sukjunhwang/VITA

Issues

• About "Maximum number of frames" in Table 4.

  #16 opened a month ago by ruohaoguo
  0

• OVIS Dataset Error

  #11 opened a year ago by 1787594808
  6

• How to get the train.json, val.json of ytvis_2021?

  #4 opened 2 years ago by xjtuwh
  8

• self.training when calling swin attention in object encoder

  #15 opened 10 months ago by bio-mlhui
  4

• about data preparation

  #14 opened a year ago by chen742
  2

• Demo

  #9 opened 2 years ago by assia855
  2

• Dear author, I did not find the fps data of VITA in your paper. Can you tell us the fps in different sizes?

  #8 opened 2 years ago by hekaijie123
  2

• Error in detectron2

  #7 opened a year ago by fanghaook
  4

• Dateset prepare

  #13 opened a year ago by ChinChyi
  1

• ytvis_2019 submit error

  #12 opened a year ago by nanle771
  2

• COCO pretrained weight

  #10 opened a year ago by fanghaook
  4

• Some training details.

  #6 opened 2 years ago by KainingYing
  9

• How to use multiple GPUs for inference?

  #5 opened 2 years ago by xjtuwh
  6

• How to get the AP for youtube_vis?

  #3 opened 2 years ago by xjtuwh
  2

• how to visualize the segmentation result and generate the bitmask png for trained model?

  #2 opened 2 years ago by f414158949
  2

• Looking forward to your excellent work open source.

  #1 opened 2 years ago by NingYuanxiang
  4