mmasana/FACIL

Issues

• How to integrate ViT in Networks?

  #46 opened 7 months ago by Snimm
  1

• Issue with ImageNet-Subset

  #45 opened 8 months ago by kandeldeepak46
  3

• How to adapt EWC and LWF for dynamic number of classes?

  #44 opened 8 months ago by appledora
  2

• GridSearch to find the accurate lambda value

  #43 opened a year ago by arnabphoenix
  1

• Unable to match the accuracy results present in the ANCL paper using FACIL framework

  #38 opened a year ago by arnabphoenix
  1

• HOW TO RUN THE FRAMEWORK ON IMAGENET DATASET?

  #40 opened a year ago by arnabphoenix
  1

• EEIL approach distillation loss

  #42 opened a year ago by jmin0530
  0

• Error coming while running on Imagenet Dataset

  #41 opened 2 years ago by sumitra009
  1

• LwM - no gradient in attention distillation loss

  #37 opened 2 years ago by fszatkowski
  5

• UNABLE TO MATCH THE ACCURACY RESULTS FOR CIFAR100 DATASET FOR LWF APPROACH

  #39 opened 2 years ago by arnabphoenix
  2

• Upperbound results

  #34 opened 2 years ago by jmin0530
  6

• LwF CIFAR-100 (10/10) No exemplars accuracy

  #36 opened 2 years ago by Yuki-Hong
  1

• accuracy

  #35 opened 2 years ago by tb626
  1

• I have an error in the file exemplars_selection it says no samples to choose from for class 240, how to fix this?

  #22 opened 2 years ago by nevasini
  1

• Trying to reproduce results in the paper

  #33 opened 2 years ago by rusonyo666
  1

• Conversion of saved trained models (at checkpoints)

  #30 opened 2 years ago by andreadaou
  2

• Varying the number of classes among the tasks

  #32 opened 2 years ago by andreadaou
  2

• Limit the number of images per class

  #31 opened 2 years ago by andreadaou
  2

• Adding a new dataset

  #29 opened 2 years ago by andreadaou
  2

• TaskID

  #24 opened 2 years ago by AndreGuerra123
  1

• Imagenet100

  #26 opened 2 years ago by zijGao
  4

• can not reproduce the similar result as paper

  #28 opened 2 years ago by wangsen1312
  2

• Unable to save models (--save-models: save trained models)

  #27 opened 2 years ago by andreadaou
  2

• There is a bug when running the code

  #25 opened 2 years ago by zhl98
  4

• Getting "RuntimeError: Expected object of scalar type Long but got scalar type Int for argument #2"

  #4 opened 3 years ago by snokh
  11

• The question of whether attention distillation loss in LwM can produce gradient.

  #9 opened 2 years ago by NUAA-XSF
  4

• The meaning of model_old is confusing. In task 1, the number of heads of model_old is sometimes 1 and sometimes 2 during def eval.

  #17 opened 3 years ago by XuMengyaAmy
  1

• Some question about the approach 'BiC'

  #16 opened 2 years ago by ZhenbangDu
  1

• could I omit the validation dataset?

  #19 opened 3 years ago by libo-huang
  6

• Some question About Task-Aware and Task-Agnostic metrics

  #18 opened 3 years ago by jumptiger66
  0

• The meaning of TAw & TAg

  #15 opened 3 years ago by Lllydialee
  2

• URL for `--approach` in your src/README.md

  #14 opened 3 years ago by letme-hj
  1

• AssertionError: Error: BiC needs exemplars.

  #13 opened 3 years ago by ChibisukeDragon
  2

• Results of iCaRL

  #12 opened 3 years ago by qsunyuan
  3

• How to understand the results?

  #11 opened 3 years ago by maawais
  4

• Error while trying to train on VGGFace2

  #10 opened 3 years ago by afonseca18
  5

• Is task-agnostic accuracy correct?

  #8 opened 3 years ago by ashok-arjun
  2

• gridsearch-tasks == -1 in args does not perform grid search

  #7 opened 3 years ago by ashok-arjun
  2

• Some questions about the reproduce results of LUCIR

  #6 opened 3 years ago by Kingofolk
  3

• The extensibility of the FACIL framework.

  #2 opened 3 years ago by Veagau
  1

• LUCIR in memoryless mode

  #3 opened 4 years ago by HabibSlim
  3