Keras: Multiple Inputs for fit_generator using flow_from_directory

Question

Is it possible to have two flow_from_directory in a fit_generator?

For example

train_generator_1 = train_datagen.flow_from_directory(
    train_data_         


        

Answer 1

You can try making a generator that contains both:

In python 3:

def doubleGenerator(generator1,generator2):

    while True:
        for (x1,y1),(x2,y2) in zip(generator1,generator2):
            yield ([x1,x2],y1)