39 lines
1.4 KiB
Python
39 lines
1.4 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.utils as utils
|
|
|
|
def discriminator_block(in_channels, out_channels, kernel_size=3, stride=1, dilation=1):
|
|
padding = (kernel_size // 2) * dilation
|
|
return nn.Sequential(
|
|
utils.spectral_norm(
|
|
nn.Conv1d(in_channels, out_channels,
|
|
kernel_size=kernel_size,
|
|
stride=stride,
|
|
dilation=dilation,
|
|
padding=padding
|
|
)
|
|
),
|
|
nn.BatchNorm1d(out_channels),
|
|
nn.LeakyReLU(0.2, inplace=True)
|
|
)
|
|
|
|
class SISUDiscriminator(nn.Module):
|
|
def __init__(self):
|
|
super(SISUDiscriminator, self).__init__()
|
|
layers = 4
|
|
self.model = nn.Sequential(
|
|
discriminator_block(1, layers, kernel_size=7, stride=2, dilation=1),
|
|
discriminator_block(layers, layers * 2, kernel_size=5, stride=2, dilation=1),
|
|
discriminator_block(layers * 2, layers * 4, kernel_size=3, dilation=4),
|
|
discriminator_block(layers * 4, layers * 4, kernel_size=5, dilation=8),
|
|
discriminator_block(layers * 4, layers * 2, kernel_size=3, dilation=16),
|
|
discriminator_block(layers * 2, layers, kernel_size=5, dilation=2),
|
|
discriminator_block(layers, 1, kernel_size=3, stride=1)
|
|
)
|
|
self.global_avg_pool = nn.AdaptiveAvgPool1d(1)
|
|
|
|
def forward(self, x):
|
|
x = self.model(x)
|
|
x = self.global_avg_pool(x)
|
|
return x.view(-1, 1)
|