NVIDIA Omniverse

NVIDIA Omniverse™ is a scalable, multi-GPU real-time reference development platform for building and operating metaverse applications and based on Pixar's Universal Scene Description and NVIDIA RTX™ technology.

This tutorial describes how you can use the Edge Impulse Data Ingestion extension within NVIDIA Omniverse to upload your synthetic datasets to your Edge Impulse project for computer vision tasks.

Getting started with NVIDIA Omniverse

Check out NVIDIA's documentation for information on getting started as a first-time user with the Omniverse platform.

Preliminary steps

Now continue with NVIDIA's Omniverse installation guide.

Installing the Edge Impulse Data Ingestion extension

Once you have installed NVIDIA Omniverse, you can now install the Edge Impulse Data Ingestion extension into your Omniverse environment by following the README in the extension's GitHub repository.

Generating a synthetic dataset

Follow this tutorial by Edge Impulse expert George Igwegbe to create a synthetic dataset using NVIDIA Omniverse Replicator.

Then, using the Edge Impulse Data Ingestion extension you installed in the previous step, upload your dataset by filling out the extension's text fields:

  • Data Path: Full directory path on your computer to the location of your synthetic dataset (i.e. C:\Users\jenny\forks\images\)

  • API Key: This key is obtained from your Edge Impulse project Dashboard > Keys > API Keys

  • Dataset: training, testing, or anomaly (default = training)

Then click Upload to Edge Impulse! Your collected synthetic dataset is automatically uploaded into your Edge Impulse project directly from NVIDIA Omniverse.

Next steps: building a machine learning model

With everything set up you can now build your machine learning model with these tutorials:

Looking to connect different sensors? The Data forwarder lets you easily send data from any sensor into Edge Impulse.

Last updated