lenscloth/RKD

Issues

• dataset link don't work

  #24 opened 6 months ago by Zhongwei-Luo
  0

• Cifar 100 and Tiny Imagenet Training

  #11 opened 5 years ago by fruffy
  3

• What is its value equal to opts.dark_ratio

  #23 opened 3 years ago by eeric
  0

• the calculation of relation

  #22 opened 3 years ago by YIBO-0805
  0

• What are the numbers in the student and teacher tensors?

  #21 opened 3 years ago by alexzhang0825
  0

• Student accuracy way below expected

  #18 opened 3 years ago by alexzhang0825
  12

• test_set and train_set's lengths mismatch with those based on README from the dataset

  #20 opened 3 years ago by alexzhang0825
  3

• Eval vs Train

  #19 opened 3 years ago by alexzhang0825
  1

• EOFError: Ran out of Input

  #17 opened 4 years ago by alexzhang0825
  0

• in loss design , is the code " torch.no_grad " essential ?

  #16 opened 4 years ago by leoluopy
  1

• A question about recall

  #15 opened 4 years ago by Youskrpig
  2

• Hi, there is a similar idea in <<Correlation Congruence for Knowledge Distillation arXiv:1904.01802v1>>. Do you think which is more efficent ?

  #13 opened 5 years ago by ZHAIXINGZHAIYUE
  1

• Few-shot learning experiments

  #14 opened 4 years ago by SebGGruber
  0

• A question about paper setting

  #9 opened 5 years ago by baek85
  1

• Can you release your trained model on cub200 ?

  #8 opened 5 years ago by UnrealPawn
  1

• torch type may not matching in pytorch==1.2

  #7 opened 5 years ago by UnrealPawn
  1

• Do you have any suggestions on how to choice the loss ratio of different distill methods?

  #6 opened 5 years ago by oxygenman
  4

• Hi，could you release the cifar-100 classification experiment?

  #5 opened 5 years ago by oxygenman
  2

• can't run the "run_distill.py"

  #4 opened 5 years ago by oxygenman
  3

• metric/utils.py

  #3 opened 5 years ago by ivylinden
  2

• Ask about your model ResNet50 model??

  #2 opened 5 years ago by littlesnowperfume
  0