TensorFlow Sequential API It helps the user stack layers on top of each other, easily creating linear models, where the input of each layer is always the output of the previous one. But what happens when your model needs to handle multiple inputs or outputs, shared layers, or non-linear connections? In those scenarios, TensorFlow Functional API allows building more advanced, flexible and customizable models, giving the user the power to design the complex architectures mentioned above with ease.
This article will explain:
- What is functional API
- How to build a simple model with the functional API
TensorFlow Functional API is a way of creating models where the layers are connected like a network graph, not just stacked linearly as in the Sequential API. Imagine building with LEGO bricks: while the sequential API would simply allow us to stack blocks on top of each other, the functional API allows us to build bridges, towers, and paths that connect different areas.
