PyTorch手写数字MNIST识别(CNN)

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets  # 放置了许多常用数据集,包括手写数字识别
import torch.nn.functional as F

数据预处理

transform = transforms.Compose([
    transforms.ToTensor(),  # 转张量，将值缩放到[0,1]之间
    transforms.Normalize((0.1307,),(0.3081,))  # 归一化，第一个为均值，第二个为方差
])

train_dataset = datasets.MNIST(root= "E:/MNIST/mnist",
                              train=True,  # 下载训练集
                              transform=transform,  # 转张量，将值缩放到[0,1]之间.也可以写成transform = transforms.ToTensor()      
                              download=True
                              )

test_dataset = datasets.MNIST(root= "E:/MNIST/mnist",
                              train=False,  # 下载训练集
                              transform=transform,  # 转张量，将值缩放到[0,1]之间
                              download=True
                              )

train_loader = DataLoader(dataset=train_dataset,
                         batch_size=64,
                         shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=64,
                         shuffle=False)

CNN模型搭建

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        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)
        self.fc = torch.nn.Linear(320, 10)
        
    def forward(self, x):
        # (n, 1, 28, 28)
        batch_size = x.size(0)  # batch_size = n
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)
        x = self.fc(x)  # 因为使用交叉熵，所以最后一层不做激活
        return x

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

训练函数

def train(epoch):
    runing_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target =data
        optimizer.zero_grad()
        
        outputs = model(inputs)
        loss = loss_fn(outputs, target)
        loss.backward()
        optimizer.step()
        
        runing_loss += loss.item()
        if batch_idx % 300  == 299:
            print("[%d, %5d] loss: %.3f" % (epoch +1, batch_idx+1, runing_loss/300))
            runing_loss = 0.0

测试函数

def test():
    correct = 0
    total =0
    with torch.no_grad():
        for data in test_loader:
            images, labels =data
            outputs = model(images)  
            _, predicted = torch.max(outputs.data, dim =1 )  # 返回两个值，第一个是最大值，第二个是最大值的索引。dim=1表示在列维度求以上结果，dim = 0表示在行维度求以上结果。         
            total += labels.size(0)  # 每一个batch_size 中labels是一个（N，1）的元组，size(0)=N
            correct +=(predicted == labels).sum().item()  # 对的总个数
    print("Accuracy on the test set %d %%" % (100*correct/total))

网络启动

if __name__=="__main__":
    for epoch in range(10):
        train(epoch)
        if epoch % 2 ==0:
            test()
            

[1,   300] loss: 0.559
[1,   600] loss: 0.169
[1,   900] loss: 0.134
Accuracy on the test set 96 %
[2,   300] loss: 0.109
[2,   600] loss: 0.091
[2,   900] loss: 0.084
[3,   300] loss: 0.072
[3,   600] loss: 0.072
[3,   900] loss: 0.071
Accuracy on the test set 98 %
[4,   300] loss: 0.067
[4,   600] loss: 0.055
[4,   900] loss: 0.058
[5,   300] loss: 0.053
[5,   600] loss: 0.053
[5,   900] loss: 0.055
Accuracy on the test set 98 %
[6,   300] loss: 0.048
[6,   600] loss: 0.048
[6,   900] loss: 0.047
[7,   300] loss: 0.042
[7,   600] loss: 0.043
[7,   900] loss: 0.045
Accuracy on the test set 98 %
[8,   300] loss: 0.043
[8,   600] loss: 0.036
[8,   900] loss: 0.038
[9,   300] loss: 0.038
[9,   600] loss: 0.032
[9,   900] loss: 0.040
Accuracy on the test set 98 %
[10,   300] loss: 0.038
[10,   600] loss: 0.029
[10,   900] loss: 0.036