Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,39 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DragGAN.gif filter=lfs diff=lfs merge=lfs -text
+stylegan_human/img/demo_V5_thumbnails-min.png filter=lfs diff=lfs merge=lfs -text
+stylegan_human/img/preview_samples1.png filter=lfs diff=lfs merge=lfs -text
+stylegan_human/img/test/test.jpg filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/PIL/.dylibs/libfreetype.6.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/PIL/.dylibs/libharfbuzz.0.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/altair/vegalite/v5/schema/__pycache__/core.cpython-310.pyc filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/fontTools/misc/bezierTools.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/gradio/frpc_darwin_arm64_v0.2 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/gradio/templates/cdn/assets/index-d9794b8f.js.map filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/gradio/templates/frontend/assets/index-0eddd93f.js.map filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/hf_transfer/hf_transfer.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/imgui/core.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/imgui/internal.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/numpy/.dylibs/libgfortran.5.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/numpy/.dylibs/libopenblas64_.0.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/numpy/core/_multiarray_umath.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/pandas/_libs/algos.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/pandas/_libs/groupby.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/pandas/_libs/hashtable.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/pandas/_libs/interval.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/pandas/_libs/join.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/.dylibs/libgfortran.5.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/.dylibs/libopenblas.0.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/linalg/_flapack.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/misc/face.dat filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/optimize/_highs/_highs_wrapper.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/sparse/_sparsetools.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/special/_ufuncs.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/special/cython_special.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/scipy/stats/_unuran/unuran_wrapper.cpython-310-darwin.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/torch/bin/protoc filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/torch/bin/protoc-3.13.0.0 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/torch/lib/libtorch_cpu.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/torch/lib/libtorch_python.dylib filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.10/site-packages/torchvision/.dylibs/libc++.1.0.dylib filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,157 @@
+# Created by .ignore support plugin (hsz.mobi)
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# IPython Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# dotenv
+.env
+
+# virtualenv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+
+# Rope project settings
+.ropeproject
+### VirtualEnv template
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+.Python
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+!scripts\download_model.bat
+pyvenv.cfg
+.venv
+pip-selfcheck.json
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and Webstorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+.idea/workspace.xml
+.idea/tasks.xml
+.idea/dictionaries
+.idea/vcs.xml
+.idea/jsLibraryMappings.xml
+
+# Sensitive or high-churn files:
+.idea/dataSources.ids
+.idea/dataSources.xml
+.idea/dataSources.local.xml
+.idea/sqlDataSources.xml
+.idea/dynamic.xml
+.idea/uiDesigner.xml
+
+# Gradle:
+.idea/gradle.xml
+.idea/libraries
+
+# Mongo Explorer plugin:
+.idea/mongoSettings.xml
+
+.idea/
+
+## File-based project format:
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+/out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Mac related
+.DS_Store
+
+checkpoints

LICENSE.txt

@@ -0,0 +1,97 @@
+Copyright (c) 2021, NVIDIA Corporation & affiliates. All rights reserved.
+
+
+NVIDIA Source Code License for StyleGAN3
+
+
+=======================================================================
+
+1. Definitions
+
+"Licensor" means any person or entity that distributes its Work.
+
+"Software" means the original work of authorship made available under
+this License.
+
+"Work" means the Software and any additions to or derivative works of
+the Software that are made available under this License.
+
+The terms "reproduce," "reproduction," "derivative works," and
+"distribution" have the meaning as provided under U.S. copyright law;
+provided, however, that 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.
+
+Works, including the Software, are "made available" under this License
+by including in or with the Work either (a) a copyright notice
+referencing the applicability of this License to the Work, or (b) a
+copy of this License.
+
+2. License Grants
+
+    2.1 Copyright Grant. Subject to the terms and conditions of this
+    License, each Licensor grants to you a perpetual, worldwide,
+    non-exclusive, royalty-free, copyright license to reproduce,
+    prepare derivative works of, publicly display, publicly perform,
+    sublicense and distribute its Work and any resulting derivative
+    works in any form.
+
+3. Limitations
+
+    3.1 Redistribution. You may reproduce or distribute the Work only
+    if (a) you do so under this License, (b) you include a complete
+    copy of this License with your distribution, and (c) you retain
+    without modification any copyright, patent, trademark, or
+    attribution notices that are present in the Work.
+
+    3.2 Derivative Works. You may specify that additional or different
+    terms apply to the use, reproduction, and distribution of your
+    derivative works of the Work ("Your Terms") only if (a) Your Terms
+    provide that the use limitation in Section 3.3 applies to your
+    derivative works, and (b) you identify the specific derivative
+    works that are subject to Your Terms. Notwithstanding Your Terms,
+    this License (including the redistribution requirements in Section
+    3.1) will continue to apply to the Work itself.
+
+    3.3 Use Limitation. The Work and any derivative works thereof only
+    may be used or intended for use non-commercially. Notwithstanding
+    the foregoing, NVIDIA and its affiliates may use the Work and any
+    derivative works commercially. As used herein, "non-commercially"
+    means for research or evaluation purposes only.
+
+    3.4 Patent Claims. If you bring or threaten to bring a patent claim
+    against any Licensor (including any claim, cross-claim or
+    counterclaim in a lawsuit) to enforce any patents that you allege
+    are infringed by any Work, then your rights under this License from
+    such Licensor (including the grant in Section 2.1) will terminate
+    immediately.
+
+    3.5 Trademarks. This License does not grant any rights to use any
+    Licensor’s or its affiliates’ names, logos, or trademarks, except
+    as necessary to reproduce the notices described in this License.
+
+    3.6 Termination. If you violate any term of this License, then your
+    rights under this License (including the grant in Section 2.1) will
+    terminate immediately.
+
+4. Disclaimer of Warranty.
+
+THE WORK IS PROVIDED "AS IS" WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OR CONDITIONS OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE OR
+NON-INFRINGEMENT. YOU BEAR THE RISK OF UNDERTAKING ANY ACTIVITIES UNDER
+THIS LICENSE.
+
+5. Limitation of Liability.
+
+EXCEPT AS PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL
+THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE
+SHALL ANY LICENSOR BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT,
+INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF
+OR RELATED TO THIS LICENSE, THE USE OR INABILITY TO USE THE WORK
+(INCLUDING BUT NOT LIMITED TO LOSS OF GOODWILL, BUSINESS INTERRUPTION,
+LOST PROFITS OR DATA, COMPUTER FAILURE OR MALFUNCTION, OR ANY OTHER
+COMMERCIAL DAMAGES OR LOSSES), EVEN IF THE LICENSOR HAS BEEN ADVISED OF
+THE POSSIBILITY OF SUCH DAMAGES.
+
+=======================================================================

README.md

@@ -1,12 +1,109 @@
 ---
 title: DragGAN
-emoji: 😻
-colorFrom: gray
-colorTo: pink
+app_file: visualizer_drag_gradio.py
 sdk: gradio
 sdk_version: 3.35.2
-app_file: app.py
-pinned: false
 ---
+<p align="center">
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+  <h1 align="center">Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold</h1>
+  <p align="center">
+    <a href="https://xingangpan.github.io/"><strong>Xingang Pan</strong></a>
+    ·
+    <a href="https://ayushtewari.com/"><strong>Ayush Tewari</strong></a>
+    ·
+    <a href="https://people.mpi-inf.mpg.de/~tleimkue/"><strong>Thomas Leimkühler</strong></a>
+    ·
+    <a href="https://lingjie0206.github.io/"><strong>Lingjie Liu</strong></a>
+    ·
+    <a href="https://www.meka.page/"><strong>Abhimitra Meka</strong></a>
+    ·
+    <a href="http://www.mpi-inf.mpg.de/~theobalt/"><strong>Christian Theobalt</strong></a>
+  </p>
+  <h2 align="center">SIGGRAPH 2023 Conference Proceedings</h2>
+  <div align="center">
+    <img src="DragGAN.gif", width="600">
+  </div>
+
+  <p align="center">
+  <br>
+    <a href="https://pytorch.org/get-started/locally/"><img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white"></a>
+    <a href="https://twitter.com/XingangP"><img alt='Twitter' src="https://img.shields.io/twitter/follow/XingangP?label=%40XingangP"></a>
+    <a href="https://arxiv.org/abs/2305.10973">
+      <img src='https://img.shields.io/badge/Paper-PDF-green?style=for-the-badge&logo=adobeacrobatreader&logoWidth=20&logoColor=white&labelColor=66cc00&color=94DD15' alt='Paper PDF'>
+    </a>
+    <a href='https://vcai.mpi-inf.mpg.de/projects/DragGAN/'>
+      <img src='https://img.shields.io/badge/DragGAN-Page-orange?style=for-the-badge&logo=Google%20chrome&logoColor=white&labelColor=D35400' alt='Project Page'></a>
+    <a href="https://colab.research.google.com/drive/1mey-IXPwQC_qSthI5hO-LTX7QL4ivtPh?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+  </p>
+</p>
+
+## Web Demos
+
+[![Open in OpenXLab](https://cdn-static.openxlab.org.cn/app-center/openxlab_app.svg)](https://openxlab.org.cn/apps/detail/XingangPan/DragGAN)
+
+<p align="left">
+  <a href="https://huggingface.co/spaces/radames/DragGan"><img alt="Huggingface" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DragGAN-orange"></a>
+</p>
+
+## Requirements
+
+If you have CUDA graphic card, please follow the requirements of [NVlabs/stylegan3](https://github.com/NVlabs/stylegan3#requirements).  
+
+Otherwise (for GPU acceleration on MacOS with Silicon Mac M1/M2, or just CPU) try the following:
+
+```sh
+cat environment.yml | \
+  grep -v -E 'nvidia|cuda' > environment-no-nvidia.yml && \
+    conda env create -f environment-no-nvidia.yml
+conda activate stylegan3
+
+# On MacOS
+export PYTORCH_ENABLE_MPS_FALLBACK=1
+```
+
+## Download pre-trained StyleGAN2 weights
+
+To download pre-trained weights, simply run:
+```sh
+sh scripts/download_model.sh
+```
+If you want to try StyleGAN-Human and the Landscapes HQ (LHQ) dataset, please download weights from these links: [StyleGAN-Human](https://drive.google.com/file/d/1dlFEHbu-WzQWJl7nBBZYcTyo000H9hVm/view?usp=sharing), [LHQ](https://drive.google.com/file/d/16twEf0T9QINAEoMsWefoWiyhcTd-aiWc/view?usp=sharing), and put them under `./checkpoints`.
+
+Feel free to try other pretrained StyleGAN.
+
+## Run DragGAN GUI
+
+To start the DragGAN GUI, simply run:
+```sh
+sh scripts/gui.sh
+```
+
+This GUI supports editing GAN-generated images. To edit a real image, you need to first perform GAN inversion using tools like [PTI](https://github.com/danielroich/PTI). Then load the new latent code and model weights to the GUI.
+
+You can run DragGAN Gradio demo as well:
+```sh
+python visualizer_drag_gradio.py
+```
+
+## Acknowledgement
+
+This code is developed based on [StyleGAN3](https://github.com/NVlabs/stylegan3). Part of the code is borrowed from [StyleGAN-Human](https://github.com/stylegan-human/StyleGAN-Human).
+
+## License
+
+The code related to the DragGAN algorithm is licensed under [CC-BY-NC](https://creativecommons.org/licenses/by-nc/4.0/).
+However, most of this project are available under a separate license terms: all codes used or modified from [StyleGAN3](https://github.com/NVlabs/stylegan3) is under the [Nvidia Source Code License](https://github.com/NVlabs/stylegan3/blob/main/LICENSE.txt).
+
+Any form of use and derivative of this code must preserve the watermarking functionality showing "AI Generated".
+
+## BibTeX
+
+```bibtex
+@inproceedings{pan2023draggan,
+    title={Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold},
+    author={Pan, Xingang and Tewari, Ayush, and Leimk{\"u}hler, Thomas and Liu, Lingjie and Meka, Abhimitra and Theobalt, Christian},
+    booktitle = {ACM SIGGRAPH 2023 Conference Proceedings},
+    year={2023}
+}
+```

checkpoints/stylegan2-afhqcat-512x512.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a83abee464242f8bb40dc6363d33c2fb087066b68fc0147677fdbf21f7a7a9
+size 363939583

checkpoints/stylegan2-car-config-f.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1618eee2b3ce87c4a3849442f7850ef12a478556bff035c8e09ee7e23b3794c
+size 364027523

checkpoints/stylegan2-cat-config-f.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08940fd616cfaf6bc7b0286b5d1a0b3f70febb26e136d64716c8d3f5e9bd3883
+size 357418027

checkpoints/stylegan2-ffhq-512x512.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b1c92f41ce8a64c55f7a75ef06c4c0eef9e17b1eb29aae8c10fb37b3e60478
+size 363939580

checkpoints/stylegan2_dogs_1024_pytorch.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e93090d02916165a602c728c0e37458fc0c58fbc58e4d75bcd096bb81c7e8c
+size 381630441

checkpoints/stylegan2_elephants_512_pytorch.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56504894f6d7121959af78a74148cf1e9d858e3710312efb11c41dbf27684363
+size 363965313

checkpoints/stylegan2_horses_256_pytorch.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f100dc32e2731a293f3b31a9038416f72aa5cc30555b3315a82e19c065f81b0c
+size 357336721

checkpoints/stylegan2_lions_512_pytorch.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a01ff8344521171b1a2eff1e9a51c1acbc48221bdc2594919187f66a3942bcc
+size 363965313

dnnlib/__init__.py

@@ -0,0 +1,9 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+from .util import EasyDict, make_cache_dir_path

