ContinualAI/clvision-challenge-2022

Issues

• Detection test set all instances have "category_id": 2, "instance_id": "unlabeled"

  #4 opened 3 years ago by zhoujuncc1
  5

• Can we use multiple GPUs in training ? or we must use one GPU (RTX 5000 with 16G GPU-memory)?

  #17 opened 3 years ago by Layjins
  3

• If Using multiple accounts on CodaLab, but the overall number of submissions are less than 20, is ok?

  #20 opened 3 years ago by Layjins
  0

• Can we add augmentation transforms to the eval transformations?

  #19 opened 3 years ago by yi94code
  2

• Track1: Could you release the upper-bound performance(average mAP) during each experience?

  #15 opened 3 years ago by ppppeng
  3

• Can you provide the evaluation server (RTX 5000 with 16G GPU-memory)?

  #18 opened 3 years ago by Layjins
  0

• Cannot iterate all data streams in one epoch.

  #16 opened 3 years ago by ifoyooo
  1

• #track 2: 'Solutions can exploit a replay buffer containing data coming from up to 3500 training instances.' For example, in task1, can we randomly sample 3500 images from the full training set (ego_objects_challenge_train.json)?

  #13 opened 3 years ago by Layjins
  2

• #track 2: can you release the upper-bound performance of task1-task5? The test set contains 277 categories, while the training set of task1 only has 159 categories, then the upper-bound of task1 is?

  #12 opened 3 years ago by Layjins
  2

• can you provide a result file JSON format?

  #10 opened 3 years ago by nicehuster
  3

• Track3 baseline doesn't work correctly

  #14 opened 3 years ago by ppppeng
  1

• can you release the metrics of task1-task5 in leadboard?

  #11 opened 3 years ago by nicehuster
  2

• Track2 Submission Problem: AttributeError: 'list' object has no attribute 'items'

  #9 opened 3 years ago by Millielele
  2

• mandatory metric only generate output of 1 json file for last experience

  #8 opened 3 years ago by zhoujuncc1
  1

• Why track2 demo results AP seems strange?

  #7 opened 3 years ago by Millielele
  4

• What's this repo actually for?

  #6 opened 3 years ago by Klawens
  1

• training set of object detection containing bboxes of 0 area

  #3 opened 3 years ago by zhoujuncc1
  4

• the challenge dataset download failed.

  #5 opened 3 years ago by nicehuster
  0

• Different classes in train/test experiences

  #2 opened 3 years ago by dentou
  0

• where is the examples.tvdetection.transforms

  #1 opened 3 years ago by WEIZHIHONG720
  0