CoAttention.py

# -*- coding: utf-8 -*-
"""
Created on Jan 21 2023
@author: JIANG Yuxin
"""


''' Define the Multi Head Co-Attention layer '''

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


class ScaledDotProductAttention(nn.Module):
    ''' Scaled Dot-Product Attention '''

    def __init__(self, temperature, attn_dropout=0.1):
        super().__init__()
        self.temperature = temperature
        self.dropout = nn.Dropout(attn_dropout)

    def forward(self, q, k, v, mask=None):

        attn = torch.matmul(q / self.temperature, k.transpose(2, 3)) # (bs, head, l, l)
        
        if mask is not None:
            # attn = attn.masked_fill(mask == 0, -1e9)
            mask = (1.0 - mask) * (-1e9)
            attn = attn + mask 
        
        attn = self.dropout(F.softmax(attn, dim=-1))
        output = torch.matmul(attn, v)

        return output, attn
    

class MultiHeadAttention(nn.Module):
    ''' Multi-Head Attention module '''

    def __init__(self, n_head, d_model, d_k, d_v, dropout=0.1, d_label=None):
        super().__init__()

        self.n_head = n_head
        self.d_k = d_k
        self.d_v = d_v
        
        if d_label:
            self.w_qs = nn.Linear(d_model, n_head * d_k, bias=False)
            self.w_ks = nn.Linear(d_label, n_head * d_k, bias=False)
            self.w_vs = nn.Linear(d_label, n_head * d_v, bias=False)
        else:
            self.w_qs = nn.Linear(d_model, n_head * d_k, bias=False)
            self.w_ks = nn.Linear(d_model, n_head * d_k, bias=False)
            self.w_vs = nn.Linear(d_model, n_head * d_v, bias=False)
            
        self.fc = nn.Linear(n_head * d_v, d_model, bias=False)

        self.attention = ScaledDotProductAttention(temperature=d_k ** 0.5)

        self.dropout = nn.Dropout(dropout)


    def forward(self, q, k, v, mask=None):

        d_k, d_v, n_head = self.d_k, self.d_v, self.n_head
        sz_b, len_q, len_k, len_v = q.size(0), q.size(1), k.size(1), v.size(1)

        residual = q

        # Pass through the pre-attention projection: b x lq x (n*dv)
        # Separate different heads: b x lq x n x dv
        q = self.w_qs(q).view(sz_b, len_q, n_head, d_k)
        k = self.w_ks(k).view(sz_b, len_k, n_head, d_k)
        v = self.w_vs(v).view(sz_b, len_v, n_head, d_v)

        # Transpose for attention dot product: b x n x lq x dv
        q, k, v = q.transpose(1, 2), k.transpose(1, 2), v.transpose(1, 2)

        q, attn = self.attention(q, k, v, mask=mask)

        # Transpose to move the head dimension back: b x lq x n x dv
        # Combine the last two dimensions to concatenate all the heads together: b x lq x (n*dv)
        q = q.transpose(1, 2).contiguous().view(sz_b, len_q, -1)
        q = self.dropout(self.fc(q))
        q += residual

        return q, attn