https://github.com/chrisdonahue/sdgan
Official implementation of "Semantically Decomposing the Latent Spaces of Generative Adversarial Networks"
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org, scholar.google -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.7%) to scientific vocabulary
Repository
Official implementation of "Semantically Decomposing the Latent Spaces of Generative Adversarial Networks"
Basic Info
Statistics
- Stars: 95
- Watchers: 8
- Forks: 19
- Open Issues: 1
- Releases: 0
Metadata Files
README.md
SD-GAN Tensorflow
Implementation of Semantically Decomposing the Latent Spaces of Generative Adversarial Networks (arXiv, demo).
Semantically decomposed GANs (SD-GANs) learn a decomposed latent space separating identity from the other contingent aspects of observations. In our paper, we demonstrate that SD-GANs can disentangle factors of variation corresponding to identity from photographs of celebrity faces and shoes. SD-GANs are especially applicable for datasets with many labels but few observations of each. Example results from an SD-GAN model; each row shares an identity and each column shares contingent factors:
We are currently in the process of improving the code for SD-BEGAN in the began branch. This branch is usable but does not produce results on par with our paper yet. To reproduce the SD-BEGAN results from our paper, please use this code (zip file), a fork of BEGAN-tensorflow.
Instructions
Download one or both of the compressed datasets to sdgan/data:
Run training:
- Navigate to:
sdgan/data - Extract a dataset:
tar xvfz msceleb12k.tar.gz - Navigate to:
sdgan - Run training:
./train.sh - Navigate to:
sdgan/train - (Optional) Run grid visualization:
./prev.sh - Run tensorboard:
tensorboard --logdir=.
Requirements
tensorflow (>= 1.0)numpy
Adding new datasets
To add new datasets, follow the naming convention in the prepackaged ones above. Dataset folder must have subdirectory called train. train must contain 64x64 png files formatted as <ID_NAME>_<OBS_NUMBER>_<?>.png. In our datasets, <?> is the original aspect ratio for the source image of the 64x64 thumbnail, though the attribute is unused in our code.
Attribution
If you use this dataset in your research, cite via the following BibTeX:
@inproceedings{donahue2018sdgan,
title={Semantically Decomposing the Latent Spaces of Generative Adversarial Networks},
author={Donahue, Chris and Lipton, Zachary C and Balsubramani, Akshay and McAuley, Julian},
booktitle={ICLR},
year={2018}
}
Reference code/datasets
Author
Owner
- Name: Chris Donahue
- Login: chrisdonahue
- Kind: user
- Location: Pittsburgh
- Website: chrisdonahue.com
- Twitter: chrisdonahuey
- Repositories: 55
- Profile: https://github.com/chrisdonahue
Assistant professor @ CMU CSD. Part-time research scientist at Google Magenta. Machine learning for music, and creative interaction.
GitHub Events
Total
Last Year
Committers
Last synced: about 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| Chris Donahue | c****e@g****m | 25 |
| Zack Chase Lipton | z****e@g****m | 1 |
Issues and Pull Requests
Last synced: about 1 year ago
All Time
- Total issues: 2
- Total pull requests: 1
- Average time to close issues: 5 days
- Average time to close pull requests: about 18 hours
- Total issue authors: 2
- Total pull request authors: 1
- Average comments per issue: 2.0
- Average comments per pull request: 0.0
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- jmgrn61 (1)
- ltt-gddxz (1)
Pull Request Authors
- zackchase (1)