hanoonaR/object-centric-ovd

Issues

• How to Fine-tune？

  #23 opened 5 months ago by sixone-Jiang
  0

• open-vocabulary object detection with MViT

  #24 opened 5 months ago by fushh
  1

• In any case, I can`t detect "person" by your model

  #22 opened 10 months ago by sixone-Jiang
  0

• Failed to run the training for `LVIS_OVD_Base_PIS` config

  #21 opened a year ago by dongwhfdyer
  0

• Questions about pseudo label in training with detection data.

  #19 opened a year ago by Edwardmark
  4

• segmentation fault when training COCO_OVD_base_PIS.yaml

  #18 opened a year ago by haixpham
  0

• Reproduce the cross-dataset evaluation

  #20 opened a year ago by tmp12316
  1

• Questions about the results

  #13 opened 2 years ago by th0214
  2

• Issues about ImageNet-21K

  #15 opened a year ago by gugite
  2

• query about the clip classification acc using gt boxes in Object-centric

  #12 opened a year ago by motoight
  7

• Change Batch-size per GPU

  #11 opened 2 years ago by th0214
  1

• Is there some difference in the baseline between Yours and PromptDet

  #14 opened a year ago by xushilin1
  1

• Open images weights

  #17 opened a year ago by ma-siddiqui
  1

• Results for 4x schedule on LVIS?

  #16 opened a year ago by Kyfafyd
  1

• A question about the results of Open-vocabulary COCO

  #10 opened 2 years ago by SCUTjinchengli
  4

• Using your pretrained models for ZSD on custom objects and images

  #8 opened 2 years ago by Ozziko
  1

• JSONDecodeError

  #7 opened 2 years ago by Millielele
  4

• Question about MViT pre-training.

  #6 opened 2 years ago by YifanXu74
  0

• Missing lvis_v1_train_norare_cat_info.json

  #3 opened 2 years ago by ma-siddiqui
  2

• Error during class-specific IN-21K proposal generation for LVIS

  #5 opened 2 years ago by muzairkhattak
  0

• Missing coco_props.tar.gz

  #4 opened 2 years ago by hq-deng
  2