Repository: joeyballentine/Material-Map-Generator
Branch: master
Commit: 13fdae317078
Files: 9
Total size: 38.4 MB
Directory structure:
gitextract_hg_23ho9/
├── .gitignore
├── LICENSE
├── README.md
├── generate.py
└── utils/
├── architecture/
│ ├── architecture.py
│ └── block.py
├── imgops.py
└── models/
├── 1x_FrankenMapGenerator-CX-Lite_215000_G.pth
└── 1x_NormalMapGenerator-CX-Lite_200000_G.pth
================================================
FILE CONTENTS
================================================
================================================
FILE: .gitignore
================================================
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
================================================
FILE: LICENSE
================================================
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
================================================
FILE: README.md
================================================
# Material Map Generator
Easily create AI generated Normal maps, Displacement maps, and Roughness maps.
|Input|Output|Output|Output|
|:-:|:-:|:-:|:-:|
|Diffuse Texture|Normal Map|Displacement Map|Roughness Map|
|
|
|
|
|
Before you begin, make sure you have numpy, opencv-python, and pytorch installed (`pip install torch --index-url https://download.pytorch.org/whl/cu117`).
To run, put images in the `input` folder, and type `python generate.py`. Output images will then be placed in the `output` folder, with the type of map appended to the file name.
To run on CPU instead of GPU (not recommended) use the `--cpu` flag.
If you run out of VRAM while generating the maps, try decreasing the tile size by using the `--tile_size` flag. `--tile size 512` is the default. You can also increase this if your GPU has a lot of VRAM.
To avoid seams and other artifacts that can be created, there are 3 optional flags included: `--seamless`, `--mirror`, and `--replicate` for creating different kinds of seamlessness or padding.
To create material maps in the format used by Ishiiruka Dolphin, use the `--ishiiruka` flag. These can then be converted using Ishiiruka's texture tool. If you want to skip having to use the texture tool, you can use the `--ishiiruka_texture_tool` flag instead, and it will generate the textures in that format instead.
Thanks to Xinntao for the ESRGAN architecture used to train these models. The included models are lighter than regular ones and therefore require less VRAM to process the images with.
================================================
FILE: generate.py
================================================
import argparse
import os
import cv2
import numpy as np
import torch
import sys
import utils.imgops as ops
import utils.architecture.architecture as arch
parser = argparse.ArgumentParser()
parser.add_argument('--input', default='input', help='Input folder')
parser.add_argument('--output', default='output', help='Output folder')
parser.add_argument('--reverse', help='Reverse Order', action="store_true")
parser.add_argument('--tile_size', default=512,
help='Tile size for splitting', type=int)
parser.add_argument('--seamless', action='store_true',
help='Seamless upscaling')
parser.add_argument('--mirror', action='store_true',
help='Mirrored seamless upscaling')
parser.add_argument('--replicate', action='store_true',
help='Replicate edge pixels for padding')
parser.add_argument('--cpu', action='store_true',
help='Use CPU instead of CUDA')
parser.add_argument('--ishiiruka', action='store_true',
help='Save textures in the format used in Ishiiruka Dolphin material map texture packs')
parser.add_argument('--ishiiruka_texture_encoder', action='store_true',
help='Save textures in the format used by Ishiiruka Dolphin\'s Texture Encoder tool')
args = parser.parse_args()
if not os.path.exists(args.input):
print('Error: Folder [{:s}] does not exist.'.format(args.input))
sys.exit(1)
elif os.path.isfile(args.input):
print('Error: Folder [{:s}] is a file.'.format(args.input))
sys.exit(1)
elif os.path.isfile(args.output):
