File size: 752 Bytes
0883aa1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

import torch
import torch.nn as nn
import numpy as np


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

    def __init__(self, temperature):
        super().__init__()
        self.temperature = temperature
        self.softmax = nn.Softmax(dim=2)

    def forward(self, q, k, v, mask=None):
        attn = torch.bmm(q, k.transpose(1, 2))
        attn = attn / self.temperature

        if mask is not None:
            attn = attn.masked_fill(mask, -np.inf)

        attn = self.softmax(attn)
        output = torch.bmm(attn, v)

        return output, attn