update

Dockerfile

+FROM nvcr.io/nvidia/pytorch:23.05-py3
+
+ENV PYTHONDONTWRITEBYTECODE 1
+ENV PYTHONUNBUFFERED 1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        make \
+        pkgconf \
+        xz-utils \
+        xorg-dev \
+        libgl1-mesa-dev \
+        libglu1-mesa-dev \
+        libxrandr-dev \
+        libxinerama-dev \
+        libxcursor-dev \
+        libxi-dev \
+        libxxf86vm-dev \
+        && rm -rf /var/lib/apt/lists/*
+
+RUN pip install --no-cache-dir --upgrade pip
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+WORKDIR /workspace
+
+RUN (printf '#!/bin/bash\nexec \"$@\"\n' >> /entry.sh) && chmod a+x /entry.sh
+ENTRYPOINT ["/entry.sh"]

LICENSE.txt

+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

+# DragGAN 
+DragGAN 模型，是一种革命性交互式图像操作方式，允许用户将图像中的任意点“拖动”到目标位置，以精确控制姿势、形状、表情和布局。
+
+## 论文
+`Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold`
+- https://arxiv.org/abs/2305.10973
+- SIGGRAPH 2023
+
+## 模型结构
+<!-- 此处一句话简要介绍模型结构 -->
+DragGAN是一种用于 GAN 的交互式图像处理方法。主要是基于 StyleGAN 模型架构：
+
+<div align=center>
+    <img src="./doc/StyleGan.png"/>
+    <div >StyleGan</div>
+</div>
+
+
+## 算法原理
+对于给定的图像，只需要设置几个处理点（红点）、目标点（蓝点），以及可选的表示编辑过程中可移动区域（较亮区域）的掩码。我们的方法迭代地执行运动监督和点跟踪。运动监控步骤驱动手柄点（红点）朝向目标点（蓝点）移动，点跟踪步骤更新手柄点以跟踪图像中的对象。此过程将继续，直到控制点达到其相应的目标点。
+
+<div align=center>
+    <img src="./doc/pipeline.png"/>
+    <div >DragGAN</div>
+</div>
+
+
+## 环境配置
+```
+mv draggan_pytoch draggan # 去框架名后缀
+# docker的-v 路径、docker_name和imageID根据实际情况修改
+```
+### Docker（方法一）
+<!-- 此处提供[光源](https://www.sourcefind.cn/#/service-details)拉取docker镜像的地址与使用步骤 -->
+```
+docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.2-py3.10 # 本镜像imageID为：2f1f619d0182
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=16G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --network=host --name docker_name imageID bash
+cd /your_code_path/draggan
+pip install -r requirements.txt
+```
+### Dockerfile（方法二）
+<!-- 此处提供dockerfile的使用方法 -->
+```
+cd /your_code_path/draggan/docker
+docker build --no-cache -t codestral:latest .
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=16G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --network=host --name docker_name imageID bash
+cd /your_code_path/draggan
+pip install -r requirements.txt
+```
+### Anaconda（方法三）
+<!-- 此处提供本地配置、编译的详细步骤，例如： -->
+
+关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
+```
+DTK驱动: dtk24.04.2
+python: python3.10
+pytorch: 2.1.0
+```
+`Tips：以上DTK驱动、python、pytorch等DCU相关工具版本需要严格一一对应`
+
+其它非深度学习库参照requirements.txt安装：
+```
+pip install -r requirements.txt
+```
+## 数据集
+无
+
+## 训练
+无
+
+## 推理
+下载模型权重:
+```
+python scripts/download_model.py
+```
+或者从 [SCNet](http://113.200.138.88:18080/aimodels/findsource-dependency/stylegan2_pytorch) 上快速下载，并放在 /checkpoints 文件夹下。
+
+可视化webui推理：
+```
+python visualizer_drag_gradio.py --listen
+```
+
+
+## result
+<!-- 此处填算法效果测试图（包括输入、输出） -->
+
+
+<div align=center>
+    <img src="./doc/gradio.png" width=600/>
+    <div >webui界面</div>
+</div>
+
+<div align=center>
+    <img src="./doc/image.png" width=600/>
+    <div >输入</div>
+</div>
+
+<div align=center>
+    <img src="./doc/image (1).png" width=600/>
+    <div >输出</div>
+</div>
+
+
+### 精度
+无
+
+
+
+## 应用场景
+### 算法类别
+
+<!-- 超出以上分类的类别命名也可参考此网址中的类别名：https://huggingface.co/ \ -->
+`AIGC`
+
+### 热点应用行业
+<!-- 应用行业的填写需要做大量调研，从而为使用者提供专业、全面的推荐，除特殊算法，通常推荐数量>=3。 -->
+`零售,制造,电商,医疗,教育`
+
+<!-- ## 预训练权重 -->
+<!-- - 此处填写预训练权重在公司内部的下载地址（预训练权重存放中心为：[SCNet AIModels](http://113.200.138.88:18080/aimodels) ，模型用到的各预训练权重请分别填上具体地址。），过小权重文件可打包到项目里。
+- 此处填写公开预训练权重官网下载地址（非必须）。 -->
+
+## 源码仓库及问题反馈
+<!-- - 此处填本项目gitlab地址 -->
+- https://developer.sourcefind.cn/codes/modelzoo/draggan_pytorch
+## 参考资料
+- https://github.com/XingangPan/DragGAN
+

README_origin.md

+<p align="center">
+
+  <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).  
+
+The usual installation steps involve the following commands, they should set up the correct CUDA version and all the python packages
+
+```
+conda env create -f environment.yml
+conda activate stylegan3
+```
+
+Then install the additional requirements
+
+```
+pip install -r requirements.txt
+```
+
+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
+```
+
+## Run Gradio visualizer in Docker 
+
+Provided docker image is based on NGC PyTorch repository. To quickly try out visualizer in Docker, run the following:  
+
+```sh
+# before you build the docker container, make sure you have cloned this repo, and downloaded the pretrained model by `python scripts/download_model.py`.
+docker build . -t draggan:latest  
+docker run -p 7860:7860 -v "$PWD":/workspace/src -it draggan:latest bash
+# (Use GPU)if you want to utilize your Nvidia gpu to accelerate in docker, please add command tag `--gpus all`, like:
+#   docker run --gpus all  -p 7860:7860 -v "$PWD":/workspace/src -it draggan:latest bash
+
+cd src && python visualizer_drag_gradio.py --listen
+```
+Now you can open a shared link from Gradio (printed in the terminal console).   
+Beware the Docker image takes about 25GB of disk space!
+
+## Download pre-trained StyleGAN2 weights
+
+To download pre-trained weights, simply run:
+
+```
+python scripts/download_model.py
+```
+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
+```
+If you are using windows, you can run:
+```
+.\scripts\gui.bat
+```
+
+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, this is universal for both windows and linux:
+```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).
+
+(cheers to the community as well)
+## 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}
+}
+```

dnnlib/__init__.py

+# 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

+# 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)

docker/Dockerfile

+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.2-py3.10
+ENV DEBIAN_FRONTEND=noninteractive
+# COPY requirements.txt requirements.txt
+# RUN pip3 install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com

environment.yml

+name: stylegan3
+channels:
+  - pytorch
+  - nvidia
+dependencies:
+  - python >= 3.8
+  - pip
+  - numpy>=1.25
+  - click>=8.0
+  - pillow=9.4.0
+  - scipy=1.11.1
+  - 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

+# 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

+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'
+]