SxJyJay / MSMDFusion

[CVPR 2023] MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection
Apache License 2.0
184 stars 11 forks source link

nuScenes validation set detection result #46

Open coderookieqi opened 3 months ago

coderookieqi commented 3 months ago

Hello, I am a student working on 3D Multi-Object Tracking. I would like to use your method as the detector for our tracking algorithm, but we need to debug it offline. May I ask if you could open-source the detection results on the nuScenes validation set?

Libraaer commented 2 months ago

Hello, I am a student working on 3D Multi-Object Tracking. I would like to use your method as the detector for our tracking algorithm, but we need to debug it offline. May I ask if you could open-source the detection results on the nuScenes validation set?

Hello, have you trained this model? I'm using A800 here but still not enough to train. If you've trained, can you give me an answer to the reason for my lack of memory here, thank you

SxJyJay commented 2 months ago

Hello, I am a student working on 3D Multi-Object Tracking. I would like to use your method as the detector for our tracking algorithm, but we need to debug it offline. May I ask if you could open-source the detection results on the nuScenes validation set?

Thanks for your interest in our work. You can generate the result file of detection results on val set by loading the provided checkpoint and inferring on the val set.

SxJyJay commented 2 months ago

Hello, I am a student working on 3D Multi-Object Tracking. I would like to use your method as the detector for our tracking algorithm, but we need to debug it offline. May I ask if you could open-source the detection results on the nuScenes validation set?

Hello, have you trained this model? I'm using A800 here but still not enough to train. If you've trained, can you give me an answer to the reason for my lack of memory here, thank you

Can you provide the specific error information? It is not normal that A800 cannot accommodate MSMDFusion training.