers.append(ResidualBlock(in_channel=out_channel,out_channel=out_channel,stride=1))

        return nn.Sequential(*layers)

    #定義正向傳播的過(guò)程
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.max_pool(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


model = ResNet34() # 創(chuàng)建ResNet殘差網(wǎng)絡(luò)結(jié)構(gòu)的模型的實(shí)例
input = V(torch.randn(1,3,224,224)) # 創(chuàng)建輸入數(shù)據(jù)趣惠，3表示的rgb三維圖像
output = model(input) # 把數(shù)據(jù)傳入模型，結(jié)果就是處理以后的數(shù)據(jù)
print(output.size()) # 輸出運(yùn)行的結(jié)果

輸出結(jié)果

D:\python3\anaconda\envs\pytorch\python.exe D:/python3/PythonProgram/smartAbulm/resnet34.py
torch.Size([1, 1000])

Process finished with exit code 0