search

prs-eth / PCAccumulation

[ECCV 2022] Dynamic 3D Scene Analysis by Point Cloud Accumulation
https://shengyuh.github.io/pcaccumulation/index.html
MIT License
120 stars 10 forks source link

About model training and other datasets preprocessing #9

Closed pppjunseo closed 1 year ago

pppjunseo commented 1 year ago

Hi. Thank you for your wonderful work. I am a student who is interested in your method. I have three questions.

  1. python main.py configs/nuscene/nuscene.yaml 10 1 --misc.mode=train --path.dataset_base_local=$MY_DATASET_FOLDER I trained the model like this code, what does 10 and 1 mean here?
  2. Is it possible to train with datasets such as KITTI? If possible, how to preprocess datasets?
  3. How to visualize the mapping results?

I look forward to hearing from you soon.