Keras, How to get the output of each layer?

Question

I have trained a binary classification model with CNN, and here is my code model = Sequential() model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],border_mode='valid',input_shape=input_shape)) model.add(Activation('relu')) model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1])) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=pool_size)) # (16, 16, 32) model.add(Convolution2D(nb_filters*2, kernel_size[0], kernel_size[1])) model.add(Activation('relu')) model.add(Convolution2D(nb_filters*2, kernel_size[0], kernel_size[1])) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=pool_size)) # (8, 8, 64) = (2048) model.add(Flatten()) model.add(Dense(1024)) model.add(Activation('relu')) model.add(Dropout(0.5)) model.add(Dense(2)) # define a binary classification problem model.add(Activation('softmax')) model.compile(loss='categorical_crossentropy,optimizer='adadelta', metrics=['accuracy']) model.fit(x_train,y_train,batch_size=batch_size,nb_epoch=nb_epoch,verbose=1,validation_data=(x_test, y_test)) And here, I wanna get the output of each layer just like TensorFlow, how can I do that? Select the correct answer from above options

Answer 1

You can easily get the output of any layer in Keras by using the following syntax: Model.layers[index].output For all layers refer the following piece of code: from keras import backend as K input1 = model.input # input placeholder output1 = [layer.output for layer in model.layers]# all layer outputs fun = K.function([input1, K.learning_phase()],output1)# evaluation function # Testing t = np.random.random(input_shape)[np.newaxis,...] layer_outputs = fun([t, 1.]) print layer_outputs// printing the outputs of layers K.function creates theano/TensorFlow tensor functions which are later used to get the output from the symbolic graph given the input. The model builds the predict function using K.function. Now K.learning_phase() is required as an input as many Keras layers like Dropout/Batchnomalization depend on it to change behavior during training and test time. You can take reference from the following link: the output of an intermediate layer in Keras. If you wish to learn more about AI, visit Artificial Intelligence Tutorial and Artificial Intelligence Course by Intellipaat. Watch this video to know more about Keras: