rameenabdal / styleflow Goto Github PK

StyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)

Home Page: http://rameenabdal.github.io/StyleFlow

Python 91.71% Cuda 8.03% Dockerfile 0.26%

stylegan sequential-edits quality faces

styleflow's Introduction

StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)

See you @ Siggraph 2021

Figure: Sequential edits using StyleFlow

High-quality, diverse, and photorealistic images can now be generated by unconditional GANs (e.g., StyleGAN). However, limited options exist to control the generation process using (semantic) attributes, while still preserving the quality of the output. Further, due to the entangled nature of the GAN latent space, performing edits along one attribute can easily result in unwanted changes along other attributes. In this paper, in the context of conditional exploration of entangled latent spaces, we investigate the two sub-problems of attribute-conditioned sampling and attribute-controlled editing. We present StyleFlow as a simple, effective, and robust solution to both the sub-problems by formulating conditional exploration as an instance of conditional continuous normalizing flows in the GAN latent space conditioned by attribute features. We evaluate our method using the face and the car latent space of StyleGAN, and demonstrate fine-grained disentangled edits along various attributes on both real photographs and StyleGAN generated images. For example, for faces, we vary camera pose, illumination variation, expression, facial hair, gender, and age. Finally, via extensive qualitative and quantitative comparisons, we demonstrate the superiority of StyleFlow to other concurrent works.

StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)
Rameen Abdal, Peihao Zhu, Niloy Mitra, Peter Wonka
KAUST, Adobe Research

[Paper] [Project Page] [Demo] [Promotional Video]

Installation

Clone this repo.

git clone https://github.com/RameenAbdal/StyleFlow.git
cd StyleFlow/

This code requires PyTorch, TensorFlow, Torchdiffeq, Python 3+ and Pyqt5. Please install dependencies by

conda env create -f environment.yml

StyleGAN2 relies on custom TensorFlow ops that are compiled on the fly using NVCC. To correctly setup the StyleGAN2 generator follow the Requirements in this repo.

Installation (Docker)

Clone this repo.

git clone https://github.com/RameenAbdal/StyleFlow.git
cd StyleFlow/

You must have CUDA (>=10.0 && <11.0) and nvidia-docker2 installed first !

Then, run :

xhost +local:docker # Letting Docker access X server
wget -P stylegan/ http://d36zk2xti64re0.cloudfront.net/stylegan2/networks/stylegan2-ffhq-config-f.pkl
docker-compose up --build # Expect some time before UI appears

When finished, run :

xhost -local:docker

UI Illustration

Loading images may take 2 - 3 seconds on the first click. Move the slider smoothly to render results.

Editing Images Using Pretrained Models

Run the main UI
```
python main.py
```
Run the Attribute Transfer UI
```
python main_attribute.py 
```

Web UI (Beta)

A web based UI is also now available. Follow webui dev branch for setup.

Training New Model

Dataset containing sampled StyleGAN2 latents, lighting SH parameters and other attributes. (Download Here)

Create ./data_numpy/ in the main folder and extract the above data or create your own dataset.

Train your model:

   python train_flow.py

Projection

Our new projection method is currently under review. To be updated! Follow the repo for updates : https://github.com/ZPdesu/II2S

License

Citation

If you use this research/codebase/dataset, please cite our papers.

@article{10.1145/3447648,
author = {Abdal, Rameen and Zhu, Peihao and Mitra, Niloy J. and Wonka, Peter},
title = {StyleFlow: Attribute-Conditioned Exploration of StyleGAN-Generated Images Using Conditional Continuous Normalizing Flows},
year = {2021},
issue_date = {May 2021},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {40},
number = {3},
issn = {0730-0301},
url = {https://doi.org/10.1145/3447648},
doi = {10.1145/3447648},
abstract = {High-quality, diverse, and photorealistic images can now be generated by unconditional GANs (e.g., StyleGAN). However, limited options exist to control the generation process using (semantic) attributes while stillpreserving the quality of the output. Further, due to the entangled nature of the GAN latent space, performing edits along one attribute can easily result in unwanted changes along other attributes. In this article, in the context of conditional exploration of entangled latent spaces, we investigate the two sub-problems of attribute-conditioned sampling and attribute-controlled editing. We present StyleFlow as a simple, effective, and robust solution to both the sub-problems by formulating conditional exploration as an instance of conditional continuous normalizing flows in the GAN latent space conditioned by attribute features. We evaluate our method using the face and the car latent space of StyleGAN, and demonstrate fine-grained disentangled edits along various attributes on both real photographs and StyleGAN generated images. For example, for faces, we vary camera pose, illumination variation, expression, facial hair, gender, and age. Finally, via extensive qualitative and quantitative comparisons, we demonstrate the superiority of StyleFlow over prior and several concurrent works. Project Page and Video: https://rameenabdal.github.io/StyleFlow.},
journal = {ACM Trans. Graph.},
month = may,
articleno = {21},
numpages = {21},
keywords = {image editing, Generative adversarial networks}
}

@INPROCEEDINGS{9008515,
  author={Abdal, Rameen and Qin, Yipeng and Wonka, Peter},
  booktitle={2019 IEEE/CVF International Conference on Computer Vision (ICCV)}, 
  title={Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?}, 
  year={2019},
  volume={},
  number={},
  pages={4431-4440},
  doi={10.1109/ICCV.2019.00453}}

Broader Impact

Important : Deep learning based facial imagery like DeepFakes and GAN generated images can be gravely misused. This can spread misinformation and lead to other offences. The intent of our work is not to promote such practices but instead be used in the areas such as identification (novel views of a subject, occlusion inpainting etc. ), security (facial composites etc.), image compression (high quality video conferencing at lower bitrates etc.) and development of algorithms for detecting DeepFakes.

Acknowledgments

This implementation builds upon the awesome work done by Karras et al. (StyleGAN2), Chen et al. (torchdiffeq) and Yang et al. (PointFlow). This work was supported by Adobe Research and KAUST Office of Sponsored Research (OSR).

styleflow's People

Contributors

Stargazers

Watchers

Forkers

visualphyzx zumbalamambo dandelion-pym dandelionym liuguoyou lotayou yalcinyakar anthonyyuan sunbest cv-ip silyfox manojkesani benjacquet longjohncoder xrcodes flavienbwk aihill aideveloper-oz tamwaiban arvindia arminbr86 sal-man rahul-sindhu hikistark justinjohn0306 cactrot xy-lin ak9250 hadryan johndpope antonlinderer rieryn ideaplexus shariqfarooq123 amir-s darkmax jacobwjs gbdevux sandboxgtasa humandotlearning jcchiba adhikarimilan evicit edwardnguyen1705 janderer kholeif hackr-space benwaldner huguensjean umairbinahmad nathanie arturovivas joserfjuniorllms samerhjr theunclebenny quynhneo js-kalsi dlintin mehmetokuyar wardenfar jbenzakoun askmetoo sohaiblaraba hack-gpt3 prilcool bobycv06fpm fidelalberto 0xsamman padmanabhan-r amirstudy adnan33 ibilux rashed1414 akchihab eusebiomarquesbenitez stevegbanton mbrukman yqgans wyuzyf r3dfruitrollup waltsky chaoso oscarrodar robingong xialuxi friendseat anhnktp zhangkejiang shadow111 jky01 everything-goes-well asdlei99 xllxll wvware ednahm insan000 haifengzeng zacsan bindaz chijuwu90

styleflow's Issues

Solving environment: failed

Downloaded it, unzipped it, opened conda prompt, cd-ed to the directory, ran conda env create -f environment.yml & got this error.

Adding Docker support

Hi,

Thanks for publishing the StyleFlow code and congratulations. That's massive work and I had no trouble installing the project. It works very well.

Would you be interested in adding Docker support to StyleFlow as an alternative install ?

Please find the PR below !

I am stuck with 'RuntimeError: NVCC returned an error.' Plz help

I am experiencing error while executing main.py in windows. I have python 3.9, VC++ and cl.exe. I added the PATH, but it still displays an error:

File "C:\Users\AA\StyleFlow\dnnlib\tflib\custom_ops.py", line 61, in _run_cmd
raise RuntimeError('NVCC returned an error. See below for full command line and output log:\n\n%s\n\n%s' % (cmd, output))
RuntimeError: NVCC returned an error. See below for full command line and output log:

/usr/local/cuda/bin/nvcc --std=c++11 -DNDEBUG "C:\Users\AA\StyleFlow\dnnlib\tflib\ops\fused_bias_act.cu" --preprocess -o "C:\Users\AA\AppData\Local\Temp\tmph4c8mkpv\fused_bias_act_tmp.cu" --keep --keep-dir "C:\Users\AA\AppData\Local\Temp\tmph4c8mkpv" --disable-warnings --include-path "C:\Users\AA\anaconda3\envs\styleflow\lib\site-packages\tensorflow\include" --include-path "C:\Users\AA\anaconda3\envs\styleflow\lib\site-packages\tensorflow\include\external\protobuf_archive\src" --include-path "C:\Users\AA\anaconda3\envs\styleflow\lib\site-packages\tensorflow\include\external\com_google_absl" --include-path "C:\Users\AA\anaconda3\envs\styleflow\lib\site-packages\tensorflow\include\external\eigen_archive" --compiler-bindir "C:/Program Files (x86)/Microsoft Visual Studio/2019/Community/VC/Tools/MSVC/14.23.28105/bin/HostX64/x64" 2>&1
cannot find the path specified

I have no idea why this is happening, nor how to fix it. Please help :(

+)
Even after changng all / in /usr/local/cuda/bin/nvcc and C:/Program Files (x86)/Microsoft Visual Studio/2019/Community/VC/Tools/MSVC/14.23.28105/bin/HostX64/x64" 2>&1 to

C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.23.28105\bin\HostX64\x64 and
'\usr\local\cuda\bin\nvcc

it is stilll not working
I first thought it was only the problem with cl.exe, since I did not get proper response with nvcc test_nvcc.cu -o test_nvcc -run.
But now I think the linux path is also a problem.

