pytorch中使用LSTM详解

在PyTorch中，LSTM是一种非常常用的循环神经网络，用于处理序列数据。本文将提供一个完整的攻略，介绍如何在PyTorch中使用LSTM。我们将提供两个示例，分别是使用单层LSTM和使用多层LSTM。

示例1：使用单层LSTM

以下是一个示例，展示如何使用单层LSTM。

1. 导入库

import torch
import torch.nn as nn

2. 定义模型

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

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = LSTM(input_size=28, hidden_size=128, num_layers=1, output_size=10).to(device)

3. 定义损失函数和优化器

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

4. 训练模型

num_epochs = 10
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, 28, 28).to(device)
        labels = labels.to(device)

        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, len(train_loader), loss.item()))

示例2：使用多层LSTM

以下是一个示例，展示如何使用多层LSTM。

1. 导入库

import torch
import torch.nn as nn

2. 定义模型

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

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = LSTM(input_size=28, hidden_size=128, num_layers=2, output_size=10).to(device)

3. 定义损失函数和优化器

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

4. 训练模型

num_epochs = 10
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, 28, 28).to(device)
        labels = labels.to(device)

        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, len(train_loader), loss.item()))