File size: 11,072 Bytes
c7b379a |
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 |
from typing import Optional, List, Tuple
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, weight_norm
from .norms import WN
from .utils import (
get_padding,
call_weight_data_normal_if_Conv,
)
LRELU_SLOPE = 0.1
class ResBlock1(torch.nn.Module):
def __init__(
self,
channels: int,
kernel_size: int = 3,
dilation: List[int] = (1, 3, 5),
):
super(ResBlock1, self).__init__()
self.convs1 = nn.ModuleList()
for d in dilation:
self.convs1.append(
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=d,
padding=get_padding(kernel_size, d),
)
),
)
self.convs1.apply(call_weight_data_normal_if_Conv)
self.convs2 = nn.ModuleList()
for _ in dilation:
self.convs2.append(
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=1,
padding=get_padding(kernel_size, 1),
)
),
)
self.convs2.apply(call_weight_data_normal_if_Conv)
self.lrelu_slope = LRELU_SLOPE
def __call__(
self,
x: torch.Tensor,
x_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
return super().__call__(x, x_mask=x_mask)
def forward(
self,
x: torch.Tensor,
x_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
for c1, c2 in zip(self.convs1, self.convs2):
xt = F.leaky_relu(x, self.lrelu_slope)
if x_mask is not None:
xt = xt * x_mask
xt = c1(xt)
xt = F.leaky_relu(xt, self.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)
def __prepare_scriptable__(self):
for l in self.convs1:
for hook in l._forward_pre_hooks.values():
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(l)
for l in self.convs2:
for hook in l._forward_pre_hooks.values():
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(l)
return self
class ResBlock2(torch.nn.Module):
"""
Actually this module is not used currently
because all configs specified "resblock": "1"
"""
def __init__(
self,
channels: int,
kernel_size=3,
dilation: List[int] = (1, 3),
):
super(ResBlock2, self).__init__()
self.convs = nn.ModuleList()
for d in dilation:
self.convs.append(
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=d,
padding=get_padding(kernel_size, d),
)
),
)
self.convs.apply(call_weight_data_normal_if_Conv)
self.lrelu_slope = LRELU_SLOPE
def __call__(
self,
x: torch.Tensor,
x_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
return super().__call__(x, x_mask=x_mask)
def forward(
self,
x: torch.Tensor,
x_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
for c in self.convs:
xt = F.leaky_relu(x, self.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)
def __prepare_scriptable__(self):
for l in self.convs:
for hook in l._forward_pre_hooks.values():
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(l)
return self
class ResidualCouplingLayer(nn.Module):
def __init__(
self,
channels: int,
hidden_channels: int,
kernel_size: int,
dilation_rate: int,
n_layers: int,
p_dropout: int = 0,
gin_channels: int = 0,
mean_only: bool = False,
):
assert channels % 2 == 0, "channels should be divisible by 2"
super(ResidualCouplingLayer, self).__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=float(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 __call__(
self,
x: torch.Tensor,
x_mask: torch.Tensor,
g: Optional[torch.Tensor] = None,
reverse: bool = False,
) -> Tuple[torch.Tensor, torch.Tensor]:
return super().__call__(x, x_mask, g=g, reverse=reverse)
def forward(
self,
x: torch.Tensor,
x_mask: torch.Tensor,
g: Optional[torch.Tensor] = None,
reverse: bool = False,
) -> Tuple[torch.Tensor, torch.Tensor]:
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
x1 = (x1 - m) * torch.exp(-logs) * x_mask
x = torch.cat([x0, x1], 1)
return x, torch.zeros([1])
def remove_weight_norm(self):
self.enc.remove_weight_norm()
def __prepare_scriptable__(self):
for hook in self.enc._forward_pre_hooks.values():
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(self.enc)
return self
class ResidualCouplingBlock(nn.Module):
class Flip(nn.Module):
"""
torch.jit.script() Compiled functions
can't take variable number of arguments or
use keyword-only arguments with defaults
"""
def forward(
self,
x: torch.Tensor,
x_mask: torch.Tensor,
g: Optional[torch.Tensor] = None,
reverse: bool = False,
) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
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, torch.zeros([1], device=x.device)
def __init__(
self,
channels: int,
hidden_channels: int,
kernel_size: int,
dilation_rate: int,
n_layers: int,
n_flows: int = 4,
gin_channels: int = 0,
):
super(ResidualCouplingBlock, self).__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.n_flows = n_flows
self.gin_channels = gin_channels
self.flows = nn.ModuleList()
for _ in range(n_flows):
self.flows.append(
ResidualCouplingLayer(
channels,
hidden_channels,
kernel_size,
dilation_rate,
n_layers,
gin_channels=gin_channels,
mean_only=True,
)
)
self.flows.append(self.Flip())
def __call__(
self,
x: torch.Tensor,
x_mask: torch.Tensor,
g: Optional[torch.Tensor] = None,
reverse: bool = False,
) -> torch.Tensor:
return super().__call__(x, x_mask, g=g, reverse=reverse)
def forward(
self,
x: torch.Tensor,
x_mask: torch.Tensor,
g: Optional[torch.Tensor] = None,
reverse: bool = False,
) -> torch.Tensor:
if not reverse:
for flow in self.flows:
x, _ = flow(x, x_mask, g=g, reverse=reverse)
else:
for flow in reversed(self.flows):
x, _ = flow.forward(x, x_mask, g=g, reverse=reverse)
return x
def remove_weight_norm(self):
for i in range(self.n_flows):
self.flows[i * 2].remove_weight_norm()
def __prepare_scriptable__(self):
for i in range(self.n_flows):
for hook in self.flows[i * 2]._forward_pre_hooks.values():
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(self.flows[i * 2])
return self
|