Windows 10 help

Hello, I saw this on Two Minute Papers and was very interested in trying it out.

Is there a prebuilt binary for Windows? Most average people don't use linux/unix. It would allow many more people to experience this work in a platform they already run.
What is xhost? This doesn't seem like an existing command on Windows. Searching this shows up as valid commands in cygwin. Is the build only for *nix environments?
The documentation says an Nvidia Docker installation is required. https://github.com/NVIDIA/nvidia-docker according to this, Windows version does not exist. How are other people building this for Windows then?

Thanks!

How do you load an image on Windows?

I've tried clicking the open file button and nothing happens, but I'm seeing other users here who are able to load images on Windows, so I'm wondering how you're able to do that.

Where is the Microsoft Face API ？

Hi, thank you for your amazing work!
the Microsoft Face API is mentioned in the paper, But in the code i do not find it.

sanity check

Hey Rameen,

Getting back to u as we would like to do sanity check and verify that our scripts that prepare data for styleFlow are bug-free. So that we can make a fair comparison against ur method. is it possible to share with us any two images (src and target) from Figure 10 (and not the projected ones)?

Many thanks

colab demo?

can you add a demo colab. thanks

When run with Docker, all I get is a black window with no user interface.

Here's a the log from an attempt to run the StyleFlow in docker with docker-compose. see ticket #28 for more background of how I got this far. Any ideas what I could try to get this working? My GPU is GeForce GTX 1650 with 4GB of RAM. Does this maybe need a beefier GPU?

I've included the console log from running the software for a few minutes below.

