Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.

What’s New in TensorFlow 2.0

  • Course Code: Artificial Intelligence - What's New in TensorFlow 2.0
  • Course Dates: Contact us to schedule.
  • Course Category: AI / Machine Learning Duration: 2 Days Audience: This course is geared for those who wants Get grips with key structural changes in TensorFlow 2.0

Course Snapshot 

  • Duration: 2 days 
  • Skill-level: Foundation-level TensorFlow skills for Intermediate skilled team members. This is not a basic class. 
  • Targeted Audience: This course is geared for those who wants Get grips with key structural changes in TensorFlow 2.0 
  • Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required. 
  • Delivery Format: This course is available for onsite private classroom presentation, or remote instructor led delivery, or CBT/WBT (by request). 
  • Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals. 

TensorFlow is an end-to-end machine learning platform for experts as well as beginners, and its new version, TensorFlow 2.0 (TF 2.0), improves its simplicity and ease of use. This course will help you understand and utilize the latest TensorFlow features. What’s New in TensorFlow 2.0 starts by focusing on advanced concepts such as the new TensorFlow Keras APIs, eager execution, and efficient distribution strategies that help you to run your machine learning models on multiple GPUs and TPUs. The course then takes you through the process of building data ingestion and training pipelines, and it provides recommendations and best practices for feeding data to models created using the new tf.keras API. You will explore the process of building an inference pipeline using TF Serving and other multi-platform deployments before moving on to explore the newly released AIY, which is essentially do-it-yourself AI. This course delves into the core APIs to help you build unified convolutional and recurrent layers and use TensorBoard to visualize deep learning models using what-if analysis. By the end of the course, you’ll have learned about compatibility between TF 2.0 and TF 1.x and be able to migrate to TF 2.0 smoothly. 

Working in a hands-on learning environment, led by our TensorFlow expert instructor, students will learn about and explore: 

  • Explore TF Keras APIs and strategies to run GPUs, TPUs, and compatible APIs across the TensorFlow ecosystem 
  • Learn and implement best practices for building data ingestion pipelines using TF 2.0 APIs 
  • Migrate your existing code from TensorFlow 1.x to TensorFlow 2.0 seamlessly 

Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below 

  • Implement tf.keras APIs in TF 2.0 to build, train, and deploy production-grade models 
  • Build models with Keras integration and eager execution 
  • Explore distribution strategies to run models on GPUs and TPUs 
  • Perform what-if analysis with TensorBoard across a variety of models 
  • Discover Vision Kit, Voice Kit, and the Edge TPU for model deployments 
  • Build complex input data pipelines for ingesting large training datasets 

Audience & Pre-Requisites 

This course is geared for attendees to Get grips with key structural changes in TensorFlow 2.0 

Pre-Requisites:  Students should have  

  • Basic to Intermediate IT Skills and Tensorflow knowledge 
  • Good foundational mathematics or logic skills 
  • Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su 

Course Agenda / Topics 

  1. Getting Started with TensorFlow 2.0 
  • Getting Started with TensorFlow 2.0 
  • Technical requirements 
  • What’s new? 
  • TF 2.0 installation and setup 
  • Using TF 2.0 
  • Rich extensions 
  1. Keras Default Integration and Eager Execution 
  • Keras Default Integration and Eager Execution 
  • Technical requirements 
  • New abstractions in TF 2.0 
  • Diving deep into the Keras API 
  • Estimators 
  • Evaluating TensorFlow graphs 
  1. Designing and Constructing Input Data Pipelines 
  • Designing and Constructing Input Data Pipelines 
  • Technical requirements 
  • Designing and constructing the data pipeline 
  • Transforming datasets 
  • Feeding the created dataset to the model 
  • Examples of complete end-to-end data pipelines 
  • Best practices and the performance optimization of a data pipeline in TF 2.0  
  • Built-in datasets in TF 2.0 
  1. Model Training and Use of TensorBoard 
  • Model Training and Use of TensorBoard 
  • Technical requirements 
  • Comparing Keras and tf.keras 
  • Creating models using tf.keras 2.0 
  • Model compilation and training 
  • Custom training logic 
  • Distributed training 
  • TensorBoard 
  1. Model Inference Pipelines – Multi-platform Deployments 
  • Model Inference Pipelines – Multi-platform Deployments 
  • Technical requirements 
  • Machine learning workflow – the inference phase 
  • Model artifact – the SavedModel format 
  • Inference on backend servers 
  • Inference in the browser 
  • Inference on mobile and IoT devices 
  1. AIY Projects and TensorFlow Lite 
  • AIY Projects and TensorFlow Lite 
  • Introduction to TFLit 
  • Getting started with TFLite 
  • Running TFLite on mobile devices 
  • Running TFLite on low-power machines 
  • Comparing TFLite and TF 
  • AIY 
  1. Migrating From TensorFlow 1.x to 2.0 
  • Migrating From TensorFlow 1.x to 2.0 
  • Major changes in TF 2. 
  • Recommended techniques to employ for idiomatic TF 2.0 
  • Making code TF 2.0-native 
  • Frequently asked questions 
  • The future of TF 2.0 
View All Courses

    Course Inquiry

    Fill in the details below and we will get back to you as quickly as we can.

    Interested in any of these related courses?