In general, KerasTuner enables to easily tune things like your data augmentation config, your optimizer config, your learning rate decay schedule, etc. It's not just for the model architecture itself
Show this thread
A very simple Kaggle notebook that shows how to use KerasTuner to automatically find a high-performing model: https://www.kaggle.com/fchollet/keras-kerastuner-best-practices/ … Includes finding the best image augmentation config as part of the parameter search (this is actually one of the most important things to tune)pic.twitter.com/pasgIGHVx5
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Is there a typo in the code? Should it not be "zoom_factor" instead of "use_zoom" as the last hyperparameter?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is a really nice example, thanks for sharing. There was a bug in the code though - the test data loader did not work properly. I have forked it and re-run it in its entirety, with the correct submission file:https://www.kaggle.com/tunguz/keras-kerastuner-best-practices?scriptVersionId=40986999 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.