SPRADB0 may   2023 AM62A3 , AM62A3-Q1 , AM62A7 , AM62A7-Q1 , AM68A , AM69A

 

  1.   1
  2.   Abstract
  3.   Trademarks
  4. 1Introduction
    1. 1.1 Intended Audience
    2. 1.2 Host Machine Information
  5. 2Creating the Dataset
    1. 2.1 Collecting Images
    2. 2.2 Labelling Images
    3. 2.3 Augmenting the Dataset (Optional)
  6. 3Selecting a Model
  7. 4Training the Model
    1. 4.1 Input Optimization (Optional)
  8. 5Compiling the Model
  9. 6Using the Model
  10. 7Building the End Application
    1. 7.1 Optimizing the Application With TI’s Gstreamer Plugins
    2. 7.2 Using a Raw MIPI-CSI2 Camera
  11. 8Summary
  12. 9References

1.1 Intended Audience

This document is intended for readers with beginner or intermediate level deep learning experience, who aim to bring their ideas onto TI processors for vision applications. It is also intended to help readers add practical knowledge to the implementation of such systems; this document intentionally provides additional tips and comments for those with theoretical understanding but less practical expertise.

For those with minimal deep learning knowledge, it is recommended to follow the Fundamental Concepts pages of the Edge AI Academy [4] in the TI Developer Zone.