yuanli2333/Teacher-free-Knowledge-Distillation
Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
PythonMIT
Issues
- 4
- 0
Does this method work on the detection tasks?
#35 opened by fmaaf - 0
KD loss is zero
#33 opened by minato1000 - 0
Does this work for dataset with only two classes
#31 opened by wugh - 1
Question about the loss function of Tf-reg KD
#24 opened by HowieMa - 0
Torch Vision Version
#28 opened by Amik-TJ - 0
Working with larger image size
#27 opened by sri9s - 0
Data augmentation for Tiny-ImageNet
#23 opened by aryanasadianuoit - 1
Difference between L_REG and LSR
#22 opened by real-brilliant - 3
Can't download the pre-trained model
#4 opened by SunCherry - 0
Implementation doesn't have loss_soft_regularization and loss_fn_kd for ImageNet dataset
#21 opened by sainatarajan - 3
- 3
Have you ever try on deeper network?
#17 opened by JiyueWang - 2
What is the difference between Born Again Network and your self-training KD method?
#18 opened by JiyueWang - 5
How to search the best temperature and alpha
#16 opened by TimeBear - 1
TFselftraining parameters in the paper ?
#14 opened by Shiro-LK - 6
questions about The two Tf-KD methods
#2 opened by pecanjk - 2
Pretrained model for student network
#15 opened by he-y - 2
- 2
- 1
It just feels like "炼丹"
#12 opened by ykk648 - 2
where's the paper?
#10 opened by vraivon - 0
a question about mobilenetv2
#8 opened by lansss - 0
- 2
- 5
Questions about KD loss
#5 opened by Paper99 - 1
- 3
Question about KD Regularization in code
#3 opened by GengZ