So far I have only really scratch built backprop. And had severe performance problems with Burn trying to do something it probably wasn’t built to do. Once I get further in makemore I should have a better idea.
So far I have only really scratch built backprop. And had severe performance problems with Burn trying to do something it probably wasn’t built to do. Once I get further in makemore I should have a better idea.
Been working through Andrej Karpathy’s ML lectures in Rust. The backprop one went pretty well, but I had to learn how to do type indirection and interior mutabilty because of the backprop graph structure. I’m now on the makemore lecture, but having a lot of trouble building the bi-gram model in Burn (the rust native ML framework), because it seems like directly incrementing the tensor values is insanely slow. His example that takes like 10 seconds to run in Python takes two and a half minutes in Rust with Burn, so trying to figure out how to optimize or speed that up.
you are missing a couple things here, both twitter and mastodon allow following “topics” in that you can follow hashtags.
additionally you can federate more content from other instances that no one follows by connecting to a relay.
not saying this entirely fixes the problems you bring up just that there are ways to somewhat address them.
Rust is named after the fungus, not oxidized metal