A modern programming language that makes developers happier.

kotlinlang

Hello, does KotlinDL have something similar to PyTorch funftional API for stateless operations (eg: Softmax, Sigmoid)? Would be nice to have it expect a Multik ndarray

• It has some activation layers like `ELU`, `LeakyReLU`, `PReLU`, `ReLU`, `Softmax`, `ThresholdedReLU`;
`ActivationLayer` but probably it's not related to the expecting Multik ndarray. Could you give some inspiration about the task or use-case?

Ok, well if it expects a float Array it's still easy to go from Multik to float array.

Our use case is we perform some score smoothing during inference while performing inference on multiple samples of a pointcloud.

We use softmax in the smoothing formula. We implemented softmax but was wondering if KotlinDL already had an implementation

I suppose it has somewhere like a helper function in Kotlin and as a activation layer for Keras compatibility, but in both cases it is not what you want.

Ok, all good I was just curious, it's not that big of a deal we'll keep our implementation since these functions are simple and easy to implement anyways.
Thanks for letting me know