Epiphqny / VisTR

[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
https://arxiv.org/abs/2011.14503
Apache License 2.0
739 stars 95 forks source link

category_id #25

Closed CuckooHXY closed 3 years ago

CuckooHXY commented 3 years ago

I notice that your category_id is from 0 to 39,while masktrackrcnn is from 1 to 40.It confuses me. I inference the validation set with the weight you trained,and delete all the results with "category_id"=0 in the results.json.But the score doesn't change.Could you please tell me why?

Epiphqny commented 3 years ago

Hi @CuckooHXY, this is the same issue as https://github.com/Epiphqny/VisTR/issues/11, I am fixing this bug, and the result improves. I will update the code and result later.

Epiphqny commented 3 years ago

Hi @CuckooHXY, I have fixed the bug and updated the code and result.