pytorch训练mnist数据集使用网络模型的代码
时间: 2023-11-11 12:02:35 浏览: 37
下面是使用PyTorch训练MNIST数据集的示例代码:
```
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.datasets as datasets
import torchvision.transforms as transforms
# 定义网络模型
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.drop = nn.Dropout2d()
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.drop(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)
# 加载数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=transforms.ToTensor(), download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transforms.ToTensor())
# 定义训练参数
batch_size = 64
learning_rate = 0.01
epochs = 10
# 定义优化器和损失函数
net = Net()
optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.5)
criterion = nn.CrossEntropyLoss()
# 开始训练
for epoch in range(epochs):
for i, (images, labels) in enumerate(torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)):
optimizer.zero_grad()
outputs = net(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f' % (epoch+1, epochs, i+1, len(train_dataset)//batch_size, loss.item()))
# 测试模型
correct = 0
total = 0
with torch.no_grad():
for images, labels in torch.utils.data.DataLoader(test_dataset, batch_size=batch_size):
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
```
这段代码定义了一个包含两个卷积层和两个全连接层的神经网络模型,并使用SGD作为优化器和交叉熵损失函数进行训练。在循环中,我们使用DataLoader来加载数据集批次,并对每个批次进行前向传播、反向传播和参数更新。最后,我们使用测试集来评估模型的性能。