Workflow for building models in Keras

The simple workflow in Keras is as follows:

1. Create the model
2. Create and add layers to the model
3. Compile the model
4. Train the model
5. Use the model for prediction or evaluation

Let's check out each of these steps.

You can follow the code examples in this chapter with the Jupyter Notebook ch-03_Keras_101 included in the code bundle.  Try modifying the code in the notebook to explore various options.