dnnlib/util.py

@@ -0,0 +1,491 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+"""Miscellaneous utility classes and functions."""
+
+import ctypes
+import fnmatch
+import importlib
+import inspect
+import numpy as np
+import os
+import shutil
+import sys
+import types
+import io
+import pickle
+import re
+import requests
+import html
+import hashlib
+import glob
+import tempfile
+import urllib
+import urllib.request
+import uuid
+
+from distutils.util import strtobool
+from typing import Any, List, Tuple, Union
+
+
+# Util classes
+# ------------------------------------------------------------------------------------------
+
+
+class EasyDict(dict):
+    """Convenience class that behaves like a dict but allows access with the attribute syntax."""
+
+    def __getattr__(self, name: str) -> Any:
+        try:
+            return self[name]
+        except KeyError:
+            raise AttributeError(name)
+
+    def __setattr__(self, name: str, value: Any) -> None:
+        self[name] = value
+
+    def __delattr__(self, name: str) -> None:
+        del self[name]
+
+
+class Logger(object):
+    """Redirect stderr to stdout, optionally print stdout to a file, and optionally force flushing on both stdout and the file."""
+
+    def __init__(self, file_name: str = None, file_mode: str = "w", should_flush: bool = True):
+        self.file = None
+
+        if file_name is not None:
+            self.file = open(file_name, file_mode)
+
+        self.should_flush = should_flush
+        self.stdout = sys.stdout
+        self.stderr = sys.stderr
+
+        sys.stdout = self
+        sys.stderr = self
+
+    def __enter__(self) -> "Logger":
+        return self
+
+    def __exit__(self, exc_type: Any, exc_value: Any, traceback: Any) -> None:
+        self.close()
+
+    def write(self, text: Union[str, bytes]) -> None:
+        """Write text to stdout (and a file) and optionally flush."""
+        if isinstance(text, bytes):
+            text = text.decode()
+        if len(text) == 0: # workaround for a bug in VSCode debugger: sys.stdout.write(''); sys.stdout.flush() => crash
+            return
+
+        if self.file is not None:
+            self.file.write(text)
+
+        self.stdout.write(text)
+
+        if self.should_flush:
+            self.flush()
+
+    def flush(self) -> None:
+        """Flush written text to both stdout and a file, if open."""
+        if self.file is not None:
+            self.file.flush()
+
+        self.stdout.flush()
+
+    def close(self) -> None:
+        """Flush, close possible files, and remove stdout/stderr mirroring."""
+        self.flush()
+
+        # if using multiple loggers, prevent closing in wrong order
+        if sys.stdout is self:
+            sys.stdout = self.stdout
+        if sys.stderr is self:
+            sys.stderr = self.stderr
+
+        if self.file is not None:
+            self.file.close()
+            self.file = None
+
+
+# Cache directories
+# ------------------------------------------------------------------------------------------
+
+_dnnlib_cache_dir = None
+
+def set_cache_dir(path: str) -> None:
+    global _dnnlib_cache_dir
+    _dnnlib_cache_dir = path
+
+def make_cache_dir_path(*paths: str) -> str:
+    if _dnnlib_cache_dir is not None:
+        return os.path.join(_dnnlib_cache_dir, *paths)
+    if 'DNNLIB_CACHE_DIR' in os.environ:
+        return os.path.join(os.environ['DNNLIB_CACHE_DIR'], *paths)
+    if 'HOME' in os.environ:
+        return os.path.join(os.environ['HOME'], '.cache', 'dnnlib', *paths)
+    if 'USERPROFILE' in os.environ:
+        return os.path.join(os.environ['USERPROFILE'], '.cache', 'dnnlib', *paths)
+    return os.path.join(tempfile.gettempdir(), '.cache', 'dnnlib', *paths)
+
+# Small util functions
+# ------------------------------------------------------------------------------------------
+
+
+def format_time(seconds: Union[int, float]) -> str:
+    """Convert the seconds to human readable string with days, hours, minutes and seconds."""
+    s = int(np.rint(seconds))
+
+    if s < 60:
+        return "{0}s".format(s)
+    elif s < 60 * 60:
+        return "{0}m {1:02}s".format(s // 60, s % 60)
+    elif s < 24 * 60 * 60:
+        return "{0}h {1:02}m {2:02}s".format(s // (60 * 60), (s // 60) % 60, s % 60)
+    else:
+        return "{0}d {1:02}h {2:02}m".format(s // (24 * 60 * 60), (s // (60 * 60)) % 24, (s // 60) % 60)
+
+
+def format_time_brief(seconds: Union[int, float]) -> str:
+    """Convert the seconds to human readable string with days, hours, minutes and seconds."""
+    s = int(np.rint(seconds))
+
+    if s < 60:
+        return "{0}s".format(s)
+    elif s < 60 * 60:
+        return "{0}m {1:02}s".format(s // 60, s % 60)
+    elif s < 24 * 60 * 60:
+        return "{0}h {1:02}m".format(s // (60 * 60), (s // 60) % 60)
+    else:
+        return "{0}d {1:02}h".format(s // (24 * 60 * 60), (s // (60 * 60)) % 24)
+
+
+def ask_yes_no(question: str) -> bool:
+    """Ask the user the question until the user inputs a valid answer."""
+    while True:
+        try:
+            print("{0} [y/n]".format(question))
+            return strtobool(input().lower())
+        except ValueError:
+            pass
+
+
+def tuple_product(t: Tuple) -> Any:
+    """Calculate the product of the tuple elements."""
+    result = 1
+
+    for v in t:
+        result *= v
+
+    return result
+
+
+_str_to_ctype = {
+    "uint8": ctypes.c_ubyte,
+    "uint16": ctypes.c_uint16,
+    "uint32": ctypes.c_uint32,
+    "uint64": ctypes.c_uint64,
+    "int8": ctypes.c_byte,
+    "int16": ctypes.c_int16,
+    "int32": ctypes.c_int32,
+    "int64": ctypes.c_int64,
+    "float32": ctypes.c_float,
+    "float64": ctypes.c_double
+}
+
+
+def get_dtype_and_ctype(type_obj: Any) -> Tuple[np.dtype, Any]:
+    """Given a type name string (or an object having a __name__ attribute), return matching Numpy and ctypes types that have the same size in bytes."""
+    type_str = None
+
+    if isinstance(type_obj, str):
+        type_str = type_obj
+    elif hasattr(type_obj, "__name__"):
+        type_str = type_obj.__name__
+    elif hasattr(type_obj, "name"):
+        type_str = type_obj.name
+    else:
+        raise RuntimeError("Cannot infer type name from input")
+
+    assert type_str in _str_to_ctype.keys()
+
+    my_dtype = np.dtype(type_str)
+    my_ctype = _str_to_ctype[type_str]
+
+    assert my_dtype.itemsize == ctypes.sizeof(my_ctype)
+
+    return my_dtype, my_ctype
+
+
+def is_pickleable(obj: Any) -> bool:
+    try:
+        with io.BytesIO() as stream:
+            pickle.dump(obj, stream)
+        return True
+    except:
+        return False
+
+
+# Functionality to import modules/objects by name, and call functions by name
+# ------------------------------------------------------------------------------------------
+
+def get_module_from_obj_name(obj_name: str) -> Tuple[types.ModuleType, str]:
+    """Searches for the underlying module behind the name to some python object.
+    Returns the module and the object name (original name with module part removed)."""
+
+    # allow convenience shorthands, substitute them by full names
+    obj_name = re.sub("^np.", "numpy.", obj_name)
+    obj_name = re.sub("^tf.", "tensorflow.", obj_name)
+
+    # list alternatives for (module_name, local_obj_name)
+    parts = obj_name.split(".")
+    name_pairs = [(".".join(parts[:i]), ".".join(parts[i:])) for i in range(len(parts), 0, -1)]
+
+    # try each alternative in turn
+    for module_name, local_obj_name in name_pairs:
+        try:
+            module = importlib.import_module(module_name) # may raise ImportError
+            get_obj_from_module(module, local_obj_name) # may raise AttributeError
+            return module, local_obj_name
+        except:
+            pass
+
+    # maybe some of the modules themselves contain errors?
+    for module_name, _local_obj_name in name_pairs:
+        try:
+            importlib.import_module(module_name) # may raise ImportError
+        except ImportError:
+            if not str(sys.exc_info()[1]).startswith("No module named '" + module_name + "'"):
+                raise
+
+    # maybe the requested attribute is missing?
+    for module_name, local_obj_name in name_pairs:
+        try:
+            module = importlib.import_module(module_name) # may raise ImportError
+            get_obj_from_module(module, local_obj_name) # may raise AttributeError
+        except ImportError:
+            pass
+
+    # we are out of luck, but we have no idea why
+    raise ImportError(obj_name)
+
+
+def get_obj_from_module(module: types.ModuleType, obj_name: str) -> Any:
+    """Traverses the object name and returns the last (rightmost) python object."""
+    if obj_name == '':
+        return module
+    obj = module
+    for part in obj_name.split("."):
+        obj = getattr(obj, part)
+    return obj
+
+
+def get_obj_by_name(name: str) -> Any:
+    """Finds the python object with the given name."""
+    module, obj_name = get_module_from_obj_name(name)
+    return get_obj_from_module(module, obj_name)
+
+
+def call_func_by_name(*args, func_name: str = None, **kwargs) -> Any:
+    """Finds the python object with the given name and calls it as a function."""
+    assert func_name is not None
+    func_obj = get_obj_by_name(func_name)
+    assert callable(func_obj)
+    return func_obj(*args, **kwargs)
+
+
+def construct_class_by_name(*args, class_name: str = None, **kwargs) -> Any:
+    """Finds the python class with the given name and constructs it with the given arguments."""
+    return call_func_by_name(*args, func_name=class_name, **kwargs)
+
+
+def get_module_dir_by_obj_name(obj_name: str) -> str:
+    """Get the directory path of the module containing the given object name."""
+    module, _ = get_module_from_obj_name(obj_name)
+    return os.path.dirname(inspect.getfile(module))
+
+
+def is_top_level_function(obj: Any) -> bool:
+    """Determine whether the given object is a top-level function, i.e., defined at module scope using 'def'."""
+    return callable(obj) and obj.__name__ in sys.modules[obj.__module__].__dict__
+
+
+def get_top_level_function_name(obj: Any) -> str:
+    """Return the fully-qualified name of a top-level function."""
+    assert is_top_level_function(obj)
+    module = obj.__module__
+    if module == '__main__':
+        module = os.path.splitext(os.path.basename(sys.modules[module].__file__))[0]
+    return module + "." + obj.__name__
+
+
+# File system helpers
+# ------------------------------------------------------------------------------------------
+
+def list_dir_recursively_with_ignore(dir_path: str, ignores: List[str] = None, add_base_to_relative: bool = False) -> List[Tuple[str, str]]:
+    """List all files recursively in a given directory while ignoring given file and directory names.
+    Returns list of tuples containing both absolute and relative paths."""
+    assert os.path.isdir(dir_path)
+    base_name = os.path.basename(os.path.normpath(dir_path))
+
+    if ignores is None:
+        ignores = []
+
+    result = []
+
+    for root, dirs, files in os.walk(dir_path, topdown=True):
+        for ignore_ in ignores:
+            dirs_to_remove = [d for d in dirs if fnmatch.fnmatch(d, ignore_)]
+
+            # dirs need to be edited in-place
+            for d in dirs_to_remove:
+                dirs.remove(d)
+
+            files = [f for f in files if not fnmatch.fnmatch(f, ignore_)]
+
+        absolute_paths = [os.path.join(root, f) for f in files]
+        relative_paths = [os.path.relpath(p, dir_path) for p in absolute_paths]
+
+        if add_base_to_relative:
+            relative_paths = [os.path.join(base_name, p) for p in relative_paths]
+
+        assert len(absolute_paths) == len(relative_paths)
+        result += zip(absolute_paths, relative_paths)
+
+    return result
+
+
+def copy_files_and_create_dirs(files: List[Tuple[str, str]]) -> None:
+    """Takes in a list of tuples of (src, dst) paths and copies files.
+    Will create all necessary directories."""
+    for file in files:
+        target_dir_name = os.path.dirname(file[1])
+
+        # will create all intermediate-level directories
+        if not os.path.exists(target_dir_name):
+            os.makedirs(target_dir_name)
+
+        shutil.copyfile(file[0], file[1])
+
+
+# URL helpers
+# ------------------------------------------------------------------------------------------
+
+def is_url(obj: Any, allow_file_urls: bool = False) -> bool:
+    """Determine whether the given object is a valid URL string."""
+    if not isinstance(obj, str) or not "://" in obj:
+        return False
+    if allow_file_urls and obj.startswith('file://'):
+        return True
+    try:
+        res = requests.compat.urlparse(obj)
+        if not res.scheme or not res.netloc or not "." in res.netloc:
+            return False
+        res = requests.compat.urlparse(requests.compat.urljoin(obj, "/"))
+        if not res.scheme or not res.netloc or not "." in res.netloc:
+            return False
+    except:
+        return False
+    return True
+
+
+def open_url(url: str, cache_dir: str = None, num_attempts: int = 10, verbose: bool = True, return_filename: bool = False, cache: bool = True) -> Any:
+    """Download the given URL and return a binary-mode file object to access the data."""
+    assert num_attempts >= 1
+    assert not (return_filename and (not cache))
+
+    # Doesn't look like an URL scheme so interpret it as a local filename.
+    if not re.match('^[a-z]+://', url):
+        return url if return_filename else open(url, "rb")
+
+    # Handle file URLs.  This code handles unusual file:// patterns that
+    # arise on Windows:
+    #
+    # file:///c:/foo.txt
+    #
+    # which would translate to a local '/c:/foo.txt' filename that's
+    # invalid.  Drop the forward slash for such pathnames.
+    #
+    # If you touch this code path, you should test it on both Linux and
+    # Windows.
+    #
+    # Some internet resources suggest using urllib.request.url2pathname() but
+    # but that converts forward slashes to backslashes and this causes
+    # its own set of problems.
+    if url.startswith('file://'):
+        filename = urllib.parse.urlparse(url).path
+        if re.match(r'^/[a-zA-Z]:', filename):
+            filename = filename[1:]
+        return filename if return_filename else open(filename, "rb")
+
+    assert is_url(url)
+
+    # Lookup from cache.
+    if cache_dir is None:
+        cache_dir = make_cache_dir_path('downloads')
+
+    url_md5 = hashlib.md5(url.encode("utf-8")).hexdigest()
+    if cache:
+        cache_files = glob.glob(os.path.join(cache_dir, url_md5 + "_*"))
+        if len(cache_files) == 1:
+            filename = cache_files[0]
+            return filename if return_filename else open(filename, "rb")
+
+    # Download.
+    url_name = None
+    url_data = None
+    with requests.Session() as session:
+        if verbose:
+            print("Downloading %s ..." % url, end="", flush=True)
+        for attempts_left in reversed(range(num_attempts)):
+            try:
+                with session.get(url) as res:
+                    res.raise_for_status()
+                    if len(res.content) == 0:
+                        raise IOError("No data received")
+
+                    if len(res.content) < 8192:
+                        content_str = res.content.decode("utf-8")
+                        if "download_warning" in res.headers.get("Set-Cookie", ""):
+                            links = [html.unescape(link) for link in content_str.split('"') if "export=download" in link]
+                            if len(links) == 1:
+                                url = requests.compat.urljoin(url, links[0])
+                                raise IOError("Google Drive virus checker nag")
+                        if "Google Drive - Quota exceeded" in content_str:
+                            raise IOError("Google Drive download quota exceeded -- please try again later")
+
+                    match = re.search(r'filename="([^"]*)"', res.headers.get("Content-Disposition", ""))
+                    url_name = match[1] if match else url
+                    url_data = res.content
+                    if verbose:
+                        print(" done")
+                    break
+            except KeyboardInterrupt:
+                raise
+            except:
+                if not attempts_left:
+                    if verbose:
+                        print(" failed")
+                    raise
+                if verbose:
+                    print(".", end="", flush=True)
+
+    # Save to cache.
+    if cache:
+        safe_name = re.sub(r"[^0-9a-zA-Z-._]", "_", url_name)
+        cache_file = os.path.join(cache_dir, url_md5 + "_" + safe_name)
+        temp_file = os.path.join(cache_dir, "tmp_" + uuid.uuid4().hex + "_" + url_md5 + "_" + safe_name)
+        os.makedirs(cache_dir, exist_ok=True)
+        with open(temp_file, "wb") as f:
+            f.write(url_data)
+        os.replace(temp_file, cache_file) # atomic
+        if return_filename:
+            return cache_file
+
+    # Return data as file object.
+    assert not return_filename
+    return io.BytesIO(url_data)

environment.yml

@@ -0,0 +1,27 @@
+name: stylegan3
+channels:
+  - pytorch
+  - nvidia
+dependencies:
+  - python >= 3.8
+  - pip
+  - numpy>=1.25
+  - click>=8.0
+  - pillow=9.4.0
+  - scipy=1.11.0
+  - pytorch>=2.0.1
+  - torchvision>=0.15.2
+  - cudatoolkit=11.1
+  - requests=2.26.0
+  - tqdm=4.62.2
+  - ninja=1.10.2
+  - matplotlib=3.4.2
+  - imageio=2.9.0
+  - pip:
+    - imgui==2.0.0
+    - glfw==2.6.1
+    - gradio==3.35.2
+    - pyopengl==3.1.5
+    - imageio-ffmpeg==0.4.3
+    # pyspng is currently broken on MacOS (see https://github.com/nurpax/pyspng/pull/6 for instance)
+    - pyspng-seunglab

gen_images.py

@@ -0,0 +1,150 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+"""Generate images using pretrained network pickle."""
+
+import os
+import re
+from typing import List, Optional, Tuple, Union
+
+import click
+import dnnlib
+import numpy as np
+import PIL.Image
+import torch
+
+import legacy
+
+#----------------------------------------------------------------------------
+
+def parse_range(s: Union[str, List]) -> List[int]:
+    '''Parse a comma separated list of numbers or ranges and return a list of ints.
+
+    Example: '1,2,5-10' returns [1, 2, 5, 6, 7]
+    '''
+    if isinstance(s, list): return s
+    ranges = []
+    range_re = re.compile(r'^(\d+)-(\d+)$')
+    for p in s.split(','):
+        m = range_re.match(p)
+        if m:
+            ranges.extend(range(int(m.group(1)), int(m.group(2))+1))
+        else:
+            ranges.append(int(p))
+    return ranges
+
+#----------------------------------------------------------------------------
+
+def parse_vec2(s: Union[str, Tuple[float, float]]) -> Tuple[float, float]:
+    '''Parse a floating point 2-vector of syntax 'a,b'.
+
+    Example:
+        '0,1' returns (0,1)
+    '''
+    if isinstance(s, tuple): return s
+    parts = s.split(',')
+    if len(parts) == 2:
+        return (float(parts[0]), float(parts[1]))
+    raise ValueError(f'cannot parse 2-vector {s}')
+
+#----------------------------------------------------------------------------
+
+def make_transform(translate: Tuple[float,float], angle: float):
+    m = np.eye(3)
+    s = np.sin(angle/360.0*np.pi*2)
+    c = np.cos(angle/360.0*np.pi*2)
+    m[0][0] = c
+    m[0][1] = s
+    m[0][2] = translate[0]
+    m[1][0] = -s
+    m[1][1] = c
+    m[1][2] = translate[1]
+    return m
+
+#----------------------------------------------------------------------------
+
+@click.command()
+@click.option('--network', 'network_pkl', help='Network pickle filename', required=True)
+@click.option('--seeds', type=parse_range, help='List of random seeds (e.g., \'0,1,4-6\')', required=True)
+@click.option('--trunc', 'truncation_psi', type=float, help='Truncation psi', default=1, show_default=True)
+@click.option('--class', 'class_idx', type=int, help='Class label (unconditional if not specified)')
+@click.option('--noise-mode', help='Noise mode', type=click.Choice(['const', 'random', 'none']), default='const', show_default=True)
+@click.option('--translate', help='Translate XY-coordinate (e.g. \'0.3,1\')', type=parse_vec2, default='0,0', show_default=True, metavar='VEC2')
+@click.option('--rotate', help='Rotation angle in degrees', type=float, default=0, show_default=True, metavar='ANGLE')
+@click.option('--outdir', help='Where to save the output images', type=str, required=True, metavar='DIR')
+def generate_images(
+    network_pkl: str,
+    seeds: List[int],
+    truncation_psi: float,
+    noise_mode: str,
+    outdir: str,
+    translate: Tuple[float,float],
+    rotate: float,
+    class_idx: Optional[int]
+):
+    """Generate images using pretrained network pickle.
+
+    Examples:
+
+    \b
+    # Generate an image using pre-trained AFHQv2 model ("Ours" in Figure 1, left).
+    python gen_images.py --outdir=out --trunc=1 --seeds=2 \\
+        --network=https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan3/versions/1/files/stylegan3-r-afhqv2-512x512.pkl
+
+    \b
+    # Generate uncurated images with truncation using the MetFaces-U dataset
+    python gen_images.py --outdir=out --trunc=0.7 --seeds=600-605 \\
+        --network=https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan3/versions/1/files/stylegan3-t-metfacesu-1024x1024.pkl
+    """
+
+    print('Loading networks from "%s"...' % network_pkl)
+    device = torch.device('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
+    dtype = torch.float32 if device.type == 'mps' else torch.float64
+    with dnnlib.util.open_url(network_pkl) as f:
+        G = legacy.load_network_pkl(f)['G_ema'].to(device, dtype=dtype) # type: ignore
+        # import pickle
+        # G = legacy.load_network_pkl(f)
+        # output = open('checkpoints/stylegan2-car-config-f-pt.pkl', 'wb')
+        # pickle.dump(G, output)
+
+    os.makedirs(outdir, exist_ok=True)
+
+    # Labels.
+    label = torch.zeros([1, G.c_dim], device=device)
+    if G.c_dim != 0:
+        if class_idx is None:
+            raise click.ClickException('Must specify class label with --class when using a conditional network')
+        label[:, class_idx] = 1
+    else:
+        if class_idx is not None:
+            print ('warn: --class=lbl ignored when running on an unconditional network')
+
+    # Generate images.
+    for seed_idx, seed in enumerate(seeds):
+        print('Generating image for seed %d (%d/%d) ...' % (seed, seed_idx, len(seeds)))
+        z = torch.from_numpy(np.random.RandomState(seed).randn(1, G.z_dim)).to(device, dtype=dtype)
+
+        # Construct an inverse rotation/translation matrix and pass to the generator.  The
+        # generator expects this matrix as an inverse to avoid potentially failing numerical
+        # operations in the network.
+        if hasattr(G.synthesis, 'input'):
+            m = make_transform(translate, rotate)
+            m = np.linalg.inv(m)
+            G.synthesis.input.transform.copy_(torch.from_numpy(m))
+
+        img = G(z, label, truncation_psi=truncation_psi, noise_mode=noise_mode)
+        img = (img.permute(0, 2, 3, 1) * 127.5 + 128).clamp(0, 255).to(torch.uint8)
+        PIL.Image.fromarray(img[0].cpu().numpy(), 'RGB').save(f'{outdir}/seed{seed:04d}.png')
+
+
+#----------------------------------------------------------------------------
+
+if __name__ == "__main__":
+    generate_images() # pylint: disable=no-value-for-parameter
+
+#----------------------------------------------------------------------------

