The Eindhoven start-up Scailable has developed software that makes it possible to process large amounts of data no longer ‘in the cloud’ but ‘on the edge’ into usable information. The cost savings, improved security and faster speed achieved by processing data where it is collected will play a major role in accelerating the adoption of Artificial Intelligence (AI). The Brabant Development Company (BOM), together with Volta Ventures and the Rabobank Innovation Fund, is investing EUR 650,000 in the further development and market introduction of the software.
How AI on the Edge (provided by Scailable) and LoRa (provided by KPN Things) jointly enable novel (I)IoT applications.
This tutorial describes a demo we recently presented during the 19th KPN Startup Afternoon; we demonstrated how we can use the Scailable Edge AI deployment platform to deploy a fairly complex AI model (a deep neural network recognizing human emotions) to a small ESP32 device. Subsequently, we used an Arduino MKR WAN 1310 and KPN Things to send the resulting emotions to the cloud via LoRa (find a short video here).
Deploy or update AI models in one click to any device. Manage a multitude of devices. Orchestrate and log your model deployments safely and securely. Fast, easy, and secure.
Image processing is one of the prominent uses of AI models. With the Scailable platform we can easily deploy image processing models anywhere. For example, with a click of a button, we were able to deploy a face blurring deep neural netwerk to the browser. Deploying such models in the browser (as opposed to in the cloud) makes that potentially private data never leaves the user’s local machine.
ONNX has been around for a while, and it is becoming a successful intermediate format to move, often heavy, trained neural networks from one training tool to another (e.g., move between pyTorch and Tensorflow), or to deploy models in the cloud using the ONNX runtime. However, ONNX can be put to a much more versatile use: ONNX can easily be used to manually specify AI/ML processing pipelines, including all the pre- and post-processing that is often necessary for real-world deployments. In this tutorial we will show how to use the
onnx helper tools in Python to create a ONNX image processing pipeline from scratch and deploy it efficiently.
ONNX has been around for a while, and it is becoming a successful intermediate format to move, often heavy, trained neural networks from one training tool to another (e.g., move between pyTorch and Tensorflow), or to deploy models in the cloud using the ONNX runtime. In these cases users often simply save a model to ONNX format, without worrying about the resulting ONNX graph.
Scailable deploys your AI and ML models instantly, anywhere. And by anywhere, we do mean, well, anywhere. As a demonstration, today, we succesfully deployed a 2021 visual convolutional neural network to a 1993 laptop.