Transformer and Self-Attention Pytorch代码

以下是使用PyTorch实现Transformer和Self-Attention的示例代码：

## Self-Attention

import torch
import torch.nn as nn

class SelfAttention(nn.Module):
    def __init__(self, embed_size, heads):
        super(SelfAttention, self).__init__()
        self.embed_size = embed_size
        self.heads = heads
        self.head_dim = embed_size // heads
        
        assert (self.head_dim * heads == embed_size), "Embed size needs to be divisible by heads"
        
        self.values = nn.Linear(self.head_dim, self.head_dim, bias=False)
        self.keys = nn.Linear(self.head_dim, self.head_dim, bias=False)
        self.queries = nn.Linear(self.head_dim, self.head_dim, bias=False)
        self.fc_out = nn.Linear(heads * self.head_dim, embed_size)
        
    def forward(self, values, keys, queries, mask):
        # Get number of training examples
        N = queries.shape[0]
        
        value_len, key_len, query_len = values.shape[1], keys.shape[1], queries.shape[1]
        
        # Split embedding into self.heads pieces
        values = values.reshape(N, value_len, self.heads, self.head_dim)
        keys = keys.reshape(N, key_len, self.heads, self.head_dim)
        queries = queries.reshape(N, query_len, self.heads, self.head_dim)
        
        # Transpose to get dimensions batch_size * self.heads * seq_len * self.head_dim
        values = values.permute(0, 2, 1, 3)
        keys = keys.permute(0, 2, 1, 3)
        queries = queries.permute(0, 2, 1, 3)
        
        # Calculate energy
        energy = torch.matmul(queries, keys.permute(0, 1, 3, 2))
        
        if mask is not None:
            energy = energy.masked_fill(mask == 0, float("-1e20"))
        
        # Apply softmax to get attention scores
        attention = torch.softmax(energy / (self.embed_size ** (1/2)), dim=-1)
        
        # Multiply attention scores with values
        out = torch.matmul(attention, values)
        
        # Concatenate and linearly transform output
        out = out.permute(0, 2, 1, 3).reshape(N, query_len, self.heads * self.head_dim)
        out = self.fc_out(out)
        
        return out

## Transformer

import torch
import torch.nn as nn
from torch.nn.modules.activation import MultiheadAttention

class TransformerBlock(nn.Module):
    def __init__(self, embed_size, heads, dropout, forward_expansion):
        super(TransformerBlock, self).__init__()
        self.attention = MultiheadAttention(embed_dim=embed_size, num_heads=heads)
        self.norm1 = nn.LayerNorm(embed_size)
        self.norm2 = nn.LayerNorm(embed_size)
        
        self.feed_forward = nn.Sequential(
            nn.Linear(embed_size, forward_expansion * embed_size),
            nn.ReLU(),
            nn.Linear(forward_expansion * embed_size, embed_size)
        )
        
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, value, key, query, mask):
        attention_output, _ = self.attention(query, key, value, attn_mask=mask)
        
        x = self.dropout(self.norm1(attention_output + query))
        
        forward_output = self.feed_forward(x)
        out = self.dropout(self.norm2(forward_output + x))
        
        return out
        

class Encoder(nn.Module):
    def __init__(self, src_vocab_size, embed_size, num_layers, heads, device, forward_expansion, dropout, max_length):
        super(Encoder, self).__init__()
        self.embed_size = embed_size
        self.device = device
        self.word_embedding = nn.Embedding(src_vocab_size, embed_size)
        self.position_embedding = nn.Embedding(max_length, embed_size)
        
        self.layers = nn.ModuleList([
            TransformerBlock(embed_size, heads, dropout, forward_expansion) for _ in range(num_layers)
        ])
        
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, mask):
        N, seq_length = x.shape
        positions = torch.arange(0, seq_length).expand(N, seq_length).to(self.device)
        
        out = self.dropout(self.word_embedding(x) + self.position_embedding(positions))
        
        for layer in self.layers:
            out = layer(out, out, out, mask)
            
        return out
    
    
class DecoderBlock(nn.Module):
    def __init__(self, embed_size, heads, forward_expansion, dropout, device):
        super(DecoderBlock, self).__init__()
        self.norm = nn.LayerNorm(embed_size)
        self.attention = MultiheadAttention(embed_size, heads)
        self.transformer_block = TransformerBlock(embed_size, heads, dropout, forward_expansion)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, value, key, src_mask, trg_mask):
        attention_output, _ = self.attention(x, x, x, attn_mask=trg_mask)
        query = self.dropout(self.norm(attention_output + x))
        out = self.transformer_block(value, key, query, src_mask)
        
        return out
    
    
class Decoder(nn.Module):
    def __init__(self, trg_vocab_size, embed_size, num_layers, heads, forward_expansion, dropout, device, max_length):
        super(Decoder, self).__init__()
        self.embed_size = embed_size
        self.device = device
        self.word_embedding = nn.Embedding(trg_vocab_size, embed_size)
        self.position_embedding = nn.Embedding(max_length, embed_size)
        
        self.layers = nn.ModuleList([
            DecoderBlock(embed_size, heads, forward_expansion, dropout, device) for _ in range(num_layers)
        ])
        
        self.fc_out = nn.Linear(embed_size, trg_vocab_size)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, enc_out, src_mask, trg_mask):
        N, seq_length = x.shape
        positions = torch.arange(0, seq_length).expand(N, seq_length).to(self.device)
        
        x = self.dropout(self.word_embedding(x) + self.position_embedding(positions))
        
        for layer in self.layers:
            x = layer(x, enc_out, enc_out, src_mask, trg_mask)
            
        out = self.fc_out(x)
        
        return out

这些代码可以用于实现Transformer和Self-Attention模型。但这只是示例，你需要根据你的数据和任务来调整这些代码中的各种超参数和结构。