【人工智能概论】构建神经网络——以用InceptionNet解决MNIST任务为例-Toy模板网

这篇具有很好参考价值的文章主要介绍了【人工智能概论】构建神经网络——以用InceptionNet解决MNIST任务为例。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

【人工智能概论】构建神经网络——以用InceptionNet解决MNIST任务为例

一. 整体思路

两条原则，四个步骤。

1.1 两条原则

从宏观到微观
把握数据形状

1.2 四个步骤

准备数据
构建模型
确定优化策略
完善训练与测试代码

二. 举例——用InceptionNet解决MNIST任务

2.1 模型简介

InceptionNet的设计思路是通过增加网络宽度来获得更好的模型性能。
其核心在于基本单元Inception结构块，如下图：
通过纵向堆叠Inception块构建完整网络。

2.2 MNIST任务

MNIST是入门级的机器学习任务；
它是一个手写数字识别的数据集。

2.3 完整的程序

# 调包
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.optim as optim


"""数据准备"""
batch_size = 64

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,),(0.3081,))
])

train_dataset = datasets.MNIST(root='./mnist/',train=True,download=True,transform=transform)
train_loader = DataLoader(train_dataset,shuffle=True,batch_size=batch_size)
test_dataset = datasets.MNIST(root='./mnist/',train=False,download=True,transform=transform)
test_loader = DataLoader(test_dataset,shuffle=False,batch_size=batch_size)


"""构建模型"""
# 需要指定输入的通道数

class Inceptiona(nn.Module): 
    def __init__(self,in_channels):
        super(Inceptiona,self).__init__()
        
        self.branch1_1 = nn.Conv2d(in_channels , 16 , kernel_size= 1)
        
        self.branch5_5_1 =nn.Conv2d(in_channels, 16, kernel_size= 1)
        self.branch5_5_2 =nn.Conv2d(16,24,kernel_size=5,padding=2)
        
        self.branch3_3_1 = nn.Conv2d(in_channels, 16,kernel_size=1)
        self.branch3_3_2 = nn.Conv2d(16,24,kernel_size=3,padding=1)
        self.branch3_3_3 = nn.Conv2d(24,24,kernel_size=3,padding=1)
        
        self.branch_pooling = nn.Conv2d(in_channels,24,kernel_size=1)
        
    def forward(self,x):
        x1 = self.branch1_1(x)
        
        x2 = self.branch5_5_1(x)
        x2 = self.branch5_5_2(x2)
        
        x3 = self.branch3_3_1(x)
        x3 = self.branch3_3_2(x3)
        x3 = self.branch3_3_3(x3)
        
        x4 = F.avg_pool2d(x,kernel_size=3,stride = 1, padding=1)
        x4 = self.branch_pooling(x4)
        
        outputs = [x1,x2,x3,x4]
        return torch.cat(outputs,dim=1)      
    
# 构建完整的网络
class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.conv1 = nn.Conv2d(1,10,kernel_size=5)
        self.conv2 = nn.Conv2d(88,20,kernel_size=5)
        
        self.incep1 = Inceptiona(in_channels=10)
        self.incep2 = Inceptiona(in_channels=20)
        
        self.mp = nn.MaxPool2d(2)
        self.fc = nn.Linear(1408,10)
        
    def forward(self,x):
        batch_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(batch_size,-1)
        x = self.fc(x)
        return x


"""确定优化策略"""
model = Net()
device = torch.device('cuda:0'if torch.cuda.is_available() else 'cpu')
model.to(device) # 指定设备

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr=0.01,momentum=0.5)



"""完善训练与测试代码"""
def train(epoch):
    running_loss = 0.0
    for batch_index, data in enumerate(train_loader,0):
        inputs, target = data
        # 把数据和模型送到同一个设备上
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs,target)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item() 
        # 用loss.item不会构建计算图，得到的不是张量，而是标量
        if batch_index % 300 == 299:
            # 每三百组计算一次平均损失
            print('[%d,%5d] loss: %.3f' %(epoch+1,batch_index+1,running_loss/300))
            # 给出的是平均每一轮的损失
            running_loss = 0.0
            
def test():
    correct = 0
    total = 0
    with torch.no_grad(): 
        # 测试的环节不用求梯度
        for data in test_loader:
            images , labels = data
            images , labels = images.to(device),  labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data,dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('accuracy on test set: %d,%%'%(100*correct/total))
    return 100*correct/total  # 将测试的准确率返回

# 执行训练
if __name__=='__main__':
    score_best = 0
    for epoch in range(10):
        train(epoch)
        score = test()
        if score > score_best:
            score_best = score
            torch.save(model.state_dict(), "model.pth")