TorchGAN
TorchGAN: A Flexible Framework for GAN Training and Evaluation - Published in JOSS (2021)
Science Score: 100.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 7 DOI reference(s) in README and JOSS metadata -
✓Academic publication links
Links to: arxiv.org, ieee.org, joss.theoj.org -
✓Committers with academic emails
3 of 10 committers (30.0%) from academic institutions -
○Institutional organization owner
-
✓JOSS paper metadata
Published in Journal of Open Source Software
Keywords
Keywords from Contributors
Scientific Fields
Repository
Research Framework for easy and efficient training of GANs based on Pytorch
Basic Info
- Host: GitHub
- Owner: torchgan
- License: mit
- Language: Python
- Default Branch: master
- Homepage: https://torchgan.readthedocs.io/en/latest/
- Size: 22.9 MB
Statistics
- Stars: 1,425
- Watchers: 29
- Forks: 169
- Open Issues: 27
- Releases: 5
Topics
Metadata Files
README.md
TorchGAN is a Pytorch based framework for designing and developing Generative Adversarial Networks. This framework has been designed to provide building blocks for popular GANs and also to allow customization for cutting edge research. Using TorchGAN's modular structure allows
- Trying out popular GAN models on your dataset.
- Plug in your new Loss Function, new Architecture, etc. with the traditional ones.
- Seamlessly visualize the training with a variety of logging backends.
| System / PyTorch Version | 1.8 | 1.9 | nightly |
| :---: | :---: | :---: | :---: |
| Linux py3.8 | 
| | | |
| Linux py3.9 | | | | |
| OSX py3.8 | | | | |
| OSX py3.9 | | | | |
| Windows py3.9 | | | | |
| Windows py3.9 | | | | |
Installation
Using pip (for stable release):
bash
$ pip install torchgan
Using pip (for latest master):
bash
$ pip install git+https://github.com/torchgan/torchgan.git
From source:
bash
$ git clone https://github.com/torchgan/torchgan.git
$ cd torchgan
$ python setup.py install
Documentation
The documentation is available here
The documentation for this package can be generated locally.
bash
$ git clone https://github.com/torchgan/torchgan.git
$ cd torchgan/docs
$ pip install -r requirements.txt
$ make html
Now open the corresponding file from build directory.
Tutorials
The tutorials directory contain a set of tutorials to get you started with torchgan. These tutorials can be run using Google Colab or Binder. It is highly recommended that you follow the tutorials in the following order.
- Introductory Tutorials:
- Intermediate Tutorials:
- Advanced Tutorials:
Supporting and Citing
This software was developed as part of academic research. If you would like to help support it, please star the repository. If you use this software as part of your research, teaching, or other activities, we would be grateful if you could cite the following:
@article{Pal2021,
doi = {10.21105/joss.02606},
url = {https://doi.org/10.21105/joss.02606},
year = {2021},
publisher = {The Open Journal},
volume = {6},
number = {66},
pages = {2606},
author = {Avik Pal and Aniket Das},
title = {TorchGAN: A Flexible Framework for GAN Training and Evaluation},
journal = {Journal of Open Source Software}
}
List of publications & submissions using TorchGAN (please open a pull request to add missing entries):
- Can GAN-Generated Network Traffic be used to Train Traffic Anomaly Classifiers?
- Ward2ICU: A Vital Signs Dataset of Inpatients from the General Ward
Contributing
We appreciate all contributions. If you are planning to contribute bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please first open an issue and discuss the feature with us. For more detailed guidelines head over to the official documentation.
Contributors
This package has been developed by * Avik Pal (@avik-pal) * Aniket Das (@Aniket1998)
This project exists thanks to all the people who contribute.