print('Error: Folder [{:s}] is a file.'.format(args.output))
sys.exit(1)
elif not os.path.exists(args.output):
os.mkdir(args.output)
device = torch.device('cpu' if args.cpu else 'cuda')
input_folder = os.path.normpath(args.input)
output_folder = os.path.normpath(args.output)
NORMAL_MAP_MODEL = 'utils/models/1x_NormalMapGenerator-CX-Lite_200000_G.pth'
OTHER_MAP_MODEL = 'utils/models/1x_FrankenMapGenerator-CX-Lite_215000_G.pth'
def process(img, model):
img = img * 1. / np.iinfo(img.dtype).max
img = img[:, :, [2, 1, 0]]
img = torch.from_numpy(np.transpose(img, (2, 0, 1))).float()
img_LR = img.unsqueeze(0)
img_LR = img_LR.to(device)
output = model(img_LR).data.squeeze(
0).float().cpu().clamp_(0, 1).numpy()
output = output[[2, 1, 0], :, :]
output = np.transpose(output, (1, 2, 0))
output = (output * 255.).round()
return output
def load_model(model_path):
global device
state_dict = torch.load(model_path)
model = arch.RRDB_Net(3, 3, 32, 12, gc=32, upscale=1, norm_type=None, act_type='leakyrelu',
mode='CNA', res_scale=1, upsample_mode='upconv')
model.load_state_dict(state_dict, strict=True)
del state_dict
model.eval()
for k, v in model.named_parameters():
v.requires_grad = False
return model.to(device)
images=[]
for root, _, files in os.walk(input_folder):
for file in sorted(files, reverse=args.reverse):
if file.split('.')[-1].lower() in ['png', 'jpg', 'jpeg', 'gif', 'bmp', 'tiff', 'tga']:
images.append(os.path.join(root, file))
models = [
# NORMAL MAP
load_model(NORMAL_MAP_MODEL),
# ROUGHNESS/DISPLACEMENT MAPS
load_model(OTHER_MAP_MODEL)
]
for idx, path in enumerate(images, 1):
base = os.path.splitext(os.path.relpath(path, input_folder))[0]
output_dir = os.path.dirname(os.path.join(output_folder, base))
os.makedirs(output_dir, exist_ok=True)
print(idx, base)
# read image
try:
img = cv2.imread(path, cv2.cv2.IMREAD_COLOR)
except:
img = cv2.imread(path, cv2.IMREAD_COLOR)
# Seamless modes
if args.seamless:
img = cv2.copyMakeBorder(img, 16, 16, 16, 16, cv2.BORDER_WRAP)
elif args.mirror:
img = cv2.copyMakeBorder(img, 16, 16, 16, 16, cv2.BORDER_REFLECT_101)
elif args.replicate:
img = cv2.copyMakeBorder(img, 16, 16, 16, 16, cv2.BORDER_REPLICATE)
img_height, img_width = img.shape[:2]
# Whether or not to perform the split/merge action
do_split = img_height > args.tile_size or img_width > args.tile_size
if do_split:
rlts = ops.esrgan_launcher_split_merge(img, process, models, scale_factor=1, tile_size=args.tile_size)
else:
rlts = [process(img, model) for model in models]
if args.seamless or args.mirror or args.replicate:
rlts = [ops.crop_seamless(rlt) for rlt in rlts]
normal_map = rlts[0]
roughness = rlts[1][:, :, 1]
displacement = rlts[1][:, :, 0]
if args.ishiiruka_texture_encoder:
r = 255 - roughness
g = normal_map[:, :, 1]
b = displacement
a = normal_map[:, :, 2]
output = cv2.merge((b, g, r, a))
cv2.imwrite(os.path.join(output_folder, '{:s}.mat.png'.format(base)), output)
else:
normal_name = '{:s}.nrm.png'.format(base) if args.ishiiruka else '{:s}_Normal.png'.format(base)
cv2.imwrite(os.path.join(output_folder, normal_name), normal_map)
rough_name = '{:s}.spec.png'.format(base) if args.ishiiruka else '{:s}_Roughness.png'.format(base)
rough_img = 255 - roughness if args.ishiiruka else roughness
cv2.imwrite(os.path.join(output_folder, rough_name), rough_img)
displ_name = '{:s}.bump.png'.format(base) if args.ishiiruka else '{:s}_Displacement.png'.format(base)
cv2.imwrite(os.path.join(output_folder, displ_name), displacement)
================================================
FILE: utils/architecture/architecture.py
================================================
import math
import torch.nn as nn
import utils.architecture.block as B
####################
# Generator
####################
class RRDB_Net(nn.Module):
def __init__(self, in_nc, out_nc, nf, nb, gc=32, upscale=4, norm_type=None, act_type='leakyrelu', \
mode='CNA', res_scale=1, upsample_mode='upconv'):
super(RRDB_Net, self).__init__()
n_upscale = int(math.log(upscale, 2))
if upscale == 3:
n_upscale = 1
