search

nmwsharp / diffusion-net

Pytorch implementation of DiffusionNet for fast and robust learning on 3D surfaces like meshes or point clouds.
https://arxiv.org/abs/2012.00888
MIT License
398 stars 50 forks source link

Unjustified cache miss #33

Open ilayshvo opened 9 months ago

ilayshvo commented 9 months ago

Hello,

I noticed a miss in my environment due to precision differences.

The cache is usually saved as float32 but when compared with the found cache the vertices are not converted to float32.

I also fixed it locally and could create a PR.