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:
Prepare the model source;
Prepare calibration data (optional);
Convert the model to one of the RVC compiled formats.
Model Source Preparation
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 Preparation (optional)
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.
Model 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:
HubAI (recommended) - conversion for all RVC platforms,
BlobConverter (legacy) - conversion for RVC2 and RVC3 platforms.
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.