NVIDIA Jetson devices are common hardware for edge AI use cases that require efficient and fast deep neural networks and real-time performance. By optimizing your models on NVIDIA Jetson Nano and Xavier NX, you can maximize the utilization of your hardware and hit your inference performance targets.
In this webinar, you’ll learn from Deci’s VP Product, Nadav Cohen, how to:
- Benchmark inference performance on NVIDIA without having to replicate Jetson environments on cloud instances
- Automatically boost performance across latency, throughput, and memory footprint for your specific Jetson device
- Discover the best production settings (e.g., batch sizes and quantization levels) for your hardware and applications requirements
After watching the webinar, you can go ahead and benchmark and optimize your models for Jetson using the free community version of Deci’s deep learning platform.