Optimize Tensorflow models using TensorRT (TF-TRT)
Use TF-TRT to optimize several deep learning models at FP32, FP16, and INT8 precision
Observe how tuning TF-TRT parameters affects performance and inference throughput
Showcase this hands-on experience in an interview
This is a hands-on, guided project on optimizing your TensorFlow models for inference with NVIDIA's TensorRT. By the end of this 1.5 hour long project, you will be able to optimize Tensorflow models using the TensorFlow integration of NVIDIA's TensorRT (TF-TRT), use TF-TRT to optimize several deep learning models at FP32, FP16, and INT8 precision, and observe how tuning TF-TRT parameters affects performance and inference throughput. Prerequisites: In order to successfully complete this project, you should be competent in Python programming, understand deep learning and what inference is, and have experience building deep learning models in TensorFlow and its Keras API. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.
It is assumed that are competent in Python programming and have prior experience with building deep learning models with TensorFlow and its Keras API
In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:
Introduction and Project Overview
Setup your TensorFlow and TensorRT Runtime
Load the Data and Pre-trained InceptionV3 Model
Create batched Input
Load the TensorFlow SavedModel
Get Baseline for Prediction Throughput and Accuracy
Convert a TensorFlow saved model into a TF-TRT Float32 Graph
Benchmark TF-TRT Float32
Convert to TF-TRT Float16 and Benchmark
Converting to TF-TRT INT8
Your workspace is a cloud desktop right in your browser, no download required
In a split-screen video, your instructor guides you step-by-step
Are Guided Projects available on desktop and mobile?
Because your workspace contains a cloud desktop that is sized for a laptop or desktop computer, Guided Projects are not available on your mobile device.
Who are the instructors for Guided Projects?
Guided Project instructors are subject matter experts who have experience in the skill, tool or domain of their project and are passionate about sharing their knowledge to impact millions of learners around the world.
Can I download the work from my Guided Project after I complete it?
You can download and keep any of your created files from the Guided Project. To do so, you can use the “File Browser” feature while you are accessing your cloud desktop.
How much experience do I need to do this Guided Project?
At the top of the page, you can press on the experience level for this Guided Project to view any knowledge prerequisites. For every level of Guided Project, your instructor will walk you through step-by-step.
Can I complete this Guided Project right through my web browser, instead of installing special software?
Yes, everything you need to complete your Guided Project will be available in a cloud desktop that is available in your browser.
What is the learning experience like with Guided Projects?
You'll learn by doing through completing tasks in a split-screen environment directly in your browser. On the left side of the screen, you'll complete the task in your workspace. On the right side of the screen, you'll watch an instructor walk you through the project, step-by-step.
More questions? Visit the Learner Help Center.