khanrc/tf.gans-comparison
TensorFlow implementations of eight GAN variants trained on CelebA and LSUN datasets for comparative analysis.
Not currently ranked — collecting fresh signals.
star history
This repository provides pure implementations of generative adversarial network architectures as described in their original papers, including DCGAN, LSGAN, WGAN, WGAN-GP, EBGAN, BEGAN, DRAGAN, and CoulombGAN. All models are implemented in TensorFlow and trained on the CelebA and LSUN bedroom image datasets at 64x64 resolution. The project aims to provide unbiased comparisons by not cherry-picking results, with training powered by TensorFlow queue runners and metrics logged to TensorBoard.
Frequently asked
- What is khanrc/tf.gans-comparison?
- TensorFlow implementations of eight GAN variants trained on CelebA and LSUN datasets for comparative analysis.
- Is tf.gans-comparison open source?
- Yes — khanrc/tf.gans-comparison is an open-source project tracked on heatdrop.
- What language is tf.gans-comparison written in?
- khanrc/tf.gans-comparison is primarily written in Python.
- How popular is tf.gans-comparison?
- khanrc/tf.gans-comparison has 470 stars on GitHub.
- Where can I find tf.gans-comparison?
- khanrc/tf.gans-comparison is on GitHub at https://github.com/khanrc/tf.gans-comparison.