Faster inference in TensorFlow 2.0 with TensorRT

Siddharth Sharma (NVIDIA), Joohoon Lee (NVIDIA)

11:50am–12:30pm Wednesday, October 30, 2019

Location: Grand Ballroom H

Accelerators

Who is this presentation for?

Developers and data scientists who are building deep learning applications in TensorFlow

Level

Intermediate

Description

TensorFlow 2.0 is tightly integrated with TensorFlow and offers high performance for deep learning inference through a simple API. Siddharth Sharma and Joohoon Lee use examples to show you how to optimize an app using TensorRT with the new Keras APIs in TensorFlow 2.0. They show you tips and tricks to get the highest performance possible on GPUs and detail examples of how to debug and profile apps using tools by NVIDIA and TensorFlow. You’ll walk away with an overview and resources to get started, and if you’re already familiar with TensorFlow, you’ll get tips on how to get the most out of your application.

Prerequisite knowledge

Experience using deep learning in TensorFlow

What you'll learn

Discover the latest and greatest in the integrated solution, workflows and tools for profiling, and tips and tricks to squeeze the most out of your inference solution

Siddharth Sharma

NVIDIA

Siddharth Sharma is a senior technical marketing manager for accelerated computing at NVIDIA. Previously, Siddharth was a product marketing manager for Simulink and Stateflow at MathWorks, working closely with automotive and aerospace companies to adopt model-based designs for creating control software.

Website

Joohoon Lee

NVIDIA

Joohoon Lee is a principal product manager for AI inference software at NVIDIA. Previously, he led the automotive deep learning software solutions team focusing on the production deployment of neural networks in DRIVE AGX platform using TensorRT. His expertise includes quantization, sparsity optimization, compilers, GPU, and AI accelerator architecture design. Joohoon received his BS and MS in electrical and computer engineering from Carnegie Mellon University.