example_images.jpg

Creating ONNX from scratch II: Image processing

 ·

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.

Maurits KapteinCreating ONNX from scratch II: Image processing
times.png

AI & Art: In times of corona

 ·

Scailable is proud to provide the AI behind Johan Nieuwenhuize’s new installation, “in times of corona”, now at the Haags Historisch Museum after a succesful exhibit at STROOM The Hague.

Robin van EmdenAI & Art: In times of corona
onnx-netron.png

Tutorial: Creating ONNX from scratch.

 ·

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.

Maurits KapteinTutorial: Creating ONNX from scratch.
386_dnn.jpg

Repurposing old hardware for new AI

 ·

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.

Robin van EmdenRepurposing old hardware for new AI
raspberry_pi.jpg

The making of “Update AI/ML models OtA”

 ·
Deploying trained AI models on edge devices might seem challenging. However, using minimal WebAssembly runtimes, and automatic conversion from ONNX to WebAssembly, modular AI/ML model deployment Over the Air (OtA) to pretty much any edge device is possible.
Maurits KapteinThe making of “Update AI/ML models OtA”
sensor.jpg

A vision on AI deployment on the edge

 ·

As more and more AI models are making their way to production—i.e, they are actually being used in day-to-day business processes—an active discussion has emerged questioning “how AI models should be deployed?” (e.g., using bloated containers? By rebuilding to stand-alone executables? By using “end-to-end” platforms with strong vendor lock in?) and “where AI models should be deployed?” (e.g., on a central cloud? On edge devices? As “close” as possible to the data generating sensors?).

For 2021 we are sharing our vision of AI deployment going forward. You can download the full white-paper here, or read the summary below.

Maurits KapteinA vision on AI deployment on the edge
adminScailable news