pytorch 使用cnn模型 声调识别代码

以下是使用CNN模型进行声调识别的PyTorch代码。该代码使用了一个简单的卷积神经网络，可以对输入的声音进行分类，以确定其所属的声调。

import torch
import torch.nn as nn
import torch.optim as optim
import torch.utils.data as data_utils
import numpy as np
import librosa

# 配置训练参数
batch_size = 64
num_epochs = 10
learning_rate = 0.001

# 加载数据
train_data = np.load('train_data.npy')
train_labels = np.load('train_labels.npy')
test_data = np.load('test_data.npy')
test_labels = np.load('test_labels.npy')

# 转换为PyTorch张量
train_data = torch.from_numpy(train_data).float()
train_labels = torch.from_numpy(train_labels).long()
test_data = torch.from_numpy(test_data).float()
test_labels = torch.from_numpy(test_labels).long()

# 创建数据集和数据加载器
train_dataset = data_utils.TensorDataset(train_data, train_labels)
train_loader = data_utils.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_dataset = data_utils.TensorDataset(test_data, test_labels)
test_loader = data_utils.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

# 定义CNN模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv1d(1, 32, 3, padding=1)
        self.pool1 = nn.MaxPool1d(2, stride=2)
        self.conv2 = nn.Conv1d(32, 64, 3, padding=1)
        self.pool2 = nn.MaxPool1d(2, stride=2)
        self.conv3 = nn.Conv1d(64, 128, 3, padding=1)
        self.pool3 = nn.MaxPool1d(2, stride=2)
        self.fc1 = nn.Linear(128 * 16, 512)
        self.fc2 = nn.Linear(512, 4)
        self.relu = nn.ReLU()

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.pool1(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.pool2(x)
        x = self.conv3(x)
        x = self.relu(x)
        x = self.pool3(x)
        x = x.view(-1, 128 * 16)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x

# 创建模型并定义损失函数和优化器
model = CNN()
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):
        optimizer.zero_grad()
        outputs = model(data.unsqueeze(1))
        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()))

# 测试模型
with torch.no_grad():
    correct = 0
    total = 0
    for data, labels in test_loader:
        outputs = model(data.unsqueeze(1))
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

在这个例子中，我们创建了一个简单的卷积神经网络，它有三个卷积层和两个全连接层。我们使用了ReLU作为激活函数，并使用了交叉熵损失函数进行训练。我们使用Adam优化器来优化模型参数。

在训练期间，我们使用了PyTorch的数据加载器来加载数据。我们还使用了一个循环，以便在每个epoch的末尾测试模型的准确性。

最后，我们使用测试数据集评估了模型的准确性。