fea_conv = B.conv_block(in_nc, nf, kernel_size=3, norm_type=None, act_type=None)
rb_blocks = [B.RRDB(nf, kernel_size=3, gc=32, stride=1, bias=True, pad_type='zero', \
norm_type=norm_type, act_type=act_type, mode='CNA') for _ in range(nb)]
LR_conv = B.conv_block(nf, nf, kernel_size=3, norm_type=norm_type, act_type=None, mode=mode)
if upsample_mode == 'upconv':
upsample_block = B.upconv_blcok
elif upsample_mode == 'pixelshuffle':
upsample_block = B.pixelshuffle_block
else:
raise NotImplementedError('upsample mode [%s] is not found' % upsample_mode)
if upscale == 3:
upsampler = upsample_block(nf, nf, 3, act_type=act_type)
else:
upsampler = [upsample_block(nf, nf, act_type=act_type) for _ in range(n_upscale)]
HR_conv0 = B.conv_block(nf, nf, kernel_size=3, norm_type=None, act_type=act_type)
HR_conv1 = B.conv_block(nf, out_nc, kernel_size=3, norm_type=None, act_type=None)
self.model = B.sequential(fea_conv, B.ShortcutBlock(B.sequential(*rb_blocks, LR_conv)),\
*upsampler, HR_conv0, HR_conv1)
def forward(self, x):
x = self.model(x)
return x
================================================
FILE: utils/architecture/block.py
================================================
from collections import OrderedDict
import torch
import torch.nn as nn
####################
# Basic blocks
####################
def act(act_type, inplace=True, neg_slope=0.2, n_prelu=1):
# helper selecting activation
# neg_slope: for leakyrelu and init of prelu
# n_prelu: for p_relu num_parameters
act_type = act_type.lower()
if act_type == 'relu':
layer = nn.ReLU(inplace)
elif act_type == 'leakyrelu':
layer = nn.LeakyReLU(neg_slope, inplace)
elif act_type == 'prelu':
layer = nn.PReLU(num_parameters=n_prelu, init=neg_slope)
else:
raise NotImplementedError('activation layer [{:s}] is not found'.format(act_type))
return layer
def norm(norm_type, nc):
# helper selecting normalization layer
norm_type = norm_type.lower()
if norm_type == 'batch':
layer = nn.BatchNorm2d(nc, affine=True)
elif norm_type == 'instance':
layer = nn.InstanceNorm2d(nc, affine=False)
else:
raise NotImplementedError('normalization layer [{:s}] is not found'.format(norm_type))
return layer
def pad(pad_type, padding):
# helper selecting padding layer
# if padding is 'zero', do by conv layers
pad_type = pad_type.lower()
if padding == 0:
return None
if pad_type == 'reflect':
layer = nn.ReflectionPad2d(padding)
elif pad_type == 'replicate':
layer = nn.ReplicationPad2d(padding)
else:
raise NotImplementedError('padding layer [{:s}] is not implemented'.format(pad_type))
return layer
def get_valid_padding(kernel_size, dilation):
kernel_size = kernel_size + (kernel_size - 1) * (dilation - 1)
padding = (kernel_size - 1) // 2
return padding
class ConcatBlock(nn.Module):
# Concat the output of a submodule to its input
def __init__(self, submodule):
super(ConcatBlock, self).__init__()
self.sub = submodule
def forward(self, x):
output = torch.cat((x, self.sub(x)), dim=1)
return output
def __repr__(self):
tmpstr = 'Identity .. \n|'
modstr = self.sub.__repr__().replace('\n', '\n|')
tmpstr = tmpstr + modstr
return tmpstr
class ShortcutBlock(nn.Module):
#Elementwise sum the output of a submodule to its input
def __init__(self, submodule):
super(ShortcutBlock, self).__init__()
self.sub = submodule
def forward(self, x):
output = x + self.sub(x)
return output
def __repr__(self):
tmpstr = 'Identity + \n|'
modstr = self.sub.__repr__().replace('\n', '\n|')
tmpstr = tmpstr + modstr
return tmpstr
class ShortcutBlockSPSR(nn.Module):
#Elementwise sum the output of a submodule to its input
def __init__(self, submodule):
super(ShortcutBlockSPSR, self).__init__()
self.sub = submodule
def forward(self, x):
return x, self.sub
def __repr__(self):
tmpstr = 'Identity + \n|'
modstr = self.sub.__repr__().replace('\n', '\n|')
tmpstr = tmpstr + modstr
return tmpstr
def sequential(*args):
# Flatten Sequential. It unwraps nn.Sequential.
if len(args) == 1:
if isinstance(args[0], OrderedDict):
raise NotImplementedError('sequential does not support OrderedDict input.')
return args[0] # No sequential is needed.
