search

bradyz / cross_view_transformers

Cross-view Transformers for real-time Map-view Semantic Segmentation (CVPR 2022 Oral)
MIT License
531 stars 81 forks source link

Scripts to generate the labels #3

Closed DerrickXuNu closed 2 years ago

DerrickXuNu commented 2 years ago

Hi Brady,

Thanks for your great work and clean coding style! I am wondering do you still have the scripts to generate the cvt_labels_nuscenes? If so, would you be willing to share it? Look forward to your reply.

bradyz commented 2 years ago

flattered by your kind words :)

i've included a short readme on how to generate the labels, but please follow up here if you run into trouble so I can improve the docs

Also, if you have a fast enough machine, with a little bit of code changes you could make the experiments render the labels on the fly, let me know if you are interested in this

DerrickXuNu commented 2 years ago

Thanks for your quick reply! I do have some fast machine, I'd appreciate it if you could show me how to render the labels during runtime.

GoroYeh56 commented 1 year ago

Hi, I want to ask a follow-up here:

In the generate_data.py, how should we change so that it will generate labels that segment 11 classes?