kodalinaveen3 / Dragan
Licence: mit
A stable algorithm for GAN training
Stars: ✭ 189
Labels
Projects that are alternatives of or similar to Dragan
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-47.09%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network, generative-model
All About The Gan
All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN
Stars: ✭ 630 (+233.33%)
Mutual labels: paper, gan, generative-adversarial-network, unsupervised-learning
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+1581.48%)
Mutual labels: paper, gan, generative-adversarial-network, generative-model
Discogan Pytorch
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
Stars: ✭ 961 (+408.47%)
Mutual labels: jupyter-notebook, gan, unsupervised-learning, generative-model
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (+171.43%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network, unsupervised-learning
Gans In Action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
Stars: ✭ 748 (+295.77%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Relativistic Average Gan Keras
The implementation of Relativistic average GAN with Keras
Stars: ✭ 36 (-80.95%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Ganspace
Discovering Interpretable GAN Controls [NeurIPS 2020]
Stars: ✭ 1,224 (+547.62%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Calogan
Generative Adversarial Networks for High Energy Physics extended to a multi-layer calorimeter simulation
Stars: ✭ 87 (-53.97%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Sprint gan
Privacy-preserving generative deep neural networks support clinical data sharing
Stars: ✭ 92 (-51.32%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (-48.68%)
Mutual labels: gan, generative-adversarial-network, generative-model
Context Encoder
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
Stars: ✭ 731 (+286.77%)
Mutual labels: gan, generative-adversarial-network, unsupervised-learning
Capsule Gan
Code for my Master thesis on "Capsule Architecture as a Discriminator in Generative Adversarial Networks".
Stars: ✭ 120 (-36.51%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Hypergan
Composable GAN framework with api and user interface
Stars: ✭ 1,104 (+484.13%)
Mutual labels: gan, generative-adversarial-network, unsupervised-learning
Fewshot Face Translation Gan
Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.
Stars: ✭ 705 (+273.02%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Psgan
Periodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (-42.86%)
Mutual labels: jupyter-notebook, gan, generative-model
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (-29.1%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Generative Adversarial Networks
Introduction to generative adversarial networks, with code to accompany the O'Reilly tutorial on GANs
Stars: ✭ 505 (+167.2%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
Semantic image inpainting
Semantic Image Inpainting
Stars: ✭ 140 (-25.93%)
Mutual labels: gan, generative-adversarial-network, generative-model
Stylegan2 Projecting Images
Projecting images to latent space with StyleGAN2.
Stars: ✭ 102 (-46.03%)
Mutual labels: jupyter-notebook, gan, generative-adversarial-network
DRAGAN (Deep Regret Analytic Generative Adversarial Networks)
Link to our paper - https://arxiv.org/abs/1705.07215
Pytorch implementation (thanks!) - https://github.com/jfsantos/dragan-pytorch
Procedure (to use our algorithm):
- Pick your favorite architecture, objective function for the game.
- Tune the hyperparameter 'c' which decides the size of local regions. Our intuition is that small values extract better performance from a given architecture due to relaxed restrictions while slightly larger values give more stability. Be careful to set it appropriately by taking into account your domain range and making sure that perturbations don't lie on the data manifold.
- Tune lambda if necessary, this has the usual meaning of regularization intensity. Set 'k' to be 1.
- If your results are still bad, go back to Step 1 and try a different architecture+objective.
Interesting discussion with Ian Goodfellow and Martin Arjovsky on why GANs are unstable and where improvements come from
https://www.facebook.com/kodali.naveen.90/posts/1047257878740881
An interesting new paper by Fedus et.al came out following this (Many paths to equilibria)
https://arxiv.org/abs/1710.08446
Some of the repositories that would be helpful and which helped us (big thanks!):
https://github.com/igul222/improved_wgan_training
https://github.com/wiseodd/generative-models/tree/master/GAN
https://github.com/openai/improved-gan/tree/master/inception_score
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].