File size: 18,555 Bytes
78b6bf0
 
 
 
 
 
 
aefd3f3
 
78b6bf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aefd3f3
78b6bf0
 
 
 
 
 
 
 
 
 
 
aefd3f3
78b6bf0
 
 
 
 
 
 
 
 
aefd3f3
78b6bf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
import math
import warnings

import torch
from torch import nn
from torch.nn import Conv1d
from torch.nn import functional as F
from torch.nn.utils import remove_weight_norm
from torch.nn.utils.parametrizations import weight_norm

import commons
from attentions import Encoder
from commons import get_padding, init_weights
from transforms import piecewise_rational_quadratic_transform

LRELU_SLOPE = 0.1


class LayerNorm(nn.Module):
    def __init__(self, channels, eps=1e-5):
        super().__init__()
        self.channels = channels
        self.eps = eps

        self.gamma = nn.Parameter(torch.ones(channels))
        self.beta = nn.Parameter(torch.zeros(channels))

    def forward(self, x):
        x = x.transpose(1, -1)
        x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
        return x.transpose(1, -1)


class ConvReluNorm(nn.Module):
    def __init__(
        self,
        in_channels,
        hidden_channels,
        out_channels,
        kernel_size,
        n_layers,
        p_dropout,
    ):
        super().__init__()
        self.in_channels = in_channels
        self.hidden_channels = hidden_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.p_dropout = p_dropout
        assert n_layers > 1, "Number of layers should be larger than 0."

        self.conv_layers = nn.ModuleList()
        self.norm_layers = nn.ModuleList()
        self.conv_layers.append(
            nn.Conv1d(
                in_channels, hidden_channels, kernel_size, padding=kernel_size // 2
            )
        )
        self.norm_layers.append(LayerNorm(hidden_channels))
        self.relu_drop = nn.Sequential(nn.ReLU(), nn.Dropout(p_dropout))
        for _ in range(n_layers - 1):
            self.conv_layers.append(
                nn.Conv1d(
                    hidden_channels,
                    hidden_channels,
                    kernel_size,
                    padding=kernel_size // 2,
                )
            )
            self.norm_layers.append(LayerNorm(hidden_channels))
        self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
        self.proj.weight.data.zero_()
        self.proj.bias.data.zero_()

    def forward(self, x, x_mask):
        x_org = x
        for i in range(self.n_layers):
            x = self.conv_layers[i](x * x_mask)
            x = self.norm_layers[i](x)
            x = self.relu_drop(x)
        x = x_org + self.proj(x)
        return x * x_mask


class DDSConv(nn.Module):
    """
    Dialted and Depth-Separable Convolution
    """

    def __init__(self, channels, kernel_size, n_layers, p_dropout=0.0):
        super().__init__()
        self.channels = channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.p_dropout = p_dropout

        self.drop = nn.Dropout(p_dropout)
        self.convs_sep = nn.ModuleList()
        self.convs_1x1 = nn.ModuleList()
        self.norms_1 = nn.ModuleList()
        self.norms_2 = nn.ModuleList()
        for i in range(n_layers):
            dilation = kernel_size**i
            padding = (kernel_size * dilation - dilation) // 2
            self.convs_sep.append(
                nn.Conv1d(
                    channels,
                    channels,
                    kernel_size,
                    groups=channels,
                    dilation=dilation,
                    padding=padding,
                )
            )
            self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
            self.norms_1.append(LayerNorm(channels))
            self.norms_2.append(LayerNorm(channels))

    def forward(self, x, x_mask, g=None):
        if g is not None:
            x = x + g
        for i in range(self.n_layers):
            y = self.convs_sep[i](x * x_mask)
            y = self.norms_1[i](y)
            y = F.gelu(y)
            y = self.convs_1x1[i](y)
            y = self.norms_2[i](y)
            y = F.gelu(y)
            y = self.drop(y)
            x = x + y
        return x * x_mask


class WN(torch.nn.Module):
    def __init__(
        self,
        hidden_channels,
        kernel_size,
        dilation_rate,
        n_layers,
        gin_channels=0,
        p_dropout=0,
    ):
        super(WN, self).__init__()
        assert kernel_size % 2 == 1
        self.hidden_channels = hidden_channels
        self.kernel_size = (kernel_size,)
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.gin_channels = gin_channels
        self.p_dropout = p_dropout

        self.in_layers = torch.nn.ModuleList()
        self.res_skip_layers = torch.nn.ModuleList()
        self.drop = nn.Dropout(p_dropout)

        if gin_channels != 0:
            cond_layer = torch.nn.Conv1d(
                gin_channels, 2 * hidden_channels * n_layers, 1
            )
            self.cond_layer = torch.nn.utils.parametrizations.weight_norm(cond_layer, name="weight")

        for i in range(n_layers):
            dilation = dilation_rate**i
            padding = int((kernel_size * dilation - dilation) / 2)
            in_layer = torch.nn.Conv1d(
                hidden_channels,
                2 * hidden_channels,
                kernel_size,
                dilation=dilation,
                padding=padding,
            )
            in_layer = torch.nn.utils.parametrizations.weight_norm(in_layer, name="weight")
            self.in_layers.append(in_layer)

