Julian Knodt
Julian Knodt
This starts adding terms into chalk so that associated consts can be equated.
By switching to []byte, it allows for arbitrary length addresses with a single API. Notably, it should allow for IPv6 and also naturally unifies with the type alias for IP:...
## Summary I was wondering if there was a way to add a differentiable `Vector3f` in `put_parameter`. When I add it to the list of parameters, it appears that it...
Starting to implement `ty::ConstKind::Abstract`, most of the match cases are stubbed out, some I was unsure what to add, others I didn't want to add until a more complete implementation...
I have been meaning to make this for quite a while, based off of this [hackmd](https://hackmd.io/@ft4bxUsFT5CEUBmRKYHr7w/rJM8BBPzD). I'm not sure where to put this opt now that I've made it, so...
Hey, this is really cool work on dynamic modeling. I was trying to reproduce the paper and found that I got significantly worse results than your reported values. I was...
When operating on meshes, I found that I wanted to normalize it based on the center of the volume, as similar looking meshes may have different concentrations of points, and...
I would like to have an external hyperparameter file, likely JSON which is read from for each of the hyperparameters in a lot of the models. I think I'm pretty...
I've not really had the chance to check if DataParallel works for multiple GPUs, so getting that to work would be fantastic.
Currently, it only uses a single level of NeRF with no refinement. It would be good to add in the refined model from the original paper using inverse sampling.