How To Print All Activation Shapes (more Detailed Than Summary()) For Tensorflow V2 Keras Model?

I've spent a lot of time with Tensorflow v.0 and v.1, and now I'm trying Tensorflow v.2 keras model. model.summary() looked easy and convenient, but lack details. Here's a toy exam

Solution 1:

The summary will not do this automatically, so you have to adapt. You can, for instance, create a recurrent summary:

deffull_summary(layer):

    #check if this layer has layersifhasattr(layer, 'layers'):
        print('summary for ' + layer.name)
        layer.summary()
        print('\n\n')

        for l in layer.layers:
            full_summary(l)

Use it as:

full_summary(my_model)