USR-DA / model /decoder.py
DS
dump shiet
e5b70eb
raw
history blame
9.32 kB
import torch
import torch.nn as nn
from torch.nn import init as init
import torch.nn.functional as F
from torch.nn.modules.batchnorm import _BatchNorm
class Decoder_Identity(nn.Module):
def __init__(self):
super(Decoder_Identity, self).__init__()
self.conv_up_2 = nn.Sequential(
nn.ConvTranspose2d(in_channels=64, out_channels=32, kernel_size=3, stride=2, padding=1, output_padding=1, dilation=1),
nn.ReLU(),
nn.Conv2d(in_channels=32, out_channels=32, kernel_size=3, padding=1, bias=True),
nn.ReLU(),
nn.Conv2d(in_channels=32, out_channels=32, kernel_size=3, padding=1, bias=True),
nn.ReLU()
)
self.conv_up_1 = nn.Sequential(
nn.ConvTranspose2d(in_channels=32, out_channels=16, kernel_size=3, stride=2, padding=1, output_padding=1, dilation=1),
nn.ReLU(),
nn.Conv2d(in_channels=16, out_channels=16, kernel_size=3, padding=1, bias=True),
nn.ReLU(),
nn.Conv2d(in_channels=16, out_channels=16, kernel_size=3, padding=1, bias=True),
nn.ReLU()
)
self.conv_last = nn.Sequential(
nn.Conv2d(in_channels=16, out_channels=3, kernel_size=1, bias=True),
nn.ReLU()
)
def forward(self, feat):
featmap_2 = self.conv_up_2(feat)
featmap_1 = self.conv_up_1(featmap_2)
out = self.conv_last(featmap_1)
return out
class Decoder_SR(nn.Module):
def __init__(self, scale=4):
super(Decoder_SR, self).__init__()
self.scale = scale
self.conv_up_2 = nn.Sequential(
nn.ConvTranspose2d(in_channels=64, out_channels=32, kernel_size=3, stride=2, padding=1, output_padding=1, dilation=1),
nn.ReLU(),
nn.Conv2d(in_channels=32, out_channels=32, kernel_size=3, padding=1, bias=True),
nn.ReLU(),
nn.Conv2d(in_channels=32, out_channels=32, kernel_size=3, padding=1, bias=True),
nn.ReLU()
)
self.conv_up_1 = nn.Sequential(
nn.ConvTranspose2d(in_channels=32, out_channels=16, kernel_size=3, stride=2, padding=1, output_padding=1, dilation=1),
nn.ReLU(),
nn.Conv2d(in_channels=16, out_channels=16, kernel_size=3, padding=1, bias=True),
nn.ReLU(),
nn.Conv2d(in_channels=16, out_channels=16, kernel_size=3, padding=1, bias=True),
nn.ReLU()
)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
# upsampling
self.upsample_1 = nn.Conv2d(in_channels=16, out_channels=16, kernel_size=3, padding=1, bias=True)
self.upsample_2 = nn.Conv2d(in_channels=16, out_channels=16, kernel_size=3, padding=1, bias=True)
self.HR_conv = nn.Conv2d(in_channels=16, out_channels=16, kernel_size=3, padding=1, bias=True)
self.conv_last = nn.Conv2d(in_channels=16, out_channels=3, kernel_size=3, padding=1, bias=True)
def forward(self, feat):
featmap_2 = self.conv_up_2(feat)
featmap_1 = self.conv_up_1(featmap_2)
if self.scale == 4:
featmap = self.lrelu(self.upsample_1(F.interpolate(featmap_1, scale_factor=2, mode='nearest')))
featmap = self.lrelu(self.upsample_2(F.interpolate(featmap, scale_factor=2, mode='nearest')))
elif self.scale == 2:
featmap = self.lrelu(self.upsample_1(F.interpolate(featmap_1, scale_factor=2, mode='nearest')))
out = self.conv_last(self.lrelu(self.HR_conv(featmap)))
return out
def default_init_weights(module_list, scale=1, bias_fill=0, **kwargs):
"""Initialize network weights.
Args:
module_list (list[nn.Module] | nn.Module): Modules to be initialized.
scale (float): Scale initialized weights, especially for residual
blocks. Default: 1.
bias_fill (float): The value to fill bias. Default: 0
kwargs (dict): Other arguments for initialization function.
