Skip to content

How to Add Latest Distillation Techniques such as DIST or KD++ to this framework #377

Discussion options

You must be logged in to vote

Hi @arpitsahni04

If you explain how those methods should work precisely

  • what teacher and student models and datasets are used
  • how their loss functions are designed
  • which layers of the teacher and student models are used to compute the losses

then, I can explain or give it a try

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by nighting0le01
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants