ON THIS PAGE

  • Model Conversion
  • Overview
  • Preparation
  • Model Source
  • Calibration Data
  • Conversion for RVC Platform
  • Tutorials

Model Conversion

Overview

To deploy your custom models on Luxonis devices, it's essential to convert them from their initial frameworks (such as PyTorch, TFLite, etc.) into a format compatible with the RVC Platform you aim to run them on. The conversion process involves the following steps:
  1. Prepare the model source;
  2. Prepare calibration data (optional);
  3. Convert the model to one of the RVC compiled formats.

Preparation

Model Source

The model of interest should be prepared in one of the following formats:
  • ONNX (.onnx),
  • OpenVINO IR (.xml and .bin), or
  • TensorFlow Lite (.tflite).
It's advised to convert the model to ONNX as it opens up the most options at conversion for the appropriate RVC Platform. Please check the Conversion to ONNX section for more information.

Calibration Data

Calibration data is used to guide the model quantization. You can read more about the process on the Concepts page. If you do not plan to quantize your model during conversion, you can skip this step.

Conversion for RVC Platform

Once the model source and calibration data are prepared, you can proceed with conversion for the RVC Platform you aim to utilize (RVC compiled format). We have prepared tools that support both online and offline conversion. Online conversion particularly convinient as it requires no system preparation and can be done in a few clicks. Offline conversion runs on your system and is useful in settings with limited internet access or for integrating the conversion into your workflow. Additionally, to allow full customability, we explain steps for manual conversion.
  • Online conversion:
  • Offline conversion:

Tutorials

We have prepared a few tutorials to help you get started with the conversion process using the ModelConverter online mode. To check them out, please visit the Tutorials page.