卷积神经网络之-Alexnet学习

Alexnet

Alexnet创新点

不足

代码实现

import torch.nn as nn
import torch
import torch.nn.functioanl as F

class AlexNet(nn.Module):
	def __init__(self,num_class=1000,init_weights=False):
		super(AlexNet,self).__init__()
		self.features=nn.Sequential(
		#nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=2),input(3,224,224) output(96,55,55)原文中是96，但是作者使用的数据集比较小所以卷积核个数减半
		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),     # output[128, 13, 13]
        nn.ReLU(inplace=True),
        nn.MaxPool2d(kernel_size=3, stride=2),             # output[128, 6, 6]
            )
        
        #全连接层
        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),#输出是类别的个数
        )
        
        #init_weights=true,ture需要初始化权重
        if init_weights:
            self._initialize_weights()
    
    #正向传播过程
    def forward(self, x):
        x = self.features(x)
        x = torch.flatten(x, start_dim=1)#展平
        x = self.classifier(x)
        return x
     
    # 初始化权重函数
    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                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)