以下是使用 PyTorch 框架基于 MNIST 手写数字识别模型的代码示例:
```python
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
# 定义模型结构
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = nn.functional.relu(nn.functional.max_pool2d(self.conv1(x), 2))
x = nn.functional.relu(nn.functional.max_pool2d(self.conv2(x), 2))
x = x.view(-1, 320)
x = nn.functional.relu(self.fc1(x))
x = self.fc2(x)
return nn.functional.log_softmax(x, dim=1)
# 定义训练函数
def train(model, device, train_loader, optimizer, epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = nn.functional.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
# 定义测试函数
def test(model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
test_loss += nn.functional.nll_loss(output, target, reduction='sum').item()
pred = output.argmax(dim=1, keepdim=True)
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
print('Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
# 设置训练参数
batch_size = 64
test_batch_size = 1000
epochs = 10
lr = 0.01
momentum = 0.5
seed = 1
log_interval = 100
# 检查是否支持 GPU
use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
# 加载数据集
torch.manual_seed(seed)
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=True, download=True,
transform=transform),
batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False, transform=transform),
batch_size=test_batch_size, shuffle=True)
# 初始化模型和优化器
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=lr, momentum=momentum)
# 训练模型
for epoch in range(1, epochs + 1):
train(model, device, train_loader, optimizer, epoch)
test(model, device, test_loader)
```
这段代码会下载 MNIST 数据集并进行训练和测试,训练过程中会输出每个 batch 的 loss 值,测试过程会输出准确率。你可以根据需要调整训练参数,例如学习率、批量大小等,以优化模型性能。