Could someone explain what the advantage of using keras.layers.InputLayer over the keras.Input tensor is? I understand that one is a tensor, the other is a layer object. However my question is more from a practical point of view as in why one would define the input in a certain way when using the functional API.
Thanks!
For the benefit of community providing solution here
It is generally recommend to use the functional layer API via Input, (which creates an InputLayer) without directly using InputLayer. When using InputLayer with Keras Sequential model, it can be skipped by moving the input_shape parameter to the first layer after the InputLayer. For more details you can refer this and this.