joel@suina:~/Source/StyleFlow$ docker-compose up
Attaching to styleflow_interface_1
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms" ...
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqeglfs.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqeglfs.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "eglfs"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QEglFSIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("eglfs")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqlinuxfb.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqlinuxfb.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "linuxfb"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QLinuxFbIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("linuxfb")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqminimal.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqminimal.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "minimal"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QMinimalIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("minimal")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqminimalegl.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqminimalegl.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "minimalegl"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QMinimalEglIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("minimalegl")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqoffscreen.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqoffscreen.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "offscreen"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QOffscreenIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("offscreen")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqvnc.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqvnc.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "vnc"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QVncIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("vnc")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-egl.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-egl.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "wayland-egl"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QWaylandEglPlatformIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("wayland-egl")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-generic.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-generic.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "wayland"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QWaylandIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("wayland")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-xcomposite-egl.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-xcomposite-egl.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "wayland-xcomposite-egl"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QWaylandXCompositeEglPlatformIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("wayland-xcomposite-egl")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-xcomposite-glx.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwayland-xcomposite-glx.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "wayland-xcomposite-glx"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QWaylandXCompositeGlxPlatformIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("wayland-xcomposite-glx")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwebgl.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqwebgl.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "webgl"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QWebGLIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("webgl")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqxcb.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqxcb.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformIntegrationFactoryInterface.5.3",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "xcb"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QXcbIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("xcb")
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/platforms" ...
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqxcb.so"
interface_1  | loaded library "Xcursor"
interface_1  | QStandardPaths: XDG_RUNTIME_DIR not set, defaulting to '/tmp/runtime-root'
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platformthemes" ...
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platformthemes/libqgtk3.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platformthemes/libqgtk3.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformThemeFactoryInterface.5.1",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "gtk3"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QGtk3ThemePlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("gtk3")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platformthemes/libqxdgdesktopportal.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platformthemes/libqxdgdesktopportal.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.QPlatformThemeFactoryInterface.5.1",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "xdgdesktopportal",
interface_1  |             "flatpak",
interface_1  |             "snap"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QXdgDesktopPortalThemePlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("xdgdesktopportal", "flatpak", "snap")
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/platformthemes" ...
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts" ...
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts/libcomposeplatforminputcontextplugin.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts/libcomposeplatforminputcontextplugin.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPlatformInputContextFactoryInterface.5.1",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "compose",
interface_1  |             "xim"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QComposePlatformInputContextPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("compose", "xim")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts/libibusplatforminputcontextplugin.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts/libibusplatforminputcontextplugin.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPlatformInputContextFactoryInterface.5.1",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "ibus"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QIbusPlatformInputContextPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("ibus")
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/platforminputcontexts" ...
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts/libcomposeplatforminputcontextplugin.so"
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/styles" ...
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/styles" ...
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/iconengines" ...
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/iconengines/libqsvgicon.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/iconengines/libqsvgicon.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QIconEngineFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "svg",
interface_1  |             "svgz",
interface_1  |             "svg.gz"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QSvgIconPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("svg", "svgz", "svg.gz")
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/iconengines" ...
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats" ...
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqgif.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqgif.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "gif"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/gif"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QGifPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("gif")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqicns.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqicns.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "icns"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/x-icns"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QICNSPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("icns")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqico.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqico.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "ico",
interface_1  |             "cur"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/vnd.microsoft.icon",
interface_1  |             "image/vnd.microsoft.icon"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QICOPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("ico", "cur")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqjpeg.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqjpeg.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "jpg",
interface_1  |             "jpeg"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/jpeg",
interface_1  |             "image/jpeg"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QJpegPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("jpg", "jpeg")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqsvg.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqsvg.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "svg",
interface_1  |             "svgz"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/svg+xml",
interface_1  |             "image/svg+xml-compressed"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QSvgPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("svg", "svgz")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtga.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtga.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "tga"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/x-tga"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QTgaPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("tga")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtiff.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtiff.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "tiff",
interface_1  |             "tif"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/tiff",
interface_1  |             "image/tiff"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QTiffPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("tiff", "tif")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwbmp.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwbmp.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "wbmp"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/vnd.wap.wbmp"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QWbmpPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("wbmp")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwebp.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwebp.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QImageIOHandlerFactoryInterface",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "webp"
interface_1  |         ],
interface_1  |         "MimeTypes": [
interface_1  |             "image/webp"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QWebpPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("webp")
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/imageformats" ...
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqgif.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqicns.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqico.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqjpeg.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqsvg.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtga.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtiff.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwbmp.so"
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwebp.so"
interface_1  | ----------------- Options ---------------
interface_1  |                 batchSize: 1                             
interface_1  |           checkpoints_dir: ./checkpoints                 
interface_1  |                  dataroot: ./data/datasetX               
interface_1  |                   gpu_ids: 0                             
interface_1  |      max_result_snapshots: 30                            
interface_1  |                     model: xxxx                          
interface_1  |                      name: XXXX                          
interface_1  |               network_pkl: gdrive:networks/stylegan2-ffhq-config-f.pkl
interface_1  |             only_for_test: ...                           
interface_1  |                     phase: test                          
interface_1  | ----------------- End -------------------
interface_1  | Found local StyleGan2 !
interface_1  | Loading networks from "/usr/app/stylegan/stylegan2-ffhq-config-f.pkl"...
interface_1  | Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Loading... Done.
interface_1  | Setting up TensorFlow plugin "upfirdn_2d.cu": Preprocessing... Loading... Done.
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/xcbglintegrations" ...
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/xcbglintegrations/libqxcb-egl-integration.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/xcbglintegrations/libqxcb-egl-integration.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.Xcb.QXcbGlIntegrationFactoryInterface.5.5",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "xcb_egl"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QXcbEglIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("xcb_egl")
interface_1  | QFactoryLoader::QFactoryLoader() looking at "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/xcbglintegrations/libqxcb-glx-integration.so"
interface_1  | Found metadata in lib /usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/xcbglintegrations/libqxcb-glx-integration.so, metadata=
interface_1  | {
interface_1  |     "IID": "org.qt-project.Qt.QPA.Xcb.QXcbGlIntegrationFactoryInterface.5.5",
interface_1  |     "MetaData": {
interface_1  |         "Keys": [
interface_1  |             "xcb_glx"
interface_1  |         ]
interface_1  |     },
interface_1  |     "archreq": 0,
interface_1  |     "className": "QXcbGlxIntegrationPlugin",
interface_1  |     "debug": false,
interface_1  |     "version": 331008
interface_1  | }
interface_1  | 
interface_1  | 
interface_1  | Got keys from plugin meta data ("xcb_glx")
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/xcbglintegrations" ...
interface_1  | loaded library "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/xcbglintegrations/libqxcb-glx-integration.so"
interface_1  | libGL error: No matching fbConfigs or visuals found
interface_1  | libGL error: failed to load driver: swrast
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/accessible" ...
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/accessible" ...
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/accessiblebridge" ...
interface_1  | QFactoryLoader::QFactoryLoader() checking directory path "/usr/bin/accessiblebridge" ...
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 503, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 506, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 510, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 517, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 521, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 529, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 533, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 538, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 541, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 546, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 549, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 554, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 557, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 562, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 565, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 570, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 574, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | qt.qpa.xcb: QXcbConnection: XCB error: 2 (BadValue), sequence: 579, resource id: 1848, major code: 130 (Unknown), minor code: 3
interface_1  | Training T : 1.0
interface_1  | Number of trainable parameters of Point CNF: 1691649
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/xcbglintegrations/libqxcb-glx-integration.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqgif.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqicns.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqico.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqjpeg.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqsvg.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtga.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtiff.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwbmp.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwebp.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts/libcomposeplatforminputcontextplugin.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqxcb.so" 
interface_1  | QLibraryPrivate::unload succeeded on "Xcursor" (faked)
styleflow_interface_1 exited with code 0

Details in CNF blocks

Hi Rameen,

What an excellent work! I am trying to reimplement your work and I really want to know about the details in CNF block. Image below is from your paper, can you please tell me the hidden units and numbers of linear layers in each linear layer? It will help me a lot!

Again, thx for your great work!!

How to run this demo on the server?

Hi, thanks for your great work!
How to run this GUI demo on the Linux server as it does not have desktop? Thank you!

0 the training code

Thanks for the paper work, I do not find the training code , could you provide it?

How to get attributes.npy of a new picture

Source code availability

Its an excellent work and It inspired me for my thesis. Just want to check if you guys have made source code available also?
The paper has no github link to source code.
Thanks for the help.

