• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1"""
2/* Copyright (c) 2023 Amazon
3   Written by Jan Buethe */
4/*
5   Redistribution and use in source and binary forms, with or without
6   modification, are permitted provided that the following conditions
7   are met:
8
9   - Redistributions of source code must retain the above copyright
10   notice, this list of conditions and the following disclaimer.
11
12   - Redistributions in binary form must reproduce the above copyright
13   notice, this list of conditions and the following disclaimer in the
14   documentation and/or other materials provided with the distribution.
15
16   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
17   ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
18   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
19   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
20   OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
21   EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
22   PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
23   PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
24   LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
25   NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
26   SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27*/
28"""
29
30import math as m
31import torch
32from torch import nn
33
34
35class ScaleEmbedding(nn.Module):
36    def __init__(self,
37                 dim,
38                 min_val,
39                 max_val,
40                 logscale=False):
41
42        super().__init__()
43
44        if min_val >= max_val:
45            raise ValueError('min_val must be smaller than max_val')
46
47        if min_val <= 0 and logscale:
48            raise ValueError('min_val must be positive when logscale is true')
49
50        self.dim = dim
51        self.logscale = logscale
52        self.min_val = min_val
53        self.max_val = max_val
54
55        if logscale:
56            self.min_val = m.log(self.min_val)
57            self.max_val = m.log(self.max_val)
58
59
60        self.offset = (self.min_val + self.max_val) / 2
61        self.scale_factors = nn.Parameter(
62            torch.arange(1, dim+1, dtype=torch.float32) * torch.pi / (self.max_val - self.min_val)
63        )
64
65    def forward(self, x):
66        if self.logscale: x = torch.log(x)
67        x = torch.clip(x, self.min_val, self.max_val) - self.offset
68        return torch.sin(x.unsqueeze(-1) * self.scale_factors - 0.5)
69