gradio_utils/__init__.py

@@ -0,0 +1,9 @@
+from .utils import (ImageMask, draw_mask_on_image, draw_points_on_image,
+                    get_latest_points_pair, get_valid_mask,
+                    on_change_single_global_state)
+
+__all__ = [
+    'draw_mask_on_image', 'draw_points_on_image',
+    'on_change_single_global_state', 'get_latest_points_pair',
+    'get_valid_mask', 'ImageMask'
+]

gradio_utils/utils.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import numpy as np
+from PIL import Image, ImageDraw
+
+
+class ImageMask(gr.components.Image):
+    """
+    Sets: source="canvas", tool="sketch"
+    """
+
+    is_template = True
+
+    def __init__(self, **kwargs):
+        super().__init__(source="upload",
+                         tool="sketch",
+                         interactive=False,
+                         **kwargs)
+
+    def preprocess(self, x):
+        if x is None:
+            return x
+        if self.tool == "sketch" and self.source in ["upload", "webcam"
+                                                     ] and type(x) != dict:
+            decode_image = gr.processing_utils.decode_base64_to_image(x)
+            width, height = decode_image.size
+            mask = np.ones((height, width, 4), dtype=np.uint8)
+            mask[..., -1] = 255
+            mask = self.postprocess(mask)
+            x = {'image': x, 'mask': mask}
+        return super().preprocess(x)
+
+
+def get_valid_mask(mask: np.ndarray):
+    """Convert mask from gr.Image(0 to 255, RGBA) to binary mask.
+    """
+    if mask.ndim == 3:
+        mask_pil = Image.fromarray(mask).convert('L')
+        mask = np.array(mask_pil)
+    if mask.max() == 255:
+        mask = mask / 255
+    return mask
+
+
+def draw_points_on_image(image,
+                         points,
+                         curr_point=None,
+                         highlight_all=True,
+                         radius_scale=0.01):
+    overlay_rgba = Image.new("RGBA", image.size, 0)
+    overlay_draw = ImageDraw.Draw(overlay_rgba)
+    for point_key, point in points.items():
+        if ((curr_point is not None and curr_point == point_key)
+                or highlight_all):
+            p_color = (255, 0, 0)
+            t_color = (0, 0, 255)
+
+        else:
+            p_color = (255, 0, 0, 35)
+            t_color = (0, 0, 255, 35)
+
+        rad_draw = int(image.size[0] * radius_scale)
+
+        p_start = point.get("start_temp", point["start"])
+        p_target = point["target"]
+
+        if p_start is not None and p_target is not None:
+            p_draw = int(p_start[0]), int(p_start[1])
+            t_draw = int(p_target[0]), int(p_target[1])
+
+            overlay_draw.line(
+                (p_draw[0], p_draw[1], t_draw[0], t_draw[1]),
+                fill=(255, 255, 0),
+                width=2,
+            )
+
+        if p_start is not None:
+            p_draw = int(p_start[0]), int(p_start[1])
+            overlay_draw.ellipse(
+                (
+                    p_draw[0] - rad_draw,
+                    p_draw[1] - rad_draw,
+                    p_draw[0] + rad_draw,
+                    p_draw[1] + rad_draw,
+                ),
+                fill=p_color,
+            )
+
+            if curr_point is not None and curr_point == point_key:
+                # overlay_draw.text(p_draw, "p", font=font, align="center", fill=(0, 0, 0))
+                overlay_draw.text(p_draw, "p", align="center", fill=(0, 0, 0))
+
+        if p_target is not None:
+            t_draw = int(p_target[0]), int(p_target[1])
+            overlay_draw.ellipse(
+                (
+                    t_draw[0] - rad_draw,
+                    t_draw[1] - rad_draw,
+                    t_draw[0] + rad_draw,
+                    t_draw[1] + rad_draw,
+                ),
+                fill=t_color,
+            )
+
+            if curr_point is not None and curr_point == point_key:
+                # overlay_draw.text(t_draw, "t", font=font, align="center", fill=(0, 0, 0))
+                overlay_draw.text(t_draw, "t", align="center", fill=(0, 0, 0))
+
+    return Image.alpha_composite(image.convert("RGBA"),
+                                 overlay_rgba).convert("RGB")
+
+
+def draw_mask_on_image(image, mask):
+    im_mask = np.uint8(mask * 255)
+    im_mask_rgba = np.concatenate(
+        (
+            np.tile(im_mask[..., None], [1, 1, 3]),
+            45 * np.ones(
+                (im_mask.shape[0], im_mask.shape[1], 1), dtype=np.uint8),
+        ),
+        axis=-1,
+    )
+    im_mask_rgba = Image.fromarray(im_mask_rgba).convert("RGBA")
+
+    return Image.alpha_composite(image.convert("RGBA"),
+                                 im_mask_rgba).convert("RGB")
+
+
+def on_change_single_global_state(keys,
+                                  value,
+                                  global_state,
+                                  map_transform=None):
+    if map_transform is not None:
+        value = map_transform(value)
+
+    curr_state = global_state
+    if isinstance(keys, str):
+        last_key = keys
+
+    else:
+        for k in keys[:-1]:
+            curr_state = curr_state[k]
+
+        last_key = keys[-1]
+
+    curr_state[last_key] = value
+    return global_state
+
+
+def get_latest_points_pair(points_dict):
+    if not points_dict:
+        return None
+    point_idx = list(points_dict.keys())
+    latest_point_idx = max(point_idx)
+    return latest_point_idx

gui_utils/__init__.py

@@ -0,0 +1,9 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+# empty

gui_utils/gl_utils.py

@@ -0,0 +1,416 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+import math
+import os
+import functools
+import contextlib
+import numpy as np
+import OpenGL.GL as gl
+import OpenGL.GL.ARB.texture_float
+import dnnlib
+
+#----------------------------------------------------------------------------
+
+def init_egl():
+    assert os.environ['PYOPENGL_PLATFORM'] == 'egl' # Must be set before importing OpenGL.
+    import OpenGL.EGL as egl
+    import ctypes
+
+    # Initialize EGL.
+    display = egl.eglGetDisplay(egl.EGL_DEFAULT_DISPLAY)
+    assert display != egl.EGL_NO_DISPLAY
+    major = ctypes.c_int32()
+    minor = ctypes.c_int32()
+    ok = egl.eglInitialize(display, major, minor)
+    assert ok
+    assert major.value * 10 + minor.value >= 14
+
+    # Choose config.
+    config_attribs = [
+        egl.EGL_RENDERABLE_TYPE,    egl.EGL_OPENGL_BIT,
+        egl.EGL_SURFACE_TYPE,       egl.EGL_PBUFFER_BIT,
+        egl.EGL_NONE
+    ]
+    configs = (ctypes.c_int32 * 1)()
+    num_configs = ctypes.c_int32()
+    ok = egl.eglChooseConfig(display, config_attribs, configs, 1, num_configs)
+    assert ok
+    assert num_configs.value == 1
+    config = configs[0]
+
+    # Create dummy pbuffer surface.
+    surface_attribs = [
+        egl.EGL_WIDTH,  1,
+        egl.EGL_HEIGHT, 1,
+        egl.EGL_NONE
+    ]
+    surface = egl.eglCreatePbufferSurface(display, config, surface_attribs)
+    assert surface != egl.EGL_NO_SURFACE
+
+    # Setup GL context.
+    ok = egl.eglBindAPI(egl.EGL_OPENGL_API)
+    assert ok
+    context = egl.eglCreateContext(display, config, egl.EGL_NO_CONTEXT, None)
+    assert context != egl.EGL_NO_CONTEXT
+    ok = egl.eglMakeCurrent(display, surface, surface, context)
+    assert ok
+
+#----------------------------------------------------------------------------
+
+_texture_formats = {
+    ('uint8',   1): dnnlib.EasyDict(type=gl.GL_UNSIGNED_BYTE, format=gl.GL_LUMINANCE,       internalformat=gl.GL_LUMINANCE8),
+    ('uint8',   2): dnnlib.EasyDict(type=gl.GL_UNSIGNED_BYTE, format=gl.GL_LUMINANCE_ALPHA, internalformat=gl.GL_LUMINANCE8_ALPHA8),
+    ('uint8',   3): dnnlib.EasyDict(type=gl.GL_UNSIGNED_BYTE, format=gl.GL_RGB,             internalformat=gl.GL_RGB8),
+    ('uint8',   4): dnnlib.EasyDict(type=gl.GL_UNSIGNED_BYTE, format=gl.GL_RGBA,            internalformat=gl.GL_RGBA8),
+    ('float32', 1): dnnlib.EasyDict(type=gl.GL_FLOAT,         format=gl.GL_LUMINANCE,       internalformat=OpenGL.GL.ARB.texture_float.GL_LUMINANCE32F_ARB),
+    ('float32', 2): dnnlib.EasyDict(type=gl.GL_FLOAT,         format=gl.GL_LUMINANCE_ALPHA, internalformat=OpenGL.GL.ARB.texture_float.GL_LUMINANCE_ALPHA32F_ARB),
+    ('float32', 3): dnnlib.EasyDict(type=gl.GL_FLOAT,         format=gl.GL_RGB,             internalformat=gl.GL_RGB32F),
+    ('float32', 4): dnnlib.EasyDict(type=gl.GL_FLOAT,         format=gl.GL_RGBA,            internalformat=gl.GL_RGBA32F),
+}
+
+def get_texture_format(dtype, channels):
+    return _texture_formats[(np.dtype(dtype).name, int(channels))]
+
+#----------------------------------------------------------------------------
+
+def prepare_texture_data(image):
+    image = np.asarray(image)
+    if image.ndim == 2:
+        image = image[:, :, np.newaxis]
+    if image.dtype.name == 'float64':
+        image = image.astype('float32')
+    return image
+
+#----------------------------------------------------------------------------
+
+def draw_pixels(image, *, pos=0, zoom=1, align=0, rint=True):
+    pos = np.broadcast_to(np.asarray(pos, dtype='float32'), [2])
+    zoom = np.broadcast_to(np.asarray(zoom, dtype='float32'), [2])
+    align = np.broadcast_to(np.asarray(align, dtype='float32'), [2])
+    image = prepare_texture_data(image)
+    height, width, channels = image.shape
+    size = zoom * [width, height]
+    pos = pos - size * align
+    if rint:
+        pos = np.rint(pos)
+    fmt = get_texture_format(image.dtype, channels)
+
+    gl.glPushAttrib(gl.GL_CURRENT_BIT | gl.GL_PIXEL_MODE_BIT)
+    gl.glPushClientAttrib(gl.GL_CLIENT_PIXEL_STORE_BIT)
+    gl.glRasterPos2f(pos[0], pos[1])
+    gl.glPixelZoom(zoom[0], -zoom[1])
+    gl.glPixelStorei(gl.GL_UNPACK_ALIGNMENT, 1)
+    gl.glDrawPixels(width, height, fmt.format, fmt.type, image)
+    gl.glPopClientAttrib()
+    gl.glPopAttrib()
+
+#----------------------------------------------------------------------------
+
+def read_pixels(width, height, *, pos=0, dtype='uint8', channels=3):
+    pos = np.broadcast_to(np.asarray(pos, dtype='float32'), [2])
+    dtype = np.dtype(dtype)
+    fmt = get_texture_format(dtype, channels)
+    image = np.empty([height, width, channels], dtype=dtype)
+
+    gl.glPushClientAttrib(gl.GL_CLIENT_PIXEL_STORE_BIT)
+    gl.glPixelStorei(gl.GL_PACK_ALIGNMENT, 1)
+    gl.glReadPixels(int(np.round(pos[0])), int(np.round(pos[1])), width, height, fmt.format, fmt.type, image)
+    gl.glPopClientAttrib()
+    return np.flipud(image)
+
+#----------------------------------------------------------------------------
+
+class Texture:
+    def __init__(self, *, image=None, width=None, height=None, channels=None, dtype=None, bilinear=True, mipmap=True):
+        self.gl_id = None
+        self.bilinear = bilinear
+        self.mipmap = mipmap
+
+        # Determine size and dtype.
+        if image is not None:
+            image = prepare_texture_data(image)
+            self.height, self.width, self.channels = image.shape
+            self.dtype = image.dtype
+        else:
+            assert width is not None and height is not None
+            self.width = width
+            self.height = height
+            self.channels = channels if channels is not None else 3
+            self.dtype = np.dtype(dtype) if dtype is not None else np.uint8
+
+        # Validate size and dtype.
+        assert isinstance(self.width, int) and self.width >= 0
+        assert isinstance(self.height, int) and self.height >= 0
+        assert isinstance(self.channels, int) and self.channels >= 1
+        assert self.is_compatible(width=width, height=height, channels=channels, dtype=dtype)
+
+        # Create texture object.
+        self.gl_id = gl.glGenTextures(1)
+        with self.bind():
+            gl.glTexParameterf(gl.GL_TEXTURE_2D, gl.GL_TEXTURE_WRAP_S, gl.GL_CLAMP_TO_EDGE)
+            gl.glTexParameterf(gl.GL_TEXTURE_2D, gl.GL_TEXTURE_WRAP_T, gl.GL_CLAMP_TO_EDGE)
+            gl.glTexParameterf(gl.GL_TEXTURE_2D, gl.GL_TEXTURE_MAG_FILTER, gl.GL_LINEAR if self.bilinear else gl.GL_NEAREST)
+            gl.glTexParameterf(gl.GL_TEXTURE_2D, gl.GL_TEXTURE_MIN_FILTER, gl.GL_LINEAR_MIPMAP_LINEAR if self.mipmap else gl.GL_NEAREST)
+        self.update(image)
+
+    def delete(self):
+        if self.gl_id is not None:
+            gl.glDeleteTextures([self.gl_id])
+            self.gl_id = None
+
+    def __del__(self):
+        try:
+            self.delete()
+        except:
+            pass
+
+    @contextlib.contextmanager
+    def bind(self):
+        prev_id = gl.glGetInteger(gl.GL_TEXTURE_BINDING_2D)
+        gl.glBindTexture(gl.GL_TEXTURE_2D, self.gl_id)
+        yield
+        gl.glBindTexture(gl.GL_TEXTURE_2D, prev_id)
+
+    def update(self, image):
+        if image is not None:
+            image = prepare_texture_data(image)
+            assert self.is_compatible(image=image)
+        with self.bind():
+            fmt = get_texture_format(self.dtype, self.channels)
+            gl.glPushClientAttrib(gl.GL_CLIENT_PIXEL_STORE_BIT)
+            gl.glPixelStorei(gl.GL_UNPACK_ALIGNMENT, 1)
+            gl.glTexImage2D(gl.GL_TEXTURE_2D, 0, fmt.internalformat, self.width, self.height, 0, fmt.format, fmt.type, image)
+            if self.mipmap:
+                gl.glGenerateMipmap(gl.GL_TEXTURE_2D)
+            gl.glPopClientAttrib()
+
+    def draw(self, *, pos=0, zoom=1, align=0, rint=False, color=1, alpha=1, rounding=0):
+        zoom = np.broadcast_to(np.asarray(zoom, dtype='float32'), [2])
+        size = zoom * [self.width, self.height]
+        with self.bind():
+            gl.glPushAttrib(gl.GL_ENABLE_BIT)
+            gl.glEnable(gl.GL_TEXTURE_2D)
+            draw_rect(pos=pos, size=size, align=align, rint=rint, color=color, alpha=alpha, rounding=rounding)
+            gl.glPopAttrib()
+
+    def is_compatible(self, *, image=None, width=None, height=None, channels=None, dtype=None): # pylint: disable=too-many-return-statements
+        if image is not None:
+            if image.ndim != 3:
+                return False
+            ih, iw, ic = image.shape
+            if not self.is_compatible(width=iw, height=ih, channels=ic, dtype=image.dtype):
+                return False
+        if width is not None and self.width != width:
+            return False
+        if height is not None and self.height != height:
+            return False
+        if channels is not None and self.channels != channels:
+            return False
+        if dtype is not None and self.dtype != dtype:
+            return False
+        return True
+
+#----------------------------------------------------------------------------
+
+class Framebuffer:
+    def __init__(self, *, texture=None, width=None, height=None, channels=None, dtype=None, msaa=0):
+        self.texture = texture
+        self.gl_id = None
+        self.gl_color = None
+        self.gl_depth_stencil = None
+        self.msaa = msaa
+
+        # Determine size and dtype.
+        if texture is not None:
+            assert isinstance(self.texture, Texture)
+            self.width = texture.width
+            self.height = texture.height
+            self.channels = texture.channels
+            self.dtype = texture.dtype
+        else:
+            assert width is not None and height is not None
+            self.width = width
+            self.height = height
+            self.channels = channels if channels is not None else 4
+            self.dtype = np.dtype(dtype) if dtype is not None else np.float32
+
+        # Validate size and dtype.
+        assert isinstance(self.width, int) and self.width >= 0
+        assert isinstance(self.height, int) and self.height >= 0
+        assert isinstance(self.channels, int) and self.channels >= 1
+        assert width is None or width == self.width
+        assert height is None or height == self.height
+        assert channels is None or channels == self.channels
+        assert dtype is None or dtype == self.dtype
+
+        # Create framebuffer object.
+        self.gl_id = gl.glGenFramebuffers(1)
+        with self.bind():
+
+            # Setup color buffer.
+            if self.texture is not None:
+                assert self.msaa == 0
+                gl.glFramebufferTexture2D(gl.GL_FRAMEBUFFER, gl.GL_COLOR_ATTACHMENT0, gl.GL_TEXTURE_2D, self.texture.gl_id, 0)
+            else:
+                fmt = get_texture_format(self.dtype, self.channels)
+                self.gl_color = gl.glGenRenderbuffers(1)
+                gl.glBindRenderbuffer(gl.GL_RENDERBUFFER, self.gl_color)
+                gl.glRenderbufferStorageMultisample(gl.GL_RENDERBUFFER, self.msaa, fmt.internalformat, self.width, self.height)
+                gl.glFramebufferRenderbuffer(gl.GL_FRAMEBUFFER, gl.GL_COLOR_ATTACHMENT0, gl.GL_RENDERBUFFER, self.gl_color)
+
+            # Setup depth/stencil buffer.
+            self.gl_depth_stencil = gl.glGenRenderbuffers(1)
+            gl.glBindRenderbuffer(gl.GL_RENDERBUFFER, self.gl_depth_stencil)
+            gl.glRenderbufferStorageMultisample(gl.GL_RENDERBUFFER, self.msaa, gl.GL_DEPTH24_STENCIL8, self.width, self.height)
+            gl.glFramebufferRenderbuffer(gl.GL_FRAMEBUFFER, gl.GL_DEPTH_STENCIL_ATTACHMENT, gl.GL_RENDERBUFFER, self.gl_depth_stencil)
+
+    def delete(self):
+        if self.gl_id is not None:
+            gl.glDeleteFramebuffers([self.gl_id])
+            self.gl_id = None
+        if self.gl_color is not None:
+            gl.glDeleteRenderbuffers(1, [self.gl_color])
+            self.gl_color = None
+        if self.gl_depth_stencil is not None:
+            gl.glDeleteRenderbuffers(1, [self.gl_depth_stencil])
+            self.gl_depth_stencil = None
+
+    def __del__(self):
+        try:
+            self.delete()
+        except:
+            pass
+
+    @contextlib.contextmanager
+    def bind(self):
+        prev_fbo = gl.glGetInteger(gl.GL_FRAMEBUFFER_BINDING)
+        prev_rbo = gl.glGetInteger(gl.GL_RENDERBUFFER_BINDING)
+        gl.glBindFramebuffer(gl.GL_FRAMEBUFFER, self.gl_id)
+        if self.width is not None and self.height is not None:
+            gl.glViewport(0, 0, self.width, self.height)
+        yield
+        gl.glBindFramebuffer(gl.GL_FRAMEBUFFER, prev_fbo)
+        gl.glBindRenderbuffer(gl.GL_RENDERBUFFER, prev_rbo)
+
+    def blit(self, dst=None):
+        assert dst is None or isinstance(dst, Framebuffer)
+        with self.bind():
+            gl.glBindFramebuffer(gl.GL_DRAW_FRAMEBUFFER, 0 if dst is None else dst.fbo)
+            gl.glBlitFramebuffer(0, 0, self.width, self.height, 0, 0, self.width, self.height, gl.GL_COLOR_BUFFER_BIT, gl.GL_NEAREST)
+
+#----------------------------------------------------------------------------
+
+def draw_shape(vertices, *, mode=gl.GL_TRIANGLE_FAN, pos=0, size=1, color=1, alpha=1):
+    assert vertices.ndim == 2 and vertices.shape[1] == 2
+    pos = np.broadcast_to(np.asarray(pos, dtype='float32'), [2])
+    size = np.broadcast_to(np.asarray(size, dtype='float32'), [2])
+    color = np.broadcast_to(np.asarray(color, dtype='float32'), [3])
+    alpha = np.clip(np.broadcast_to(np.asarray(alpha, dtype='float32'), []), 0, 1)
+
+    gl.glPushClientAttrib(gl.GL_CLIENT_VERTEX_ARRAY_BIT)
+    gl.glPushAttrib(gl.GL_CURRENT_BIT | gl.GL_TRANSFORM_BIT)
+    gl.glMatrixMode(gl.GL_MODELVIEW)
+    gl.glPushMatrix()
+
+    gl.glEnableClientState(gl.GL_VERTEX_ARRAY)
+    gl.glEnableClientState(gl.GL_TEXTURE_COORD_ARRAY)
+    gl.glVertexPointer(2, gl.GL_FLOAT, 0, vertices)
+    gl.glTexCoordPointer(2, gl.GL_FLOAT, 0, vertices)
+    gl.glTranslate(pos[0], pos[1], 0)
+    gl.glScale(size[0], size[1], 1)
+    gl.glColor4f(color[0] * alpha, color[1] * alpha, color[2] * alpha, alpha)
+    gl.glDrawArrays(mode, 0, vertices.shape[0])
+
+    gl.glPopMatrix()
+    gl.glPopAttrib()
+    gl.glPopClientAttrib()
+
+#----------------------------------------------------------------------------
+
+def draw_arrow(x1, y1, x2, y2, l=10, width=1.0):
+    # Compute the length and angle of the arrow
+    dx = x2 - x1
+    dy = y2 - y1
+    length = math.sqrt(dx**2 + dy**2)
+    if length < l:
+        return
+    angle = math.atan2(dy, dx)
+    
+    # Save the current modelview matrix
+    gl.glPushMatrix()
+    
+    # Translate and rotate the coordinate system
+    gl.glTranslatef(x1, y1, 0.0)
+    gl.glRotatef(angle * 180.0 / math.pi, 0.0, 0.0, 1.0)
+    
+    # Set the line width
+    gl.glLineWidth(width)
+    # gl.glColor3f(0.75, 0.75, 0.75)
+    
+    # Begin drawing lines
+    gl.glBegin(gl.GL_LINES)
+    
+    # Draw the shaft of the arrow
+    gl.glVertex2f(0.0, 0.0)
+    gl.glVertex2f(length, 0.0)
+    
+    # Draw the head of the arrow
+    gl.glVertex2f(length, 0.0)
+    gl.glVertex2f(length - 2 * l, l)
+    gl.glVertex2f(length, 0.0)
+    gl.glVertex2f(length - 2 * l, -l)
+    
+    # End drawing lines
+    gl.glEnd()
+    
+    # Restore the modelview matrix
+    gl.glPopMatrix()
+
+#----------------------------------------------------------------------------
+
+def draw_rect(*, pos=0, pos2=None, size=None, align=0, rint=False, color=1, alpha=1, rounding=0):
+    assert pos2 is None or size is None
+    pos = np.broadcast_to(np.asarray(pos, dtype='float32'), [2])
+    pos2 = np.broadcast_to(np.asarray(pos2, dtype='float32'), [2]) if pos2 is not None else None
+    size = np.broadcast_to(np.asarray(size, dtype='float32'), [2]) if size is not None else None
+    size = size if size is not None else pos2 - pos if pos2 is not None else np.array([1, 1], dtype='float32')
+    pos = pos - size * align
+    if rint:
+        pos = np.rint(pos)
+    rounding = np.broadcast_to(np.asarray(rounding, dtype='float32'), [2])
+    rounding = np.minimum(np.abs(rounding) / np.maximum(np.abs(size), 1e-8), 0.5)
+    if np.min(rounding) == 0:
+        rounding *= 0
+    vertices = _setup_rect(float(rounding[0]), float(rounding[1]))
+    draw_shape(vertices, mode=gl.GL_TRIANGLE_FAN, pos=pos, size=size, color=color, alpha=alpha)
+
+@functools.lru_cache(maxsize=10000)
+def _setup_rect(rx, ry):
+    t = np.linspace(0, np.pi / 2, 1 if max(rx, ry) == 0 else 64)
+    s = 1 - np.sin(t); c = 1 - np.cos(t)
+    x = [c * rx, 1 - s * rx, 1 - c * rx, s * rx]
+    y = [s * ry, c * ry, 1 - s * ry, 1 - c * ry]
+    v = np.stack([x, y], axis=-1).reshape(-1, 2)
+    return v.astype('float32')
+
+#----------------------------------------------------------------------------
+
+def draw_circle(*, center=0, radius=100, hole=0, color=1, alpha=1):
+    hole = np.broadcast_to(np.asarray(hole, dtype='float32'), [])
+    vertices = _setup_circle(float(hole))
+    draw_shape(vertices, mode=gl.GL_TRIANGLE_STRIP, pos=center, size=radius, color=color, alpha=alpha)
+
+@functools.lru_cache(maxsize=10000)
+def _setup_circle(hole):
+    t = np.linspace(0, np.pi * 2, 128)
+    s = np.sin(t); c = np.cos(t)
+    v = np.stack([c, s, c * hole, s * hole], axis=-1).reshape(-1, 2)
+    return v.astype('float32')
+
+#----------------------------------------------------------------------------

