首先,你需要导入 PyTorch 库:
```python
import torch
import torch.nn as nn
import torch.optim as optim
```
然后,定义一个继承自 nn.Module 的 CNN-LSTM 模型类,该类由两个子模块组成:一个卷积神经网络和一个长短时记忆网络。
```python
class CNN_LSTM(nn.Module):
def __init__(self, num_classes):
super(CNN_LSTM, self).__init__()
self.cnn = nn.Sequential(
nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.lstm = nn.LSTM(input_size=64, hidden_size=128, num_layers=2, batch_first=True)
self.fc = nn.Linear(128, num_classes)
def forward(self, x):
x = self.cnn(x)
x = x.reshape(x.size(0), -1, 64)
out, (h_n, c_n) = self.lstm(x)
out = self.fc(out[:, -1, :])
return out
```
在上面的代码中,我们定义了一个 CNN_LSTM 类,该类包含三个主要的组件:
1. CNN:由三个卷积层和三个最大池化层组成的卷积神经网络,用于从图像中提取特征。
2. LSTM:一个具有两个隐藏层和 128 个隐藏单元的 LSTM,用于学习序列数据之间的依赖关系。
3. 全连接层:将 LSTM 输出转换成模型预测的类别。
最后,我们可以定义模型的超参数并进行训练。
```python
# 定义超参数
num_classes = 10
learning_rate = 0.001
batch_size = 64
num_epochs = 10
# 加载数据集
train_dataset = torchvision.datasets.CIFAR10(root='./data', train=True, transform=transforms.ToTensor(), download=True)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_dataset = torchvision.datasets.CIFAR10(root='./data', train=False, transform=transforms.ToTensor())
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)
# 实例化模型
model = CNN_LSTM(num_classes)
# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
# 训练模型
total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.permute(0, 2, 3, 1) # 调整图像维度
outputs = model(images)
loss = criterion(outputs, labels)
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()))
# 测试模型
model.eval()
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.permute(0, 2, 3, 1)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))
```
在上面的代码中,我们首先加载 CIFAR-10 数据集并实例化 CNN-LSTM 模型。然后,我们定义了损失函数和优化器,并在训练过程中进行了模型的优化。最后,我们使用测试数据集对模型进行评估并输出准确率。