Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
I am training a DNN with CNN in Keras. Though, I can write an EarlyStopping criteria based on val_loss but due to minor oscillations in the val_loss, I want to monitor the average validation loss over last n epoches and with n patience.
How can I do this in Keras?
You can always write a custom callback inheriting the tf.keras.callbacks.Callback() class. You would need to override the on_epoch_end() method with your custom logic.