gui_utils/glfw_window.py

@@ -0,0 +1,229 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+import time
+import glfw
+import OpenGL.GL as gl
+from . import gl_utils
+
+#----------------------------------------------------------------------------
+
+class GlfwWindow: # pylint: disable=too-many-public-methods
+    def __init__(self, *, title='GlfwWindow', window_width=1920, window_height=1080, deferred_show=True, close_on_esc=True):
+        self._glfw_window           = None
+        self._drawing_frame         = False
+        self._frame_start_time      = None
+        self._frame_delta           = 0
+        self._fps_limit             = None
+        self._vsync                 = None
+        self._skip_frames           = 0
+        self._deferred_show         = deferred_show
+        self._close_on_esc          = close_on_esc
+        self._esc_pressed           = False
+        self._drag_and_drop_paths   = None
+        self._capture_next_frame    = False
+        self._captured_frame        = None
+
+        # Create window.
+        glfw.init()
+        glfw.window_hint(glfw.VISIBLE, False)
+        self._glfw_window = glfw.create_window(width=window_width, height=window_height, title=title, monitor=None, share=None)
+        self._attach_glfw_callbacks()
+        self.make_context_current()
+
+        # Adjust window.
+        self.set_vsync(False)
+        self.set_window_size(window_width, window_height)
+        if not self._deferred_show:
+            glfw.show_window(self._glfw_window)
+
+    def close(self):
+        if self._drawing_frame:
+            self.end_frame()
+        if self._glfw_window is not None:
+            glfw.destroy_window(self._glfw_window)
+            self._glfw_window = None
+        #glfw.terminate() # Commented out to play it nice with other glfw clients.
+
+    def __del__(self):
+        try:
+            self.close()
+        except:
+            pass
+
+    @property
+    def window_width(self):
+        return self.content_width
+
+    @property
+    def window_height(self):
+        return self.content_height + self.title_bar_height
+
+    @property
+    def content_width(self):
+        width, _height = glfw.get_window_size(self._glfw_window)
+        return width
+
+    @property
+    def content_height(self):
+        _width, height = glfw.get_window_size(self._glfw_window)
+        return height
+
+    @property
+    def title_bar_height(self):
+        _left, top, _right, _bottom = glfw.get_window_frame_size(self._glfw_window)
+        return top
+
+    @property
+    def monitor_width(self):
+        _, _, width, _height = glfw.get_monitor_workarea(glfw.get_primary_monitor())
+        return width
+
+    @property
+    def monitor_height(self):
+        _, _, _width, height = glfw.get_monitor_workarea(glfw.get_primary_monitor())
+        return height
+
+    @property
+    def frame_delta(self):
+        return self._frame_delta
+
+    def set_title(self, title):
+        glfw.set_window_title(self._glfw_window, title)
+
+    def set_window_size(self, width, height):
+        width = min(width, self.monitor_width)
+        height = min(height, self.monitor_height)
+        glfw.set_window_size(self._glfw_window, width, max(height - self.title_bar_height, 0))
+        if width == self.monitor_width and height == self.monitor_height:
+            self.maximize()
+
+    def set_content_size(self, width, height):
+        self.set_window_size(width, height + self.title_bar_height)
+
+    def maximize(self):
+        glfw.maximize_window(self._glfw_window)
+
+    def set_position(self, x, y):
+        glfw.set_window_pos(self._glfw_window, x, y + self.title_bar_height)
+
+    def center(self):
+        self.set_position((self.monitor_width - self.window_width) // 2, (self.monitor_height - self.window_height) // 2)
+
+    def set_vsync(self, vsync):
+        vsync = bool(vsync)
+        if vsync != self._vsync:
+            glfw.swap_interval(1 if vsync else 0)
+            self._vsync = vsync
+
+    def set_fps_limit(self, fps_limit):
+        self._fps_limit = int(fps_limit)
+
+    def should_close(self):
+        return glfw.window_should_close(self._glfw_window) or (self._close_on_esc and self._esc_pressed)
+
+    def skip_frame(self):
+        self.skip_frames(1)
+
+    def skip_frames(self, num): # Do not update window for the next N frames.
+        self._skip_frames = max(self._skip_frames, int(num))
+
+    def is_skipping_frames(self):
+        return self._skip_frames > 0
+
+    def capture_next_frame(self):
+        self._capture_next_frame = True
+
+    def pop_captured_frame(self):
+        frame = self._captured_frame
+        self._captured_frame = None
+        return frame
+
+    def pop_drag_and_drop_paths(self):
+        paths = self._drag_and_drop_paths
+        self._drag_and_drop_paths = None
+        return paths
+
+    def draw_frame(self): # To be overridden by subclass.
+        self.begin_frame()
+        # Rendering code goes here.
+        self.end_frame()
+
+    def make_context_current(self):
+        if self._glfw_window is not None:
+            glfw.make_context_current(self._glfw_window)
+
+    def begin_frame(self):
+        # End previous frame.
+        if self._drawing_frame:
+            self.end_frame()
+
+        # Apply FPS limit.
+        if self._frame_start_time is not None and self._fps_limit is not None:
+            delay = self._frame_start_time - time.perf_counter() + 1 / self._fps_limit
+            if delay > 0:
+                time.sleep(delay)
+        cur_time = time.perf_counter()
+        if self._frame_start_time is not None:
+            self._frame_delta = cur_time - self._frame_start_time
+        self._frame_start_time = cur_time
+
+        # Process events.
+        glfw.poll_events()
+
+        # Begin frame.
+        self._drawing_frame = True
+        self.make_context_current()
+
+        # Initialize GL state.
+        gl.glViewport(0, 0, self.content_width, self.content_height)
+        gl.glMatrixMode(gl.GL_PROJECTION)
+        gl.glLoadIdentity()
+        gl.glTranslate(-1, 1, 0)
+        gl.glScale(2 / max(self.content_width, 1), -2 / max(self.content_height, 1), 1)
+        gl.glMatrixMode(gl.GL_MODELVIEW)
+        gl.glLoadIdentity()
+        gl.glEnable(gl.GL_BLEND)
+        gl.glBlendFunc(gl.GL_ONE, gl.GL_ONE_MINUS_SRC_ALPHA) # Pre-multiplied alpha.
+
+        # Clear.
+        gl.glClearColor(0, 0, 0, 1)
+        gl.glClear(gl.GL_COLOR_BUFFER_BIT | gl.GL_DEPTH_BUFFER_BIT)
+
+    def end_frame(self):
+        assert self._drawing_frame
+        self._drawing_frame = False
+
+        # Skip frames if requested.
+        if self._skip_frames > 0:
+            self._skip_frames -= 1
+            return
+
+        # Capture frame if requested.
+        if self._capture_next_frame:
+            self._captured_frame = gl_utils.read_pixels(self.content_width, self.content_height)
+            self._capture_next_frame = False
+
+        # Update window.
+        if self._deferred_show:
+            glfw.show_window(self._glfw_window)
+            self._deferred_show = False
+        glfw.swap_buffers(self._glfw_window)
+
+    def _attach_glfw_callbacks(self):
+        glfw.set_key_callback(self._glfw_window, self._glfw_key_callback)
+        glfw.set_drop_callback(self._glfw_window, self._glfw_drop_callback)
+
+    def _glfw_key_callback(self, _window, key, _scancode, action, _mods):
+        if action == glfw.PRESS and key == glfw.KEY_ESCAPE:
+            self._esc_pressed = True
+
+    def _glfw_drop_callback(self, _window, paths):
+        self._drag_and_drop_paths = paths
+
+#----------------------------------------------------------------------------