MSVC/GCC/CLANG

RuntimeError: Could not find MSVC/GCC/CLANG installation on this computer. Check compiler_bindir_search_path list in "C:\Users\Administrator\styleflow\dnnlib\tflib\custom_ops.py".

I'm having a similar issue. I already did: C:"Program Files (x86)""Microsoft Visual Studio"\2019\Community\VC\Auxiliary\Build\vcvars64.bat

Seems to have not helped.
I'm python 3.6.16
cuda 10.1
windows server 2019
and have microsoft visual studio community 2019

Any suggestions?

Support for animals?

Is it possible to grow a cat a beard or is it not possible due to the non-existence of cat moustaches in the dataset?

Environment yaml for MacOS

Same as for windows, conda env create -f environment.yml fails on macOS because of the Linux builds in the enironment.yml file.

Maybe exporting the environment using conda env export --from-history will fix the problem and make it work cross platforms.

UI Illustration

I got the error below when I run "python main.py"

How can I fix this?? please.

I did not use docker.

Traceback (most recent call last):
File "main.py", line 6, in
import qdarkgraystyle
ModuleNotFoundError: No module named 'qdarkgraystyle'

After docker build, `docker-compose up` fails with `Found no NVIDIA driver on your system.`

I installed nvidia-docker as instructed in the linked repo for ubuntu 20.04 and the test for that seems to indicate I have everything in order:

joel@suina:~/Source/StyleFlow$ docker run --rm --gpus all nvidia/cuda:10.0-base nvidia-smi
Sat Jan  9 18:39:24 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 450.80.02    Driver Version: 450.80.02    CUDA Version: 11.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  GeForce GTX 1650    Off  | 00000000:01:00.0  On |                  N/A |
| 30%   30C    P8     7W /  75W |    571MiB /  3910MiB |      1%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
+-----------------------------------------------------------------------------+

However, when I try to start StyleFlow with docker-compose up, I get the following output and no GUI.

oel@suina:~/Source/StyleFlow$ docker-compose up
Starting styleflow_interface_1 ... done
Attaching to styleflow_interface_1

... (Edit3: removed a lot of QT debug from here, it turned out to be irrelevant) ...

interface_1  | ----------------- Options ---------------
interface_1  |                 batchSize: 1                             
interface_1  |           checkpoints_dir: ./checkpoints                 
interface_1  |                  dataroot: ./data/datasetX               
interface_1  |                   gpu_ids: 0                             
interface_1  |      max_result_snapshots: 30                            
interface_1  |                     model: xxxx                          
interface_1  |                      name: XXXX                          
interface_1  |               network_pkl: gdrive:networks/stylegan2-ffhq-config-f.pkl
interface_1  |             only_for_test: ...                           
interface_1  |                     phase: test                          
interface_1  | ----------------- End -------------------
interface_1  | Traceback (most recent call last):
interface_1  |   File "/usr/app/main.py", line 365, in <module>
interface_1  |     ex = ExWindow(opt)
interface_1  |   File "/usr/app/main.py", line 40, in __init__
interface_1  |     self.EX = Ex(opt)
interface_1  |   File "/usr/app/main.py", line 64, in __init__
interface_1  |     self.zero_padding = torch.zeros(1, 18, 1).cuda()
interface_1  |   File "/usr/local/lib/python3.7/dist-packages/torch/cuda/__init__.py", line 162, in _lazy_init
interface_1  |     _check_driver()
interface_1  |   File "/usr/local/lib/python3.7/dist-packages/torch/cuda/__init__.py", line 82, in _check_driver
interface_1  |     http://www.nvidia.com/Download/index.aspx""")
interface_1  | AssertionError: 
interface_1  | Found no NVIDIA driver on your system. Please check that you
interface_1  | have an NVIDIA GPU and installed a driver from
interface_1  | http://www.nvidia.com/Download/index.aspx
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqgif.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqicns.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqico.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqjpeg.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqsvg.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtga.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqtiff.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwbmp.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/imageformats/libqwebp.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforminputcontexts/libcomposeplatforminputcontextplugin.so" 
interface_1  | QLibraryPrivate::unload succeeded on "/usr/local/lib/python3.7/dist-packages/PyQt5/Qt/plugins/platforms/libqxcb.so" 
interface_1  | QLibraryPrivate::unload succeeded on "Xcursor" (faked)
styleflow_interface_1 exited with code 1

Any idea what might be going wrong?

Edit: After figuring out how to get a shell inside the docker-compose container, I managed to get the following information:

root@623a41c9882d:/usr/app# python3.7 -c 'import torch; print(torch.version.cuda)'
9.0.176
root@623a41c9882d:/usr/app# nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:01_CDT_2018
Cuda compilation tools, release 10.0, V10.0.130

Perhaps I need to figure out how to get the docker built with CUDA 9 instead of 10.

Edit2: After installing updates for nvidia driver files (I guess they came from the nvidia-docker repo), adding nvidia as the default docker-runtime, rebooting to make docker work again and translating the docker-compose.yml into the following docker command, I managed to get the program to show me a black screen.

docker run --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY -e QT_X11_NO_MITSHM=1 -e QT_DEBUG_PLUGINS=1 styleflow_interface python3.7 /usr/app/main.py

With docker-compose up the result is still the same as above. I guess I'll see if upgrading docker-composer helps. Version 1.22.0 is probably rather old.

