pytorch lstm实例

以下是基于PyTorch实现的LSTM实例：

import torch
import torch.nn as nn

# 定义LSTM网络
class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, output_size):
        super(LSTM, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        
        out, _ = self.lstm(x, (h0, c0))
        out = self.fc(out[:, -1, :])
        
        return out

# 实例化网络
input_size = 28
hidden_size = 128
num_layers = 2
output_size = 10
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
net = LSTM(input_size, hidden_size, num_layers, output_size).to(device)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(net.parameters(), lr=0.001)

# 训练网络
num_epochs = 10
for epoch in range(num_epochs):
    for i, (inputs, labels) in enumerate(train_loader):
        inputs = inputs.to(device)
        labels = labels.to(device)
        
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        if (i+1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, len(train_loader), loss.item()))

# 测试网络
with torch.no_grad():
    correct = 0
    total = 0
    for inputs, labels in test_loader:
        inputs = inputs.to(device)
        labels = labels.to(device)
        outputs = net(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

上述代码实现了一个LSTM网络，用于手写数字识别任务。其中，输入数据是28x28的图片，输出是10个数字的概率。在训练过程中，使用交叉熵损失函数和Adam优化器。在测试过程中，计算准确率来评估网络性能。