TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.
Why do you think that https://github.com/sail-sg/poolformer is a good alternative to FunMatch-Distillation
TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.
Why do you think that https://github.com/sail-sg/poolformer is a good alternative to FunMatch-Distillation