Comment on page
Introduction
Although we provide a large library of models that you can use to create off-the-shelf edge AI applications using the Scailable AI manager and Scailable platform, it is often useful to be able to create your own models for edge AI deployment. In this section of our documentation we describe how you can create your own vision models that can easily be deployed to your edge devices.
In this section of the docs we focus on creating models. Once you have a model ready in ONNX format, you can find instructions on how to upload ONNX models to the Scailable platform here.
Our standard process for creating your own models is to:
- 1.Create a model using your favourite training tools. You can create an ONNX model / pipeline from scratch, or you can import a model from one of the training tools that we integrate with.
- 1.
- 2.Once you have your model ready, you can upload your model to the Scailable platform; we will automatically convert it to SPMF and ensure that it can be deployed to any edge device running the Scailable AI manager highly efficiently.
In this section of the docs you can find:
- Tips and tricks for testing models both before uploading them to the Scailable platform, and aftter.
Last modified 2mo ago