Although the virtual 2021 Embedded Vision Summit has passed, your opportunity to get all the great content hasn't. Register for the to soak up all the valuable insights that came from our expert speakers.

Trainings

Deep Learning for Computer Vision with TensorFlow 2.0 and Keras

Now available as an online training!

For less than $300, you can enjoy a first-rate training created by a Google Developer Expert on how to use TensorFlow and Keras for deep learning on computer vision projects.

Originally an in-person class offered at the Embedded Vision Summit, we’ve moved the training to an online, on-demand format—but with the same great content, Jupyter Notebook labs, and as many instructor office hours as you need!

Take Me to the Details

If you are considering signing up for a training course, you’ll almost certainly want to register for the Embedded Vision Summit. The Summit is your gateway to a world of information on practical computer vision. Inspiring keynote presentations, dozens of practical sessions that help you deploy embedded vision products, and the Technology Showcase, where top suppliers are on hand with your projects in mind and the tools you need to achieve your vision. Learn more about the Embedded Vision Summit!

Are you an engineer who wants to design intelligent computer vision systems that learn from complex or large-scale datasets?

Get the hands-on knowledge you need to develop deep learning computer vision applications—both on embedded systems and in the cloud—with TensorFlow, today’s most popular framework for deep learning.

TensorFlow 2.0 and Keras Training Course Overview

Our online program will provide you with a hands-on overview of deep learning applications of TensorFlow, from the convenience of your home or office!

Course Outline

The class consists of 14 self-paced video lectures and 6 lab exercises using Jupyter Notebooks. We cover the following topics:

  • Introduction to AI, machine learning, TensorFlow 2.0, and Keras
  • Neural networks in TensorFlow
    • Linear regression
    • Classification
    • Logistic regression
    • Deep neural networks
    • Convolutional neural networks (CNNs)
  • Data set creation and augmentaion
  • Off-the-shelf network architectures; transfer learning
  • Object detection
  • Looking forward

Labs are conducted using Jupyter Notebooks and Google Colab on GPU-enabled instances for speedy training. Our instructor takes you through each lab and then you have an opportunity to do the lab on your own and then learn by enhancing it.

Enroll Now!

Don’t get stuck!

Get the help you need.

Sure, there are other online training courses for TensorFlow out there. But what you’ll have a harder time finding is that direct communication you need with an expert to guide you through challenging content and techniques.

With the Deep Learning for Computer Vision with TensorFlow 2.0 and Keras training course, you can get as many office-hour sessions and as much email support from our expert instructor as you need to get all your questions answered.

Instructor office hours are available via Zoom on Mondays, 8-9 am PT, and Wednesdays, 4-5 pm PT.

Prerequisites

The class covers deep learning for computer vision applications using TensorFlow 2.0. We assume that:

  • You know the basics of deep learning algorithms and concepts for computer vision, including convolutional neural networks.
  • You know the basics of the Python programming language.
  • You do not know TensorFlow or TensorFlow 2.0.

To make sure you’re up to speed on Python, please review sections 1-5 of this online Python tutorial before class:  https://docs.python.org/3/tutorial.

Learn More About the Instructor

Learn More About the Instructor

Doug Perry, is a Google Developer Expert for TensorFlow. He is an experienced hardware engineer who has has worked in the field of artificial intelligence since 2007. Recent examples of some of his projects include an AI-based sports application for golf and baseball swing classification and a consumer application using facial recognition technology to categorize facial features. He also architected a quantized neural network accelerator using FPGAs that showed a 100X speedup relative to GPU based architectures. His most recent project is a TensorFlow model for financial option trading. He the author of numerous books on hardware design, holds several patents related to hardware instrumentation and debugging, and has been an instructor for both in-person and online classes for many years.