Keras: weighted binary crossentropy

Question

I tried to implement a weighted binary crossentropy with Keras, but I am not sure if the code is correct. The training output seems to be a bit confusing. After a few epochs I j

Answer 1

I think using class weight in model.fit is not correct. {0：0.11， 1：0.89}, 0 here is the index, not the 0 class. Keras Documentation: https://keras.io/models/sequential/ class_weight: Optional dictionary mapping class indices (integers) to a weight (float) value, used for weighting the loss function (during training only). This can be useful to tell the model to "pay more attention" to samples from an under-represented class.