models/vocoders/gan/discriminator/msd.py

# 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 import Conv1d, AvgPool1d
from torch.nn.utils import weight_norm, spectral_norm
from torch import nn
from modules.vocoder_blocks import *


LRELU_SLOPE = 0.1


class DiscriminatorS(nn.Module):
    def __init__(self, use_spectral_norm=False):
        super(DiscriminatorS, self).__init__()

        norm_f = weight_norm if use_spectral_norm == False else spectral_norm

        self.convs = nn.ModuleList(
            [
                norm_f(Conv1d(1, 128, 15, 1, padding=7)),
                norm_f(Conv1d(128, 128, 41, 2, groups=4, padding=20)),
                norm_f(Conv1d(128, 256, 41, 2, groups=16, padding=20)),
                norm_f(Conv1d(256, 512, 41, 4, groups=16, padding=20)),
                norm_f(Conv1d(512, 1024, 41, 4, groups=16, padding=20)),
                norm_f(Conv1d(1024, 1024, 41, 1, groups=16, padding=20)),
                norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
            ]
        )

        self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))

    def forward(self, x):
        fmap = []

        for l in self.convs:
            x = l(x)
            x = F.leaky_relu(x, LRELU_SLOPE)
            fmap.append(x)

        x = self.conv_post(x)
        fmap.append(x)
        x = torch.flatten(x, 1, -1)

        return x, fmap


class MultiScaleDiscriminator(nn.Module):
    def __init__(self, cfg):
        super(MultiScaleDiscriminator, self).__init__()

        self.cfg = cfg

        self.discriminators = nn.ModuleList(
            [
                DiscriminatorS(use_spectral_norm=True),
                DiscriminatorS(),
                DiscriminatorS(),
            ]
        )

        self.meanpools = nn.ModuleList(
            [AvgPool1d(4, 2, padding=2), AvgPool1d(4, 2, padding=2)]
        )

    def forward(self, y, y_hat):
        y_d_rs = []
        y_d_gs = []
        fmap_rs = []
        fmap_gs = []

        for i, d in enumerate(self.discriminators):
            if i != 0:
                y = self.meanpools[i - 1](y)
                y_hat = self.meanpools[i - 1](y_hat)
            y_d_r, fmap_r = d(y)
            y_d_g, fmap_g = d(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


class MultiScaleDiscriminator_JETS(nn.Module):
    def __init__(self):
        super(MultiScaleDiscriminator_JETS, self).__init__()

        self.discriminators = nn.ModuleList(
            [
                DiscriminatorS(use_spectral_norm=True),
                DiscriminatorS(),
                DiscriminatorS(),
            ]
        )

        self.meanpools = nn.ModuleList(
            [AvgPool1d(4, 2, padding=2), AvgPool1d(4, 2, padding=2)]
        )

    def forward(self, y):
        y_d_rs = []  # p, y, groud-truth
        fmap_rs = []

        for i, d in enumerate(self.discriminators):
            if i != 0:
                y = self.meanpools[i - 1](y)
            y_d_r, fmap_r = d(y)
            y_d_rs.append(y_d_r)
            fmap_rs.append(fmap_r)

        return y_d_rs, fmap_rs
        # fmap_rs is real, fmap_gs is generated.