textcnn声调识别模型pytorch代码

以下是一个简单的 TextCNN 声调识别模型的 PyTorch 代码示例：

import torch
import torch.nn as nn
import torch.nn.functional as F

class TextCNN(nn.Module):
    def __init__(self, vocab_size, embedding_dim, num_filters, filter_sizes, output_dim, dropout):
        super().__init__()

        self.embedding = nn.Embedding(vocab_size, embedding_dim)
        self.convs = nn.ModuleList([
            nn.Conv2d(in_channels=1, out_channels=num_filters, kernel_size=(fs, embedding_dim))
            for fs in filter_sizes
        ])
        self.fc = nn.Linear(len(filter_sizes) * num_filters, output_dim)
        self.dropout = nn.Dropout(dropout)

    def forward(self, text):
        # text: (batch_size, seq_len)

        embedded = self.embedding(text)  # embedded: (batch_size, seq_len, embedding_dim)
        embedded = embedded.unsqueeze(1)  # embedded: (batch_size, 1, seq_len, embedding_dim)

        conved = [F.relu(conv(embedded)).squeeze(3) for conv in self.convs]  # conved[i]: (batch_size, num_filters, seq_len - filter_sizes[i] + 1)
        pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved]  # pooled[i]: (batch_size, num_filters)

        cat = self.dropout(torch.cat(pooled, dim=1))  # cat: (batch_size, len(filter_sizes) * num_filters)

        output = self.fc(cat)  # output: (batch_size, output_dim)

        return output

其中，`num_filters` 是卷积核的数量，`filter_sizes` 是卷积核的尺寸列表，`dropout` 是 dropout 的概率，`output_dim` 是输出的维度（本例中为两个声调，分别是 0 和 1）。在模型的 `forward` 方法中，首先将输入的文本进行 embedding，然后根据不同的 filter 尺寸进行卷积和池化，最后将池化后的结果拼接在一起，通过一个全连接层得到最终的输出。