modules = []
for module in args:
if isinstance(module, nn.Sequential):
for submodule in module.children():
modules.append(submodule)
elif isinstance(module, nn.Module):
modules.append(module)
return nn.Sequential(*modules)
def conv_block(in_nc, out_nc, kernel_size, stride=1, dilation=1, groups=1, bias=True, \
pad_type='zero', norm_type=None, act_type='relu', mode='CNA'):
'''
Conv layer with padding, normalization, activation
mode: CNA --> Conv -> Norm -> Act
NAC --> Norm -> Act --> Conv (Identity Mappings in Deep Residual Networks, ECCV16)
'''
assert mode in ['CNA', 'NAC', 'CNAC'], 'Wrong conv mode [{:s}]'.format(mode)
padding = get_valid_padding(kernel_size, dilation)
p = pad(pad_type, padding) if pad_type and pad_type != 'zero' else None
padding = padding if pad_type == 'zero' else 0
c = nn.Conv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding, \
dilation=dilation, bias=bias, groups=groups)
a = act(act_type) if act_type else None
if 'CNA' in mode:
n = norm(norm_type, out_nc) if norm_type else None
return sequential(p, c, n, a)
elif mode == 'NAC':
if norm_type is None and act_type is not None:
a = act(act_type, inplace=False)
# Important!
# input----ReLU(inplace)----Conv--+----output
# |________________________|
# inplace ReLU will modify the input, therefore wrong output
n = norm(norm_type, in_nc) if norm_type else None
return sequential(n, a, p, c)
####################
# Useful blocks
####################
class ResNetBlock(nn.Module):
'''
ResNet Block, 3-3 style
with extra residual scaling used in EDSR
(Enhanced Deep Residual Networks for Single Image Super-Resolution, CVPRW 17)
'''
def __init__(self, in_nc, mid_nc, out_nc, kernel_size=3, stride=1, dilation=1, groups=1, \
bias=True, pad_type='zero', norm_type=None, act_type='relu', mode='CNA', res_scale=1):
super(ResNetBlock, self).__init__()
conv0 = conv_block(in_nc, mid_nc, kernel_size, stride, dilation, groups, bias, pad_type, \
norm_type, act_type, mode)
if mode == 'CNA':
act_type = None
if mode == 'CNAC': # Residual path: |-CNAC-|
act_type = None
norm_type = None
conv1 = conv_block(mid_nc, out_nc, kernel_size, stride, dilation, groups, bias, pad_type, \
norm_type, act_type, mode)
# if in_nc != out_nc:
# self.project = conv_block(in_nc, out_nc, 1, stride, dilation, 1, bias, pad_type, \
# None, None)
# print('Need a projecter in ResNetBlock.')
# else:
# self.project = lambda x:x
self.res = sequential(conv0, conv1)
self.res_scale = res_scale
def forward(self, x):
res = self.res(x).mul(self.res_scale)
return x + res
class ResidualDenseBlock_5C(nn.Module):
'''
Residual Dense Block
style: 5 convs
The core module of paper: (Residual Dense Network for Image Super-Resolution, CVPR 18)
'''
def __init__(self, nc, kernel_size=3, gc=32, stride=1, bias=True, pad_type='zero', \
norm_type=None, act_type='leakyrelu', mode='CNA'):
super(ResidualDenseBlock_5C, self).__init__()
# gc: growth channel, i.e. intermediate channels
self.conv1 = conv_block(nc, gc, kernel_size, stride, bias=bias, pad_type=pad_type, \
norm_type=norm_type, act_type=act_type, mode=mode)
self.conv2 = conv_block(nc+gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type, \
norm_type=norm_type, act_type=act_type, mode=mode)
self.conv3 = conv_block(nc+2*gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type, \
norm_type=norm_type, act_type=act_type, mode=mode)
self.conv4 = conv_block(nc+3*gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type, \
norm_type=norm_type, act_type=act_type, mode=mode)
if mode == 'CNA':
last_act = None
else:
last_act = act_type
self.conv5 = conv_block(nc+4*gc, nc, 3, stride, bias=bias, pad_type=pad_type, \
norm_type=norm_type, act_type=last_act, mode=mode)
def forward(self, x):
x1 = self.conv1(x)
x2 = self.conv2(torch.cat((x, x1), 1))
x3 = self.conv3(torch.cat((x, x1, x2), 1))
x4 = self.conv4(torch.cat((x, x1, x2, x3), 1))
x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
return x5.mul(0.2) + x
class RRDB(nn.Module):
'''
Residual in Residual Dense Block
(ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks)
'''
def __init__(self, nc, kernel_size=3, gc=32, stride=1, bias=True, pad_type='zero', \
norm_type=None, act_type='leakyrelu', mode='CNA'):
super(RRDB, self).__init__()
self.RDB1 = ResidualDenseBlock_5C(nc, kernel_size, gc, stride, bias, pad_type, \
norm_type, act_type, mode)