Edit3: after upgrading docker-composer, docker-compose up now gets the same black window up that I got with the above command. I saw these two lines in the log, though:

interface_1  | libGL error: No matching fbConfigs or visuals found
interface_1  | libGL error: failed to load driver: swrast

So I did some googling with the errors and found that running export LIBGL_ALWAYS_INDIRECT=1 before starting main.py gets rid of those errors, but the result is still a black window that does nothing.

Edit4: Since I've solved the original issue that I made this ticket about. I'll leave it here. Hopefully it's helpful for someone. I'll make a new ticket for the black window issue.

support for windows 10?

Errors during installation.

I've installed 64 bit version of miniconda, after installation was done I've started up it's Anaconda Prompt, opened the project folder using cd command and pasted conda env create -f environment.yml, it starts to load and then gives me the following error:

`Collecting package metadata (repodata.json): done
Solving environment: failed

ResolvePackageNotFound:

bzip2==1.0.8=h7f98852_4
libtiff==4.0.10=h2733197_2
libstdcxx-ng==9.1.0=hdf63c60_0
mkl_random==1.0.2=py37hd81dba3_0
nettle==3.6=he412f7d_0
intel-openmp==2019.4=243
_libgcc_mutex==0.1=conda_forge
ca-certificates==2020.12.8=h06a4308_0
_openmp_mutex==4.5=1_llvm
libedit==3.1.20181209=hc058e9b_0
openh264==2.1.1=h8b12597_0
libpng==1.6.37=hbc83047_0
freetype==2.9.1=h8a8886c_1
gmp==6.2.1=h58526e2_0
libffi==3.2.1=hd88cf55_4
ffmpeg==4.3.1=h3215721_1
libgcc-ng==9.3.0=h5dbcf3e_17
av==8.0.2=py37h06622b3_4
ncurses==6.1=he6710b0_1
sqlite==3.28.0=h7b6447c_0
jpeg==9b=h024ee3a_2
numpy-base==1.16.4=py37hde5b4d6_0
numpy==1.16.4=py37h7e9f1db_0
libgfortran-ng==7.3.0=hdf63c60_0
xz==5.2.4=h14c3975_4
x264==1!152.20180806=h14c3975_0
readline==7.0=h7b6447c_5
zstd==1.3.7=h0b5b093_0
openssl==1.1.1i=h27cfd23_0
tk==8.6.8=hbc83047_0
llvm-openmp==11.0.0=hfc4b9b4_1
libiconv==1.16=h516909a_0
lame==3.100=h7f98852_1001
scikit-learn==0.22.1=py37hd81dba3_0
python==3.7.3=h0371630_0
mkl-service==2.3.0=py37he904b0f_0
zlib==1.2.11=h7b6447c_3
mkl==2019.4=243
certifi==2020.12.5=py37h06a4308_0
mkl_fft==1.0.12=py37ha843d7b_0
gnutls==3.6.13=h85f3911_1`

What could be causing this error? After this failed attempt I tried to move all dependencies to be under - pip: and that gave me errors like ERROR: Invalid requirement: 'python=3.7.3=h0371630_0' = is not a valid operator. Did you mean == ? Then I tried to replace single = with double ==, got errors related to '_libgcc_mutex=0.1=conda_forge' and '_openmp_mutex=4.5=1_llvm',

Just to try one more thing I've removed _ from those and it skipped those (probably because this _ is a part of the filename) and gave me "= is not a valid operator" errors again

I've also tried to leave pip dependency under - dependencies: as I was getting a warning: "Warning: you have pip-installed dependencies in your environment file, but you do not list pip itself as one of your conda dependencies. Conda may not use the correct pip to install your packages, and they may end up in the wrong place. Please add an explicit pip dependency. I'm adding one for you, but still nagging you."

Last error I got after that was ERROR: No matching distribution found for av==8.0.2==py37h06622b3_4 (from -r \StyleFlow\condaenv.cu4kalq8.requirements.txt (line 1))

At that point I tried to run install it again with original file (after each try I ran conda env remove -n StyleFlow) and again got the long error with list of dependencies.

Opening its own photos

Hi,

When will the photo opening be implemented in StyleFlow?

Will we have to adjust the initial parameters (such as yaw for example) or will it be automatically detected?

Thanks!

An error is reported even if there is a GPU, RuntimeError: No GPU devices found

+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1369 G /usr/lib/xorg/Xorg 18MiB |
| 0 1402 G /usr/bin/gnome-shell 69MiB |
| 0 7849 G /usr/lib/xorg/Xorg 96MiB |
| 0 7981 G /usr/bin/gnome-shell 89MiB |
+-----------------------------------------------------------------------------+

nvcc -V:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Fri_Feb__8_19:08:17_PST_2019
Cuda compilation tools, release 10.1, V10.1.105

python main.py:
RuntimeError: No GPU devices found

How should I solve this problem?