gui_utils/imgui_utils.py

@@ -0,0 +1,191 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+import contextlib
+import imgui
+
+#----------------------------------------------------------------------------
+
+def set_default_style(color_scheme='dark', spacing=9, indent=23, scrollbar=27):
+    s = imgui.get_style()
+    s.window_padding        = [spacing, spacing]
+    s.item_spacing          = [spacing, spacing]
+    s.item_inner_spacing    = [spacing, spacing]
+    s.columns_min_spacing   = spacing
+    s.indent_spacing        = indent
+    s.scrollbar_size        = scrollbar
+    s.frame_padding         = [4, 3]
+    s.window_border_size    = 1
+    s.child_border_size     = 1
+    s.popup_border_size     = 1
+    s.frame_border_size     = 1
+    s.window_rounding       = 0
+    s.child_rounding        = 0
+    s.popup_rounding        = 3
+    s.frame_rounding        = 3
+    s.scrollbar_rounding    = 3
+    s.grab_rounding         = 3
+
+    getattr(imgui, f'style_colors_{color_scheme}')(s)
+    c0 = s.colors[imgui.COLOR_MENUBAR_BACKGROUND]
+    c1 = s.colors[imgui.COLOR_FRAME_BACKGROUND]
+    s.colors[imgui.COLOR_POPUP_BACKGROUND] = [x * 0.7 + y * 0.3 for x, y in zip(c0, c1)][:3] + [1]
+
+#----------------------------------------------------------------------------
+
+@contextlib.contextmanager
+def grayed_out(cond=True):
+    if cond:
+        s = imgui.get_style()
+        text = s.colors[imgui.COLOR_TEXT_DISABLED]
+        grab = s.colors[imgui.COLOR_SCROLLBAR_GRAB]
+        back = s.colors[imgui.COLOR_MENUBAR_BACKGROUND]
+        imgui.push_style_color(imgui.COLOR_TEXT, *text)
+        imgui.push_style_color(imgui.COLOR_CHECK_MARK, *grab)
+        imgui.push_style_color(imgui.COLOR_SLIDER_GRAB, *grab)
+        imgui.push_style_color(imgui.COLOR_SLIDER_GRAB_ACTIVE, *grab)
+        imgui.push_style_color(imgui.COLOR_FRAME_BACKGROUND, *back)
+        imgui.push_style_color(imgui.COLOR_FRAME_BACKGROUND_HOVERED, *back)
+        imgui.push_style_color(imgui.COLOR_FRAME_BACKGROUND_ACTIVE, *back)
+        imgui.push_style_color(imgui.COLOR_BUTTON, *back)
+        imgui.push_style_color(imgui.COLOR_BUTTON_HOVERED, *back)
+        imgui.push_style_color(imgui.COLOR_BUTTON_ACTIVE, *back)
+        imgui.push_style_color(imgui.COLOR_HEADER, *back)
+        imgui.push_style_color(imgui.COLOR_HEADER_HOVERED, *back)
+        imgui.push_style_color(imgui.COLOR_HEADER_ACTIVE, *back)
+        imgui.push_style_color(imgui.COLOR_POPUP_BACKGROUND, *back)
+        yield
+        imgui.pop_style_color(14)
+    else:
+        yield
+
+#----------------------------------------------------------------------------
+
+@contextlib.contextmanager
+def item_width(width=None):
+    if width is not None:
+        imgui.push_item_width(width)
+        yield
+        imgui.pop_item_width()
+    else:
+        yield
+
+#----------------------------------------------------------------------------
+
+def scoped_by_object_id(method):
+    def decorator(self, *args, **kwargs):
+        imgui.push_id(str(id(self)))
+        res = method(self, *args, **kwargs)
+        imgui.pop_id()
+        return res
+    return decorator
+
+#----------------------------------------------------------------------------
+
+def button(label, width=0, enabled=True):
+    with grayed_out(not enabled):
+        clicked = imgui.button(label, width=width)
+    clicked = clicked and enabled
+    return clicked
+
+#----------------------------------------------------------------------------
+
+def collapsing_header(text, visible=None, flags=0, default=False, enabled=True, show=True):
+    expanded = False
+    if show:
+        if default:
+            flags |= imgui.TREE_NODE_DEFAULT_OPEN
+        if not enabled:
+            flags |= imgui.TREE_NODE_LEAF
+        with grayed_out(not enabled):
+            expanded, visible = imgui.collapsing_header(text, visible=visible, flags=flags)
+        expanded = expanded and enabled
+    return expanded, visible
+
+#----------------------------------------------------------------------------
+
+def popup_button(label, width=0, enabled=True):
+    if button(label, width, enabled):
+        imgui.open_popup(label)
+    opened = imgui.begin_popup(label)
+    return opened
+
+#----------------------------------------------------------------------------
+
+def input_text(label, value, buffer_length, flags, width=None, help_text=''):
+    old_value = value
+    color = list(imgui.get_style().colors[imgui.COLOR_TEXT])
+    if value == '':
+        color[-1] *= 0.5
+    with item_width(width):
+        imgui.push_style_color(imgui.COLOR_TEXT, *color)
+        value = value if value != '' else help_text
+        changed, value = imgui.input_text(label, value, buffer_length, flags)
+        value = value if value != help_text else ''
+        imgui.pop_style_color(1)
+    if not flags & imgui.INPUT_TEXT_ENTER_RETURNS_TRUE:
+        changed = (value != old_value)
+    return changed, value
+
+#----------------------------------------------------------------------------
+
+def drag_previous_control(enabled=True):
+    dragging = False
+    dx = 0
+    dy = 0
+    if imgui.begin_drag_drop_source(imgui.DRAG_DROP_SOURCE_NO_PREVIEW_TOOLTIP):
+        if enabled:
+            dragging = True
+            dx, dy = imgui.get_mouse_drag_delta()
+            imgui.reset_mouse_drag_delta()
+        imgui.end_drag_drop_source()
+    return dragging, dx, dy
+
+#----------------------------------------------------------------------------
+
+def drag_button(label, width=0, enabled=True):
+    clicked = button(label, width=width, enabled=enabled)
+    dragging, dx, dy = drag_previous_control(enabled=enabled)
+    return clicked, dragging, dx, dy
+
+#----------------------------------------------------------------------------
+
+def drag_hidden_window(label, x, y, width, height, enabled=True):
+    imgui.push_style_color(imgui.COLOR_WINDOW_BACKGROUND, 0, 0, 0, 0)
+    imgui.push_style_color(imgui.COLOR_BORDER, 0, 0, 0, 0)
+    imgui.set_next_window_position(x, y)
+    imgui.set_next_window_size(width, height)
+    imgui.begin(label, closable=False, flags=(imgui.WINDOW_NO_TITLE_BAR | imgui.WINDOW_NO_RESIZE | imgui.WINDOW_NO_MOVE))
+    dragging, dx, dy = drag_previous_control(enabled=enabled)
+    imgui.end()
+    imgui.pop_style_color(2)
+    return dragging, dx, dy
+
+#----------------------------------------------------------------------------
+
+def click_hidden_window(label, x, y, width, height, img_w, img_h, enabled=True):
+    imgui.push_style_color(imgui.COLOR_WINDOW_BACKGROUND, 0, 0, 0, 0)
+    imgui.push_style_color(imgui.COLOR_BORDER, 0, 0, 0, 0)
+    imgui.set_next_window_position(x, y)
+    imgui.set_next_window_size(width, height)
+    imgui.begin(label, closable=False, flags=(imgui.WINDOW_NO_TITLE_BAR | imgui.WINDOW_NO_RESIZE | imgui.WINDOW_NO_MOVE))
+    clicked, down = False, False
+    img_x, img_y = 0, 0
+    if imgui.is_mouse_down():
+        posx, posy = imgui.get_mouse_pos()
+        if posx >= x and posx < x + width and posy >= y and posy < y + height:
+            if imgui.is_mouse_clicked():
+                clicked = True
+            down = True
+            img_x = round((posx - x) / (width - 1) * (img_w - 1))
+            img_y = round((posy - y) / (height - 1) * (img_h - 1))
+    imgui.end()
+    imgui.pop_style_color(2)
+    return clicked, down, img_x, img_y
+
+#----------------------------------------------------------------------------

gui_utils/imgui_window.py

@@ -0,0 +1,103 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+import os
+import imgui
+import imgui.integrations.glfw
+
+from . import glfw_window
+from . import imgui_utils
+from . import text_utils
+
+#----------------------------------------------------------------------------
+
+class ImguiWindow(glfw_window.GlfwWindow):
+    def __init__(self, *, title='ImguiWindow', font=None, font_sizes=range(14,24), **glfw_kwargs):
+        if font is None:
+            font = text_utils.get_default_font()
+        font_sizes = {int(size) for size in font_sizes}
+        super().__init__(title=title, **glfw_kwargs)
+
+        # Init fields.
+        self._imgui_context  = None
+        self._imgui_renderer = None
+        self._imgui_fonts    = None
+        self._cur_font_size  = max(font_sizes)
+
+        # Delete leftover imgui.ini to avoid unexpected behavior.
+        if os.path.isfile('imgui.ini'):
+            os.remove('imgui.ini')
+
+        # Init ImGui.
+        self._imgui_context = imgui.create_context()
+        self._imgui_renderer = _GlfwRenderer(self._glfw_window)
+        self._attach_glfw_callbacks()
+        imgui.get_io().ini_saving_rate = 0 # Disable creating imgui.ini at runtime.
+        imgui.get_io().mouse_drag_threshold = 0 # Improve behavior with imgui_utils.drag_custom().
+        self._imgui_fonts = {size: imgui.get_io().fonts.add_font_from_file_ttf(font, size) for size in font_sizes}
+        self._imgui_renderer.refresh_font_texture()
+
+    def close(self):
+        self.make_context_current()
+        self._imgui_fonts = None
+        if self._imgui_renderer is not None:
+            self._imgui_renderer.shutdown()
+            self._imgui_renderer = None
+        if self._imgui_context is not None:
+            #imgui.destroy_context(self._imgui_context) # Commented out to avoid creating imgui.ini at the end.
+            self._imgui_context = None
+        super().close()
+
+    def _glfw_key_callback(self, *args):
+        super()._glfw_key_callback(*args)
+        self._imgui_renderer.keyboard_callback(*args)
+
+    @property
+    def font_size(self):
+        return self._cur_font_size
+
+    @property
+    def spacing(self):
+        return round(self._cur_font_size * 0.4)
+
+    def set_font_size(self, target): # Applied on next frame.
+        self._cur_font_size = min((abs(key - target), key) for key in self._imgui_fonts.keys())[1]
+
+    def begin_frame(self):
+        # Begin glfw frame.
+        super().begin_frame()
+
+        # Process imgui events.
+        self._imgui_renderer.mouse_wheel_multiplier = self._cur_font_size / 10
+        if self.content_width > 0 and self.content_height > 0:
+            self._imgui_renderer.process_inputs()
+
+        # Begin imgui frame.
+        imgui.new_frame()
+        imgui.push_font(self._imgui_fonts[self._cur_font_size])
+        imgui_utils.set_default_style(spacing=self.spacing, indent=self.font_size, scrollbar=self.font_size+4)
+
+    def end_frame(self):
+        imgui.pop_font()
+        imgui.render()
+        imgui.end_frame()
+        self._imgui_renderer.render(imgui.get_draw_data())
+        super().end_frame()
+
+#----------------------------------------------------------------------------
+# Wrapper class for GlfwRenderer to fix a mouse wheel bug on Linux.
+
+class _GlfwRenderer(imgui.integrations.glfw.GlfwRenderer):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.mouse_wheel_multiplier = 1
+
+    def scroll_callback(self, window, x_offset, y_offset):
+        self.io.mouse_wheel += y_offset * self.mouse_wheel_multiplier
+
+#----------------------------------------------------------------------------

gui_utils/text_utils.py

@@ -0,0 +1,123 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+import functools
+from typing import Optional
+
+import dnnlib
+import numpy as np
+import PIL.Image
+import PIL.ImageFont
+import scipy.ndimage
+
+from . import gl_utils
+
+#----------------------------------------------------------------------------
+
+def get_default_font():
+    url = 'http://fonts.gstatic.com/s/opensans/v17/mem8YaGs126MiZpBA-U1UpcaXcl0Aw.ttf' # Open Sans regular
+    return dnnlib.util.open_url(url, return_filename=True)
+
+#----------------------------------------------------------------------------
+
+@functools.lru_cache(maxsize=None)
+def get_pil_font(font=None, size=32):
+    if font is None:
+        font = get_default_font()
+    return PIL.ImageFont.truetype(font=font, size=size)
+
+#----------------------------------------------------------------------------
+
+def get_array(string, *, dropshadow_radius: int=None, **kwargs):
+    if dropshadow_radius is not None:
+        offset_x = int(np.ceil(dropshadow_radius*2/3))
+        offset_y = int(np.ceil(dropshadow_radius*2/3))
+        return _get_array_priv(string, dropshadow_radius=dropshadow_radius, offset_x=offset_x, offset_y=offset_y, **kwargs)
+    else:
+        return _get_array_priv(string, **kwargs)
+
+@functools.lru_cache(maxsize=10000)
+def _get_array_priv(
+    string: str, *,
+    size: int = 32,
+    max_width: Optional[int]=None,
+    max_height: Optional[int]=None,
+    min_size=10,
+    shrink_coef=0.8,
+    dropshadow_radius: int=None,
+    offset_x: int=None,
+    offset_y: int=None,
+    **kwargs
+):
+    cur_size = size
+    array = None
+    while True:
+        if dropshadow_radius is not None:
+            # separate implementation for dropshadow text rendering
+            array = _get_array_impl_dropshadow(string, size=cur_size, radius=dropshadow_radius, offset_x=offset_x, offset_y=offset_y, **kwargs)
+        else:
+            array = _get_array_impl(string, size=cur_size, **kwargs)
+        height, width, _ = array.shape
+        if (max_width is None or width <= max_width) and (max_height is None or height <= max_height) or (cur_size <= min_size):
+            break
+        cur_size = max(int(cur_size * shrink_coef), min_size)
+    return array
+
+#----------------------------------------------------------------------------
+
+@functools.lru_cache(maxsize=10000)
+def _get_array_impl(string, *, font=None, size=32, outline=0, outline_pad=3, outline_coef=3, outline_exp=2, line_pad: int=None):
+    pil_font = get_pil_font(font=font, size=size)
+    lines = [pil_font.getmask(line, 'L') for line in string.split('\n')]
+    lines = [np.array(line, dtype=np.uint8).reshape([line.size[1], line.size[0]]) for line in lines]
+    width = max(line.shape[1] for line in lines)
+    lines = [np.pad(line, ((0, 0), (0, width - line.shape[1])), mode='constant') for line in lines]
+    line_spacing = line_pad if line_pad is not None else size // 2
+    lines = [np.pad(line, ((0, line_spacing), (0, 0)), mode='constant') for line in lines[:-1]] + lines[-1:]
+    mask = np.concatenate(lines, axis=0)
+    alpha = mask
+    if outline > 0:
+        mask = np.pad(mask, int(np.ceil(outline * outline_pad)), mode='constant', constant_values=0)
+        alpha = mask.astype(np.float32) / 255
+        alpha = scipy.ndimage.gaussian_filter(alpha, outline)
+        alpha = 1 - np.maximum(1 - alpha * outline_coef, 0) ** outline_exp
+        alpha = (alpha * 255 + 0.5).clip(0, 255).astype(np.uint8)
+        alpha = np.maximum(alpha, mask)
+    return np.stack([mask, alpha], axis=-1)
+
+#----------------------------------------------------------------------------
+
+@functools.lru_cache(maxsize=10000)
+def _get_array_impl_dropshadow(string, *, font=None, size=32, radius: int, offset_x: int, offset_y: int, line_pad: int=None, **kwargs):
+    assert (offset_x > 0) and (offset_y > 0)
+    pil_font = get_pil_font(font=font, size=size)
+    lines = [pil_font.getmask(line, 'L') for line in string.split('\n')]
+    lines = [np.array(line, dtype=np.uint8).reshape([line.size[1], line.size[0]]) for line in lines]
+    width = max(line.shape[1] for line in lines)
+    lines = [np.pad(line, ((0, 0), (0, width - line.shape[1])), mode='constant') for line in lines]
+    line_spacing = line_pad if line_pad is not None else size // 2
+    lines = [np.pad(line, ((0, line_spacing), (0, 0)), mode='constant') for line in lines[:-1]] + lines[-1:]
+    mask = np.concatenate(lines, axis=0)
+    alpha = mask
+
+    mask = np.pad(mask, 2*radius + max(abs(offset_x), abs(offset_y)), mode='constant', constant_values=0)
+    alpha = mask.astype(np.float32) / 255
+    alpha = scipy.ndimage.gaussian_filter(alpha, radius)
+    alpha = 1 - np.maximum(1 - alpha * 1.5, 0) ** 1.4
+    alpha = (alpha * 255 + 0.5).clip(0, 255).astype(np.uint8)
+    alpha = np.pad(alpha, [(offset_y, 0), (offset_x, 0)], mode='constant')[:-offset_y, :-offset_x]
+    alpha = np.maximum(alpha, mask)
+    return np.stack([mask, alpha], axis=-1)
+
+#----------------------------------------------------------------------------
+
+@functools.lru_cache(maxsize=10000)
+def get_texture(string, bilinear=True, mipmap=True, **kwargs):
+    return gl_utils.Texture(image=get_array(string, **kwargs), bilinear=bilinear, mipmap=mipmap)
+
+#----------------------------------------------------------------------------

