Hyperactive – Easy Neural Architecture Search for Deep Learning in Python (github.com)

6 comments

[ 3.4 ms ] story [ 28.7 ms ] thread

Check out the Neural Architecture Search Tutorial here: https://nbviewer.jupyter.org/github/SimonBlanke/hyperactive-...

Neural Architecture Search is just one of many optimization applications you can work on with Hyperactive. Check out the examples in the official github repository: https://github.com/SimonBlanke/Hyperactive/tree/master/examp...

superfreek 5y ago ↗

Looks very promising! I like that you can fill the search space with python objects. Is it possible to search through numpy arrays? This would be nice for feature selection.

simonblanke 5y ago ↗

Thank you very much :-) yes you can put anything you want into the search space. Even pandas dataframes, numpy arrays or classes. Here is an example: https://github.com/SimonBlanke/Hyperactive/blob/master/examp...

JoeCoo7 5y ago ↗

Interesting approach to nas. Can this package do optimization with the hyperband algorithm?

simonblanke 5y ago ↗

I am glad you like it. Hyperband relies on early stopping of the model. So it is something you would do inside the objective function by yourself. I have plans to add some helper functions for early stopping in the future.

Avernar 5y ago ↗

Looks very nice! Does it support multi gpu training during the search?