upit
A fastai/PyTorch package for unpaired image-to-image translation.
Science Score: 59.0%
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
Found .zenodo.json file -
✓DOI references
Found 4 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org, zenodo.org -
✓Committers with academic emails
1 of 4 committers (25.0%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.7%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
A fastai/PyTorch package for unpaired image-to-image translation.
Basic Info
- Host: GitHub
- Owner: tmabraham
- License: apache-2.0
- Language: Jupyter Notebook
- Default Branch: master
- Homepage: https://tmabraham.github.io/UPIT
- Size: 205 MB
Statistics
- Stars: 136
- Watchers: 4
- Forks: 21
- Open Issues: 6
- Releases: 4
Topics
Metadata Files
README.md
Unpaired image-to-image translation
This is a package for training and testing unpaired image-to-image translation models. It currently only includes the CycleGAN, DualGAN, and GANILLA models, but other models will be implemented in the future.
This package uses fastai to accelerate deep learning experimentation. Additionally, nbdev was used to develop the package and produce documentation based on a series of notebooks.
Install
To install, use pip:
pip install git+https://github.com/tmabraham/UPIT.git
The package uses torch 1.7.1, torchvision 0.8.2, and fastai 2.3.0 (and its dependencies). It also requires nbdev 1.1.13 if you would like to add features to the package. Finally, for creating a web app model interface, gradio 1.1.6 is used.
How to use
Training a CycleGAN model is easy with UPIT! Given the paths of the
images from the two domains trainA_path and trainB_path, you can do
the following:
python
from upit.data.unpaired import *
from upit.models.cyclegan import *
from upit.train.cyclegan import *
python
dls = get_dls(trainA_path, trainB_path)
cycle_gan = CycleGAN(3,3,64)
learn = cycle_learner(dls, cycle_gan,opt_func=partial(Adam,mom=0.5,sqr_mom=0.999))
learn.fit_flat_lin(100,100,2e-4)
The GANILLA model is only a different generator model architecture
(thats meant to strike a better balance between style and content), so
the same
cycle_learner
class can be used.
python
from upit.models.ganilla import *
python
ganilla = GANILLA(3,3,64)
learn = cycle_learner(dls, ganilla,opt_func=partial(Adam,mom=0.5,sqr_mom=0.999))
learn.fit_flat_lin(100,100,2e-4)
Finally, we provide separate functions/classes for
DualGAN
model and training:
python
from upit.models.dualgan import *
from upit.train.dualgan import *
python
dual_gan = DualGAN(3,64,3)
learn = dual_learner(dls, dual_gan, opt_func=RMSProp)
learn.fit_flat_lin(100,100,2e-4)
Additionally, we provide metrics for quantitative evaluation of the models, as well as experiment tracking with Weights and Biases. Check the documentation for more information!
Citing UPIT
If you use UPIT in your research please use the following BibTeX entry:
@software{Abraham_UPIT_-_A,
author = {Abraham, Tanishq Mathew},
doi = {10.5281/zenodo.7889405},
title = {{UPIT - A fastai/PyTorch package for unpaired image-to-image translation.}},
url = {https://github.com/tmabraham/UPIT},
version = {0.2.3}
}
Owner
- Name: Tanishq Abraham
- Login: tmabraham
- Kind: user
- Twitter: iScienceLuvr
- Repositories: 9
- Profile: https://github.com/tmabraham
GitHub Events
Total
- Watch event: 2
Last Year
- Watch event: 2
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Tanishq Abraham | t****m@u****u | 134 |
| dependabot[bot] | 4****] | 8 |
| loh04 | l****a@g****m | 2 |
| Hamel Husain | h****u@g****m | 2 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 8 months ago
All Time
- Total issues: 21
- Total pull requests: 24
- Average time to close issues: about 1 month
- Average time to close pull requests: 10 days
- Total issue authors: 7
- Total pull request authors: 5
- Average comments per issue: 2.19
- Average comments per pull request: 0.58
- Merged pull requests: 19
- Bot issues: 0
- Bot pull requests: 10
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
- tmabraham (8)
- hno2 (4)
- rbunn80110 (3)
- turgut090 (3)
- lohithmunakala (1)
- SHREYAS290601 (1)
- many-hats (1)
Pull Request Authors
- dependabot[bot] (10)
- tmabraham (9)
- lohithmunakala (3)
- hamelsmu (1)
- drscotthawley (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 15 last-month
- Total dependent packages: 0
- Total dependent repositories: 1
- Total versions: 4
- Total maintainers: 1
pypi.org: upit
Unpaired Image-to-Image Translation with PyTorch+fastai
- Homepage: https://github.com/tmabraham/UPIT/tree/master/
- Documentation: https://upit.readthedocs.io/
- License: Apache Software License 2.0
-
Latest release: 0.2.2
published over 3 years ago
Rankings
Maintainers (1)
Dependencies
- gradio *
- torchvision *
- upit *
- gradio *
- fastai/workflows/quarto-ghp master composite
- actions/checkout v3 composite
- actions/setup-python v3 composite