Kaustubh Mani
Kaustubh Mani
Sorry for the late reply. You need to write a separate data loader for the NuScenes dataset in https://github.com/hbutsuak95/monolayout/blob/master/monolayout/datasets.py.
As suggested in the monolayout paper, we have made separate decoders for static and dynamic participants in a scene. But Lane estimation for example was solved as a multi-class classification...
The code has been written particularly with the MBBL benchmark in mind which only supports torch==1.4.0. I'll try making a separate branch for Pybullet, mujoco env and Duckietown.