Scribd
Upload
18 views

TensorFlow and Keras - Deep Learning - Great Learning

Uploaded by

Ajanta Bearing
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
18 views

TensorFlow and Keras - Deep Learning - Great Learning

Uploaded by

Ajanta Bearing
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Go Back to Deep Learning

Course Content

TensorFlow and Keras

TensorFlow

TensorFlow is an open-source machine learning platform developed by Google which helps in training large-
scale neural networks with many layers. It provides a comprehensive ecosystem of tools for developers,
enterprises, and researchers who want to push the state-of-the-art in Machine Learning and build scalable ML-
powered applications.

Why TensorFlow?

TensorFlow provides an accessible and readable syntax which is essential for making programming
resources easier to use.
It can carry out high-performance numerical computations.
It provides excellent architecture support which allows easy deployment of computations across a variety
of platforms, ranging from desktops to clusters of servers, mobiles, and edge devices.
It helps researchers implement new technologies.

If you want to know about the implementation of TensorFlow in Python, kindly refer to the following
tutorials: https://www.tensorflow.org/tutorials (Links to an external site.)Links to an external site.

Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. It
was developed with a focus on enabling fast experimentation. Being able to go from idea to result as fast as
possible is key to doing good research.

In Python, we can import TensorFlow as:


import tensorflow as tf

After importing TensorFlow, we can use tf.keras, which is used to implement the Keras version having a
TensorFlow backend.

Why use tf.keras?

Using tf.keras allows you to design, fit, evaluate, and use deep learning models to make predictions in just a few
lines of code.

It makes common deep learning tasks, such as classification, regression, and predictive modeling, accessible to
average developers looking to get things done.

Keras has many inbuilt APIs which highly simplify the implementation of different types of neural networks.

You can refer to the link given here (Links to an external site.)Links to an external site. if you want to read about
these APIs.

You can either install Keras and TensorFlow in your system and implement them using a Jupyter notebook or
you can use Google Colab. We recommend using Google Colab for this course.

Google Colab is a cloud-based alternative to Jupyter notebooks and is designed to run notebooks online on
your browser. It comes with different pre-installed packages and you can start working on it with very few
dependencies.

For this week, we will be using Google Colab for the implementation of neural networks using TensorFlow and
Keras.

Next, we will look at how to get started with Google Colab.

Previous Next

Proprietary content. ©Great Learning. All Rights Reserved. Unauthorized use or distribution prohibited.

© 2022 All rights reserved Privacy Terms of service Help

You might also like