search

Owen-Liuyuxuan / visualDet3D

Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving / YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
https://owen-liuyuxuan.github.io/papers_reading_sharing.github.io/3dDetection/GroundAwareConvultion/
Apache License 2.0
362 stars 77 forks source link

AP #30

Open Yongsz opened 2 years ago

Yongsz commented 2 years ago

Hello, author, when reproducing the code, I got the following results with regard to the evaluation indicators in simple, medium, and difficult cases. Why does the detection result on pedestrians appear to have higher evaluation indicators in simple cases? , Hope to get your answer, thank you. 1628065250787

Owen-Liuyuxuan commented 2 years ago

This model seems trained on the "test_split" -> that is going to submit to the website? If you want to reproduce the validation result, you should train on the "chen_split".

https://github.com/Owen-Liuyuxuan/visualDet3D/blob/master/config/Yolo3D_example#L84