Python深度学习基于PyTorch(6.1 视觉处理基础/卷积神经网络简介 )

 

import torch
import torch.nn as nn
import torch.nn.functional as F


device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

class CNNNet(nn.Module):
    def __init__(self):
        super(CNNNet,self).__init__()
            self.conv1 = nn.Conv2d(in_channels=3,out_channels=16,kernel_size=5,stride=1)
            self.pool1 = nn.MaxPool2d(kernel_size=2,stride=2)
            
            self.conv2 = nn.Conv2d(in_channels=16,out_channels=36,kernel_size=3,stride=1)
            self.pool2 = nn.MaxPool2d(kernel_size=2,stride=2)
            
            self.fc1 = nn.Linear(1296,128)
            self.fc2 = nn.Linear(128,10)
            
    def forward(self,x):
        x = self.pool1(F.relu(self.conv1(x)))#第一层卷积层后再进行池化操作
        x = self.pool2(F.relu(self.conv2(x)))#第二层卷积层后再进行池化操作
        #print(x.shape)
        x = x.view(-1,36*6*6)#平坦层
        x = F.relu(self.fc2(F.relu(self.fc1(x))))#这部包含：两次全连接和两次激活激活
        return x
    
net = CNNNet()#实例化
net = net.to(device)