def __init__(self, in_channels, out_channels, kernel_size, stride, padding):
super(ResidualLayer, self).__init__()
self.conv1d_layer = nn.Sequential(
nn.Conv1d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=1,
padding=padding,
),
nn.InstanceNorm1d(num_features=out_channels, affine=True),
)
self.conv_layer_gates = nn.Sequential(
nn.Conv1d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=1,
padding=padding,
),
nn.InstanceNorm1d(num_features=out_channels, affine=True),
)
self.conv1d_out_layer = nn.Sequential(
nn.Conv1d(
in_channels=out_channels,
out_channels=in_channels,
kernel_size=kernel_size,
stride=1,
padding=padding,
),
nn.InstanceNorm1d(num_features=in_channels, affine=True),
)
def __init__(
self,
c_in,
c_cond,
c_h,
c_out,
kernel_size,
n_conv_blocks,
upsample,
act,
sn,
dropout_rate,
):
super(Decoder, self).__init__()
self.n_conv_blocks = n_conv_blocks
self.upsample = upsample
self.act = get_act(act)
f = lambda x: x
self.in_conv_layer = f(nn.Conv1d(c_in, c_h, kernel_size=1))
self.first_conv_layers = nn.ModuleList([
f(nn.Conv1d(c_h, c_h, kernel_size=kernel_size))
for _ in range(n_conv_blocks)
])
self.second_conv_layers = nn.ModuleList([
f(nn.Conv1d(c_h, c_h * up, kernel_size=kernel_size))
for _, up in zip(range(n_conv_blocks), self.upsample)
])
self.norm_layer = nn.InstanceNorm1d(c_h, affine=False)
self.conv_affine_layers = nn.ModuleList(
[f(nn.Linear(c_cond, c_h * 2)) for _ in range(n_conv_blocks * 2)])
self.out_conv_layer = f(nn.Conv1d(c_h, c_out, kernel_size=1))
self.dropout_layer = nn.Dropout(p=dropout_rate)
def downsample(self, in_channels, out_channels, kernel_size, stride, padding):
self.ConvLayer = nn.Sequential(
nn.Conv1d(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
),
nn.InstanceNorm1d(num_features=out_channels, affine=True),
GLU(),
)
return self.ConvLayer
def __init__(
self,
c_in,
c_h,
c_out,
kernel_size,
bank_size,
bank_scale,
c_bank,
n_conv_blocks,
subsample,
act,
dropout_rate,
):
super(ContentEncoder, self).__init__()
self.n_conv_blocks = n_conv_blocks
self.subsample = subsample
self.act = get_act(act)
self.conv_bank = nn.ModuleList([
nn.Conv1d(c_in, c_bank, kernel_size=k)
for k in range(bank_scale, bank_size + 1, bank_scale)
])
in_channels = c_bank * (bank_size // bank_scale) + c_in
self.in_conv_layer = nn.Conv1d(in_channels, c_h, kernel_size=1)
self.first_conv_layers = nn.ModuleList([
nn.Conv1d(c_h, c_h, kernel_size=kernel_size)
for _ in range(n_conv_blocks)
])
self.second_conv_layers = nn.ModuleList([
nn.Conv1d(c_h, c_h, kernel_size=kernel_size, stride=sub)
for sub, _ in zip(subsample, range(n_conv_blocks))
])
self.norm_layer = nn.InstanceNorm1d(c_h, affine=False)
self.mean_layer = nn.Conv1d(c_h, c_out, kernel_size=1)
self.std_layer = nn.Conv1d(c_h, c_out, kernel_size=1)
self.dropout_layer = nn.Dropout(p=dropout_rate)
def __init__(self):
super(Generator, self).__init__()
# 2D Conv Layer
self.conv1 = nn.Conv2d(
in_channels=1,
out_channels=128,
kernel_size=(5, 15),
stride=(1, 1),
padding=(2, 7),
)
self.conv1_gates = nn.Conv2d(
in_channels=1,
out_channels=128,
kernel_size=(5, 15),
stride=1,
padding=(2, 7),
)
# 2D Downsample Layer
self.downSample1 = downSample_Generator(in_channels=128,
out_channels=256,
kernel_size=5,
stride=2,
padding=2)
self.downSample2 = downSample_Generator(in_channels=256,
out_channels=256,
kernel_size=5,
stride=2,
padding=2)
# 2D -> 1D Conv
self.conv2dto1dLayer = nn.Sequential(
nn.Conv1d(in_channels=2304,
out_channels=256,
kernel_size=1,
stride=1,
padding=0),
nn.InstanceNorm1d(num_features=256, affine=True),
)
# Residual Blocks
self.residualLayer1 = ResidualLayer(in_channels=256,
out_channels=512,
kernel_size=3,
stride=1,
