search

pqhieu / jsis3d

[CVPR'19] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds
https://pqhieu.com/research/cvpr19/
MIT License
175 stars 36 forks source link

about plot.py #13

Closed zhangmenghan closed 4 years ago

zhangmenghan commented 4 years ago

Hello, I want to execute plot.py to check the result, and the parameter "metric" has reported an error. I would like to ask you what the parameter "metric" means and what the default value you set is. Thank you.

pqhieu commented 4 years ago

The --metric flag is to determine which metric you want to plot. Possible values are accuracy, IoU, precision, and recall.

zhangmenghan commented 4 years ago

I would also like to ask you about how you did the visualization after the segmentation of the scene, thank you

pqhieu commented 4 years ago

I use my inhouse visualizer. There's a visualization flag in eval.py, you can use that to save the point clouds to .ply files and use MeshLab to view. However, you need to implement color mapping before saving to see semantic/instance segmentation.

zhangmenghan commented 4 years ago

Thank you for your reply very much

longmalongma commented 4 years ago

color mapping

Hello,how to implement color mapping before saving to see semantic segmentation?have you implemented color mapping in your code?

longmalongma commented 4 years ago

Thank you for your reply very much

Hello,do you implement color mapping?can you provide code about color mapping?looking forward your reply.