MNIST 手写数字识别 卷积神经网络 Pytorch框架

MNIST 手写数字识别 卷积神经网络 Pytorch框架

谨此纪念刚入门的我在卷积神经网络上面的摸爬滚打

说明

这个代码是在网上寻找的，具体来源不明，可以正常运行测试，自己添加了一些注释，方便查看。

代码实现

import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
#这里是个python的三元表达式，如果cuda存在的话，divice='cuda:0'，否者就是'cpu'
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# Hyper parameters
num_epochs = 5  #全部训练集使用的次数
num_classes = 10 #
batch_size = 100  #批处理的图片的个数
learning_rate = 0.001 #学习率，在梯度下降法里面的系数

# MNIST dataset
#下载训练数据集，位置放在本文件的父文件夹下的data文件夹里面，数据需要转换格式为Tensor
#如果想要更改数据集下载位置，可以改为root='./data/'
train_dataset = torchvision.datasets.FashionMNIST(root='../data/',
                                           train=True, 
                                           transform=transforms.ToTensor(),
                                           download=True)
#下载测试集，位置放在放在本文件的父文件夹下的data文件夹里面，数据需要转换为Tensor格式
#如果想要更改数据集下载位置，可以改为root='./data/'
test_dataset = torchvision.datasets.FashionMNIST(root='../data/',
                                          train=False, 
                                          transform=transforms.ToTensor())

# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size, 
                                          shuffle=False)

# Convolutional neural network (two convolutional layers)
#定义一个卷积类，这里需要继承nn.Module
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        #调用父类的初始化函数
        super(ConvNet, self).__init__()
        #
        self.layer1 = nn.Sequential(
            #输入通道数1，输出通道数16，卷积核大小为5*5，步长为1，零填充2圈
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
             #BatchNorm2d是卷积网络中防止梯度消失或爆炸的函数，参数是卷积的输出通道数
            nn.BatchNorm2d(16),
            #激活函数
            nn.ReLU(),
            #池化
            nn.MaxPool2d(kernel_size=2, stride=2))
        #两层
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            #这个是激活函数
            nn.ReLU(),
            #下采样，最大池化
            nn.MaxPool2d(kernel_size=2, stride=2))
        #线性函数构造
        self.fc = nn.Linear(7*7*32, num_classes)
        
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out
model = ConvNet(num_classes).to(device)

# Loss and optimizer
#损失函数，
criterion = nn.CrossEntropyLoss()
#优化函数
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)
        
        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# Test the model
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')