pytorch使用biLSTM实现一维语音分类代码

以下是一个简单的基于pytorch使用biLSTM实现一维语音分类的代码示例：

import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np

# 构建BiLSTM模型
class BiLSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(BiLSTM, 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, bidirectional=True)
        self.fc = nn.Linear(hidden_size*2, num_classes)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device)
        c0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device)

        out, _ = self.lstm(x, (h0, c0))
        out = self.fc(out[:, -1, :])
        return out

# 超参数设置
input_size = 1
hidden_size = 64
num_layers = 2
num_classes = 10
batch_size = 64
learning_rate = 0.001
num_epochs = 10

# 准备数据
train_data = np.load('train_data.npy')
train_labels = np.load('train_labels.npy')

train_data = np.expand_dims(train_data, axis=2)
train_labels = torch.from_numpy(train_labels).long()

train_dataset = torch.utils.data.TensorDataset(torch.from_numpy(train_data), train_labels)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)

# 定义设备
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# 初始化模型、损失函数和优化器
model = BiLSTM(input_size, hidden_size, num_layers, num_classes).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
for epoch in range(num_epochs):
    for i, (data, labels) in enumerate(train_loader):
        data = data.to(device)
        labels = labels.to(device)

        outputs = model(data)
        loss = criterion(outputs, labels)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 10 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, len(train_loader), loss.item()))

# 测试模型
model.eval()
test_data = np.load('test_data.npy')
test_labels = np.load('test_labels.npy')

test_data = np.expand_dims(test_data, axis=2)
test_labels = torch.from_numpy(test_labels).long()

test_dataset = torch.utils.data.TensorDataset(torch.from_numpy(test_data), test_labels)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

with torch.no_grad():
    correct = 0
    total = 0
    for data, labels in test_loader:
        data = data.to(device)
        labels = labels.to(device)

        outputs = model(data)
        _, predicted = torch.max(outputs.data, 1)

        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the {} test images: {} %'.format(total, 100 * correct / total))

在这个例子中，我们使用了一个由两个双向LSTM层组成的模型，并将其应用于一维语音分类任务。我们使用Adam优化器来更新模型参数，并使用交叉熵损失函数来计算损失。在训练完成后，我们在测试集上评估模型的准确率。