Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,910 Bytes
c968fc3 |
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 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
# 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.functional as F
import torch.nn as nn
from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
from torch import nn
LRELU_SLOPE = 0.1
# This code is a refined MRD adopted from BigVGAN under the MIT License
# https://github.com/NVIDIA/BigVGAN
class DiscriminatorR(nn.Module):
def __init__(self, cfg, resolution):
super().__init__()
self.resolution = resolution
assert (
len(self.resolution) == 3
), "MRD layer requires list with len=3, got {}".format(self.resolution)
self.lrelu_slope = LRELU_SLOPE
norm_f = (
weight_norm if cfg.model.mrd.use_spectral_norm == False else spectral_norm
)
if cfg.model.mrd.mrd_override:
print(
"INFO: overriding MRD use_spectral_norm as {}".format(
cfg.model.mrd.mrd_use_spectral_norm
)
)
norm_f = (
weight_norm
if cfg.model.mrd.mrd_use_spectral_norm == False
else spectral_norm
)
self.d_mult = cfg.model.mrd.discriminator_channel_mult_factor
if cfg.model.mrd.mrd_override:
print(
"INFO: overriding mrd channel multiplier as {}".format(
cfg.model.mrd.mrd_channel_mult
)
)
self.d_mult = cfg.model.mrd.mrd_channel_mult
self.convs = nn.ModuleList(
[
norm_f(nn.Conv2d(1, int(32 * self.d_mult), (3, 9), padding=(1, 4))),
norm_f(
nn.Conv2d(
int(32 * self.d_mult),
int(32 * self.d_mult),
(3, 9),
stride=(1, 2),
padding=(1, 4),
)
),
norm_f(
nn.Conv2d(
int(32 * self.d_mult),
int(32 * self.d_mult),
(3, 9),
stride=(1, 2),
padding=(1, 4),
)
),
norm_f(
nn.Conv2d(
int(32 * self.d_mult),
int(32 * self.d_mult),
(3, 9),
stride=(1, 2),
padding=(1, 4),
)
),
norm_f(
nn.Conv2d(
int(32 * self.d_mult),
int(32 * self.d_mult),
(3, 3),
padding=(1, 1),
)
),
]
)
self.conv_post = norm_f(
nn.Conv2d(int(32 * self.d_mult), 1, (3, 3), padding=(1, 1))
)
def forward(self, x):
fmap = []
x = self.spectrogram(x)
x = x.unsqueeze(1)
for l in self.convs:
x = l(x)
x = F.leaky_relu(x, self.lrelu_slope)
fmap.append(x)
x = self.conv_post(x)
fmap.append(x)
x = torch.flatten(x, 1, -1)
return x, fmap
def spectrogram(self, x):
n_fft, hop_length, win_length = self.resolution
x = F.pad(
x,
(int((n_fft - hop_length) / 2), int((n_fft - hop_length) / 2)),
mode="reflect",
)
x = x.squeeze(1)
x = torch.stft(
x,
n_fft=n_fft,
hop_length=hop_length,
win_length=win_length,
center=False,
return_complex=True,
)
x = torch.view_as_real(x) # [B, F, TT, 2]
mag = torch.norm(x, p=2, dim=-1) # [B, F, TT]
return mag
class MultiResolutionDiscriminator(nn.Module):
def __init__(self, cfg, debug=False):
super().__init__()
self.resolutions = cfg.model.mrd.resolutions
assert (
len(self.resolutions) == 3
), "MRD requires list of list with len=3, each element having a list with len=3. got {}".format(
self.resolutions
)
self.discriminators = nn.ModuleList(
[DiscriminatorR(cfg, resolution) for resolution in self.resolutions]
)
def forward(self, y, y_hat):
y_d_rs = []
y_d_gs = []
fmap_rs = []
fmap_gs = []
for i, d in enumerate(self.discriminators):
y_d_r, fmap_r = d(x=y)
y_d_g, fmap_g = d(x=y_hat)
y_d_rs.append(y_d_r)
fmap_rs.append(fmap_r)
y_d_gs.append(y_d_g)
fmap_gs.append(fmap_g)
return y_d_rs, y_d_gs, fmap_rs, fmap_gs
|