self.RDB2 = ResidualDenseBlock_5C(nc, kernel_size, gc, stride, bias, pad_type, \
norm_type, act_type, mode)
self.RDB3 = ResidualDenseBlock_5C(nc, kernel_size, gc, stride, bias, pad_type, \
norm_type, act_type, mode)
def forward(self, x):
out = self.RDB1(x)
out = self.RDB2(out)
out = self.RDB3(out)
return out.mul(0.2) + x
####################
# Upsampler
####################
def pixelshuffle_block(in_nc, out_nc, upscale_factor=2, kernel_size=3, stride=1, bias=True, \
pad_type='zero', norm_type=None, act_type='relu'):
'''
Pixel shuffle layer
(Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional
Neural Network, CVPR17)
'''
conv = conv_block(in_nc, out_nc * (upscale_factor ** 2), kernel_size, stride, bias=bias, \
pad_type=pad_type, norm_type=None, act_type=None)
pixel_shuffle = nn.PixelShuffle(upscale_factor)
n = norm(norm_type, out_nc) if norm_type else None
a = act(act_type) if act_type else None
return sequential(conv, pixel_shuffle, n, a)
def upconv_blcok(in_nc, out_nc, upscale_factor=2, kernel_size=3, stride=1, bias=True, \
pad_type='zero', norm_type=None, act_type='relu', mode='nearest'):
# Up conv
# described in https://distill.pub/2016/deconv-checkerboard/
upsample = nn.Upsample(scale_factor=upscale_factor, mode=mode)
conv = conv_block(in_nc, out_nc, kernel_size, stride, bias=bias, \
pad_type=pad_type, norm_type=norm_type, act_type=act_type)
return sequential(upsample, conv)
================================================
FILE: utils/imgops.py
================================================
import numpy as np
import math
def crop_seamless(img):
img_height, img_width = img.shape[:2]
y, x = 16, 16
h, w = img_height - 32, img_width - 32
img = img[y:y+h, x:x+w]
return img
# from https://github.com/ata4/esrgan-launcher/blob/master/upscale.py
def esrgan_launcher_split_merge(input_image, upscale_function, models, scale_factor=4, tile_size=512, tile_padding=0.125):
width, height, depth = input_image.shape
output_width = width * scale_factor
output_height = height * scale_factor
output_shape = (output_width, output_height, depth)
# start with black image
output_images = [np.zeros(output_shape, np.uint8) for i in range(len(models))]
tile_padding = math.ceil(tile_size * tile_padding)
tile_size = math.ceil(tile_size / scale_factor)
tiles_x = math.ceil(width / tile_size)
tiles_y = math.ceil(height / tile_size)
for y in range(tiles_y):
for x in range(tiles_x):
# extract tile from input image
ofs_x = x * tile_size
ofs_y = y * tile_size
# input tile area on total image
input_start_x = ofs_x
input_end_x = min(ofs_x + tile_size, width)
input_start_y = ofs_y
input_end_y = min(ofs_y + tile_size, height)
# input tile area on total image with padding
input_start_x_pad = max(input_start_x - tile_padding, 0)
input_end_x_pad = min(input_end_x + tile_padding, width)
input_start_y_pad = max(input_start_y - tile_padding, 0)
input_end_y_pad = min(input_end_y + tile_padding, height)
# input tile dimensions
input_tile_width = input_end_x - input_start_x
input_tile_height = input_end_y - input_start_y
input_tile = input_image[input_start_x_pad:input_end_x_pad, input_start_y_pad:input_end_y_pad]
for idx, model in enumerate(models):
# upscale tile
output_tile = upscale_function(input_tile, model)
# output tile area on total image
output_start_x = input_start_x * scale_factor
output_end_x = input_end_x * scale_factor
output_start_y = input_start_y * scale_factor
output_end_y = input_end_y * scale_factor
# output tile area without padding
output_start_x_tile = (input_start_x - input_start_x_pad) * scale_factor
output_end_x_tile = output_start_x_tile + input_tile_width * scale_factor
output_start_y_tile = (input_start_y - input_start_y_pad) * scale_factor
output_end_y_tile = output_start_y_tile + input_tile_height * scale_factor
# put tile into output image
output_images[idx][output_start_x:output_end_x, output_start_y:output_end_y] = \
output_tile[output_start_x_tile:output_end_x_tile, output_start_y_tile:output_end_y_tile]
return output_images
================================================
FILE: utils/models/1x_FrankenMapGenerator-CX-Lite_215000_G.pth
================================================
[File too large to display: 19.2 MB]
================================================
FILE: utils/models/1x_NormalMapGenerator-CX-Lite_200000_G.pth
================================================
[File too large to display: 19.2 MB]