legacy.py

@@ -0,0 +1,323 @@
+# Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
+#
+# NVIDIA CORPORATION and its licensors retain all intellectual property
+# and proprietary rights in and to this software, related documentation
+# and any modifications thereto.  Any use, reproduction, disclosure or
+# distribution of this software and related documentation without an express
+# license agreement from NVIDIA CORPORATION is strictly prohibited.
+
+"""Converting legacy network pickle into the new format."""
+
+import click
+import pickle
+import re
+import copy
+import numpy as np
+import torch
+import dnnlib
+from torch_utils import misc
+
+#----------------------------------------------------------------------------
+
+def load_network_pkl(f, force_fp16=False):
+    data = _LegacyUnpickler(f).load()
+
+    # Legacy TensorFlow pickle => convert.
+    if isinstance(data, tuple) and len(data) == 3 and all(isinstance(net, _TFNetworkStub) for net in data):
+        tf_G, tf_D, tf_Gs = data
+        G = convert_tf_generator(tf_G)
+        D = convert_tf_discriminator(tf_D)
+        G_ema = convert_tf_generator(tf_Gs)
+        data = dict(G=G, D=D, G_ema=G_ema)
+
+    # Add missing fields.
+    if 'training_set_kwargs' not in data:
+        data['training_set_kwargs'] = None
+    if 'augment_pipe' not in data:
+        data['augment_pipe'] = None
+
+    # Validate contents.
+    assert isinstance(data['G'], torch.nn.Module)
+    assert isinstance(data['D'], torch.nn.Module)
+    assert isinstance(data['G_ema'], torch.nn.Module)
+    assert isinstance(data['training_set_kwargs'], (dict, type(None)))
+    assert isinstance(data['augment_pipe'], (torch.nn.Module, type(None)))
+
+    # Force FP16.
+    if force_fp16:
+        for key in ['G', 'D', 'G_ema']:
+            old = data[key]
+            kwargs = copy.deepcopy(old.init_kwargs)
+            fp16_kwargs = kwargs.get('synthesis_kwargs', kwargs)
+            fp16_kwargs.num_fp16_res = 4
+            fp16_kwargs.conv_clamp = 256
+            if kwargs != old.init_kwargs:
+                new = type(old)(**kwargs).eval().requires_grad_(False)
+                misc.copy_params_and_buffers(old, new, require_all=True)
+                data[key] = new
+    return data
+
+#----------------------------------------------------------------------------
+
+class _TFNetworkStub(dnnlib.EasyDict):
+    pass
+
+class _LegacyUnpickler(pickle.Unpickler):
+    def find_class(self, module, name):
+        if module == 'dnnlib.tflib.network' and name == 'Network':
+            return _TFNetworkStub
+        return super().find_class(module, name)
+
+#----------------------------------------------------------------------------
+
+def _collect_tf_params(tf_net):
+    # pylint: disable=protected-access
+    tf_params = dict()
+    def recurse(prefix, tf_net):
+        for name, value in tf_net.variables:
+            tf_params[prefix + name] = value
+        for name, comp in tf_net.components.items():
+            recurse(prefix + name + '/', comp)
+    recurse('', tf_net)
+    return tf_params
+
+#----------------------------------------------------------------------------
+
+def _populate_module_params(module, *patterns):
+    for name, tensor in misc.named_params_and_buffers(module):
+        found = False
+        value = None
+        for pattern, value_fn in zip(patterns[0::2], patterns[1::2]):
+            match = re.fullmatch(pattern, name)
+            if match:
+                found = True
+                if value_fn is not None:
+                    value = value_fn(*match.groups())
+                break
+        try:
+            assert found
+            if value is not None:
+                tensor.copy_(torch.from_numpy(np.array(value)))
+        except:
+            print(name, list(tensor.shape))
+            raise
+
+#----------------------------------------------------------------------------
+
+def convert_tf_generator(tf_G):
+    if tf_G.version < 4:
+        raise ValueError('TensorFlow pickle version too low')
+
+    # Collect kwargs.
+    tf_kwargs = tf_G.static_kwargs
+    known_kwargs = set()
+    def kwarg(tf_name, default=None, none=None):
+        known_kwargs.add(tf_name)
+        val = tf_kwargs.get(tf_name, default)
+        return val if val is not None else none
+
+    # Convert kwargs.
+    from training import networks_stylegan2
+    network_class = networks_stylegan2.Generator
+    kwargs = dnnlib.EasyDict(
+        z_dim               = kwarg('latent_size',          512),
+        c_dim               = kwarg('label_size',           0),
+        w_dim               = kwarg('dlatent_size',         512),
+        img_resolution      = kwarg('resolution',           1024),
+        img_channels        = kwarg('num_channels',         3),
+        channel_base        = kwarg('fmap_base',            16384) * 2,
+        channel_max         = kwarg('fmap_max',             512),
+        num_fp16_res        = kwarg('num_fp16_res',         0),
+        conv_clamp          = kwarg('conv_clamp',           None),
+        architecture        = kwarg('architecture',         'skip'),
+        resample_filter     = kwarg('resample_kernel',      [1,3,3,1]),
+        use_noise           = kwarg('use_noise',            True),
+        activation          = kwarg('nonlinearity',         'lrelu'),
+        mapping_kwargs      = dnnlib.EasyDict(
+            num_layers      = kwarg('mapping_layers',       8),
+            embed_features  = kwarg('label_fmaps',          None),
+            layer_features  = kwarg('mapping_fmaps',        None),
+            activation      = kwarg('mapping_nonlinearity', 'lrelu'),
+            lr_multiplier   = kwarg('mapping_lrmul',        0.01),
+            w_avg_beta      = kwarg('w_avg_beta',           0.995,  none=1),
+        ),
+    )
+
+    # Check for unknown kwargs.
+    kwarg('truncation_psi')
+    kwarg('truncation_cutoff')
+    kwarg('style_mixing_prob')
+    kwarg('structure')
+    kwarg('conditioning')
+    kwarg('fused_modconv')
+    unknown_kwargs = list(set(tf_kwargs.keys()) - known_kwargs)
+    if len(unknown_kwargs) > 0:
+        raise ValueError('Unknown TensorFlow kwarg', unknown_kwargs[0])
+
+    # Collect params.
+    tf_params = _collect_tf_params(tf_G)
+    for name, value in list(tf_params.items()):
+        match = re.fullmatch(r'ToRGB_lod(\d+)/(.*)', name)
+        if match:
+            r = kwargs.img_resolution // (2 ** int(match.group(1)))
+            tf_params[f'{r}x{r}/ToRGB/{match.group(2)}'] = value
+            kwargs.synthesis.kwargs.architecture = 'orig'
+    #for name, value in tf_params.items(): print(f'{name:<50s}{list(value.shape)}')
+
+    # Convert params.
+    G = network_class(**kwargs).eval().requires_grad_(False)
+    # pylint: disable=unnecessary-lambda
+    # pylint: disable=f-string-without-interpolation
+    _populate_module_params(G,
+        r'mapping\.w_avg',                                  lambda:     tf_params[f'dlatent_avg'],
+        r'mapping\.embed\.weight',                          lambda:     tf_params[f'mapping/LabelEmbed/weight'].transpose(),
+        r'mapping\.embed\.bias',                            lambda:     tf_params[f'mapping/LabelEmbed/bias'],
+        r'mapping\.fc(\d+)\.weight',                        lambda i:   tf_params[f'mapping/Dense{i}/weight'].transpose(),
+        r'mapping\.fc(\d+)\.bias',                          lambda i:   tf_params[f'mapping/Dense{i}/bias'],
+        r'synthesis\.b4\.const',                            lambda:     tf_params[f'synthesis/4x4/Const/const'][0],
+        r'synthesis\.b4\.conv1\.weight',                    lambda:     tf_params[f'synthesis/4x4/Conv/weight'].transpose(3, 2, 0, 1),
+        r'synthesis\.b4\.conv1\.bias',                      lambda:     tf_params[f'synthesis/4x4/Conv/bias'],
+        r'synthesis\.b4\.conv1\.noise_const',               lambda:     tf_params[f'synthesis/noise0'][0, 0],
+        r'synthesis\.b4\.conv1\.noise_strength',            lambda:     tf_params[f'synthesis/4x4/Conv/noise_strength'],
+        r'synthesis\.b4\.conv1\.affine\.weight',            lambda:     tf_params[f'synthesis/4x4/Conv/mod_weight'].transpose(),
+        r'synthesis\.b4\.conv1\.affine\.bias',              lambda:     tf_params[f'synthesis/4x4/Conv/mod_bias'] + 1,
+        r'synthesis\.b(\d+)\.conv0\.weight',                lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/weight'][::-1, ::-1].transpose(3, 2, 0, 1),
+        r'synthesis\.b(\d+)\.conv0\.bias',                  lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/bias'],
+        r'synthesis\.b(\d+)\.conv0\.noise_const',           lambda r:   tf_params[f'synthesis/noise{int(np.log2(int(r)))*2-5}'][0, 0],
+        r'synthesis\.b(\d+)\.conv0\.noise_strength',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/noise_strength'],
+        r'synthesis\.b(\d+)\.conv0\.affine\.weight',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/mod_weight'].transpose(),
+        r'synthesis\.b(\d+)\.conv0\.affine\.bias',          lambda r:   tf_params[f'synthesis/{r}x{r}/Conv0_up/mod_bias'] + 1,
+        r'synthesis\.b(\d+)\.conv1\.weight',                lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/weight'].transpose(3, 2, 0, 1),
+        r'synthesis\.b(\d+)\.conv1\.bias',                  lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/bias'],
+        r'synthesis\.b(\d+)\.conv1\.noise_const',           lambda r:   tf_params[f'synthesis/noise{int(np.log2(int(r)))*2-4}'][0, 0],
+        r'synthesis\.b(\d+)\.conv1\.noise_strength',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/noise_strength'],
+        r'synthesis\.b(\d+)\.conv1\.affine\.weight',        lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/mod_weight'].transpose(),
+        r'synthesis\.b(\d+)\.conv1\.affine\.bias',          lambda r:   tf_params[f'synthesis/{r}x{r}/Conv1/mod_bias'] + 1,
+        r'synthesis\.b(\d+)\.torgb\.weight',                lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/weight'].transpose(3, 2, 0, 1),
+        r'synthesis\.b(\d+)\.torgb\.bias',                  lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/bias'],
+        r'synthesis\.b(\d+)\.torgb\.affine\.weight',        lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/mod_weight'].transpose(),
+        r'synthesis\.b(\d+)\.torgb\.affine\.bias',          lambda r:   tf_params[f'synthesis/{r}x{r}/ToRGB/mod_bias'] + 1,
+        r'synthesis\.b(\d+)\.skip\.weight',                 lambda r:   tf_params[f'synthesis/{r}x{r}/Skip/weight'][::-1, ::-1].transpose(3, 2, 0, 1),
+        r'.*\.resample_filter',                             None,
+        r'.*\.act_filter',                                  None,
+    )
+    return G
+
+#----------------------------------------------------------------------------
+
+def convert_tf_discriminator(tf_D):
+    if tf_D.version < 4:
+        raise ValueError('TensorFlow pickle version too low')
+
+    # Collect kwargs.
+    tf_kwargs = tf_D.static_kwargs
+    known_kwargs = set()
+    def kwarg(tf_name, default=None):
+        known_kwargs.add(tf_name)
+        return tf_kwargs.get(tf_name, default)
+
+    # Convert kwargs.
+    kwargs = dnnlib.EasyDict(
+        c_dim                   = kwarg('label_size',           0),
+        img_resolution          = kwarg('resolution',           1024),
+        img_channels            = kwarg('num_channels',         3),
+        architecture            = kwarg('architecture',         'resnet'),
+        channel_base            = kwarg('fmap_base',            16384) * 2,
+        channel_max             = kwarg('fmap_max',             512),
+        num_fp16_res            = kwarg('num_fp16_res',         0),
+        conv_clamp              = kwarg('conv_clamp',           None),
+        cmap_dim                = kwarg('mapping_fmaps',        None),
+        block_kwargs = dnnlib.EasyDict(
+            activation          = kwarg('nonlinearity',         'lrelu'),
+            resample_filter     = kwarg('resample_kernel',      [1,3,3,1]),
+            freeze_layers       = kwarg('freeze_layers',        0),
+        ),
+        mapping_kwargs = dnnlib.EasyDict(
+            num_layers          = kwarg('mapping_layers',       0),
+            embed_features      = kwarg('mapping_fmaps',        None),
+            layer_features      = kwarg('mapping_fmaps',        None),
+            activation          = kwarg('nonlinearity',         'lrelu'),
+            lr_multiplier       = kwarg('mapping_lrmul',        0.1),
+        ),
+        epilogue_kwargs = dnnlib.EasyDict(
+            mbstd_group_size    = kwarg('mbstd_group_size',     None),
+            mbstd_num_channels  = kwarg('mbstd_num_features',   1),
+            activation          = kwarg('nonlinearity',         'lrelu'),
+        ),
+    )
+
+    # Check for unknown kwargs.
+    kwarg('structure')
+    kwarg('conditioning')
+    unknown_kwargs = list(set(tf_kwargs.keys()) - known_kwargs)
+    if len(unknown_kwargs) > 0:
+        raise ValueError('Unknown TensorFlow kwarg', unknown_kwargs[0])
+
+    # Collect params.
+    tf_params = _collect_tf_params(tf_D)
+    for name, value in list(tf_params.items()):
+        match = re.fullmatch(r'FromRGB_lod(\d+)/(.*)', name)
+        if match:
+            r = kwargs.img_resolution // (2 ** int(match.group(1)))
+            tf_params[f'{r}x{r}/FromRGB/{match.group(2)}'] = value
+            kwargs.architecture = 'orig'
+    #for name, value in tf_params.items(): print(f'{name:<50s}{list(value.shape)}')
+
+    # Convert params.
+    from training import networks_stylegan2
+    D = networks_stylegan2.Discriminator(**kwargs).eval().requires_grad_(False)
+    # pylint: disable=unnecessary-lambda
+    # pylint: disable=f-string-without-interpolation
+    _populate_module_params(D,
+        r'b(\d+)\.fromrgb\.weight',     lambda r:       tf_params[f'{r}x{r}/FromRGB/weight'].transpose(3, 2, 0, 1),
+        r'b(\d+)\.fromrgb\.bias',       lambda r:       tf_params[f'{r}x{r}/FromRGB/bias'],
+        r'b(\d+)\.conv(\d+)\.weight',   lambda r, i:    tf_params[f'{r}x{r}/Conv{i}{["","_down"][int(i)]}/weight'].transpose(3, 2, 0, 1),
+        r'b(\d+)\.conv(\d+)\.bias',     lambda r, i:    tf_params[f'{r}x{r}/Conv{i}{["","_down"][int(i)]}/bias'],
+        r'b(\d+)\.skip\.weight',        lambda r:       tf_params[f'{r}x{r}/Skip/weight'].transpose(3, 2, 0, 1),
+        r'mapping\.embed\.weight',      lambda:         tf_params[f'LabelEmbed/weight'].transpose(),
+        r'mapping\.embed\.bias',        lambda:         tf_params[f'LabelEmbed/bias'],
+        r'mapping\.fc(\d+)\.weight',    lambda i:       tf_params[f'Mapping{i}/weight'].transpose(),
+        r'mapping\.fc(\d+)\.bias',      lambda i:       tf_params[f'Mapping{i}/bias'],
+        r'b4\.conv\.weight',            lambda:         tf_params[f'4x4/Conv/weight'].transpose(3, 2, 0, 1),
+        r'b4\.conv\.bias',              lambda:         tf_params[f'4x4/Conv/bias'],
+        r'b4\.fc\.weight',              lambda:         tf_params[f'4x4/Dense0/weight'].transpose(),
+        r'b4\.fc\.bias',                lambda:         tf_params[f'4x4/Dense0/bias'],
+        r'b4\.out\.weight',             lambda:         tf_params[f'Output/weight'].transpose(),
+        r'b4\.out\.bias',               lambda:         tf_params[f'Output/bias'],
+        r'.*\.resample_filter',         None,
+    )
+    return D
+
+#----------------------------------------------------------------------------
+
+@click.command()
+@click.option('--source', help='Input pickle', required=True, metavar='PATH')
+@click.option('--dest', help='Output pickle', required=True, metavar='PATH')
+@click.option('--force-fp16', help='Force the networks to use FP16', type=bool, default=False, metavar='BOOL', show_default=True)
+def convert_network_pickle(source, dest, force_fp16):
+    """Convert legacy network pickle into the native PyTorch format.
+
+    The tool is able to load the main network configurations exported using the TensorFlow version of StyleGAN2 or StyleGAN2-ADA.
+    It does not support e.g. StyleGAN2-ADA comparison methods, StyleGAN2 configs A-D, or StyleGAN1 networks.
+
+    Example:
+
+    \b
+    python legacy.py \\
+        --source=https://nvlabs-fi-cdn.nvidia.com/stylegan2/networks/stylegan2-cat-config-f.pkl \\
+        --dest=stylegan2-cat-config-f.pkl
+    """
+    print(f'Loading "{source}"...')
+    with dnnlib.util.open_url(source) as f:
+        data = load_network_pkl(f, force_fp16=force_fp16)
+    print(f'Saving "{dest}"...')
+    with open(dest, 'wb') as f:
+        pickle.dump(data, f)
+    print('Done.')
+
+#----------------------------------------------------------------------------
+
+if __name__ == "__main__":
+    convert_network_pickle() # pylint: disable=no-value-for-parameter
+
+#----------------------------------------------------------------------------

requirements.txt

@@ -0,0 +1,9 @@
+torch
+torchvision
+Ninja
+gradio
+huggingface_hub
+hf_transfer
+pyopengl
+imgui
+glfw

scripts/download_model.bat

@@ -0,0 +1,23 @@
+@echo off
+mkdir checkpoints
+cd checkpoints
+
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('https://storage.googleapis.com/self-distilled-stylegan/lions_512_pytorch.pkl', 'lions_512_pytorch.pkl')"
+ren lions_512_pytorch.pkl stylegan2_lions_512_pytorch.pkl
+
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('https://storage.googleapis.com/self-distilled-stylegan/dogs_1024_pytorch.pkl', 'dogs_1024_pytorch.pkl')"
+ren dogs_1024_pytorch.pkl stylegan2_dogs_1024_pytorch.pkl
+
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('https://storage.googleapis.com/self-distilled-stylegan/horses_256_pytorch.pkl', 'horses_256_pytorch.pkl')"
+ren horses_256_pytorch.pkl stylegan2_horses_256_pytorch.pkl
+
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('https://storage.googleapis.com/self-distilled-stylegan/elephants_512_pytorch.pkl', 'elephants_512_pytorch.pkl')"
+ren elephants_512_pytorch.pkl stylegan2_elephants_512_pytorch.pkl
+
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan2/versions/1/files/stylegan2-ffhq-512x512.pkl', 'stylegan2-ffhq-512x512.pkl')"
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan2/versions/1/files/stylegan2-afhqcat-512x512.pkl', 'stylegan2-afhqcat-512x512.pkl')"
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('http://d36zk2xti64re0.cloudfront.net/stylegan2/networks/stylegan2-car-config-f.pkl', 'stylegan2-car-config-f.pkl')"
+powershell -Command "(New-Object System.Net.WebClient).DownloadFile('http://d36zk2xti64re0.cloudfront.net/stylegan2/networks/stylegan2-cat-config-f.pkl', 'stylegan2-cat-config-f.pkl')"
+
+echo "Done"
+pause

scripts/download_model.sh

@@ -0,0 +1,19 @@
+mkdir checkpoints
+cd checkpoints
+
+wget https://storage.googleapis.com/self-distilled-stylegan/lions_512_pytorch.pkl
+mv lions_512_pytorch.pkl stylegan2_lions_512_pytorch.pkl
+
+wget https://storage.googleapis.com/self-distilled-stylegan/dogs_1024_pytorch.pkl
+mv dogs_1024_pytorch.pkl stylegan2_dogs_1024_pytorch.pkl
+
+wget https://storage.googleapis.com/self-distilled-stylegan/horses_256_pytorch.pkl
+mv horses_256_pytorch.pkl stylegan2_horses_256_pytorch.pkl
+
+wget https://storage.googleapis.com/self-distilled-stylegan/elephants_512_pytorch.pkl
+mv elephants_512_pytorch.pkl stylegan2_elephants_512_pytorch.pkl
+
+wget https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan2/versions/1/files/stylegan2-ffhq-512x512.pkl
+wget https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan2/versions/1/files/stylegan2-afhqcat-512x512.pkl
+wget http://d36zk2xti64re0.cloudfront.net/stylegan2/networks/stylegan2-car-config-f.pkl
+wget http://d36zk2xti64re0.cloudfront.net/stylegan2/networks/stylegan2-cat-config-f.pkl

scripts/gui.bat

@@ -0,0 +1,12 @@
+@echo off
+python visualizer_drag.py ^
+    checkpoints/stylegan2_lions_512_pytorch.pkl ^
+    checkpoints/stylegan2-ffhq-512x512.pkl ^
+    checkpoints/stylegan2-afhqcat-512x512.pkl ^
+    checkpoints/stylegan2-car-config-f.pkl ^
+    checkpoints/stylegan2_dogs_1024_pytorch.pkl ^
+    checkpoints/stylegan2_horses_256_pytorch.pkl ^
+    checkpoints/stylegan2-cat-config-f.pkl ^
+    checkpoints/stylegan2_elephants_512_pytorch.pkl ^
+    checkpoints/stylegan_human_v2_512.pkl ^
+    checkpoints/stylegan2-lhq-256x256.pkl

scripts/gui.sh

@@ -0,0 +1,11 @@
+python visualizer_drag.py \
+    checkpoints/stylegan2_lions_512_pytorch.pkl \
+    checkpoints/stylegan2-ffhq-512x512.pkl \
+    checkpoints/stylegan2-afhqcat-512x512.pkl \
+    checkpoints/stylegan2-car-config-f.pkl \
+    checkpoints/stylegan2_dogs_1024_pytorch.pkl \
+    checkpoints/stylegan2_horses_256_pytorch.pkl \
+    checkpoints/stylegan2-cat-config-f.pkl \
+    checkpoints/stylegan2_elephants_512_pytorch.pkl \
+    checkpoints/stylegan_human_v2_512.pkl \
+    checkpoints/stylegan2-lhq-256x256.pkl

stylegan_human/.gitignore

@@ -0,0 +1,10 @@
+.DS_Store
+__pycache__
+*.pt
+*.pth
+*.pdparams
+*.pdiparams
+*.pdmodel
+*.pkl
+*.info
+*.yaml