padding=1)
self.residualLayer2 = ResidualLayer(in_channels=256,
out_channels=512,
kernel_size=3,
stride=1,
padding=1)
self.residualLayer3 = ResidualLayer(in_channels=256,
out_channels=512,
kernel_size=3,
stride=1,
padding=1)
self.residualLayer4 = ResidualLayer(in_channels=256,
out_channels=512,
kernel_size=3,
stride=1,
padding=1)
self.residualLayer5 = ResidualLayer(in_channels=256,
out_channels=512,
kernel_size=3,
stride=1,
padding=1)
self.residualLayer6 = ResidualLayer(in_channels=256,
out_channels=512,
kernel_size=3,
stride=1,
padding=1)
# 1D -> 2D Conv
self.conv1dto2dLayer = nn.Sequential(
nn.Conv1d(in_channels=256,
out_channels=2304,
kernel_size=1,
stride=1,
padding=0),
nn.InstanceNorm1d(num_features=2304, affine=True),
)
# UpSample Layer
self.upSample1 = self.upSample(in_channels=256,
out_channels=1024,
kernel_size=5,
stride=1,
padding=2)
self.upSample2 = self.upSample(in_channels=256,
out_channels=512,
kernel_size=5,
stride=1,
padding=2)
self.lastConvLayer = nn.Conv2d(
in_channels=128,
out_channels=1,
kernel_size=(5, 15),
stride=(1, 1),
padding=(2, 7),
)
def __init__(self, input_shape=(80, 64), residual_in_channels=256):
super(Generator, self).__init__()
Cx, Tx = input_shape
self.flattened_channels = (Cx // 4) * residual_in_channels
# 2D Conv Layer
self.conv1 = nn.Conv2d(
in_channels=2,
out_channels=residual_in_channels // 2,
kernel_size=(5, 15),
stride=(1, 1),
padding=(2, 7),
)
self.conv1_gates = nn.Conv2d(
in_channels=2,
out_channels=residual_in_channels // 2,
kernel_size=(5, 15),
stride=1,
padding=(2, 7),
)
# 2D Downsampling Layers
self.downSample1 = DownSampleGenerator(
in_channels=residual_in_channels // 2,
out_channels=residual_in_channels,
kernel_size=5,
stride=2,
padding=2,
)
self.downSample2 = DownSampleGenerator(
in_channels=residual_in_channels,
out_channels=residual_in_channels,
kernel_size=5,
stride=2,
padding=2,
)
# 2D -> 1D Conv
self.conv2dto1dLayer = nn.Conv1d(
in_channels=self.flattened_channels,
out_channels=residual_in_channels,
kernel_size=1,
stride=1,
padding=0,
)
self.conv2dto1dLayer_tfan = nn.InstanceNorm1d(
num_features=residual_in_channels, affine=True
)
# Residual Blocks
self.residualLayer1 = ResidualLayer(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 2,
kernel_size=3,
stride=1,
padding=1,
)
self.residualLayer2 = ResidualLayer(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 2,
kernel_size=3,
stride=1,
padding=1,
)
self.residualLayer3 = ResidualLayer(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 2,
kernel_size=3,
stride=1,
padding=1,
)
self.residualLayer4 = ResidualLayer(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 2,
kernel_size=3,
stride=1,
padding=1,
)
self.residualLayer5 = ResidualLayer(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 2,
kernel_size=3,
stride=1,
padding=1,
)
self.residualLayer6 = ResidualLayer(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 2,
kernel_size=3,
stride=1,
padding=1,
)
# 1D -> 2D Conv
self.conv1dto2dLayer = nn.Conv1d(
in_channels=residual_in_channels,
out_channels=self.flattened_channels,
kernel_size=1,
stride=1,
padding=0,
)
self.conv1dto2dLayer_tfan = nn.InstanceNorm1d(
num_features=self.flattened_channels, affine=True
)
# UpSampling Layers
self.upSample1 = self.upsample(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 4,
kernel_size=5,
stride=1,
padding=2,
)
self.glu = GLU()
self.upSample2 = self.upsample(
in_channels=residual_in_channels,
out_channels=residual_in_channels * 2,
kernel_size=5,
stride=1,
padding=2,
)
# 2D Conv Layer
self.lastConvLayer = nn.Conv2d(
in_channels=residual_in_channels // 2,
out_channels=1,
kernel_size=(5, 15),
stride=(1, 1),
padding=(2, 7),
)