Transformer 架构从原理到实现

import torch
import torch.nn as nn
import math

class SelfAttention(nn.Module):
    def __init__(self, embed_size, heads):
        super().__init__()
        self.embed_size = embed_size
        self.heads = heads
        self.head_dim = embed_size // heads
        
        self.values = nn.Linear(embed_size, embed_size)
        self.keys = nn.Linear(embed_size, embed_size)
        self.queries = nn.Linear(embed_size, embed_size)
        self.fc_out = nn.Linear(embed_size, embed_size)
    
    def forward(self, values, keys, query, mask):
        N = query.shape[0]
        value_len, key_len, query_len = values.shape[1], keys.shape[1], query.shape[1]
        
        # 分割多头
        values = self.values(values).reshape(N, value_len, self.heads, self.head_dim)
        keys = self.keys(keys).reshape(N, key_len, self.heads, self.head_dim)
        queries = self.queries(query).reshape(N, query_len, self.heads, self.head_dim)
        
        # 注意力分数
        energy = torch.einsum("nqhd,nkhd->nhqk", [queries, keys])
        attention = torch.softmax(energy / math.sqrt(self.head_dim), dim=3)
        
        out = torch.einsum("nhql,nlhd->nqhd", [attention, values])
        out = out.reshape(N, query_len, self.heads * self.head_dim)
        return self.fc_out(out)

class PositionalEncoding(nn.Module):
    def __init__(self, embed_size, max_len=5000):
        super().__init__()
        pe = torch.zeros(max_len, embed_size)
        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, embed_size, 2).float() * (-math.log(10000.0) / embed_size))
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        self.pe = pe.unsqueeze(0)
    
    def forward(self, x):
        return x + self.pe[:, :x.size(1)]