LSTM代码

import numpy as np
import matplotlib.pyplot as pltimport torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import DataLoader, TensorDatasetfrom sklearn.model_selection import train_test_split# 生成数据集
def generate_data(num_samples, seq_length):# 生成正弦波形数据（类别0）half_num_samples=num_samples//2 # 整除x_sin = np.array([np.sin(0.06 * np.arange(seq_length) + np.random.rand()) for _ in range(half_num_samples)])y_sin = np.zeros(half_num_samples, dtype=np.int64)# 生成余弦波形数据（类别1），频率略有不同x_cos = np.array([np.cos(0.05 * np.arange(seq_length) + np.random.rand()) for _ in range(half_num_samples)])y_cos = np.ones(half_num_samples, dtype=np.int64)# 合并数据x = np.concatenate((x_sin, x_cos), axis=0)y = np.concatenate((y_sin, y_cos), axis=0)# 打乱数据indices = np.arange(num_samples)np.random.shuffle(indices)x = x[indices]y = y[indices]# 转换为pytorch张量，LSTM需要3D tensor [batch, seq_len, features]，# 所以用unsqueeze(2)在第二个维度上增加一个维度x_tensor = torch.tensor(x, dtype=torch.float32).unsqueeze(2)  print('x_tensor.shape:',x_tensor.shape) # x_tensor.shape: torch.Size([1000, 100, 1])y_tensor = torch.tensor(y, dtype=torch.int64) # y_tensor.shape: torch.Size([1000])print('y_tensor.shape:',y_tensor.shape)return x_tensor, y_tensor# LSTM分类模型
class LSTMClassifier(nn.Module):def __init__(self, input_dim, hidden_dim, output_dim, n_layers):super(LSTMClassifier, self).__init__()self.hidden_dim = hidden_dimself.n_layers = n_layers# LSTM Layerself.lstm = nn.LSTM(input_dim, hidden_dim, n_layers, batch_first=True)# 全连接层（Fully connected layer）self.fc = nn.Linear(hidden_dim, output_dim)# forward方法在模型训练时会自动调用def forward(self, x):# 用零初始化隐藏层的状态h0 = torch.zeros(self.n_layers, x.size(0), self.hidden_dim).requires_grad_()# 用零初始化细胞状态c0 = torch.zeros(self.n_layers, x.size(0), self.hidden_dim).requires_grad_()out, (hn, cn) = self.lstm(x, (h0.detach(), c0.detach()))out = self.fc(out[:, -1, :])return out# 训练模型
def train_model(model, train_loader, criterion, optimizer, num_epochs):for epoch in range(num_epochs):for i, (sequences, labels) in enumerate(train_loader):# Forward passoutputs = model(sequences)loss = criterion(outputs, labels)# Backward and optimizeoptimizer.zero_grad()loss.backward()optimizer.step()if (i+1) % 100 == 0:print(f'Epoch [{epoch+1}/{num_epochs}], Step [{i+1}], Loss: {loss.item():.4f}')# 评估模型
def evaluate_model(model, test_loader):model.eval()  # Set model to evaluation modewith torch.no_grad():correct = 0total = 0for sequences, labels in test_loader:outputs = model(sequences)_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()print(f'Accuracy of the model on the test sequences: {100 * correct / total} %')if __name__=='__main__':# ----------------- 生成样本数据 ----------------- num_samples = 1000  # 训练总样本数seq_length = 100    # 每个样本的序列长度（可以看作是特征的长度）x_data,y_data = generate_data(num_samples, seq_length) # 产生总的样本x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.2, random_state=2) # ----------------- 数据加载器 ----------------- batch_size=64train_loader = DataLoader(TensorDataset(x_train, y_train), batch_size=batch_size, shuffle=True)test_loader = DataLoader(TensorDataset(x_test, y_test), batch_size=batch_size, shuffle=False)# ----------------- 可视化数据 ----------------- plt.figure(figsize=(12, 6))for i in range(6):plt.subplot(2, 3, i+1)plt.plot(x_train[i].numpy().flatten(), label=f"Class {y_train[i].item()}")plt.legend()plt.tight_layout()plt.show() # 不想看数据，可以注释掉这行# ----------------- 超参设定 ----------------- input_dim = 10    # 输入特征的维数hidden_dim = 50   # LSTM 隐藏层的维度output_dim = 2    # 输出的维度（分类的类别数）n_layers = 1      # 堆叠的 LSTM 层的数量（默认为1层）# ----------------- 创建模型 ----------------- model = LSTMClassifier(input_dim=1, hidden_dim=50, output_dim=2, n_layers=1)criterion = nn.CrossEntropyLoss() # 损失函数optimizer = optim.Adam(model.parameters(), lr=0.01) # 优化器# ----------------- 训练模型 ----------------- train_model(model, train_loader, criterion, optimizer, num_epochs=10)# ----------------- 评估模型 ----------------- evaluate_model(model, test_loader)

双向LSTM，需要修改哪几个参数？

需要在 nn.LSTM 的构造函数中设置 bidirectional=True。此外，由于双向 LSTM 在每个时间步将会有两个隐藏状态（正向和反向），因此全连接层的输入特征数需要调整为 2 * hidden_size。

下面是对您的代码的修改部分，以及需要注意的几个点：

1. 在 nn.LSTM 中设置 bidirectional=True来启用双向功能。
2. h0 和 c0 的尺寸都乘以了 2，因为对于每一层 LSTM，我们现在有两个隐藏层状态（一个用于前向传播，一个用于后向传播）。
3. 调整全连接层的输入特征数，由 hidden_size 改为 2 * hidden_size，以适应双向输出。

修改后的代码如下：

import torch
import torch.nn as nn# 定义LSTM网络
class LSTM_Model(nn.Module):"""input_size：输入特征的维数hidden_size：LSTM 隐藏层的维度num_layers：堆叠的 LSTM 层的数量class_num: 分类的类别数batch_first: 输入和输出的维度顺序是否为 (batch, seq, feature)"""def __init__(self, input_size, hidden_size, num_layers, class_num):super(LSTM_Model, self).__init__()self.hidden_size = hidden_size self.num_layers = num_layers# 修改为双向LSTMself.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True, bidirectional=True)# 修改全连接层输入特征数为 2 * hidden_sizeself.fc = nn.Linear(in_features=2 * hidden_size, out_features=class_num)def forward(self, x):DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')# 初始化隐藏层状态全为0h0 = torch.zeros(self.num_layers * 2, x.size(0), self.hidden_size).requires_grad_().to(DEVICE)  # 注意乘以2，因为是双向c0 = torch.zeros(self.num_layers * 2, x.size(0), self.hidden_size).requires_grad_().to(DEVICE)  # 注意乘以2，因为是双向x = x.view(x.size(0), 1, -1)out, (hn, cn) = self.lstm(x, (h0.detach(), c0.detach()))# 只需要最后一层隐层的状态，考虑双向，所以取最后一步的输出out = self.fc(out[:, -1, :])  # 这里不用改变return out