How can Keras be used to implement ensembling in Python?

Tensorflow is a machine learning framework that is provided by Google. It is an open-source framework used in conjunction with Python to implement algorithms, deep learning applications and much more. It is used in research and for production purposes.

The ‘tensorflow’ package can be installed on Windows using the below line of code −

pip install tensorflow

Keras was developed as a part of the 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 the 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.

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 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 to implement Ensemble model −


def get_model():
   inputs = keras.Input(shape=(128,))
   outputs = layers.Dense(1)(inputs)
   return keras.Model(inputs, outputs)
print("Calling the 'get_model' method ")
model_1 = get_model()
model_2 = get_model()
model_3 = get_model()

my_inputs = keras.Input(shape=(128,))
y1 = model_1(my_inputs)
y2 = model_2(my_inputs)
y3 = model_3(my_inputs)
print("The average of the layers in the model")
my_outputs = layers.average([y1, y2, y3])
print("Ensemble model is being created")
ensemble_model = keras.Model(inputs=my_inputs, outputs=my_outputs)

Code credit −


Calling the 'get_model' method
The average of the layers in the model
Ensemble model is being created


  • A model can be nested, which means it can contain sub-models.

  • Sub-models are used in ensembling.

  • This means multiple models are combined together into a single model and the predictions from every model is averaged.