Created by @RisingSayak
Original paper by Beyer et al.https://arxiv.org/abs/2106.05237
Show this thread
New code example on http://keras.io : recipes to improve knowledge distillation workflows (training smaller "student" models that retain the performance of larger "teacher" models).https://keras.io/examples/keras_recipes/better_knowledge_distillation/ …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Sir when will you release second edition of your book?
-
About November, i got it from manning's website.
End of conversation
New conversation -
-
-
But in DINO, student and teacher are of the same size right ?!!
-
That is actually a bit different. The purpose there is to NOT compress a bigger model into a smaller one.
End of conversation
New conversation -
-
-
Thank you! I like your recipes
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.