search

TiagoCortinhal / SalsaNext

Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
MIT License
417 stars 102 forks source link

About Number of Parameters and FLOPs #17

Closed iris0329 closed 4 years ago

iris0329 commented 4 years ago

Thank you for opening the source code of this briliant work!

The values of Number of Parameters and FLOPs are shown in the paper.

I'm curious how do you calculate these two values? Which tools/packages do you use for calculation?

Best, Iris

TiagoCortinhal commented 4 years ago

Hello @iris0329!

For the Number of Parameters we used the built-in functions of Pytorch like so: sum(p.numel() for p in model.parameters() if p.requires_grad)

For the FLOPs we used this package: https://github.com/sovrasov/flops-counter.pytorch

Best, Tiago

iris0329 commented 4 years ago

@TiagoCortinhal Thank you for your generous reply！