Upgrade code to support stylegan2-ada / tensorflow2

This code is based on outdated 2019 code.
The internals dnn folder was bumped here for 2020
https://github.com/NVlabs/stylegan2-ada

There are a bunch of fixes / support across the board.
https://github.com/NVlabs/stylegan2-ada/blob/main/dnnlib/tflib/custom_ops.py

I performed a drop in / and worked on other projects because the file formats / pkl saved files are the same.

N.b. - nvidia are abandoning tensorflow and going to pytorch -
I have a branch that supports tensorflow2
https://github.com/johndpope/stylegan2-ada/

more elaborate / cherry picked branch here with training support.
https://github.com/johndpope/stylegan2-ada/tree/digressions

RuntimeError: Could not find MSVC/GCC/CLANG installation on this computer.

light transfer

Hi Rameen,

Thank for this sharing the code, i was trying to reproduce ur results on my own images. i prepared all the npy and pickle files.

I still have two questions:
for light: I used SfsNet to estimate SH light and then used sfs2shtools from DRP to convert to shtools format. after running light transfer with styleFlow, i have the feeling that the light is mirrored on vetical axis. can you plz tell us if something is wrong with what we did? is that what StyleFLow is expecting for light representation ?

for MS azure expression: can u tell which field u are using exactly?

Cheers

change size of output

First of all, thanks for your nice code!
this is the image of output, when I run the code. How can I change the output size?
Image

Cannot open include file: 'tensorflow/core/framework/op.h': No such file or directory

Any ideas on how to fix this error on Windows 10 X64?

No UI showing up (Windows 10)

When launching main.py or main_attribute.py, I don't get any UI opening up and CLI stays in the state shown..

Using anaconda3 in Anaconda Prompt

Am I doing anything wrong or does anyone have an idea what I could try?

Web UI version working on colab with minimal changes.

Hey I managed to get the webui working on colab (using local tunnel) with really minimal changes (basically just some path changes in code)
The results I got were really amazing,

If you would like me to share the NB please let me know

Code

Could you please say how long will it take to publish your code?
PS Is it possible to publish it with a google collab link?

Sharing dataset?

Hi Rameen, so glad to see your work accepted by TOG!
I wonder if you could share your training dataset (w and corresponding labels)? Only for research and learning use.

Error while running Attribute Transfer UI on Windows.

Error while running Attribute Transfer UI and adjusting the slider (python main_attribute.py ).
says (AttributeError: 'Ex' object has no attribute 'pre_attr_distance')

Not finding gpu

Not sure why i'm getting this error. I'm on a aws ec2 p2 instance with a nvidia tesla v100 gpu. I'm running python 3.6, and cuda 10.1. Any thoughts?

0 hi，how can I sample the conditioned images?

sorry，I don't find any codes about image sampling in your repo.
so I wonder how can I sample conditioned images.

Amazing work

Torch not compiled with CUDA enabled

I installed using the env_windows.yml and all installed without problems, but when executing

python main.py

it shows this error

Any ideas?
Thanks

Web UI (Beta) RuntimeError: CUDA out of memory

Hi, thank you for your amazing work!

I've tried to run the Web UI on my own PC, but it seems that I've encountered this error:

is there any work around for CUDA out of memory?

This is my GPU usage btw when running the Streamlit:

Thank you!

environment.yml Solving Enviroment: Failed ResolvePackageNotFound..

i can't install because i get this error. Is there a solution?

GUI needs improvement for Windows

I'm not able to resize the window/gui.

RTX3080 / CUDA 11.0 support

Really wanted to try this out but sadly won't be able to because only CUDA 10.x is supported. Has anyone found a way to get this working with CUDA 11?

UI web

(StyleFlow) ➜ webui git:(webui) ✗ streamlit run app.py

You can now view your Streamlit app in your browser.

Local URL: http://localhost:8501
Network URL: http://192.168.7.70:8501

<class 'dict'>
2021-02-01 10:49:36.074271: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2021-02-01 10:49:36.084342: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3399670000 Hz
2021-02-01 10:49:36.084905: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fb76a4ce790 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-02-01 10:49:36.084924: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2021-02-01 10:49:36.087294: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
2021-02-01 10:49:36.291809: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fb76a55e2c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2021-02-01 10:49:36.291853: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): TITAN Xp, Compute Capability 6.1
2021-02-01 10:49:36.291865: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (1): TITAN Xp, Compute Capability 6.1
2021-02-01 10:49:36.295251: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: TITAN Xp major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:03:00.0
2021-02-01 10:49:36.296538: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 1 with properties:
name: TITAN Xp major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:05:00.0
2021-02-01 10:49:36.296842: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2021-02-01 10:49:36.298539: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2021-02-01 10:49:36.300010: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2021-02-01 10:49:36.300351: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2021-02-01 10:49:36.302363: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2021-02-01 10:49:36.304095: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2021-02-01 10:49:36.308688: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2021-02-01 10:49:36.311371: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0, 1
2021-02-01 10:49:36.311450: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2021-02-01 10:49:36.313280: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-02-01 10:49:36.313299: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 1
2021-02-01 10:49:36.313306: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N Y
2021-02-01 10:49:36.313310: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 1: Y N
2021-02-01 10:49:36.316099: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 11444 MB memory) -> physical GPU (device: 0, name: TITAN Xp, pci bus id: 0000:03:00.0, compute capability: 6.1)
2021-02-01 10:49:36.318149: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 10098 MB memory) -> physical GPU (device: 1, name: TITAN Xp, pci bus id: 0000:05:00.0, compute capability: 6.1)
----------------- Options ---------------
batchSize: 1
checkpoints_dir: ./checkpoints
dataroot: ./data/datasetX
gpu_ids: 0
max_result_snapshots: 30
model: xxxx
name: XXXX
network_pkl: gdrive:networks/stylegan2-ffhq-config-f.pkl
only_for_test: ...
phase: test
----------------- End -------------------
Loading networks from "gdrive:networks/stylegan2-ffhq-config-f.pkl"...
Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Failed!
/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/dask/dataframe/utils.py:15: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.
import pandas.util.testing as tm

