Pytorch搭建AlexNet网络

AlexNet详解

model.py

'''
python3.7
-*- coding: UTF-8 -*-
@Project -> File   ：pythonProject -> model
@IDE    ：PyCharm
@Author ：YangShouWei
@USER: 296714435
@Date   ：2022/2/19 18:20:28
@LastEditor:
'''

import torch
import torch.nn as nn


class AlexNet(nn.Module):
    def __init__(self,num_classes=1000, init_weights=False):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2), # input[3, 224,224] output[48, 55, 55]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2), # output[48,27, 27]
            nn.Conv2d(48, 128, kernel_size=5, padding=2), # output [128, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 13, 13]
            nn.Conv2d(128, 192,kernel_size=3,padding=1), # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 192,kernel_size=3,padding=1), # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 128,kernel_size=3,padding=1), # [128, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 6, 6]
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(128 * 6 * 6, 2048),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(2048, 2048),
            nn.ReLU(inplace=True),
            nn.Linear(2048, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self,x):
        x = self.features(x)
        x = torch.flatten(x, start_dim=1) # 展平操作，[batch，channel，Height，Width] 参数1表示从channel开始，把C，H，W三个维度展成一维向量。不去改动batch
        x = self.classifier(x)
        return x

    def _initialize_weights(self):
        for m in self.modules(): # self.modules 继承nn.Modules, 返回一个层结构迭代器，里面包含了上面网络定义中的每一层结构
            if isinstance(m, nn.Conv2d): # 遍历到自己定义的卷积层以后就进行卷积初始化
                nn.init.kaiming_normal_(m.weight,mode='fan_out',nonlinearity='relu') # 对卷积权重进行初始化。
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)