Skip to content

Latest commit

 

History

History
16 lines (12 loc) · 971 Bytes

README.md

File metadata and controls

16 lines (12 loc) · 971 Bytes
Raw

VITA_reproduction

A code reproduction of VITA.

Installation

  1. see Mask2Former
  2. see IFC
  3. The Datasets need to be placed up the root of detertrons as follows ：catalogue_desc
  4. You need to add the YouTubeVIS 2019 model weight of Mask2Former about Video Instance Segmentation to the weights folder as for a pre-training model.

Note

  • Based on detectron2.
  • The codes are under projects/ folder, which follows the convention of detectron2.
  • You can easily import our project to the latest detectron2 by following below.
  • inserting VITA_1 folder