[人工智能]卷积神经网络和循环神经网络

import torch
import torch.nn.functional as F
# 神经网络的类
class Net(torch.nn.Module):
    def __init__(self):
        super().__init__()
        # 两个卷积层
        self.conv1=torch.nn.Conv2d(1,10,kernel_size=5)
        self.conv2=torch.nn.Conv2d(10,20,kernel_size=5)
        self.pooling=torch.nn.MaxPool2d(2)#  池化层
        self.fc=torch.nn.Linear(320,10)# 线性变换层
    
    def forward(self,x):
        batch_size=x.size(0)  #input的第一个维度
        x=F.relu(self.pooling(self.conv1(x)))  #relu非线性函数  激活函数
        x=F.relu(self.pooling(self.conv2(x)))
        x=x.view(batch_size,-1)
        x=self.fc(x) #线性全连接网络
        return x
    
model=Net()
#如果显卡可用则转移到显卡上面进行运算
device=torch.device("cuda:0"if torch.cuda.is_available() else "cpu")
model.to(device)
#从CPU转换到显卡，只需将网络和输入输出转移到显卡上即可
def train(epoch):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target=data
        inputs,target=inputs.to(device),target.to(device)
        optimizer.zero_grad()  #权重清零
        
        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()#更新
        
        running_loss+=loss.item()
        if batch.idx%300==299:
            print('[%d,%5d] loss:%.3f' %(epoch+1,batch_idx+1,running_loss/300))
            running_loss=0.0
        
def test():
    correct=0
    total=0
    with torch.no_grad():
        for data in test_loader:
            inputs,target=data
            outputs=model(inputs)
            _,predict=torch.max(output.data,dim=1) #维度1 对应行 取出一行中最大值及其下标
            total+=target.size(0) #总的样本大小
            correct+=(predict==target).sum().item()
     print('猜对的比率是：%d %%'%(100*correct/total))

以上代码不是很完整，只是体现大致思路。

梯度消失和梯度爆炸

import torch
import torch.nn.functional as F
#网状卷积神经网络
class InceptionA(torch.nn.Module):
    def __init__(self,in_channels):
        super().__init__()
        self.branch1x1=torch.nn.Conv2d(in_channels,16,kernel_size=1)
        
        self.branch5x5_1=torch.nn.Conv2d(in_channels,16,kernel_size=1)
        self.branch5x5_2=torch.nn.Conv2d(16,24,kernel_size=5,podding=2)
        
        self.branch3x3_1=torch.nn.Conv2d(in_channels,16,kernel_size=1)
        self.branch3x3_2=torch.nn.COnv2d(16,24,kernel_size=3,podding=1)
        self.branch3x3_3=torch.nn.Conv2d(24,24,kernel_size=3,podding=1)
        
        self.branch_pool=torch.nn.Conv2d(in_channels,24,kernel_size=1)
        
    def forward(self,x):
        branch1x1=self.branch1x1(x)
        
        branch5x5=self.branch5x5_1(x)
        branch5x5=self.branch5x5_2(branch5x5)
        
        branch3x3=self.branch3x3_1(x)
        branch3x3=self.branch3x3_2(branch3x3)
        branch3x3=self.branch3x3_3(branch3x3)
        
        branch_pool=F.avg_pool2d(x,kernel_size=3,stride=1,padding=1)
        branch_pool=self.branch_pool(branch_pool)
        
        outputs=[branch1x1,branch5x5,branch3x3,branch_pool]
        return torch.cat(outputs,dim=1) #在行的维度上将所有的数据进行连接

class Net(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1=torch.nn.Conv2d(1,10,kernel_size=5)
        self.conv2=torch.nn.Conv2d(88,20,kernel_size=5)
        
        self.incep1=InceptionA(in_channels=10)
        self.incep2=InceptionA(in_channels=20)
        
        self.mp=torch.nn.MaxPool2d(2)  #最大池化层  长和宽都变为原来的一半
        self.fc=torch.nn.Linear(1408,10)
        
        def forward(self,x):
            in_size=x.size(0)
            x=F.relu(self.mp(self.conv1(x)))
            x=self.incep1(x)
            x=F.relu(self.mp(self.conv2(x)))
            x=self.incep2(x)
            x=x.view(in_size,-1)
            x=self.fc(x)
            return x