原生transformer代码 pytorch

以下是一个简单的原生Transformer代码示例，使用PyTorch实现：

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

class Transformer(nn.Module):
    def __init__(self, src_vocab_size, tgt_vocab_size, d_model, nhead, num_encoder_layers, num_decoder_layers, dim_feedforward, dropout=0.1):
        super(Transformer, self).__init__()
        
        self.d_model = d_model
        self.embedding_src = nn.Embedding(src_vocab_size, d_model)
        self.embedding_tgt = nn.Embedding(tgt_vocab_size, d_model)
        self.pos_encoder = PositionalEncoding(d_model, dropout)
        
        self.transformer = nn.Transformer(d_model=d_model, nhead=nhead, num_encoder_layers=num_encoder_layers, 
                                          num_decoder_layers=num_decoder_layers, dim_feedforward=dim_feedforward, dropout=dropout)
        
        self.fc = nn.Linear(d_model, tgt_vocab_size)
        self.softmax = nn.Softmax(dim=-1)
        
    def forward(self, src, tgt):
        src = self.embedding_src(src) * math.sqrt(self.d_model)
        src = self.pos_encoder(src)
        
        tgt = self.embedding_tgt(tgt) * math.sqrt(self.d_model)
        tgt = self.pos_encoder(tgt)
        
        output = self.transformer(src, tgt)
        output = self.fc(output)
        output = self.softmax(output)
        
        return output
        
class PositionalEncoding(nn.Module):
    def __init__(self, d_model, dropout=0.1, max_len=5000):
        super(PositionalEncoding, self).__init__()
        self.dropout = nn.Dropout(p=dropout)
        
        pe = torch.zeros(max_len, d_model)
        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        pe = pe.unsqueeze(0).transpose(0, 1)
        self.register_buffer('pe', pe)
        
    def forward(self, x):
        x = x + self.pe[:x.size(0), :]
        return self.dropout(x)

这是一个基本的Transformer模型，包含一个由嵌入层和位置编码层组成的编码器和解码器，以及一个标准的Transformer层。在正向传递中，输入经过嵌入和位置编码处理后，被送入Transformer层进行处理，最后通过全连接层和Softmax层输出结果。在位置编码层中，我们使用了一个可学习的嵌入向量和一个固定的位置编码矩阵，以将位置信息融入到输入中。