[vip-help] Request for advice regarding Hyperparameter Optimization of GAN models

[Chen, Alain]

Hi,

You should try to implement it from scratch if you can. We aren't familiar with that library you mentioned so we can't help too much about that part. Have you found any read some papers on how this is usually done?

Thanks,


*****
Alain Chen
Ph.D. Student
Research Assistant
Video and Image Processing Laboratory (VIPER)
School of Electrical and Computer Engineering
Purdue University
465 Northwestern Avenue
West Lafayette, IN 47907-2035
U.S.A.
email: chen2967 at purdue.edu
URL: <http://engineering.purdue.edu/~aparrapo> https://skynet.ecn.purdue.edu/~chen2967/

VIPER Lab Telephone: +1 765 494 3351
*****
________________________________
From: vip-help <vip-help-bounces at ecn.purdue.edu> on behalf of Gurung, Kris <kgurung at purdue.edu>
Sent: Sunday, February 4, 2024 8:38:00 PM
To: vip-help at ecn.purdue.edu <vip-help at ecn.purdue.edu>
Subject: [vip-help] Request for advice regarding Hyperparameter Optimization of GAN models

Some people who received this message don't often get email from kgurung at purdue.edu. Learn why this is important<https://aka.ms/LearnAboutSenderIdentification>
Hi,

I am currently trying to optimize the hyperparameters of our model, and plan to implement Bayesian Optimization to do so. Are we allowed to use libraries/frameworks to do so, or are we required to implement it from scratch? Also, would Optuna be a good and easy-to-use framework for hyperparameter optimization? Any advice regarding hyperparameter optimization (or good practices) or/and it's implementation would be greatly appreciated, as I don't have any prior experience. Thank you!

Regards,
Kris Gurung
-------------- next part --------------
An HTML attachment was scrubbed...
URL: </ECN/mailman/archives/vip-help/attachments/20240205/2bb5c4cb/attachment-0001.htm>