Unpaired image-to-image translation
A fastai/PyTorch package for unpaired image-to-image translation currently with CycleGAN implementation.
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:
#cuda
from upit.data.unpaired import *
from upit.models.cyclegan import *
from upit.train.cyclegan import *
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 (that's meant to strike a better balance between style and content), so the same cycle_learner class can be used.
#cuda
from upit.models.ganilla import *
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:
#cuda
from upit.models.dualgan import *
from upit.train.dualgan import *
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:
@Misc{UPIT,
author = {Tanishq Mathew Abraham},
title = {UPIT - A fastai/PyTorch package for unpaired image-to-image translation.},
howpublished = {Github},
year = {2021},
url = {https://github.com/tmabraham/UPIT}
}
The Colab link: https://colab.research.google.com/drive/13rrNLBgDulgeHclovxJNtQVbVYcGMKm0?usp=sharing
4 Mar 10, 2022
5 Jul 01, 2022
3 Oct 10, 2021
2 Apr 16, 2022
2 Jan 16, 2022
152 Dec 20, 2022
10 Dec 19, 2022
2 Sep 28, 2022
2 Nov 16, 2022
1.2k Dec 29, 2022
4 Oct 26, 2022
285 Dec 08, 2022
8 Jul 29, 2022
5 Dec 16, 2021
1.6k Jan 04, 2023
20 Jan 06, 2023
2 Oct 11, 2021
11 Jul 17, 2022
21 Dec 25, 2022
363 Dec 28, 2022