Skip to content

Analog signal shape classifier built on STM32, TFLite (embedded network), Keras (Python network) with training data generation (Python)

Notifications You must be signed in to change notification settings

m-chwast/wdssn-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Signal type classifier

Setup environment

  • run setup.py to create virtual environment
  • activate environment with generated script in {venv name}/Scripts/activate
  • then install requred modules with pip install -r requirements.txt comment

Data setup

  • Generating data:
    • enter data-gen directory
    • generate the data by running data-gen.py with uncommented generate() function in main
  • Running IA:
    • enter network directory
    • run network.py

Creating your own Pattern

If you have an idea to expande model with new, more deficult signals, all you have to do is to create a new class that will inherits from SignalBase and override get_sample(self, arg: float) -> float method.

About

Analog signal shape classifier built on STM32, TFLite (embedded network), Keras (Python network) with training data generation (Python)

Topics

Resources

Stars

Watchers

Forks

Languages