Hyperactive – Easy Neural Architecture Search for Deep Learning in Python

Y	Hacker News new \| ask \| show \| jobs

	Hyperactive – Easy Neural Architecture Search for Deep Learning in Python (github.com)
	13 points by simonblanke 1919 days ago

4 comments

simonblanke 1919 days ago

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...

link

JoeCoo7 1919 days ago

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

link

simonblanke 1919 days 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.

link

superfreek 1919 days 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.

link

simonblanke 1919 days 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...

link

Avernar 1919 days ago

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

link