Owner
- Name: torchgan
- Login: torchgan
- Kind: organization
- Email: avikpal@iitk.ac.in
- Repositories: 2
- Profile: https://github.com/torchgan
Lightweight framework for easily and efficiently training Generative Adversarial Networks in PyTorch
JOSS Publication
TorchGAN: A Flexible Framework for GAN Training and Evaluation
Authors
Indian Institute of Technology Kanpur
Indian Institute of Technology Kanpur
Editor
Arfon Smith
Tags
Deep Learning Machine Learning Generative Adversarial Networks Unsupervised Learning Computer Vision Generative ModelsCitation (CITATION.bib)
@article{Pal2021,
doi = {10.21105/joss.02606},
url = {https://doi.org/10.21105/joss.02606},
year = {2021},
publisher = {The Open Journal},
volume = {6},
number = {66},
pages = {2606},
author = {Avik Pal and Aniket Das},
title = {TorchGAN: A Flexible Framework for GAN Training and Evaluation},
journal = {Journal of Open Source Software}
}
GitHub Events
Total
- Watch event: 25
- Pull request event: 1
- Fork event: 2
Last Year
- Watch event: 25
- Pull request event: 1
- Fork event: 2
Committers
Last synced: 5 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Avik Pal | a****l@i****n | 83 |
| Aniket Das | 1****s@g****m | 30 |
| 向阳 | 9****g | 1 |
| jess | j****r@g****m | 1 |
| dependabot[bot] | 4****] | 1 |
| Weili Shi | me@s****m | 1 |
| Naman Biyani | n****b@i****n | 1 |
| Joseph Spisak | s****o@g****m | 1 |
| Avinandan Bose | 4****2 | 1 |
| Yatin Dandi | y****d@i****n | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 4 months ago
All Time
- Total issues: 46
- Total pull requests: 56
- Average time to close issues: 3 months
- Average time to close pull requests: 15 days
- Total issue authors: 30
- Total pull request authors: 14
- Average comments per issue: 1.7
- Average comments per pull request: 1.21
- Merged pull requests: 46
- Bot issues: 0
- Bot pull requests: 1
Past Year
- Issues: 0
- Pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: 9 months
- Issue authors: 0
- Pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- avik-pal (11)
- dsevero (3)
- Xylobyte (2)
- Aniket1998 (2)
- xujin1184104394 (2)
- namanbiyani (2)
- Xaffle (1)
- alexorona (1)
- kayuksel (1)
- bosaving (1)
- sixin-zh (1)
- PasqualeZingo (1)
- FelixAbrahamsson (1)
- amine-boukriba (1)
- xfguo-ucas (1)
Pull Request Authors
- avik-pal (36)
- Aniket1998 (5)
- namanbiyani (4)
- AmmarBattah (2)
- Avinandan22 (1)
- jspisak (1)
- nirmal-suthar (1)
- monkeywithacupcake (1)
- shi-weili (1)
- kayuksel (1)
- dependabot[bot] (1)
- XiangYyang (1)
- TrellixVulnTeam (1)
- yatindandi (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 2
-
Total downloads:
- pypi 11,504 last-month
- Total docker downloads: 9
-
Total dependent packages: 0
(may contain duplicates) -
Total dependent repositories: 11
(may contain duplicates) - Total versions: 12
- Total maintainers: 1
proxy.golang.org: github.com/torchgan/torchgan
- Documentation: https://pkg.go.dev/github.com/torchgan/torchgan#section-documentation
- License: mit
-
Latest release: v0.1.0
published about 4 years ago
Rankings
pypi.org: torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
- Homepage: https://github.com/torchgan/torchgan
- Documentation: https://torchgan.readthedocs.io/
- License: MIT
-
Latest release: 0.1.0
published about 4 years ago
Rankings
Maintainers (1)
Dependencies
- sphinx *
- sphinx_rtd_theme *
- numpy *
- pillow *
- scipy *
- torch >=1.2
- torchvision >=0.4
- wget *
- actions/checkout v1 composite
- actions/setup-python v1 composite
- actions/checkout master composite
- actions/setup-python master composite
- actions/checkout v1 composite
- actions/setup-python v1 composite
- actions/checkout master composite
- cirrus-actions/rebase 1.2 composite