Deep Learning with TensorFlow 2.0

Use Tensorflow 2.0 to build predictors, classifiers, generative models, neural networks.

Course Format


Accreditation Type


Skill Level


Course Cost


Deep Learning with TensorFlow 2.0


TensorFlow is a popular and machine learning library developed by Google for deep learning, numeric computation, and large-scale machine learning. TensorFlow 2.0, released in Jan 2019, is the newest version of TensorFlow and includes improvements in eager execution, compatibility and API consistency.

This instructor-led, live training (online or onsite) is aimed at developers and data scientists who wish to use Tensorflow 2.0 to build predictors, classifiers, generative models, neural networks and so on.

  • Introduction

    • TensorFlow 2.0 vs previous versions -- What's new

    Setting up Tensoflow 2.0

    Overview of TensorFlow 2.0 Features and Architecture

    How Neural Networks Work

    Using TensorFlow 2.0 to Create Deep Learning Models

    Analyzing Data

    Preprocessing Data

    Building a Model

    Implementing a State-of-the-Art Image Classifier

    Training the Model

    Training on a GPU vs a TPU

    Evaluating the Model

    Making Predictions

    Evaluating the Predictions

    Debugging the Model

    Saving a Model

    Deploying a Model to the Cloud

    Deploying a Model to a Mobile Device

    Deploying a Model to an Embedded System (IoT)

    Integrating a Model with Different Languages


    Summary and Conclusion

  • Programming experience in Python.
  • Experience with the Linux command line.

21 hours (usually 3 days including breaks)


  • Install and configure TensorFlow 2.0.
  • Understand the benefits of TensorFlow 2.0 over previous versions.
  • Build deep learning models.
  • Implement an advanced image classifier.
  • Deploy a deep learning model to the cloud, mobile and IoT devices.


This course is NOT credit bearing


This course is available under Attribution-ShareAlike 2.0 South Africa