huanglianghua/GlobalTrack

COCO 、LaSOT、GOT10K preprocess

cifar10 opened this issue · 2 comments

Thank you for the author's code. Do we need to preprocess the coco, LaSOT, GOT10K data when reproducing the code ourselves, or just put it in the corresponding folder?

Hi, you don't need to preprocess the data. Just download and extract them, and specify the paths in the code.

For example, the extract dataset structure would be like:

- ./data
  - GOT-10k
    - train
    - val
    - test
  - LaSOTBenchmark
  - coco
    - train2017
    - val2017
    - annotations

Get it ,thank you very much