and it stucks with no result

Code release date

Hello! Very great article!
We are waiting for code release to reproduce!

RuntimeError: No GPU devices found

when trying to run main.py i am getting the following error

File "/home/projects/StyleFlow/main.py", line 365, in
ex = ExWindow(opt)
File "/home/projects/StyleFlow/main.py", line 40, in init
self.EX = Ex(opt)
File "/home/projects/StyleFlow/main.py", line 70, in init
self.init_deep_model(opt)
File "/home/projects/StyleFlow/main.py", line 105, in init_deep_model
self.model = Build_model(self.opt)
File "/home/projects/StyleFlow/utils.py", line 200, in init
_G, _D, Gs = pretrained_networks.load_networks(network_pkl)
File "/home/projects/StyleFlow/pretrained_networks.py", line 76, in load_networks
G, D, Gs = pickle.load(stream, encoding='latin1')
File "/home/projects/StyleFlow/dnnlib/tflib/network.py", line 297, in setstate
self._init_graph()
File "/home/projects/StyleFlow/dnnlib/tflib/network.py", line 154, in _init_graph
out_expr = self._build_func(*self.input_templates, **build_kwargs)
File "", line 491, in G_synthesis_stylegan2
File "", line 455, in layer
File "", line 99, in modulated_conv2d_layer
File "", line 68, in apply_bias_act
File "/home/projects/StyleFlow/dnnlib/tflib/ops/fused_bias_act.py", line 68, in fused_bias_act
return impl_dict[impl](x=x, b=b, axis=axis, act=act, alpha=alpha, gain=gain)
File "/home/projects/StyleFlow/dnnlib/tflib/ops/fused_bias_act.py", line 122, in _fused_bias_act_cuda
cuda_kernel = _get_plugin().fused_bias_act
File "/home/projects/StyleFlow/dnnlib/tflib/ops/fused_bias_act.py", line 16, in _get_plugin
return custom_ops.get_plugin(os.path.splitext(file)[0] + '.cu')
File "/home/projects/StyleFlow/dnnlib/tflib/custom_ops.py", line 132, in get_plugin
compile_opts += ' --gpu-architecture=%s' % _get_cuda_gpu_arch_string()
File "/home/projects/StyleFlow/dnnlib/tflib/custom_ops.py", line 52, in _get_cuda_gpu_arch_string
raise RuntimeError('No GPU devices found')
RuntimeError: No GPU devices found
what can be the problem

About code

hello, really interesting your work, I am trying to implement your work but stuck in some issues, so how long do you plan to release the official code?

qt.qpa.xcb: could not connect to display :0

Please guide me. I tried many ways but unable to solve this issue.

Loading your own images into StyleFlow

Hi there! Just got SyleFlow working an a Windows 10 machine using this repo: https://github.com/justinjohn0306/StyleFlow-Windows-10

Thank you for sharing the code! Amazing work.

How would I go about loading up an image of my own for manipulation?

Stress test option

I noticed the min / max dicts that feed Parameters_widgets can be changed to allow a wider variety of extreme options which the model accepts.
This is great because you can push the limits of the model and I think most people would enjoy observing what the model does when stressed (expression max of 3 is a joy).

min_dic = {'Gender': 0, 'Glasses': 0, 'Yaw': -55, 'Pitch': -30, 'Baldness': 0, 'Beard': 0.0, 'Age': 0, 'Expression': -1}
max_dic = {'Gender': 1, 'Glasses': 1, 'Yaw': 55, 'Pitch': 30, 'Baldness': 1, 'Beard': 1, 'Age': 110, 'Expression': 3}

While I am sure certain combinations will cause model collapse, it would be a shame if the average user didn't have these options.

rameenabdal / styleflow Goto Github PK

styleflow's Introduction

StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)

See you @ Siggraph 2021

Installation

Installation (Docker)

UI Illustration

Editing Images Using Pretrained Models

Web UI (Beta)

Training New Model

Projection

License

Citation

Broader Impact

Acknowledgments

styleflow's People

Contributors

Stargazers

Watchers

Forkers

styleflow's Issues

Recommend Projects

Recommend Topics

Recommend Org