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

Is it a typo? #27

Closed amiltonwong closed 1 year ago

amiltonwong commented 2 years ago

Hi, @nmwsharp,

From the experiment in functional correspondences, is there a typo in the last line command in README.md? Should it be : python functional_correspondence.py --test_dataset=faust --input_features=xyz --load_model=pretrainedmodels/faustxyz.pth or python functional_correspondence.py --test_dataset=faust --input_features=hks --load_model=pretrainedmodels/fausthks.pth

pvnieo commented 1 year ago

Hi @amiltonwong Yes, it's a typo, you either use xyz features with the faust_xyz.pth model or the hks features with the faust_hks.pth model. Thank you for noticing it, I'll correct it soon!