.. include:: /keyword.rst

=========================
Get Started With AI Tools
=========================

This section introduces the NeuroPilot development tools used to prepare, convert, and analyze AI models for Genio platforms.
The examples use the **YOLOv5s** model to illustrate a typical end-to-end workflow from a source model to on-device execution.

.. important::

   The documentation provides a **reference example** based on specific models and may not apply to all neural network architectures.
   Developers must design evaluation tools and workflows tailored to the unique characteristics and requirements of their specific models.

.. image:: /_asset/ai-workflow-overview.png
   :alt: NeuroPilot Development Tool Workflow
   :align: center
   :width: 800px

.. raw:: html

   <br>

With these tools, developers can:

#. :doc:`Convert to TFLite </ai_hub/ai-workflow/model_converter>`– Transform source models into ``.tflite`` format using either the **NP Converter** (for optimized hardware acceleration) or **open-source converters**.
#. :doc:`Visualize models </ai_hub/ai-workflow/model_visualization>` – Inspect the converted ``.tflite`` models to verify tensor shapes, data types, and layer connections using tools like Netron or ``ncc-tflite``.
#. :doc:`Compile and deploy </ai_hub/ai-workflow/neuron-sdk>`– Use the **Neuron SDK** (``ncc-tflite``) to convert models into the MediaTek proprietary **DLA** format for offline execution and run them on-device with ``neuronrt``.
#. :doc:`Profile performance </ai_hub/ai-workflow/neuron_studio>` – Use **Neuron Studio** to analyze NPU utilization, memory bandwidth, and execution latency with detailed metrics.
#. :doc:`Evaluate accuracy </ai_hub/ai-workflow/accuracy_evaluation>` – Compare the accuracy of the original model against the converted ``.tflite`` and compiled ``.dla`` models to ensure model integrity.

Please refer to each section for more detailed information.