Compile the sequential model with compile method - Keras and Python

Keras was developed as a part of research for the project ONEIROS (Open ended Neuro-Electronic Intelligent Robot Operating System). Keras is a deep learning API, which is written in Python. It is a high-level API that has a productive interface that helps solve machine learning problems.

It runs on top of Tensorflow framework. It was built to help experiment in a quick manner. It provides essential abstractions and building blocks that are essential in developing and encapsulating machine learning solutions.

It is highly scalable, and comes with cross platform abilities. This means Keras can be run on TPU or clusters of GPUs. Keras models can also be exported to run in a web browser or a mobile phone as well.

Keras is already present within the Tensorflow package. It can be accessed using the below line of code.

import tensorflow
from tensorflow import keras

The Keras functional API helps create models that are more flexible in comparison to models created using sequential API. The functional API can work with models that have non-linear topology, can share layers and work with multiple inputs and outputs. A deep learning model is usually a directed acyclic graph (DAG) that contains multiple layers. The functional API helps build the graph of layers.

We are using the Google Colaboratory to run the below code. Google Colab or Colaboratory helps run Python code over the browser and requires zero configuration and free access to GPUs (Graphical Processing Units). Colaboratory has been built on top of Jupyter Notebook. Following is the code snippet −

Example

print("Model is being compiled")
model.compile(
   optimizer=keras.optimizers.RMSprop(1e-3),
   loss={
      "priority": keras.losses.BinaryCrossentropy(from_logits=True),
      "department": keras.losses.CategoricalCrossentropy(from_logits=True),
   },
   loss_weights=[1.0, 0.2],
)

Code credit − https://www.tensorflow.org/guide/keras/functional

Output

Model is being compiled

Explanation

• The model is compiled using the ‘compile’ method.

• Different losses can be assigned to every output when the compilation is going on.

• Different weights can also be assigned to different losses, this way the total training loss will be modulated.