audio_event_detection

Audio event detection (AED) STM32 model zoo

Directory components:

• docs contains all readmes and documentation specific to the audio event detection use case.
• tf/src contains tools to train, evaluate, benchmark, quantize and deploy your model on your STM32 target.
• config_files_example contains YAML configuration file examples. It's a good place to get started if you are lost.
• datasets is a placeholder folder for AED datasets. You do not need to use it, it is there for convenience.

Tutorials and documentation:

• Complete AED model zoo and configuration file documentation
• A short tutorial on training a model using the model zoo
• A short tutorial on quantizing a model using the model zoo
• A short tutorial on deploying a model on an STM32 board

The different values of the operation_mode attribute and the corresponding operations are described in the table below. In the names of the chain modes, 't' stands for training, 'e' for evaluation, 'q' for quantization, 'b' for benchmark and 'd' for deployment on an STM32 board.

operation_mode	Operations
training	Train a model
evaluation	Evaluate the accuracy of a float or quantized model on a test or validation dataset
quantization	Quantize a float model
prediction	Predict the classes some audio events belong to using a float or quantized model
benchmarking	Benchmark a float or quantized model on an STM32 board
deployment	Deploy a model on an STM32 board
chain_tqeb	Sequentially: training, quantization of trained model, evaluation of quantized model, benchmarking of quantized model
chain_tqe	Sequentially: training, quantization of trained model, evaluation of quantized model
chain_eqe	Sequentially: evaluation of a float model, quantization, evaluation of the quantized model
chain_qb	Sequentially: quantization of a float model, benchmarking of quantized model
chain_eqeb	Sequentially: evaluation of a float model, quantization, evaluation of quantized model, benchmarking of quantized model
chain_qd	Sequentially: quantization of a float model, deployment of quantized model

You don't know where to start? You feel lost?

Don't forget to follow our tuto below for a quick ramp up :

• How to define and train my own model?
• How to fine tune a model on my own dataset?
• How can I evaluate my model before and after quantization?
• How can I quickly check the performance of my model using the dev cloud?
• How can I deploy my model?
• How can I evaluate my model on STM32N6 target?

Remember that minimalistic yaml files are available here to play with specific services, and that all pre-trained models in the STM32 model zoo are provided with their configuration .yaml file used to generate them. These are a great way to get started.

Changes in version 4.0

Interface changes

• In the YAML config files, the model section of has been moved out of the training section and given its own standalone section.
• The model_path attribute, previously under the general section has moved to this new section.
• The name attribute has been changed to model_name.
• The model names of each model have been slightly changed.
• For more details on these changes, how the new model section works, and the model_name associated with each model, consult sections 3.5 of the main README, and appendix A of the same README.