【PyTorch】卷积神经网络/Convolutional Neural Network（CNN）

1 模型描述

• 卷积神经网络是用来处理图像识别的强大算法（之一）
• 模型针对的是MNIST手写数字的十分类问题
• 模型通过nn.Sequential构建两个卷积层
• 卷积层函数Conv2d的参数介绍参考https://zhuanlan.zhihu.com/p/218266092
• 主要步骤包括卷积计算、ReLU、Maxpool、Softmax
• 输出层是线性的softmax，得到最大概率的分类作为结果

2 具体代码

# convolutional neural network
import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# Hyper parameters
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(
    root = 'data',
    train = True,
    transform = transforms.ToTensor(),
    download = True
)

test_dataset = torchvision.datasets.MNIST(
    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)
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        # set two conv layer
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        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
criterion = nn.CrossEntropyLoss()
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)

        # Bachward and optimizer
        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')

3 程序输出

程序训练速度较快，精度很好，测试精度达到99.1%，相当优秀的图像识别算法。

Epoch [1/5], Step [100/600],Loss:0.2283
Epoch [1/5], Step [200/600],Loss:0.1261
Epoch [1/5], Step [300/600],Loss:0.0269
Epoch [1/5], Step [400/600],Loss:0.1152
Epoch [1/5], Step [500/600],Loss:0.0703
Epoch [1/5], Step [600/600],Loss:0.1074
Epoch [2/5], Step [100/600],Loss:0.0654
Epoch [2/5], Step [200/600],Loss:0.0257
Epoch [2/5], Step [300/600],Loss:0.0075
Epoch [2/5], Step [400/600],Loss:0.0634
Epoch [2/5], Step [500/600],Loss:0.0597
Epoch [2/5], Step [600/600],Loss:0.0364
Epoch [3/5], Step [100/600],Loss:0.0147
Epoch [3/5], Step [200/600],Loss:0.0209
Epoch [3/5], Step [300/600],Loss:0.0162
Epoch [3/5], Step [400/600],Loss:0.0184
Epoch [3/5], Step [500/600],Loss:0.0231
Epoch [3/5], Step [600/600],Loss:0.0449
Epoch [4/5], Step [100/600],Loss:0.0116
Epoch [4/5], Step [200/600],Loss:0.0337
Epoch [4/5], Step [300/600],Loss:0.0036
Epoch [4/5], Step [400/600],Loss:0.0358
Epoch [4/5], Step [500/600],Loss:0.0068
Epoch [4/5], Step [600/600],Loss:0.0865
Epoch [5/5], Step [100/600],Loss:0.0023
Epoch [5/5], Step [200/600],Loss:0.0117
Epoch [5/5], Step [300/600],Loss:0.0021
Epoch [5/5], Step [400/600],Loss:0.0192
Epoch [5/5], Step [500/600],Loss:0.0219
Epoch [5/5], Step [600/600],Loss:0.0135
Test Accuracy of the model on the 10000 test images: 99.1 %