Spaces:
Running on Zero
Running on Zero
File size: 4,393 Bytes
d1f1097 | 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 | import math
import torch
from torch import nn
from torch.nn.utils import weight_norm
def WNConv1d(*args, **kwargs):
return weight_norm(nn.Conv1d(*args, **kwargs))
def WNConvTranspose1d(*args, **kwargs):
return weight_norm(nn.ConvTranspose1d(*args, **kwargs))
# Scripting this brings model speed up 1.4x
@torch.jit.script
def snake(x, alpha):
shape = x.shape
x = x.reshape(shape[0], shape[1], -1)
x = x + (alpha + 1e-9).reciprocal() * torch.sin(alpha * x).pow(2)
x = x.reshape(shape)
return x
class Snake1d(nn.Module):
def __init__(self, channels):
super().__init__()
self.alpha = nn.Parameter(torch.ones(1, channels, 1))
def forward(self, x):
return snake(x, self.alpha)
class ResidualUnit(nn.Module):
def __init__(self, dim: int = 16, dilation: int = 1):
super().__init__()
pad = ((7 - 1) * dilation) // 2
self.block = nn.Sequential(
Snake1d(dim),
WNConv1d(dim, dim, kernel_size=7, dilation=dilation, padding=pad),
Snake1d(dim),
WNConv1d(dim, dim, kernel_size=1),
)
def forward(self, x):
y = self.block(x)
pad = (x.shape[-1] - y.shape[-1]) // 2
if pad > 0:
x = x[..., pad:-pad]
return x + y
class EncoderBlock(nn.Module):
def __init__(self, dim: int = 16, stride: int = 1):
super().__init__()
self.block = nn.Sequential(
ResidualUnit(dim // 2, dilation=1),
ResidualUnit(dim // 2, dilation=3),
ResidualUnit(dim // 2, dilation=9),
Snake1d(dim // 2),
WNConv1d(
dim // 2,
dim,
kernel_size=2 * stride,
stride=stride,
padding=math.ceil(stride / 2),
),
)
def forward(self, x):
return self.block(x)
class Encoder(nn.Module):
def __init__(
self,
input_channel: int = 2,
n_filters: int = 128,
strides: list = [2, 4, 8, 8],
d_latent: int = 64,
):
super().__init__()
self.input_channel = input_channel
# Create first convolution
self.block = [WNConv1d(self.input_channel, n_filters, kernel_size=7, padding=3)]
# Create EncoderBlocks that double channels as they downsample by `stride`
for stride in strides:
n_filters *= 2
self.block += [EncoderBlock(n_filters, stride=stride)]
# Create last convolution
self.block += [
Snake1d(n_filters),
WNConv1d(n_filters, d_latent, kernel_size=3, padding=1),
]
# Wrap black into nn.Sequential
self.block = nn.Sequential(*self.block)
self.enc_dim = n_filters
def forward(self, x):
return self.block(x)
class DecoderBlock(nn.Module):
def __init__(self, input_dim: int = 16, output_dim: int = 8, stride: int = 1):
super().__init__()
self.block = nn.Sequential(
Snake1d(input_dim),
WNConvTranspose1d(
input_dim,
output_dim,
kernel_size=2 * stride,
stride=stride,
padding=math.ceil(stride / 2),
),
ResidualUnit(output_dim, dilation=1),
ResidualUnit(output_dim, dilation=3),
ResidualUnit(output_dim, dilation=9),
)
def forward(self, x):
return self.block(x)
class Decoder(nn.Module):
def __init__(
self,
d_latent,
n_filters,
rates,
out_channel: int = 2,
):
super().__init__()
channels = n_filters * (2 ** len(rates))
# Add first conv layer
layers = [WNConv1d(d_latent, channels, kernel_size=7, padding=3)]
# Add upsampling + MRF blocks
for i, stride in enumerate(rates):
input_dim = channels // 2 ** i
output_dim = channels // 2 ** (i + 1)
layers += [DecoderBlock(input_dim, output_dim, stride)]
# Add final conv layer
layers += [
Snake1d(output_dim),
WNConv1d(output_dim, out_channel, kernel_size=7, padding=3),
# nn.Tanh(),
]
self.model = nn.Sequential(*layers)
def forward(self, x):
return self.model(x)
|