search

Luoyadan / CRB-active-3Ddet

The official PyTorch implementation of "Exploring Active 3D Object Detection from a Generalization Perspective" (ICLR Spotlight 2023).
Apache License 2.0
54 stars 7 forks source link

【Reproduce Experiment】How to reproduce experimental results in the paper #8

Closed Coolshanlan closed 11 months ago

Coolshanlan commented 1 year ago

I use your default yaml file to train different strategy models, but the results presented are far from the paper experiment. What should I do to have a similar result as in the paper?

I only set USE_ROAD_PLANE to False in yaml

The following are the results of my experiment: image image

Thanks

zhuoxiao-chen commented 1 year ago

Hi,

Your reproduced performance of all methods is very low, which is strange. Have you tried setting USE_ROAD_PLANE to True? According to https://github.com/open-mmlab/OpenPCDet/issues/619, performance seems to improve a lot when USE_ROAD_PLANE is set to True.

Regards, Ivan