How to start contributing?

[jonathanBieler]

Something you can do is implement models from the literature, there’s a bunch here but you can probably find something missing (you need to be a bit acquainted with the domain though):

GitHub - FluxML/model-zoo: Please do not feed the models

You also have stuff like this:

Creating Parametric ReLU in Flux

I would like to create Parametric ReLU (PReLU), an activation function, that is described in [1502.01852] Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification I know I should use using Flux.Tracker but I am a bit lost. My major challenge here is that for each layer of the network I need the trainable parameter ‘a’ of PReLU to be shared across the activations in that layer. So if the network has say 10 layers, then only 10 scalar trainable parameters shou…

If that’s really useful (need to be tested) then it could be added to the libraries.

For optimization I think BlackBoxOptim doesn’t have a generic interface, there’s no good CMA-ES implementation (I’ve got one that works but it’s not as good as Python’s), and there’s probably plenty of little things one can do, but you need to be well informed about the packages (which comes by using them mainly, and reading the issues/PR).