Google Code-in

The tf.keras Functional API can handle models with non-linear topology, models with shared layers, and models with multiple inputs or outputs.

It's based on the idea that a deep learning model is usually a directed acyclic graph (DAG) of layers. The Functional API a set of tools for building graphs of layers.

To get credit for this task, use the tf.Keras Functional API to create a model for classifying digits in the MNIST dataset. P.S. for grading purposes, your model should have at least one Convolutional layer.