How to use advanced activation layers in Keras?

Question

I am working on the following code: model = Sequential() a = keras.layers.advanced_activations.PReLU(init='zero', weights=None) model.add(Dense(64, input_dim=14, init='uniform')) model.add(Activation(a)) model.add(Dropout(0.15)) model.add(Dense(64, init='uniform')) model.add(Activation('softplus')) model.add(Dropout(0.15)) model.add(Dense(2, init='uniform')) model.add(Activation('softmax')) sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True) model.compile(loss='binary_crossentropy', optimizer=sgd) model.fit(X_train, y_train, nb_epoch=20, batch_size=16, show_accuracy=True, validation_split=0.2, verbose = 2) Here the problem is I am getting an error “ TypeError: 'PReLU' object is not callable” at the model.compile line. I have checked all the non-advanced activation function is working , only the advanced activation function is not working. Can anyone explain the solution to this? Select the correct answer from above options

Answer 1

@kavita ,The best way to use PReLU is with the add() method and not wrapping it using Activation class. Ex: model = Sequential() a = keras.layers.advanced_activations.PReLU(init='zero', weights=None) model.add(Dense(64, input_dim=14, init='uniform')) model.add(a)