-
I want use it on Android Or iOS, but 96M file obviously too big for mobile app. How can i do it let model less more then 60M?
-
## how good or bad are the predicted probabilities??
low probability --> high penalty
-log(1.0) = 0
-log(0.8) = 0.22314
-log(0.6) = 0.51082
y = -log(x)
에서 작은 모델(student)로 지식을 전이하여 모델 경량화나 추론 속도 개선을 이루면서도 성능을 유지하거나 향상시키는 기법
- KD는 큰 모델의 성능을 작은 모델에 전이하기 때문에, student 모델이 경량화되어 더 빠른 추론 속도를 제공하면서도 성능 저하를 최소화
- Object Detecti…
-
Inspired by < Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation > I expanded the original English-only model to support Chinese,I use the script - make_multilingual.py，a…
-
-
Hi,
Your work is amazing! I'm wondering whether you are going to release the code for :1. Data-free pruning 2. Data-free Knowledge Transfer 3. Data-free Continual Learning.
Thanks!
-
Hi wentianli
I've been testing the knowledge distillation method for a while by playing with Caffe's available layers and I was able to achieve nearly good results with some simple models. It's bee…