XuyangBai / TransFusion

[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496
Apache License 2.0
642 stars 77 forks source link

why training time is so long #31

Closed AndyYuan96 closed 2 years ago

AndyYuan96 commented 2 years ago

Hi, thanks for sharing the code, I use 8 v100, without changing config file, for pillar_L.py config, it need 1day and 4hours to finish training, and data_time is almost zero。does the time is normal?

XuyangBai commented 2 years ago

It is normal.

AndyYuan96 commented 2 years ago

It is normal.

Ok,thank you.