Understanding Class Weights

Using class weights, you make the classifier aware of how to treat the various classes in the cost function.

In this process, you give higher weights to certain classes & lower weights to other classes.

from sklearn.utils.class_weight import compute_class_weight
class_weights = compute_class_weight('balanced', np.unique(y), y)

In Keras, class_weight parameter in the fit() is commonly used to adjust such setting.

You can also use the following format,

class_weight = {0: 1.,
                1: 50.,
                2: 2.}

In the above statement, every one instance of class 1 would be equivalent of 50 instances of class 0 & 25 instances of class 2.

Then pass either the sklearn's class_weights or the dictionary method class weights in the fit() function as a parameter for model training.