pytorch实现图像分类

PyTorch 是一个基于 Python 的机器学习库，它提供了丰富的工具和接口，可以帮助用户快速构建和训练深度学习模型。下面是一个使用 PyTorch 实现图像分类的简单示例。

1. 准备数据

首先，需要准备数据集。常见的图像分类数据集有 MNIST、CIFAR-10、ImageNet 等。这里以 MNIST 数据集为例，它包含了 60000 张 28x28 像素的手写数字图片，以及相应的标签。

import torch
from torchvision import datasets, transforms

# 定义数据预处理
transform = transforms.Compose([
    transforms.ToTensor(), # 将图像转换为张量
    transforms.Normalize((0.1307,), (0.3081,)) # 标准化
])

# 加载数据集
train_dataset = datasets.MNIST('./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST('./data', train=False, download=True, transform=transform)

# 定义数据加载器
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)

2. 构建模型

接下来，需要构建一个 CNN 模型，用于对图像进行分类。这里使用了两个卷积层、两个池化层和三个全连接层。

import torch.nn as nn

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 5 * 5, 512)
        self.fc2 = nn.Linear(512, 10)

    def forward(self, x):
        x = self.pool(nn.functional.relu(self.conv1(x)))
        x = self.pool(nn.functional.relu(self.conv2(x)))
        x = x.view(-1, 64 * 5 * 5)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 实例化模型
model = Net()

3. 训练模型

定义好模型后，可以开始训练。这里使用交叉熵损失函数和随机梯度下降优化器进行训练。

import torch.optim as optim

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

# 训练模型
for epoch in range(10):
    for i, (inputs, labels) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        if i % 100 == 0:
            print('Epoch: {}, Batch: {}, Loss: {:.4f}'.format(epoch+1, i+1, loss.item()))

4. 评估模型

最后，使用测试集对模型进行评估。

# 在测试集上验证模型
correct = 0
total = 0
with torch.no_grad():
    for inputs, labels in test_loader:
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy: {:.2f}%'.format(100 * correct / total))

完整代码如下：

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms

# 准备数据
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

train_dataset = datasets.MNIST('./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST('./data', train=False, download=True, transform=transform)

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)

# 构建模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 5 * 5, 512)
        self.fc2 = nn.Linear(512, 10)

    def forward(self, x):
        x = self.pool(nn.functional.relu(self.conv1(x)))
        x = self.pool(nn.functional.relu(self.conv2(x)))
        x = x.view(-1, 64 * 5 * 5)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return x

model = Net()

# 训练模型
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

for epoch in range(10):
    for i, (inputs, labels) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        if i % 100 == 0:
            print('Epoch: {}, Batch: {}, Loss: {:.4f}'.format(epoch+1, i+1, loss.item()))

# 评估模型
correct = 0
total = 0
with torch.no_grad():
    for inputs, labels in test_loader:
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy: {:.2f}%'.format(100 * correct / total))