search

strongwolf / o2f

One-to-Few Label Assignment for End-to-End Dense Detection (CVPR2023)
Apache License 2.0
40 stars 3 forks source link

When I inference CrowdHuman, there was an error here #3

Closed GarlicPineapple closed 1 year ago

GarlicPineapple commented 1 year ago

'hbox':res['bbox_vis'], # here is wrong, but no matter error image I want to know how can I inference this, thanks

strongwolf commented 1 year ago

I think this is due to your dataset since this code is OK for me. You can change this line to 'hbox':res['bbox'], and try again.

GarlicPineapple commented 1 year ago

My problem has been resolved, perhaps there was an error when I converted odgt to json, thanks