You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Currently I want to build a custom objective for my imageclassification model. The objective does not only depend on the predictions and validations, but also some characteristics of the network itself. I know you can build a custom objective using kerastuner.objective, yet this one only works for y_true and y_pred (https://autokeras.com/tutorial/faq/). This is why I started looking into the kerastuner hypermodel (https://keras.io/guides/keras_tuner/getting_started/). However, I've not seen kt.hypermodel used in combination with autokeras.
Does anyone know how to do this or any tips?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Currently I want to build a custom objective for my imageclassification model. The objective does not only depend on the predictions and validations, but also some characteristics of the network itself. I know you can build a custom objective using kerastuner.objective, yet this one only works for y_true and y_pred (https://autokeras.com/tutorial/faq/). This is why I started looking into the kerastuner hypermodel (https://keras.io/guides/keras_tuner/getting_started/). However, I've not seen kt.hypermodel used in combination with autokeras.
Does anyone know how to do this or any tips?
Beta Was this translation helpful? Give feedback.
All reactions