stylegan_human/PP_HumanSeg/deploy/infer.py

@@ -0,0 +1,180 @@
+# Copyright (c) SenseTime Research. All rights reserved.
+
+
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# 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.
+
+import codecs
+import os
+import time
+
+import yaml
+import numpy as np
+import cv2
+import paddle
+import paddleseg.transforms as T
+from paddle.inference import create_predictor, PrecisionType
+from paddle.inference import Config as PredictConfig
+from paddleseg.core.infer import reverse_transform
+from paddleseg.cvlibs import manager
+from paddleseg.utils import TimeAverager
+
+from ..scripts.optic_flow_process import optic_flow_process
+
+
+class DeployConfig:
+    def __init__(self, path):
+        with codecs.open(path, 'r', 'utf-8') as file:
+            self.dic = yaml.load(file, Loader=yaml.FullLoader)
+
+        self._transforms = self._load_transforms(self.dic['Deploy'][
+            'transforms'])
+        self._dir = os.path.dirname(path)
+
+    @property
+    def transforms(self):
+        return self._transforms
+
+    @property
+    def model(self):
+        return os.path.join(self._dir, self.dic['Deploy']['model'])
+
+    @property
+    def params(self):
+        return os.path.join(self._dir, self.dic['Deploy']['params'])
+
+    def _load_transforms(self, t_list):
+        com = manager.TRANSFORMS
+        transforms = []
+        for t in t_list:
+            ctype = t.pop('type')
+            transforms.append(com[ctype](**t))
+
+        return transforms
+
+
+class Predictor:
+    def __init__(self, args):
+        self.cfg = DeployConfig(args.cfg)
+        self.args = args
+        self.compose = T.Compose(self.cfg.transforms)
+        resize_h, resize_w = args.input_shape
+
+        self.disflow = cv2.DISOpticalFlow_create(
+            cv2.DISOPTICAL_FLOW_PRESET_ULTRAFAST)
+        self.prev_gray = np.zeros((resize_h, resize_w), np.uint8)
+        self.prev_cfd = np.zeros((resize_h, resize_w), np.float32)
+        self.is_init = True
+
+        pred_cfg = PredictConfig(self.cfg.model, self.cfg.params)
+        pred_cfg.disable_glog_info()
+        if self.args.use_gpu:
+            pred_cfg.enable_use_gpu(100, 0)
+
+        self.predictor = create_predictor(pred_cfg)
+        if self.args.test_speed:
+            self.cost_averager = TimeAverager()
+
+    def preprocess(self, img):
+        ori_shapes = []
+        processed_imgs = []
+        processed_img = self.compose(img)[0]
+        processed_imgs.append(processed_img)
+        ori_shapes.append(img.shape)
+        return processed_imgs, ori_shapes
+
+    def run(self, img, bg):
+        input_names = self.predictor.get_input_names()
+        input_handle = self.predictor.get_input_handle(input_names[0])
+        processed_imgs, ori_shapes = self.preprocess(img)
+        data = np.array(processed_imgs)
+        input_handle.reshape(data.shape)
+        input_handle.copy_from_cpu(data)
+        if self.args.test_speed:
+            start = time.time()
+
+        self.predictor.run()
+
+        if self.args.test_speed:
+            self.cost_averager.record(time.time() - start)
+        output_names = self.predictor.get_output_names()
+        output_handle = self.predictor.get_output_handle(output_names[0])
+        output = output_handle.copy_to_cpu()
+        return self.postprocess(output, img, ori_shapes[0], bg)
+
+
+    def postprocess(self, pred, img, ori_shape, bg):
+        if not os.path.exists(self.args.save_dir):
+            os.makedirs(self.args.save_dir)
+        resize_w = pred.shape[-1]
+        resize_h = pred.shape[-2]
+        if self.args.soft_predict:
+            if self.args.use_optic_flow:
+                score_map = pred[:, 1, :, :].squeeze(0)
+                score_map = 255 * score_map
+                cur_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+                cur_gray = cv2.resize(cur_gray, (resize_w, resize_h))
+                optflow_map = optic_flow_process(cur_gray, score_map, self.prev_gray, self.prev_cfd, \
+                        self.disflow, self.is_init)
+                self.prev_gray = cur_gray.copy()
+                self.prev_cfd = optflow_map.copy()
+                self.is_init = False
+
+                score_map = np.repeat(optflow_map[:, :, np.newaxis], 3, axis=2)
+                score_map = np.transpose(score_map, [2, 0, 1])[np.newaxis, ...]
+                score_map = reverse_transform(
+                    paddle.to_tensor(score_map),
+                    ori_shape,
+                    self.cfg.transforms,
+                    mode='bilinear')
+                alpha = np.transpose(score_map.numpy().squeeze(0),
+                                     [1, 2, 0]) / 255
+            else:
+                score_map = pred[:, 1, :, :]
+                score_map = score_map[np.newaxis, ...]
+                score_map = reverse_transform(
+                    paddle.to_tensor(score_map),
+                    ori_shape,
+                    self.cfg.transforms,
+                    mode='bilinear')
+                alpha = np.transpose(score_map.numpy().squeeze(0), [1, 2, 0])
+
+        else:
+            if pred.ndim == 3:
+                pred = pred[:, np.newaxis, ...]
+            result = reverse_transform(
+                paddle.to_tensor(
+                    pred, dtype='float32'),
+                ori_shape,
+                self.cfg.transforms,
+                mode='bilinear')
+
+            result = np.array(result)
+            if self.args.add_argmax:
+                result = np.argmax(result, axis=1)
+            else:
+                result = result.squeeze(1)
+            alpha = np.transpose(result, [1, 2, 0])
+
+        # background replace
+        h, w, _ = img.shape
+        if bg is None:
+            bg = np.ones_like(img)*255
+        else:
+            bg = cv2.resize(bg, (w, h))
+            if bg.ndim == 2:
+                bg = bg[..., np.newaxis]
+
+        comb = (alpha * img + (1 - alpha) * bg).astype(np.uint8)
+        return comb, alpha, bg, img

stylegan_human/PP_HumanSeg/export_model/download_export_model.py

@@ -0,0 +1,44 @@
+# coding: utf8
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserve.
+#
+# 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.
+
+import sys
+import os
+
+LOCAL_PATH = os.path.dirname(os.path.abspath(__file__))
+TEST_PATH = os.path.join(LOCAL_PATH, "../../../", "test")
+sys.path.append(TEST_PATH)
+
+from paddleseg.utils.download import download_file_and_uncompress
+
+model_urls = {
+    "pphumanseg_lite_portrait_398x224_with_softmax":
+    "https://paddleseg.bj.bcebos.com/dygraph/ppseg/ppseg_lite_portrait_398x224_with_softmax.tar.gz",
+    "deeplabv3p_resnet50_os8_humanseg_512x512_100k_with_softmax":
+    "https://paddleseg.bj.bcebos.com/dygraph/humanseg/export/deeplabv3p_resnet50_os8_humanseg_512x512_100k_with_softmax.zip",
+    "fcn_hrnetw18_small_v1_humanseg_192x192_with_softmax":
+    "https://paddleseg.bj.bcebos.com/dygraph/humanseg/export/fcn_hrnetw18_small_v1_humanseg_192x192_with_softmax.zip",
+    "pphumanseg_lite_generic_humanseg_192x192_with_softmax":
+    "https://paddleseg.bj.bcebos.com/dygraph/humanseg/export/pphumanseg_lite_generic_192x192_with_softmax.zip",
+}
+
+if __name__ == "__main__":
+    for model_name, url in model_urls.items():
+        download_file_and_uncompress(
+            url=url,
+            savepath=LOCAL_PATH,
+            extrapath=LOCAL_PATH,
+            extraname=model_name)
+
+    print("Export model download success!")

stylegan_human/PP_HumanSeg/pretrained_model/download_pretrained_model.py

@@ -0,0 +1,44 @@
+# coding: utf8
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserve.
+#
+# 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.
+
+import sys
+import os
+
+LOCAL_PATH = os.path.dirname(os.path.abspath(__file__))
+TEST_PATH = os.path.join(LOCAL_PATH, "../../../", "test")
+sys.path.append(TEST_PATH)
+
+from paddleseg.utils.download import download_file_and_uncompress
+
+model_urls = {
+    "pphumanseg_lite_portrait_398x224":
+    "https://paddleseg.bj.bcebos.com/dygraph/ppseg/ppseg_lite_portrait_398x224.tar.gz",
+    "deeplabv3p_resnet50_os8_humanseg_512x512_100k":
+    "https://paddleseg.bj.bcebos.com/dygraph/humanseg/train/deeplabv3p_resnet50_os8_humanseg_512x512_100k.zip",
+    "fcn_hrnetw18_small_v1_humanseg_192x192":
+    "https://paddleseg.bj.bcebos.com/dygraph/humanseg/train/fcn_hrnetw18_small_v1_humanseg_192x192.zip",
+    "pphumanseg_lite_generic_human_192x192":
+    "https://paddleseg.bj.bcebos.com/dygraph/humanseg/train/pphumanseg_lite_generic_192x192.zip",
+}
+
+if __name__ == "__main__":
+    for model_name, url in model_urls.items():
+        download_file_and_uncompress(
+            url=url,
+            savepath=LOCAL_PATH,
+            extrapath=LOCAL_PATH,
+            extraname=model_name)
+
+    print("Pretrained model download success!")

stylegan_human/README.md

@@ -0,0 +1,229 @@
+# StyleGAN-Human:  A Data-Centric Odyssey of Human Generation
+<img src="./img/demo_V5_thumbnails-min.png" width="96%" height="96%">
+
+<!--
+**stylegan-human/StyleGAN-Human** is a ✨ _special_ ✨ repository because its `README.md` (this file) appears on your GitHub profile.
+
+-->
+
+> 
+>
+> **Abstract:** *Unconditional human image generation is an important task in vision and graphics, which enables various applications in the creative industry. Existing studies in this field mainly focus on "network engineering" such as designing new components and objective functions. This work takes a data-centric perspective and investigates multiple critical aspects in "data engineering", which we believe would complement the current practice. To facilitate a comprehensive study, we collect and annotate a large-scale human image dataset with over 230K samples capturing diverse poses and textures. Equipped with this large dataset, we rigorously investigate three essential factors in data engineering for StyleGAN-based human generation, namely data size, data distribution, and data alignment. Extensive experiments reveal several valuable observations w.r.t. these aspects: 1) Large-scale data, more than 40K images, are needed to train a high-fidelity unconditional human generation model with vanilla StyleGAN. 2) A balanced training set helps improve the generation quality with rare face poses compared to the long-tailed counterpart, whereas simply balancing the clothing texture distribution does not effectively bring an improvement. 3) Human GAN models with body centers for alignment outperform models trained using face centers or pelvis points as alignment anchors. In addition, a model zoo and human editing applications are demonstrated to facilitate future research in the community.* <br>
+**Keyword:** Human Image Generation, Data-Centric, StyleGAN
+ 
+[Jianglin Fu](mailto:fujianglin@sensetime.com), [Shikai Li](mailto:lishikai@sensetime.com), [Yuming Jiang](https://yumingj.github.io/), [Kwan-Yee Lin](https://kwanyeelin.github.io/), [Chen Qian](https://scholar.google.com/citations?user=AerkT0YAAAAJ&hl=zh-CN), [Chen Change Loy](https://www.mmlab-ntu.com/person/ccloy/), [Wayne Wu](https://wywu.github.io/), and [Ziwei Liu](https://liuziwei7.github.io/) <br>
+**[[Demo Video]](https://youtu.be/nIrb9hwsdcI)** | **[[Project Page]](https://stylegan-human.github.io/)** | **[[Paper]](https://arxiv.org/pdf/2204.11823.pdf)**
+
+## Updates
+- [20/07/2022] [SHHQ-1.0](./docs/Dataset.md) dataset with 40K images is released! :sparkles:
+- [15/06/2022] Data alignment and real-image inversion scripts are released. 
+- [26/04/2022] Technical report released!
+- [22/04/2022] Technical report will be released before May.
+- [21/04/2022] The codebase and project page are created.
+
+## Data Download
+The first version SHHQ-1.0, with 40K images is released. To download and use the dataset set, please read the instructions in [Dataset.md](./docs/Dataset.md)
+
+（We are currently facing large incoming applications, and we need to carefully verify all the applicants, please be patient, and we will reply to you as soon as possible.）
+
+## Model Zoo
+
+| Structure | 1024x512 | Metric | Scores |  512x256 | Metric | Scores | 
+| --------- |:----------:| :----------:| :----------:|  :-----: |  :-----: |  :-----: | 
+| StyleGAN1 |[stylegan_human_v1_1024.pkl](https://drive.google.com/file/d/1h-R-IV-INGdPEzj4P9ml6JTEvihuNgLX/view?usp=sharing)| fid50k | 3.79 | to be released | - | - |
+| StyleGAN2 |[stylegan_human_v2_1024.pkl](https://drive.google.com/file/d/1FlAb1rYa0r_--Zj_ML8e6shmaF28hQb5/view?usp=sharing)| fid50k_full | 1.57 |[stylegan_human_v2_512.pkl](https://drive.google.com/file/d/1dlFEHbu-WzQWJl7nBBZYcTyo000H9hVm/view?usp=sharing) | fid50k_full | 1.97 |
+| StyleGAN3 |to be released | - | - |  [stylegan_human_v3_512.pkl](https://drive.google.com/file/d/1_274jk_N6WSCkKWeu7hjHycqGvbuOFf5/view?usp=sharing) | fid50k_full | 2.54 |
+
+
+
+## Web Demo 
+
+Integrated into [Huggingface Spaces 🤗](https://huggingface.co/spaces) using [Gradio](https://github.com/gradio-app/gradio). Try out the Web Demo for generation: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/hysts/StyleGAN-Human) and interpolation [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/hysts/StyleGAN-Human-Interpolation)
+
+
+
+<a href="https://colab.research.google.com/drive/1sgxoDM55iM07FS54vz9ALg1XckiYA2On"><img src="https://colab.research.google.com/assets/colab-badge.svg" height=22.5></a> 
+
+We prepare a Colab demo to allow you to synthesize images with the provided models, as well as visualize the performance of style-mixing, interpolation, and attributes editing.
+The notebook will guide you to install the necessary environment and download pretrained models. The output images can be found in `./StyleGAN-Human/outputs/`.
+Hope you enjoy!
+
+## Usage
+
+### System requirements
+* The original code bases are [stylegan (tensorflow)](https://github.com/NVlabs/stylegan), [stylegan2-ada (pytorch)](https://github.com/NVlabs/stylegan2-ada-pytorch), [stylegan3 (pytorch)](https://github.com/NVlabs/stylegan3), released by NVidia
+
+* We tested in Python 3.8.5 and PyTorch 1.9.1 with CUDA 11.1. (See https://pytorch.org for PyTorch install instructions.)
+
+### Installation
+To work with this project on your own machine, you need to install the environmnet as follows: 
+
+```
+conda env create -f environment.yml
+conda activate stylehuman
+# [Optional: tensorflow 1.x is required for StyleGAN1. ]
+pip install nvidia-pyindex
+pip install nvidia-tensorflow[horovod]
+pip install nvidia-tensorboard==1.15
+```
+Extra notes:
+1. In case having some conflicts when calling CUDA version, please try to empty the LD_LIBRARY_PATH. For example:
+```
+LD_LIBRARY_PATH=; python generate.py --outdir=out/stylegan_human_v2_1024 --trunc=1 --seeds=1,3,5,7 
+--network=pretrained_models/stylegan_human_v2_1024.pkl --version 2
+```
+
+
+2. We found the following troubleshooting links might be helpful: [1.](https://github.com/NVlabs/stylegan3), [2.](https://github.com/NVlabs/stylegan3/blob/main/docs/troubleshooting.md)
+
+### Train
+The training scripts are based on the original [stylegan1](https://github.com/NVlabs/stylegan), [stylegan2-ada](https://github.com/NVlabs/stylegan2-ada-pytorch), and [stylegan3](https://github.com/NVlabs/stylegan3) with minor changes. Here we only provide the scripts with modifications for SG2 and SG3. You can replace the old files with the provided scripts to train. (assume SHHQ-1.0 is placed under data/)
+
+#### Train Stylegan2-ada-pytorch with SHHQ-1.0
+```
+python train.py --outdir=training_results/sg2/ --data=data/SHHQ-1.0/ \
+    --gpus=8 --aug=noaug --mirror=1 --snap=250 --cfg=shhq --square=False
+```
+#### Train Stylegan3 with SHHQ-1.0 
+```
+python train.py --outdir=training_results/sg3/ --cfg=stylegan3-r --gpus=8 --batch=32 --gamma=12.4 \
+    --mirror=1 --aug=noaug --data=data/SHHQ-1.0/ --square=False --snap=250
+```
+
+### Pretrained models
+Please put the downloaded pretrained models [from above link](#Model-Zoo) under the folder 'pretrained_models'.
+
+
+### Generate full-body human images using our pretrained model
+```
+# Generate human full-body images without truncation
+python generate.py --outdir=outputs/generate/stylegan_human_v2_1024 --trunc=1 --seeds=1,3,5,7 --network=pretrained_models/stylegan_human_v2_1024.pkl --version 2
+
+# Generate human full-body images with truncation 
+python generate.py --outdir=outputs/generate/stylegan_human_v2_1024 --trunc=0.8 --seeds=0-10 --network=pretrained_models/stylegan_human_v2_1024.pkl --version 2
+
+# Generate human full-body images using stylegan V1
+python generate.py --outdir=outputs/generate/stylegan_human_v1_1024 --network=pretrained_models/stylegan_human_v1_1024.pkl --version 1 --seeds=1,3,5
+
+# Generate human full-body images using stylegan V3
+python generate.py --outdir=outputs/generate/stylegan_human_v3_512 --network=pretrained_models/stylegan_human_v3_512.pkl --version 3 --seeds=1,3,5
+```
+
+
+#### Note: The following demos are generated based on models related to StyleGAN V2 (stylegan_human_v2_512.pkl and stylegan_human_v2_1024.pkl). If you want to see results for V1 or V3, you need to change the loading method of the corresponding models.
+
+
+### Interpolation
+```
+python interpolation.py --network=pretrained_models/stylegan_human_v2_1024.pkl  --seeds=85,100 --outdir=outputs/inter_gifs
+```
+
+### Style-mixing **image** using stylegan2
+```
+python style_mixing.py --network=pretrained_models/stylegan_human_v2_1024.pkl --rows=85,100,75,458,1500 \\
+    --cols=55,821,1789,293 --styles=0-3 --outdir=outputs/stylemixing 
+```
+
+### Style-mixing **video** using stylegan2
+```
+python stylemixing_video.py --network=pretrained_models/stylegan_human_v2_1024.pkl --row-seed=3859 \\
+    --col-seeds=3098,31759,3791 --col-styles=8-12 --trunc=0.8 --outdir=outputs/stylemixing_video
+```
+
+### Aligned raw images
+For alignment, we use [openpose-pytorch](https://github.com/Hzzone/pytorch-openpose) for body-keypoints detection and [PaddlePaddle](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.5/contrib/PP-HumanSeg) for human segmentation.
+Before running the alignment script, few models need to be installed:
+1. download [body_pose_model.pth](https://drive.google.com/drive/folders/1JsvI4M4ZTg98fmnCZLFM-3TeovnCRElG?usp=sharing) and place it into openpose/model/.
+2. download and extract [deeplabv3p_resnet50_os8_humanseg_512x512_100k_with_softmax](https://paddleseg.bj.bcebos.com/dygraph/humanseg/export/deeplabv3p_resnet50_os8_humanseg_512x512_100k_with_softmax.zip) into PP_HumanSeg/export_model/deeplabv3p_resnet50_os8_humanseg_512x512_100k_with_softmax.
+3. download and extract [deeplabv3p_resnet50_os8_humanseg_512x512_100k](https://paddleseg.bj.bcebos.com/dygraph/humanseg/train/deeplabv3p_resnet50_os8_humanseg_512x512_100k.zip) into PP_HumanSeg/pretrained_model/deeplabv3p_resnet50_os8_humanseg_512x512_100k.
+4. install paddlepaddel: ``` pip install paddleseg ```
+
+Then you can start alignment: 
+```
+python alignment.py --image-folder img/test/ --output-folder aligned_image/
+```
+
+### Invert real image with [PTI](https://github.com/danielroich/PTI)
+Before inversion, please download our PTI weights: [e4e_w+.pt](https://drive.google.com/file/d/1NUfSJqLhsrU7c9PwAtlZ9xtrxhzS_6tu/view?usp=sharing) into /pti/.
+
+Few parameters you can change:
+- /pti/pti_configs/hyperparameters.py:
+    - first_inv_type = 'w+' -> Use pretrained e4e encoder
+    - first_inv_type = 'w'  -> Use projection and optimization
+- /pti/pti_configs/paths_config.py:
+    - input_data_path: path of real images
+    - e4e: path of e4e_w+.pt
+    - stylegan2_ada_shhq: pretrained stylegan2-ada model for SHHQ
+
+```
+python run_pti.py
+```
+Note: we used the test image under 'aligned_image/' (the output of alignment.py), the inverted latent code and fine-tuned generator will be saved in 'outputs/pti/'
+
+
+### Editing with InterfaceGAN, StyleSpace, and Sefa
+```
+python edit.py --network pretrained_models/stylegan_human_v2_1024.pkl --attr_name upper_length \\
+    --seeds 61531,61570,61571,61610 --outdir outputs/edit_results
+``` 
+
+### Editing using inverted latent code
+```
+python edit.py ---network outputs/pti/checkpoints/model_test.pkl --attr_name upper_length \\
+    --outdir outputs/edit_results --real True --real_w_path outputs/pti/embeddings/test/PTI/test/0.pt --real_img_path aligned_image/test.png
+```
+
+Note: 
+1. ''upper_length'' and ''bottom_length'' of ''attr_name'' are available for demo.
+2. Layers to control and editing strength are set in edit/edit_config.py.
+
+
+### Demo for [InsetGAN](https://arxiv.org/abs/2203.07293)
+
+We implement a quick demo using the key idea from InsetGAN: combining the face generated by FFHQ with the human-body generated by our pretrained model, optimizing both face and body latent codes to get a coherent full-body image.
+Before running the script, you need to download the [FFHQ face model]( https://docs.google.com/uc?export=download&confirm=t&id=125OG7SMkXI-Kf2aqiwLLHyCvSW-gZk3M), or you can use your own face model, as well as [pretrained face landmark](https://docs.google.com/uc?export=download&confirm=&id=1A82DnJBJzt8wI2J8ZrCK5fgHcQ2-tcWM) and [pretrained CNN face detection model for dlib](https://docs.google.com/uc?export=download&confirm=&id=1MduBgju5KFNrQfDLoQXJ_1_h5MnctCIG)
+```
+python insetgan.py --body_network=pretrained_models/stylegan_human_v2_1024.pkl --face_network=pretrained_models/ffhq.pkl \\
+    --body_seed=82 --face_seed=43  --trunc=0.6 --outdir=outputs/insetgan/ --video 1 
+```
+
+## Results
+
+### Editing with inverted real image
+(from left to right: real image | inverted image | InterFaceGAN result | StyleSpace result | SeFa result)
+
+https://user-images.githubusercontent.com/98547009/173773800-bb7fe54a-84d3-4b30-9864-a6b7b311f8ff.mp4
+
+
+### For more demo, please visit our [**web page**](https://stylegan-human.github.io/) .
+  
+
+## TODO List
+
+- [ ] Release 1024x512 version of StyleGAN-Human based on StyleGAN3 
+- [ ] Release 512x256 version of StyleGAN-Human based on StyleGAN1 
+- [ ] Extension of downstream application (InsetGAN): Add face inversion interface to support fusing user face image and stylegen-human body image
+- [x] Add Inversion Script into the provided editing pipeline
+- [ ] Release Dataset
+
+
+## Related Works
+* (SIGGRAPH 2022) **Text2Human: Text-Driven Controllable Human Image Generation**, Yuming Jiang et al. [[Paper](https://arxiv.org/pdf/2205.15996.pdf)], [[Code](https://github.com/yumingj/Text2Human)], [[Project Page](https://yumingj.github.io/projects/Text2Human.html)], [[Dataset](https://github.com/yumingj/DeepFashion-MultiModal)]
+* (ICCV 2021) **Talk-to-Edit: Fine-Grained Facial Editing via Dialog**, Yuming Jiang et al. [[Paper](https://arxiv.org/abs/2109.04425)], [[Code](https://github.com/yumingj/Talk-to-Edit)], [[Project Page](https://www.mmlab-ntu.com/project/talkedit/)], [[Dataset](https://mmlab.ie.cuhk.edu.hk/projects/CelebA/CelebA_Dialog.html)]
+* (Technical Report 2022) **Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis**, Wei Cheng et al. [[Paper](https://arxiv.org/pdf/2204.11798.pdf)], [[Code](https://github.com/generalizable-neural-performer/gnr)], [[Project Page](https://generalizable-neural-performer.github.io/)], [[Dataset](https://generalizable-neural-performer.github.io/genebody.html)]
+
+## Citation
+
+If you find this work useful for your research, please consider citing our paper:
+
+```bibtex
+@article{fu2022styleganhuman,
+      title={StyleGAN-Human: A Data-Centric Odyssey of Human Generation}, 
+      author={Fu, Jianglin and Li, Shikai and Jiang, Yuming and Lin, Kwan-Yee and Qian, Chen and Loy, Chen-Change and Wu, Wayne and Liu, Ziwei},
+      journal   = {arXiv preprint},
+      volume    = {arXiv:2204.11823},
+      year    = {2022}
+```
+
+## Acknowlegement
+Part of the code is borrowed from [stylegan (tensorflow)](https://github.com/NVlabs/stylegan), [stylegan2-ada (pytorch)](https://github.com/NVlabs/stylegan2-ada-pytorch), [stylegan3 (pytorch)](https://github.com/NVlabs/stylegan3).

