Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by math_rachel on 2019-05-04 (UTC).

Improving the resolution of microscopy images and adding color to old movies using fastai, @PyTorch, U-Nets, feature loss, & 1-cycle learning (almost no GANs needed!). Great #F8 talk by @jeremyphoward @citnaj @manorlaboratory https://t.co/x5GIyOcSau pic.twitter.com/ALkCjVbeSX

— Rachel Thomas (@math_rachel) May 4, 2019
applicationvideocvgan
by jeremyphoward on 2019-05-04 (UTC).

Presenting "Decrappification, DeOldification, and Super Resolution", with @citnaj, @manorlaboratory & many collaborators. Click below to learn about brain mapping, restoring classic movies, & more!

Special thanks to @PyTorch, @salkinstitute & @313V.https://t.co/LUavSCk4zS pic.twitter.com/QhYtoLLVWX

— Jeremy Howard (@jeremyphoward) May 4, 2019
applicationcv
by math_rachel on 2019-05-04 (UTC).

GANs: A Love/Hate Relationship @citnaj

GANs are great!
1. Learn the loss function
2. Convincing realism
3. Flexible

But... They're also:
1. Slow
2. Unstable
3. Extremely difficult to get righthttps://t.co/x5GIyOcSau pic.twitter.com/1zjols0ifK

— Rachel Thomas (@math_rachel) May 4, 2019
ganlearning

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib