Get in Touch
 Duration 21 hours

Course Outline

Introduction to Edge AI and NVIDIA Jetson

  • Exploration of key edge AI application scenarios
  • Overview of NVIDIA Jetson hardware capabilities
  • Analysis of JetPack SDK components and the associated development ecosystem

Establishing the Development Environment

  • Installation of JetPack SDK and configuration of the Jetson board
  • In-depth look at TensorRT and strategies for model optimization
  • Configuration of the runtime environment for optimal performance

Optimizing AI Models for Edge Deployment

  • Application of model quantization and pruning techniques
  • Leveraging TensorRT for significant model acceleration
  • Process for converting models into ONNX format

Deploying AI Models on Jetson Devices

  • Execution of inference workflows using TensorRT
  • Integration of AI models into real-time application frameworks
  • Techniques for performance tuning and latency reduction

Computer Vision and Deep Learning on Jetson

  • Deployment of image classification and object detection models
  • Utilizing AI for advanced real-time video analytics
  • Development of AI-driven robotics applications

Edge AI Security and Performance Optimization

  • Strategies for securing AI models on edge infrastructure
  • Managing power efficiency and thermal constraints
  • Scaling AI applications effectively across Jetson platforms

Project Implementation and Real-World Use Cases

  • Construction of an AI-powered IoT solution
  • Deployment of AI technologies in autonomous systems
  • Review of industry case studies involving edge AI

Summary and Next Steps

Requirements

  • Practical experience in training and running AI inference models.
  • Foundational understanding of embedded systems.
  • Proficiency in Python programming.

Intended Audience

  • AI Developers
  • Embedded Engineers
  • Robotics Engineers

Number of participants


Price per participant (excl. VAT)

Testimonials (1)

Upcoming Courses

Related Categories