NeuralSPOT documentation is spread throughout the repository - generally, every component has its own documentation, which can be overwhelming. We've created the following high level documents as a starting point for understanding neuralSPOT's overall structure and intended usage.
The best way to read this documentation is here: https://ambiqai.github.io/neuralSPOT
| Document | Description |
|---|---|
| AI at Ambiq | A high level introduction to Ambiq's model zoo and neuralSPOT |
| Introduction to NeuralSPOT | A high level introduction to neuralSPOT |
| NeuralSPOT Feature Guide | A brief list of neuralSPOT's features and examples, with links to deeper documentation |
| Release Notes | Latest neuralSPOT release notes and errata |
| Apollo5 Application Note | Apollo5 EB and EVB considerations |
| Apollo3 Application Note | Apollo3 considerations |
| Developing AI with NeuralSPOT | Overview of the various ways neuralSPOT can be used to develop and deploy AI models |
| Developing for NeuralSPOT | Describes how neuralSPOT's components (libraries, examples, external components, and projects) are structured, and how to add to them |
| NeuralSPOT Nests | NeuralSPOT Nests are way of deploying entire neuralSPOT applications as components of other applications. |
| From TF to EVB - testing, profiling, and depploying AI models | A quick guide to optimizing power efficiency and performance using neuralSPOT |
| Optimizing using NeuralSPOT | A guide to using NeuralSPOT's AutoDeploy tools to analyze and deploy TFLite files on Ambiq processors |
| Deploying EdgeImpulse Models using neuralSPOT Nests | A walkthrough of how to use Nests to deploy complex external SW packages |
| Understanding neuralSPOT via the Basic Tensorflow Example | A walkthrough of neuralSPOT's core example |
| Building NeuralSPOT | Comprehensive makefile guide |