SPRADB0 may   2023 AM62A3 , AM62A3-Q1 , AM62A7 , AM62A7-Q1 , AM67A , 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

1.2 Host Machine Information

A host machine, i.e.,a laptop or desktop computer, is necessary to handle dataset preparation, neural network training, and neural network compilation. In the making of this application, the host machine was a 64-bit x86 CPU running Ubuntu 18.04 LTS. The machine includes a 512 GB SSD, 16 GB of RAM, and NVIDIA A2000 GPU for training.

Python 3.6 is the dominant programming environment on the host. For guidance on how to setup a Python3 virtual environment with the necessary dependencies, see edgeai-modelmaker.