            # last one is not necessary
            if i < n_layers - 1:
                res_skip_channels = 2 * hidden_channels
            else:
                res_skip_channels = hidden_channels

            res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
            res_skip_layer = torch.nn.utils.parametrizations.weight_norm(res_skip_layer, name="weight")
            self.res_skip_layers.append(res_skip_layer)

    def forward(self, x, x_mask, g=None, **kwargs):
        output = torch.zeros_like(x)
        n_channels_tensor = torch.IntTensor([self.hidden_channels])

        if g is not None:
            g = self.cond_layer(g)

        for i in range(self.n_layers):
            x_in = self.in_layers[i](x)
            if g is not None:
                cond_offset = i * 2 * self.hidden_channels
                g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
            else:
                g_l = torch.zeros_like(x_in)

            acts = commons.fused_add_tanh_sigmoid_multiply(x_in, g_l, n_channels_tensor)
            acts = self.drop(acts)

            res_skip_acts = self.res_skip_layers[i](acts)
            if i < self.n_layers - 1:
                res_acts = res_skip_acts[:, : self.hidden_channels, :]
                x = (x + res_acts) * x_mask
                output = output + res_skip_acts[:, self.hidden_channels :, :]
            else:
                output = output + res_skip_acts
        return output * x_mask

    def remove_weight_norm(self):
        if self.gin_channels != 0:
            torch.nn.utils.remove_weight_norm(self.cond_layer)
        for l in self.in_layers:
            torch.nn.utils.remove_weight_norm(l)
        for l in self.res_skip_layers:
            torch.nn.utils.remove_weight_norm(l)


class ResBlock1(torch.nn.Module):
    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
        super(ResBlock1, self).__init__()
        self.convs1 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=get_padding(kernel_size, dilation[1]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[2],
                        padding=get_padding(kernel_size, dilation[2]),
                    )
                ),
            ]
        )
        self.convs1.apply(init_weights)

        self.convs2 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
            ]
        )
        self.convs2.apply(init_weights)

    def forward(self, x, x_mask=None):
        for c1, c2 in zip(self.convs1, self.convs2):
            xt = F.leaky_relu(x, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c1(xt)
            xt = F.leaky_relu(xt, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c2(xt)
            x = xt + x
        if x_mask is not None:
            x = x * x_mask
        return x

    def remove_weight_norm(self):
        for l in self.convs1:
            remove_weight_norm(l)
        for l in self.convs2:
            remove_weight_norm(l)


class ResBlock2(torch.nn.Module):
    def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
        super(ResBlock2, self).__init__()
        self.convs = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=get_padding(kernel_size, dilation[1]),
                    )
                ),
            ]
        )
        self.convs.apply(init_weights)

    def forward(self, x, x_mask=None):
        for c in self.convs:
            xt = F.leaky_relu(x, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c(xt)
            x = xt + x
        if x_mask is not None:
            x = x * x_mask
        return x

    def remove_weight_norm(self):
        for l in self.convs:
            remove_weight_norm(l)


class Log(nn.Module):
    def forward(self, x, x_mask, reverse=False, **kwargs):
        if not reverse:
            y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
            logdet = torch.sum(-y, [1, 2])
            return y, logdet
        else:
            x = torch.exp(x) * x_mask
            return x


class Flip(nn.Module):
    def forward(self, x, *args, reverse=False, **kwargs):
        x = torch.flip(x, [1])
        if not reverse:
            logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
            return x, logdet
        else:
            return x


class ElementwiseAffine(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.channels = channels
        self.m = nn.Parameter(torch.zeros(channels, 1))
        self.logs = nn.Parameter(torch.zeros(channels, 1))

    def forward(self, x, x_mask, reverse=False, **kwargs):
        if not reverse:
            y = self.m + torch.exp(self.logs) * x
            y = y * x_mask
            logdet = torch.sum(self.logs * x_mask, [1, 2])
            return y, logdet
        else:
            x = (x - self.m) * torch.exp(-self.logs) * x_mask
            return x


class ResidualCouplingLayer(nn.Module):
    def __init__(
        self,
        channels,
        hidden_channels,
        kernel_size,
        dilation_rate,
        n_layers,
        p_dropout=0,
        gin_channels=0,
        mean_only=False,
    ):
        assert channels % 2 == 0, "channels should be divisible by 2"
        super().__init__()
        self.channels = channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.half_channels = channels // 2
        self.mean_only = mean_only