stylegan_human/alignment.py

@@ -0,0 +1,223 @@
+# Copyright (c) SenseTime Research. All rights reserved.
+
+
+import os
+import argparse 
+import numpy as np
+import torch
+from torch.utils.data import DataLoader
+from torchvision.transforms import transforms
+from utils.ImagesDataset import ImagesDataset
+
+import cv2
+import time
+import copy
+import imutils
+
+# for openpose body keypoint detector : # (src:https://github.com/Hzzone/pytorch-openpose)
+from openpose.src import util
+from openpose.src.body import Body
+
+# for paddlepaddle human segmentation : #(src: https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.5/contrib/PP-HumanSeg/)
+from PP_HumanSeg.deploy.infer import Predictor as PP_HumenSeg_Predictor
+
+import math
+def angle_between_points(p0,p1,p2):
+    if p0[1]==-1 or p1[1]==-1 or p2[1]==-1:
+        return -1
+    a = (p1[0]-p0[0])**2 + (p1[1]-p0[1])**2
+    b = (p1[0]-p2[0])**2 + (p1[1]-p2[1])**2
+    c = (p2[0]-p0[0])**2 + (p2[1]-p0[1])**2 
+    if a * b == 0:
+        return -1
+    return math.acos((a+b-c) / math.sqrt(4*a*b)) * 180 / math.pi
+
+
+def crop_img_with_padding(img, keypoints, rect):
+    person_xmin,person_xmax, ymin, ymax= rect
+    img_h,img_w,_ = img.shape    ## find body center using keypoints
+    middle_shoulder_x = keypoints[1][0]
+    middle_hip_x = (keypoints[8][0] + keypoints[11][0]) // 2
+    mid_x = (middle_hip_x + middle_shoulder_x) // 2    
+    mid_y = (ymin + ymax) // 2
+    ## find which side (l or r) is further than center x, use the further side
+    if abs(mid_x-person_xmin) > abs(person_xmax-mid_x): #left further
+        xmin = person_xmin
+        xmax = mid_x + (mid_x-person_xmin)
+    else:
+        ############### may be negtive
+        ### in this case, the script won't output any image, leave the case like this
+        ### since we don't want to pad human body
+        xmin = mid_x - (person_xmax-mid_x)   
+        xmax = person_xmax 
+
+    w = xmax - xmin
+    h = ymax - ymin
+    ## pad rectangle to w:h = 1:2 ## calculate desired border length
+    if h / w >= 2: #pad horizontally
+        target_w = h // 2
+        xmin_prime = int(mid_x - target_w / 2)
+        xmax_prime = int(mid_x + target_w / 2)
+        if xmin_prime < 0:
+            pad_left = abs(xmin_prime)# - xmin
+            xmin = 0
+        else:
+            pad_left = 0
+            xmin = xmin_prime
+        if xmax_prime > img_w:
+            pad_right = xmax_prime - img_w
+            xmax = img_w
+        else:
+            pad_right = 0
+            xmax = xmax_prime
+
+        cropped_img = img[int(ymin):int(ymax), int(xmin):int(xmax)]
+        im_pad = cv2.copyMakeBorder(cropped_img, 0, 0, int(pad_left),  int(pad_right), cv2.BORDER_REPLICATE) 
+    else: #pad vertically
+        target_h = w * 2
+        ymin_prime = mid_y - (target_h / 2)
+        ymax_prime = mid_y + (target_h / 2) 
+        if ymin_prime < 0: 
+            pad_up = abs(ymin_prime)# - ymin
+            ymin = 0
+        else:
+            pad_up = 0
+            ymin = ymin_prime
+        if ymax_prime > img_h:
+            pad_down = ymax_prime - img_h
+            ymax = img_h
+        else:
+            pad_down = 0
+            ymax = ymax_prime
+        print(ymin,ymax, xmin,xmax, img.shape)
+
+        cropped_img = img[int(ymin):int(ymax), int(xmin):int(xmax)]
+        im_pad = cv2.copyMakeBorder(cropped_img, int(pad_up), int(pad_down), 0,
+                                    0, cv2.BORDER_REPLICATE) 
+    result = cv2.resize(im_pad,(512,1024),interpolation = cv2.INTER_AREA)
+    return result
+
+
+def run(args):
+    os.makedirs(args.output_folder, exist_ok=True)
+    dataset = ImagesDataset(args.image_folder, transforms.Compose([transforms.ToTensor()]))
+    dataloader = DataLoader(dataset, batch_size=1, shuffle=False)
+
+    body_estimation = Body('openpose/model/body_pose_model.pth')
+
+    total = len(dataloader)
+    print('Num of dataloader : ', total)
+    os.makedirs(f'{args.output_folder}', exist_ok=True)
+    # os.makedirs(f'{args.output_folder}/middle_result', exist_ok=True)
+    
+    ## initialzide HumenSeg
+    human_seg_args = {}
+    human_seg_args['cfg'] = 'PP_HumanSeg/export_model/deeplabv3p_resnet50_os8_humanseg_512x512_100k_with_softmax/deploy.yaml'
+    human_seg_args['input_shape'] = [1024,512]
+    human_seg_args['save_dir'] = args.output_folder
+    human_seg_args['soft_predict'] = False
+    human_seg_args['use_gpu'] = True
+    human_seg_args['test_speed'] = False
+    human_seg_args['use_optic_flow'] = False
+    human_seg_args['add_argmax'] = True
+    human_seg_args= argparse.Namespace(**human_seg_args)
+    human_seg = PP_HumenSeg_Predictor(human_seg_args)
+
+    from tqdm import tqdm
+    for fname, image in tqdm(dataloader):
+        # try:
+        ## tensor to numpy image
+        fname = fname[0]
+        print(f'Processing \'{fname}\'.')
+        
+        image = (image.permute(0, 2, 3, 1) * 255).clamp(0, 255)
+        image = image.squeeze(0).numpy() # --> tensor to numpy, (H,W,C)
+        # avoid super high res img
+        if image.shape[0] >= 2000: # height  ### for shein image
+            ratio = image.shape[0]/1200 #height
+            dim = (int(image.shape[1]/ratio),1200)#(width, height)
+            image = cv2.resize(image, dim, interpolation = cv2.INTER_AREA)
+        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+
+        ## create segmentation
+        # mybg = cv2.imread('mybg.png') 
+        comb, segmentation, bg, ori_img = human_seg.run(image,None)  #mybg) 
+        # cv2.imwrite('comb.png',comb)  # [0,255]
+        # cv2.imwrite('alpha.png',segmentation*255) # segmentation [0,1] --> [0.255]
+        # cv2.imwrite('bg.png',bg)  #[0,255]
+        # cv2.imwrite('ori_img.png',ori_img) # [0,255]
+
+        masks_np = (segmentation* 255)# .byte().cpu().numpy() #1024,512,1
+        mask0_np = masks_np[:,:,0].astype(np.uint8)#[0, :, :]
+        contours = cv2.findContours(mask0_np,  cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+        cnts = imutils.grab_contours(contours)
+        c = max(cnts, key=cv2.contourArea)
+        extTop = tuple(c[c[:, :, 1].argmin()][0])
+        extBot = tuple(c[c[:, :, 1].argmax()][0])
+        extBot = list(extBot)
+        extTop = list(extTop)
+        pad_range = int((extBot[1]-extTop[1])*0.05)
+        if (int(extTop[1])<=5 and int(extTop[1])>0) and (comb.shape[0]>int(extBot[1]) and int(extBot[1])>=comb.shape[0]-5): #seg mask already reaches to the edge
+            #pad with pure white, top 100 px, bottom 100 px
+            comb= cv2.copyMakeBorder(comb,pad_range+5,pad_range+5,0,0,cv2.BORDER_CONSTANT,value=[255,255,255]) 
+        elif int(extTop[1])<=0 or int(extBot[1])>=comb.shape[0]:
+            print('PAD: body out of boundary', fname) #should not happened
+            return {}
+        else:
+            comb = cv2.copyMakeBorder(comb, pad_range+5, pad_range+5, 0, 0, cv2.BORDER_REPLICATE) #105 instead of 100: give some extra space
+        extBot[1] = extBot[1] + pad_range+5
+        extTop[1] = extTop[1] + pad_range+5
+
+        extLeft = tuple(c[c[:, :, 0].argmin()][0])
+        extRight = tuple(c[c[:, :, 0].argmax()][0])
+        extLeft = list(extLeft)
+        extRight = list(extRight)
+        person_ymin = int(extTop[1])-pad_range # 100
+        person_ymax = int(extBot[1])+pad_range # 100 #height
+        if person_ymin<0 or person_ymax>comb.shape[0]: # out of range
+            return {}
+        person_xmin = int(extLeft[0])
+        person_xmax = int(extRight[0])
+        rect =  [person_xmin,person_xmax,person_ymin, person_ymax]
+        # recimg = copy.deepcopy(comb)
+        # cv2.rectangle(recimg,(person_xmin,person_ymin),(person_xmax,person_ymax),(0,255,0),2)
+        # cv2.imwrite(f'{args.output_folder}/middle_result/{fname}_rec.png',recimg)
+
+        ## detect keypoints
+        keypoints, subset = body_estimation(comb)
+        # print(keypoints, subset, len(subset))
+        if len(subset) != 1 or (len(subset)==1 and subset[0][-1]<15): 
+            print(f'Processing \'{fname}\'. Please import image contains one person only. Also can check segmentation mask. ')
+            continue
+
+        # canvas = copy.deepcopy(comb)
+        # canvas = util.draw_bodypose(canvas, keypoints, subset, show_number=True)
+        # cv2.imwrite(f'{args.output_folder}/middle_result/{fname}_keypoints.png',canvas)
+
+        comb = crop_img_with_padding(comb, keypoints, rect)
+
+        
+        cv2.imwrite(f'{args.output_folder}/{fname}.png', comb)
+        print(f' -- Finished processing \'{fname}\'. --')
+        # except:
+        #     print(f'Processing \'{fname}\'. Not satisfied the alignment strategy.')
+        
+        
+if __name__ == '__main__':
+    torch.backends.cudnn.benchmark = True
+    torch.backends.cudnn.deterministic = False
+    
+    t1 = time.time()
+    arg_formatter = argparse.ArgumentDefaultsHelpFormatter
+    description = 'StyleGAN-Human data process'
+    parser = argparse.ArgumentParser(formatter_class=arg_formatter,
+                                     description=description)
+    parser.add_argument('--image-folder', type=str, dest='image_folder')
+    parser.add_argument('--output-folder', dest='output_folder', default='results', type=str)
+    # parser.add_argument('--cfg', dest='cfg for segmentation', default='PP_HumanSeg/export_model/ppseg_lite_portrait_398x224_with_softmax/deploy.yaml', type=str)
+
+    print('parsing arguments')
+    cmd_args = parser.parse_args()
+    run(cmd_args)
+
+    print('total time elapsed: ', str(time.time() - t1))