Open dnabanita7 opened 2 years ago
I think that would be something we can support. There's some efforts to get datasets standardised as well so that should help with some of the models being replaced. we can come up with a plan to move the structure to accommodate the MLPack and MLCommons structure
For FluxBench, Can I suggest of having a structure like mlpack benchmarks. I really like how they are using valgrind for memory benchmarks and profiling, sqlite to store results, etc. The comparison amongst other ML libraries provides a better depiction of Flux and why to use Flux over other libraries.