Spaces:
Running
Running
File size: 7,429 Bytes
85ce65e |
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 |
import torch
import torch.nn as nn
from .constants import N_MELS
class ConvBlockRes(nn.Module):
def __init__(self, in_channels, out_channels, momentum=0.01):
super(ConvBlockRes, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(in_channels=in_channels,
out_channels=out_channels,
kernel_size=(3, 3),
stride=(1, 1),
padding=(1, 1),
bias=False),
nn.BatchNorm2d(out_channels, momentum=momentum),
nn.ReLU(),
nn.Conv2d(in_channels=out_channels,
out_channels=out_channels,
kernel_size=(3, 3),
stride=(1, 1),
padding=(1, 1),
bias=False),
nn.BatchNorm2d(out_channels, momentum=momentum),
nn.ReLU(),
)
if in_channels != out_channels:
self.shortcut = nn.Conv2d(in_channels, out_channels, (1, 1))
self.is_shortcut = True
else:
self.is_shortcut = False
def forward(self, x):
if self.is_shortcut:
return self.conv(x) + self.shortcut(x)
else:
return self.conv(x) + x
class ResEncoderBlock(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size, n_blocks=1, momentum=0.01):
super(ResEncoderBlock, self).__init__()
self.n_blocks = n_blocks
self.conv = nn.ModuleList()
self.conv.append(ConvBlockRes(in_channels, out_channels, momentum))
for i in range(n_blocks - 1):
self.conv.append(ConvBlockRes(out_channels, out_channels, momentum))
self.kernel_size = kernel_size
if self.kernel_size is not None:
self.pool = nn.AvgPool2d(kernel_size=kernel_size)
def forward(self, x):
for i in range(self.n_blocks):
x = self.conv[i](x)
if self.kernel_size is not None:
return x, self.pool(x)
else:
return x
class ResDecoderBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride, n_blocks=1, momentum=0.01):
super(ResDecoderBlock, self).__init__()
out_padding = (0, 1) if stride == (1, 2) else (1, 1)
self.n_blocks = n_blocks
self.conv1 = nn.Sequential(
nn.ConvTranspose2d(in_channels=in_channels,
out_channels=out_channels,
kernel_size=(3, 3),
stride=stride,
padding=(1, 1),
output_padding=out_padding,
bias=False),
nn.BatchNorm2d(out_channels, momentum=momentum),
nn.ReLU(),
)
self.conv2 = nn.ModuleList()
self.conv2.append(ConvBlockRes(out_channels * 2, out_channels, momentum))
for i in range(n_blocks-1):
self.conv2.append(ConvBlockRes(out_channels, out_channels, momentum))
def forward(self, x, concat_tensor):
x = self.conv1(x)
x = torch.cat((x, concat_tensor), dim=1)
for i in range(self.n_blocks):
x = self.conv2[i](x)
return x
class Encoder(nn.Module):
def __init__(self, in_channels, in_size, n_encoders, kernel_size, n_blocks, out_channels=16, momentum=0.01):
super(Encoder, self).__init__()
self.n_encoders = n_encoders
self.bn = nn.BatchNorm2d(in_channels, momentum=momentum)
self.layers = nn.ModuleList()
self.latent_channels = []
for i in range(self.n_encoders):
self.layers.append(ResEncoderBlock(in_channels, out_channels, kernel_size, n_blocks, momentum=momentum))
self.latent_channels.append([out_channels, in_size])
in_channels = out_channels
out_channels *= 2
in_size //= 2
self.out_size = in_size
self.out_channel = out_channels
def forward(self, x):
concat_tensors = []
x = self.bn(x)
for i in range(self.n_encoders):
_, x = self.layers[i](x)
concat_tensors.append(_)
return x, concat_tensors
class Intermediate(nn.Module):
def __init__(self, in_channels, out_channels, n_inters, n_blocks, momentum=0.01):
super(Intermediate, self).__init__()
self.n_inters = n_inters
self.layers = nn.ModuleList()
self.layers.append(ResEncoderBlock(in_channels, out_channels, None, n_blocks, momentum))
for i in range(self.n_inters-1):
self.layers.append(ResEncoderBlock(out_channels, out_channels, None, n_blocks, momentum))
def forward(self, x):
for i in range(self.n_inters):
x = self.layers[i](x)
return x
class Decoder(nn.Module):
def __init__(self, in_channels, n_decoders, stride, n_blocks, momentum=0.01):
super(Decoder, self).__init__()
self.layers = nn.ModuleList()
self.n_decoders = n_decoders
for i in range(self.n_decoders):
out_channels = in_channels // 2
self.layers.append(ResDecoderBlock(in_channels, out_channels, stride, n_blocks, momentum))
in_channels = out_channels
def forward(self, x, concat_tensors):
for i in range(self.n_decoders):
x = self.layers[i](x, concat_tensors[-1-i])
return x
class TimbreFilter(nn.Module):
def __init__(self, latent_rep_channels):
super(TimbreFilter, self).__init__()
self.layers = nn.ModuleList()
for latent_rep in latent_rep_channels:
self.layers.append(ConvBlockRes(latent_rep[0], latent_rep[0]))
def forward(self, x_tensors):
out_tensors = []
for i, layer in enumerate(self.layers):
out_tensors.append(layer(x_tensors[i]))
return out_tensors
class DeepUnet(nn.Module):
def __init__(self, kernel_size, n_blocks, en_de_layers=5, inter_layers=4, in_channels=1, en_out_channels=16):
super(DeepUnet, self).__init__()
self.encoder = Encoder(in_channels, N_MELS, en_de_layers, kernel_size, n_blocks, en_out_channels)
self.intermediate = Intermediate(self.encoder.out_channel // 2, self.encoder.out_channel, inter_layers, n_blocks)
self.tf = TimbreFilter(self.encoder.latent_channels)
self.decoder = Decoder(self.encoder.out_channel, en_de_layers, kernel_size, n_blocks)
def forward(self, x):
x, concat_tensors = self.encoder(x)
x = self.intermediate(x)
concat_tensors = self.tf(concat_tensors)
x = self.decoder(x, concat_tensors)
return x
class DeepUnet0(nn.Module):
def __init__(self, kernel_size, n_blocks, en_de_layers=5, inter_layers=4, in_channels=1, en_out_channels=16):
super(DeepUnet0, self).__init__()
self.encoder = Encoder(in_channels, N_MELS, en_de_layers, kernel_size, n_blocks, en_out_channels)
self.intermediate = Intermediate(self.encoder.out_channel // 2, self.encoder.out_channel, inter_layers, n_blocks)
self.tf = TimbreFilter(self.encoder.latent_channels)
self.decoder = Decoder(self.encoder.out_channel, en_de_layers, kernel_size, n_blocks)
def forward(self, x):
x, concat_tensors = self.encoder(x)
x = self.intermediate(x)
x = self.decoder(x, concat_tensors)
return x
|