        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
        self.enc = WN(
            hidden_channels,
            kernel_size,
            dilation_rate,
            n_layers,
            p_dropout=p_dropout,
            gin_channels=gin_channels,
        )
        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
        self.post.weight.data.zero_()
        self.post.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0) * x_mask
        h = self.enc(h, x_mask, g=g)
        stats = self.post(h) * x_mask
        if not self.mean_only:
            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
        else:
            m = stats
            logs = torch.zeros_like(m)

        if not reverse:
            x1 = m + x1 * torch.exp(logs) * x_mask
            x = torch.cat([x0, x1], 1)
            logdet = torch.sum(logs, [1, 2])
            return x, logdet
        else:
            x1 = (x1 - m) * torch.exp(-logs) * x_mask
            x = torch.cat([x0, x1], 1)
            return x


class ConvFlow(nn.Module):
    def __init__(
        self,
        in_channels,
        filter_channels,
        kernel_size,
        n_layers,
        num_bins=10,
        tail_bound=5.0,
    ):
        super().__init__()
        self.in_channels = in_channels
        self.filter_channels = filter_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.num_bins = num_bins
        self.tail_bound = tail_bound
        self.half_channels = in_channels // 2

        self.pre = nn.Conv1d(self.half_channels, filter_channels, 1)
        self.convs = DDSConv(filter_channels, kernel_size, n_layers, p_dropout=0.0)
        self.proj = nn.Conv1d(
            filter_channels, self.half_channels * (num_bins * 3 - 1), 1
        )
        self.proj.weight.data.zero_()
        self.proj.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0)
        h = self.convs(h, x_mask, g=g)
        h = self.proj(h) * x_mask

        b, c, t = x0.shape
        h = h.reshape(b, c, -1, t).permute(0, 1, 3, 2)  # [b, cx?, t] -> [b, c, t, ?]

        unnormalized_widths = h[..., : self.num_bins] / math.sqrt(self.filter_channels)
        unnormalized_heights = h[..., self.num_bins : 2 * self.num_bins] / math.sqrt(
            self.filter_channels
        )
        unnormalized_derivatives = h[..., 2 * self.num_bins :]

        x1, logabsdet = piecewise_rational_quadratic_transform(
            x1,
            unnormalized_widths,
            unnormalized_heights,
            unnormalized_derivatives,
            inverse=reverse,
            tails="linear",
            tail_bound=self.tail_bound,
        )

        x = torch.cat([x0, x1], 1) * x_mask
        logdet = torch.sum(logabsdet * x_mask, [1, 2])
        if not reverse:
            return x, logdet
        else:
            return x


class TransformerCouplingLayer(nn.Module):
    def __init__(
        self,
        channels,
        hidden_channels,
        kernel_size,
        n_layers,
        n_heads,
        p_dropout=0,
        filter_channels=0,
        mean_only=False,
        wn_sharing_parameter=None,
        gin_channels=0,
    ):
        assert channels % 2 == 0, "channels should be divisible by 2"
        super().__init__()
        self.channels = channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.half_channels = channels // 2
        self.mean_only = mean_only

        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
        self.enc = (
            Encoder(
                hidden_channels,
                filter_channels,
                n_heads,
                n_layers,
                kernel_size,
                p_dropout,
                isflow=True,
                gin_channels=gin_channels,
            )
            if wn_sharing_parameter is None
            else wn_sharing_parameter
        )
        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
        self.post.weight.data.zero_()
        self.post.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0) * x_mask
        h = self.enc(h, x_mask, g=g)
        stats = self.post(h) * x_mask
        if not self.mean_only:
            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
        else:
            m = stats
            logs = torch.zeros_like(m)

        if not reverse:
            x1 = m + x1 * torch.exp(logs) * x_mask
            x = torch.cat([x0, x1], 1)
            logdet = torch.sum(logs, [1, 2])
            return x, logdet
        else:
            x1 = (x1 - m) * torch.exp(-logs) * x_mask
            x = torch.cat([x0, x1], 1)
            return x