Tuning hyper-parameters with bayesian optimization

(Renato Hermoza) #1

Hi guys, I found this awesome library scikit-optimize that helps a lot for doing bayesian optimization and made some notebooks while trying it here.

1 Like

(dinesh) #2

Hii can we replicate the same for tuning hyper-parameters in fastai library?

0 Likes

(Zachary Mueller) #3

Absolutely! I’ve played around with it myself. This is the library:

So long as you set the hyperparameters to your choosing, just fit the training loop you want to run in it, and you’re off to the races. If you are confused I can show a notebook.

0 Likes

(dinesh) #4

Hey, Please share the notebook in which you did the same with fastai library. I am new to the library. Thanks in advance!

0 Likes

(Zachary Mueller) #5

Sure, give me a moment to clean up the notebook.

1 Like

(Zachary Mueller) #6

@msrdinesh here is a notebook. It is very basic, I just use the tabular problem as an example. Anything you want changed/optimized you do within the fit_with function. If you say wanted to mess with image sizes, make the databunch in the fit_with and have the image size as a hyperparameter. Let me know any questions!

1 Like

(dinesh) #7

Thankyou @muellerzr.

0 Likes