TransGAN - Two Transformers Can Make One Strong GAN - Machine Learning Research Paper Explained

TransGAN - Two Transformers Can Make One Strong GAN - Machine Learning Research Paper Explained

Yannic Kilcher via YouTube Direct link

- Trick 2: Super-Resolution Co-Training

8 of 11

8 of 11

- Trick 2: Super-Resolution Co-Training

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

TransGAN - Two Transformers Can Make One Strong GAN - Machine Learning Research Paper Explained

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Introduction & Overview
  2. 2 - Discriminator Architecture
  3. 3 - Generator Architecture
  4. 4 - Upsampling with PixelShuffle
  5. 5 - Architecture Recap
  6. 6 - Vanilla TransGAN Results
  7. 7 - Trick 1: Data Augmentation with DiffAugment
  8. 8 - Trick 2: Super-Resolution Co-Training
  9. 9 - Trick 3: Locality-Aware Initialization for Self-Attention
  10. 10 - Scaling Up & Experimental Results
  11. 11 - Recap & Conclusion

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.