tianyu0207/PEBAL

Issues

• Training results

  #34 opened a year ago by Porphy
  1

• How to continue my training

  #33 opened a year ago by Orange-rightperson
  6

• 离群点的像素是通过阈值筛选出来的吗？

  #25 opened 2 years ago by Runist
  3

• Training pebal with custom backbone model and dataset

  #26 opened 2 years ago by mei0824
  1

• Eq.3 logits or probabilities

  #30 opened 2 years ago by Yang-Li-2000
  1

• Doubt about Fishyscapes

  #31 opened 2 years ago by matteosodano
  4

• 数据集对不上

  #32 opened 2 years ago by tang576225574
  2

• can't get the good results on the FS datasets

  #15 opened 2 years ago by StarWanan
  10

• How to generate the city_scape dataset?

  #17 opened 2 years ago by aldipiroli
  6

• what is ood_seg_train2017

  #29 opened 2 years ago by Yang-Li-2000
  0

• Which deeplabv3+ checkpoint should I download?

  #28 opened 2 years ago by Yang-Li-2000
  1

• Having issues in model training

  #14 opened 2 years ago by yzpick
  6

• Fishyscape test result

  #27 opened 2 years ago by hyunjunChhoi
  1

• Cannot reproduce the paper result and checkpoint result

  #24 opened 2 years ago by hyunjunChhoi
  3

• RuntimeError: CUDA error: device-side assert triggered

  #23 opened 2 years ago by Runist
  3

• cannot reproduce the result on "Lost And Found testing set"

  #22 opened 2 years ago by DevinCheung
  1

• Typo of "WideResNet34"

  #21 opened 2 years ago by DevinCheung
  1

• EBM loss on D_out formula seems wrong

  #20 opened 2 years ago by luoyuchenmlcv
  1

• Confused about the PAL loss on the outlier pixels.

  #18 opened 2 years ago by gaozhitong
  5

• why larger aω means lower inlier free energy

  #19 opened 2 years ago by luoyuchenmlcv
  3

• What pixels are predicted as the extra class Y+1?

  #8 opened 2 years ago by zhd2rng
  7

• Is there a link to download the best checkpoints?

  #16 opened 2 years ago by laodar
  1

• data structure

  #13 opened 2 years ago by chaoqinhuang
  2

• Some question about paper

  #9 opened 2 years ago by jyang68sh
  4

• Train Custom Data

  #12 opened 2 years ago by lilin19890401
  1

• Question for Data prepration

  #11 opened 2 years ago by hyunjunChhoi
  1

• PAL loss question

  #10 opened 2 years ago by jyang68sh
  1

• dataset structure

  #1 opened 3 years ago by danielzhangau
  1

• Can you offer the fishyscapes and coco (for outlier exposures) datasets baidu netdisk for training?

  #7 opened 2 years ago by liuxubit
  3

• inlier vs outlier

  #6 opened 2 years ago by jyang68sh
  4

• How to get result of Initial Prediction and Final Prediction?

  #5 opened 3 years ago by Matt-Dinh
  2

• Inference on input image

  #3 opened 3 years ago by MoaazAbdulrahman
  5

• Some more guide to data preperation?

  #4 opened 3 years ago by imesu2378
  2

• training script

  #2 opened 3 years ago by zhuyifan1993
  1