Closed sinsin1998 closed 1 year ago
Our method trains for two stages. In the first stage, we train a pure lidar-only backbone exactly the same as TransFusion-L. In the second stage, we add the camera branch for multi-modal training. The whole training process can be done on 8 RTX 3090 (24G mem) GPUs. The whole training procedure costs about 3-4 days.
Code has been released, you can try to run it on your machine.
Could you provide the information above? Such that i can tell whether if can run on my machine? Thanks a lot..