search

OreoChocolate / MUREN

The official code for Relational Context Learning for Human-Object Interaction Detection, CVPR2023.
http://cvlab.postech.ac.kr/research/MUREN/
48 stars 5 forks source link

bbox formats #10

Open anjugopinath opened 6 months ago

anjugopinath commented 6 months ago

Hi,

I wanted to use your code to train on a custom dataset. What is the expected bbox format ? And should it be normalized before loading the data for training?

OreoChocolate commented 2 months ago

I apologize for the delayed response, and thank you for your patience. The expected bounding box format for the code is xywh (x-center, y-center, width, height). Please ensure that the bounding boxes are normalized before loading the data for training, meaning the coordinates and dimensions should be scaled between 0 and 1 relative to the image size.

If you have any further questions or need more details, feel free to reach out!