Example of self-attention model

self-attention.py

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 number of 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, query, mask):
        N = query.shape[0]
        value_len, key_len, query_len = values.shape[1], keys.shape[1], query.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)
        query = query.reshape(N, query_len, self.heads, self.head_dim)
        
        values = self.values(values)
        keys = self.keys(keys)
        queries = self.queries(query)
        
        energy = torch.einsum("nqhd, nkhd -> nhqk", [queries, keys])
        
        if mask is not None:
            energy = energy.masked_fill(mask == 0, float("-1e20"))
        
        attention = torch.softmax(energy / (self.embed_size ** (1/2)), dim=3)
        
        out = torch.einsum("nhql, nlhd -> nqhd", [attention, values]).reshape(N, query_len, self.heads * self.head_dim)
        out = self.fc_out(out)
        
        return out
        

class TransformerBlock(nn.Module):
    def __init__(self, embed_size, heads, dropout, forward_expansion):
        super(TransformerBlock, self).__init__()
        self.attention = SelfAttention(embed_size, 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 = self.attention(value, key, query, mask)
        x = self.dropout(self.norm1(attention + query))
        forward = self.feed_forward(x)
        out = self.dropout(self.norm2(forward + 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):
        # x est une séquence de seq_length mots, correspondant à des vecteurs creux d'un vocabulaire de N mots.  
        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