File size: 2,455 Bytes
b725c5a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
# 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.

# This code is modified from https://github.com/Po-Hsun-Su/pytorch-ssim

import torch
import torch.nn.functional as F
from torch.autograd import Variable
from math import exp


def gaussian(window_size, sigma):
    gauss = torch.Tensor(
        [
            exp(-((x - window_size // 2) ** 2) / float(2 * sigma**2))
            for x in range(window_size)
        ]
    )
    return gauss / gauss.sum()


def create_window(window_size, channel):
    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
    window = Variable(
        _2D_window.expand(channel, 1, window_size, window_size).contiguous()
    )
    return window


def _ssim(img1, img2, window, window_size, channel, size_average=True):
    mu1 = F.conv2d(img1, window, padding=window_size // 2, groups=channel)
    mu2 = F.conv2d(img2, window, padding=window_size // 2, groups=channel)

    mu1_sq = mu1.pow(2)
    mu2_sq = mu2.pow(2)
    mu1_mu2 = mu1 * mu2

    sigma1_sq = (
        F.conv2d(img1 * img1, window, padding=window_size // 2, groups=channel) - mu1_sq
    )
    sigma2_sq = (
        F.conv2d(img2 * img2, window, padding=window_size // 2, groups=channel) - mu2_sq
    )
    sigma12 = (
        F.conv2d(img1 * img2, window, padding=window_size // 2, groups=channel)
        - mu1_mu2
    )

    C1 = 0.01**2
    C2 = 0.03**2

    ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / (
        (mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2)
    )

    if size_average:
        return ssim_map.mean()
    else:
        return ssim_map.mean(1)


class SSIM(torch.nn.Module):
    def __init__(self, window_size=11, size_average=True):
        super(SSIM, self).__init__()
        self.window_size = window_size
        self.size_average = size_average
        self.channel = 1
        self.window = create_window(window_size, self.channel)

    def forward(self, fake, real, bias=6.0):
        fake = fake[:, None, :, :] + bias  # [B, 1, T, n_mels]
        real = real[:, None, :, :] + bias  # [B, 1, T, n_mels]
        self.window = self.window.to(dtype=fake.dtype, device=fake.device)
        loss = 1 - _ssim(
            fake, real, self.window, self.window_size, self.channel, self.size_average
        )
        return loss