"""
if not isinstance(module_list, list):
module_list = [module_list]
for module in module_list:
for m in module.modules():
if isinstance(m, nn.Conv2d):
init.kaiming_normal_(m.weight, **kwargs)
m.weight.data *= scale
if m.bias is not None:
m.bias.data.fill_(bias_fill)
elif isinstance(m, nn.Linear):
init.kaiming_normal_(m.weight, **kwargs)
m.weight.data *= scale
if m.bias is not None:
m.bias.data.fill_(bias_fill)
elif isinstance(m, _BatchNorm):
init.constant_(m.weight, 1)
if m.bias is not None:
m.bias.data.fill_(bias_fill)
def make_layer(basic_block, num_basic_block, **kwarg):
"""Make layers by stacking the same blocks.
Args:
basic_block (nn.module): nn.module class for basic block.
num_basic_block (int): number of blocks.
Returns:
nn.Sequential: Stacked blocks in nn.Sequential.
"""
layers = []
for _ in range(num_basic_block):
layers.append(basic_block(**kwarg))
return nn.Sequential(*layers)
class ResidualDenseBlock(nn.Module):
"""Residual Dense Block.
Used in RRDB block in ESRGAN.
Args:
num_feat (int): Channel number of intermediate features.
num_grow_ch (int): Channels for each growth.
"""
def __init__(self, num_feat=64, num_grow_ch=32):
super(ResidualDenseBlock, self).__init__()
self.conv1 = nn.Conv2d(num_feat, num_grow_ch, 3, 1, 1)
self.conv2 = nn.Conv2d(num_feat + num_grow_ch, num_grow_ch, 3, 1, 1)
self.conv3 = nn.Conv2d(num_feat + 2 * num_grow_ch, num_grow_ch, 3, 1, 1)
self.conv4 = nn.Conv2d(num_feat + 3 * num_grow_ch, num_grow_ch, 3, 1, 1)
self.conv5 = nn.Conv2d(num_feat + 4 * num_grow_ch, num_feat, 3, 1, 1)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
# initialization
default_init_weights([self.conv1, self.conv2, self.conv3, self.conv4, self.conv5], 0.1)
def forward(self, x):
x1 = self.lrelu(self.conv1(x))
x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1)))
x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1)))
x4 = self.lrelu(self.conv4(torch.cat((x, x1, x2, x3), 1)))
x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
# Emperically, we use 0.2 to scale the residual for better performance
return x5 * 0.2 + x
class RRDB(nn.Module):
"""Residual in Residual Dense Block.
Used in RRDB-Net in ESRGAN.
Args:
num_feat (int): Channel number of intermediate features.
num_grow_ch (int): Channels for each growth.
"""
def __init__(self, num_feat, num_grow_ch=32):
super(RRDB, self).__init__()
self.rdb1 = ResidualDenseBlock(num_feat, num_grow_ch)
self.rdb2 = ResidualDenseBlock(num_feat, num_grow_ch)
self.rdb3 = ResidualDenseBlock(num_feat, num_grow_ch)
def forward(self, x):
out = self.rdb1(x)
out = self.rdb2(out)
out = self.rdb3(out)
# Emperically, we use 0.2 to scale the residual for better performance
return out * 0.2 + x
class Decoder_Id_RRDB(nn.Module):
def __init__(self, num_in_ch, num_out_ch=3, scale=4, num_feat=64, num_block=10, num_grow_ch=32):
super(Decoder_Id_RRDB, self).__init__()
self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1)
self.body = make_layer(RRDB, num_block, num_feat=num_feat, num_grow_ch=num_grow_ch)
self.conv_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
def forward(self, x):
feat = self.conv_first(x)
body_feat = self.conv_body(self.body(feat))
feat = feat + body_feat
out = self.conv_last(self.lrelu(self.conv_hr(feat)))
return out
class Decoder_SR_RRDB(nn.Module):
def __init__(self, num_in_ch, num_out_ch=3, scale=4, num_feat=64, num_block=23, num_grow_ch=32):
super(Decoder_SR_RRDB, self).__init__()
self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1)
self.body = make_layer(RRDB, num_block, num_feat=num_feat, num_grow_ch=num_grow_ch)
self.conv_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
# upsample
self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
def forward(self, x):
feat = self.conv_first(x)
body_feat = self.conv_body(self.body(feat))
feat = feat + body_feat
# upsample
feat = self.lrelu(self.conv_up1(F.interpolate(feat, scale_factor=2, mode='nearest')))
feat = self.lrelu(self.conv_up2(F.interpolate(feat, scale_factor=2, mode='nearest')))
out = self.conv_last(self.lrelu(self.conv_hr(feat)))
return out