mihirparadkar
mihirparadkar
Why are the matrix and vector types separate depending on the value they contain? (i.e. `Matrix32[M, N]` and `Matrix64[M, N]` instead of `Matrix[M, N, T]`) ? Since the implementations of...
I'm trying to build this library so that I can link it to rocBLAS and have a functioning gemm implementation in HIP (similarly to [this PR](https://github.com/ROCmSoftwarePlatform/rocRAND/pull/116)) for gfx1010/gfx1012. I saw...
AFAIK, only python currently supports tensorflow eager execution. This would make prototyping and designing dynamic graphs much easier, and would really leverage Julia's strengths in low-overhead loops and function calls.
Right now LowRankModels implements an OrdinalHingeLoss which is related to the HingeLoss. However, as we port the losses over to LossFunctions, I was thinking that this ordinalization is not unique...
I think it's worth it to move the implementations of loss functions from here to LossFunctions.jl. This package has a lot of the multivariate and ordinal losses lacking in that...
**Short Description** Single-Image Super-Resolution describes the domain of enhancing image resolution for single images (as opposed to groups of images of a scene, for example). Solutions in this domain have...
Similarly to https://github.com/JuliaML/LossFunctions.jl/issues/86 I think merging some of the regularizers (such as NonNegConstraint and KSparseConstraint) could be useful in making this package more full-featured and generally useful (like the prox!...