Edge Impulse Launches Integration with NVIDIA TAO Toolkit to Supercharge Edge AI

Developers and enterprises can optimize performance and accelerate time to market of edge AI applications with NVIDIA TAO on Edge Impulse

Supercharge edge AI with NVIDIA TAO on Edge Impulse (Graphic: Business Wire)

SAN JOSE, Calif.--()--Edge Impulse, a leading platform for building, refining and deploying machine learning models and algorithms to edge devices, announced today that it has integrated the new NVIDIA TAO Toolkit 5.0 into its edge AI platform.

The NVIDIA TAO Toolkit is a low-code AI framework for accelerating and simplifying vision AI model development. With the latest TAO integration, Edge Impulse can now quickly offer access to NVIDIA’s pretrained models to complement its suite of edge AI tools and features, from data collection to model training and deployment. Developers can also take advantage of the Edge Impulse platform to build production AI with TAO for any edge device. Edge Impulse’s quick-start development environment will allow TAO customers to deploy at the edge faster, reduce the amount of time needed to write code for edge devices, and optimize AI models for the constraints of operating on the edge.

Edge Impulse’s platform integrated with NVIDIA TAO Toolkit helps customers:

  • Get to market faster: Build efficient models faster by combining the power of transfer learning and the latest NVIDIA TAO models across the entire Edge Impulse ecosystem of devices, silicon, and sensors.
  • Work on any device — microcontroller units, CPUs, neural accelerators, GPUs: Collect data, train and validate models, and optimize libraries to run on any edge device, from extremely low-power MCUs to efficient Linux CPU targets to any NVIDIA GPU or neural accelerator.
  • Fast track to enterprise-grade production: Start fast with 100+ NVIDIA-optimized model architectures, like transformers and fully attentional networks. Fine-tune the models with proprietary data, enabling a much faster development process.
  • Do more with less data: Efficiently collect data from any edge device and use Edge Impulse auto-labeling tools to increase data quality.
  • Optimize for edge devices: Profile the performance of a model on different hardware to find the optimal target given specific use cases and hardware constraints.
  • Collaborate with ease: Enjoy an edge AI development environment built for enterprise-wide collaboration that enables teams with diverse expertise to collaborate from anywhere in real time.

“This collaboration is a significant boon to our customers, who will now have access to state-of-the-art machine learning research and model architectures from NVIDIA,” said Jan Jongboom, co-founder and CTO of Edge Impulse. “TAO users will also get Edge Impulse’s complete integrated development environment to collect new data, train and validate models, and deploy to any device under the sun – from the smallest microcontrollers to the latest GPUs and neural accelerators – while being fully compatible with your existing TAO training pipelines; and without having to provision your own hardware.”

Get set up on Edge Impulse with NVIDIA TAO today. Learn more about how to train NVIDIA TAO models in Edge Impulse in this short video from Edge Impulse’s co-founder and CTO Jan Jongboom.

About Edge Impulse

Edge Impulse offers the latest in machine learning tooling, enabling all enterprises to build smarter edge products. Their technology empowers developers to bring more AI products to market faster, and helps enterprise teams rapidly develop industry-specific solutions in weeks instead of years. Edge Impulse provides powerful automations and low-code capabilities to make it easier to build valuable datasets and develop advanced AI for edge devices. Used by makers of health-wearable devices like Oura, Know Labs, and NOWATCH, industrial organizations like NASA, as well as top silicon vendors and over 80,000 developers, Edge Impulse has become the trusted platform for enterprises and developers alike. It provides a seamless integration experience to optimize and deploy with confidence across the largest hardware ecosystem. To learn more, visit edgeimpulse.com.

Contacts

Marie Williams
Coderella
(415) 707-2793
press@edgeimpulse.com

Contacts

Marie Williams
Coderella
(415) 707-2793
press@edgeimpulse.com