Ensure class balanced batches while hyperparameter tuning keras models with grid search

Ensuring class balanced batches while training keras models is possible using fit_generator method. I used imblearn.keras.BalancedBatchGenerator for that and it works fine!

But i wanted to do that with GridSearchCV to fine-tune my model, so i created an inherited class KerasBatchClassifier(KerasClassifier) as a Keras Wrapper for the Scikit-Learn API. (Inspired by this StackOverflow question)

Ensuring class balanced batches to fit the model is working, but i haven’t figured out how to do it with validation data ! Any ideas to do that ?