No video
How to train a GAN, NIPS 2016 | Soumith Chintala, Facebook AI Research
Рет қаралды 9,204
7 жыл бұрынNIPS 2016 Workshop on Adversarial Training
Soumith Chintala, Facebook AI Research
github.com/sou...
While research in Generative Adversarial Networks (GANs) continues to improve the fundamental stability of these models, we use a bunch of tricks to train them and make them stable day to day.
Here are a summary of some of the tricks.
@noirmist3777 5 жыл бұрын
1. Normalize the input [-1.+1] 2. Modified Loss function :min(log(1-D) to max(D) 3. Use Spherical Z rather than Uniform one - Sampling Generative Networks 4. Do not mix Real and Fake data by BatchNorm 5. Avoid Sparse Gradients (ReLU to Leaky ReLU, Maxpool to Average Pool 6. Label Smoothing 7. DCGANS/Hybrid models (KL + GAN, VAE+GAN) 8. Use RL stochastic tricks 9. ADAM 10. Trank Failure early- check loss
@vaibhav6431 5 жыл бұрын
github.com/soumith/ganhacks
@FireSonix 5 жыл бұрын
For those strangers who wanna go a little further: 11. Don't balance via loss statistics (Do not use D/G Losses for any hyperparameter tuning) 12. If you have labels, use them (Use Additional information from labels, e.g. in AC-GAN. CGAN etc) 13. Add noise to inputs, decay over time 14. Train discriminator more, sometimes 15. Batch Discrimination 16. Discrete Variable (Use additional information other than labels)
@iansullivan8 6 жыл бұрын
'things are fucking up' , I like that
Preserve Knowledge
Рет қаралды 3,3 М.
Family Games Media
Рет қаралды 31 МЛН
Preserve Knowledge
Рет қаралды 59 М.
WIRED
Рет қаралды 2,3 МЛН
Steven Van Vaerenbergh
Рет қаралды 125 М.
Preserve Knowledge
Рет қаралды 23 М.