ValueError: None values not supported.

[woreom]

when you run the train_softmax.py first it raises categorical_feature is not define then when you fix it with columntransformer, it raises ValueError

[woreom]

you have to change the optimizer in the model in order to fix this problem

[haivmptit]

you have to change the optimizer in the model in order to fix this problem

Hi you, can you tell me How to change, please ?

[woreom]

I think I meant sth like this in softmax.py

optimizer = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False)
        model.compile(loss=keras.losses.categorical_crossentropy,
                      optimizer=optimizer,
                      metrics=['accuracy'])