mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
126 lines
4.7 KiB
Python
126 lines
4.7 KiB
Python
import torch
|
|
from torch import nn as nn
|
|
from torch.nn import functional as F
|
|
|
|
from invokeai.backend.image_util.basicsr.arch_util import default_init_weights, make_layer, pixel_unshuffle
|
|
|
|
|
|
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: int = 64, num_grow_ch: int = 32) -> None:
|
|
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: torch.Tensor) -> torch.Tensor:
|
|
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))
|
|
# Empirically, 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: int, num_grow_ch: int = 32) -> None:
|
|
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: torch.Tensor) -> torch.Tensor:
|
|
out = self.rdb1(x)
|
|
out = self.rdb2(out)
|
|
out = self.rdb3(out)
|
|
# Empirically, we use 0.2 to scale the residual for better performance
|
|
return out * 0.2 + x
|
|
|
|
|
|
class RRDBNet(nn.Module):
|
|
"""Networks consisting of Residual in Residual Dense Block, which is used
|
|
in ESRGAN.
|
|
|
|
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks.
|
|
|
|
We extend ESRGAN for scale x2 and scale x1.
|
|
Note: This is one option for scale 1, scale 2 in RRDBNet.
|
|
We first employ the pixel-unshuffle (an inverse operation of pixelshuffle to reduce the spatial size
|
|
and enlarge the channel size before feeding inputs into the main ESRGAN architecture.
|
|
|
|
Args:
|
|
num_in_ch (int): Channel number of inputs.
|
|
num_out_ch (int): Channel number of outputs.
|
|
num_feat (int): Channel number of intermediate features.
|
|
Default: 64
|
|
num_block (int): Block number in the trunk network. Defaults: 23
|
|
num_grow_ch (int): Channels for each growth. Default: 32.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
num_in_ch: int,
|
|
num_out_ch: int,
|
|
scale: int = 4,
|
|
num_feat: int = 64,
|
|
num_block: int = 23,
|
|
num_grow_ch: int = 32,
|
|
) -> None:
|
|
super(RRDBNet, self).__init__()
|
|
self.scale = scale
|
|
if scale == 2:
|
|
num_in_ch = num_in_ch * 4
|
|
elif scale == 1:
|
|
num_in_ch = num_in_ch * 16
|
|
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: torch.Tensor) -> torch.Tensor:
|
|
if self.scale == 2:
|
|
feat = pixel_unshuffle(x, scale=2)
|
|
elif self.scale == 1:
|
|
feat = pixel_unshuffle(x, scale=4)
|
|
else:
|
|
feat = x
|
|
feat = self.conv_first(feat)
|
|
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
|