Nicholas Sharp

Awesome! Thank you for writing up your progress already, I'm sure this will be super helpful for folks. It would be awesome to add a page on the docs with...

If you're up to it, the most actionable thing to do is to try cloning & building the C++ library in debug mode and running unit tests in your CI...

Hi! Thanks for following up on this again. This is indeed a very important issue, though it has eluded me every time I've tried to dig in! A quick note:...

I will try to set up a reproducing case on my end soon and dig deep, but I don't have time immediately! Any info you can share here will only...

Actually, in the current version of Polyscope, we use `glm::vec3` everywhere, which means float precision. Perhaps we should switch to double?

Hi! Thank you for the pull request. This seems reasonable, though can you add a default version so that existing code that just calls `getVertexPositions()` still works? Perhaps something like:...

Hi! This sounds like a really awesome problem, and one that DiffusionNet should be well-suited for, I'm happy to try to help out. I'm surprised to hear that DiffusionNet isn't...

Also, are your classes balanced? (E.g. roughly 50/50 distribution?) If it's very unbalanced, sometimes networks get trapped in a local minimum where they prefer majority. If so, re-weighting the examples...

> hyperparameters The settings you're using sound reasonable to me. Indeed this code is configured for batch size of 1 (so a `None` in the dataloader). The main hyperparameter that...

Awesome, thanks for sharing these results! Just to double-check, when you say normalizing do you mean centering/unit-scaling shapes before processing? If so what you say makes sense, it has also...