Fast Track AI to the Edge with NVIDIA TAO & Edge Impulse

Fast Track AI to the Edge with NVIDIA TAO & Edge Impulse

‍

If you’re using artificial intelligence to build smart devices such as computer vision monitoring for predictive maintenance, you know that collecting, cleaning, and labeling data is time consuming, tedious, and expensive. Edge Impulse and pretrained models from NVIDIA TAO help get you on the fast track to enterprise-grade production with 100+ NVIDIA-optimized model architectures, like vision transformers and fully attentional networks. Fine-tune the models with your own data, enabling a much faster development process.

Watch the webinar, ‘Fast Track AI to the Edge with NVIDIA TAO & Edge Impulse’, to hear from NVIDIA’s Debraj Sinha (Product Marketing Manager), Edge Impulse’s Jan Jongboom (CTO & Cofounder) and Jenny Plunkett (Senior Engineer) about the latest in edge AI and how to leverage pretrained models from NVIDIA to deploy on edge devices.

‍

Learn how to:

• Build efficient vision ML pipelines 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.
• Profile the performance of your model on different hardware to find the optimal target given your use case and hardware constraints.
• Efficiently collect data from any edge device and use Edge Impulse auto-labeling tools to increase data quality.
• Collect data, train and validate your model, 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.