请编写Python代码,使用Pytorch库构建一个简单的卷积神经网络模型,并对MNIST手写数字数据集进行训练和测试。
时间: 2023-11-27 08:53:50 浏览: 37
好的,下面是一个简单的卷积神经网络模型的代码,使用Pytorch库对MNIST手写数字数据集进行训练和测试:
```python
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
# 定义数据预处理方式
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
# 加载MNIST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)
# 定义网络模型
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Conv2d(1, 32, kernel_size=3, padding=1)
self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
self.dropout1 = nn.Dropout2d(0.25)
self.dropout2 = nn.Dropout2d(0.5)
self.fc1 = nn.Linear(64 * 7 * 7, 128)
self.fc2 = nn.Linear(128, 10)
def forward(self, x):
x = nn.functional.relu(self.conv1(x))
x = nn.functional.relu(self.conv2(x))
x = nn.functional.max_pool2d(x, 2)
x = self.dropout1(x)
x = torch.flatten(x, 1)
x = nn.functional.relu(self.fc1(x))
x = self.dropout2(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('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
# 定义主函数
def main():
# 设置参数
epochs = 10
batch_size = 64
learning_rate = 0.01
# 设置设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# 加载数据
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True)
# 初始化模型
model = CNN().to(device)
# 定义优化器
optimizer = optim.SGD(model.parameters(), lr=learning_rate, momentum=0.5)
# 训练和测试模型
for epoch in range(1, epochs + 1):
train(model, device, train_loader, optimizer, epoch)
test(model, device, test_loader)
# 保存模型
torch.save(model.state_dict(), "mnist_cnn.pt")
if __name__ == '__main__':
main()
```
这里我们使用了一个简单的卷积神经网络模型,包括两个卷积层和两个全连接层。在训练和测试时,我们使用了SGD优化器和交叉熵损失函数。运行代码后,我们可以得到模型在MNIST数据集上的测试准确率,同时将模型保存在“mnist_cnn.pt”文件中。