Maurits Kaptein February 8, 2021 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
Maurits Kaptein February 5, 2021 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
Maurits Kaptein January 16, 2021 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 Kaptein January 16, 2021 An uncommon combination allows efficient sequential learning on the edge.
Maurits Kaptein January 16, 2021 With orthogonal persistence we can implement sequential learning on Edge devices
Maurits Kaptein January 16, 2021 Reducing the memory footprint and improving the speed and portability of deployed models.
Maurits Kaptein January 3, 2021 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
Maurits Kaptein October 2, 2020 With Scailable, deploying complex AI models to the browser (and beyond) is surprisingly easy.
Maurits Kaptein August 10, 2020 Using PyTorch, ONNX, WebAssembly, and the sclbl-webnode to deploy object recognition models directly in the browser.
Honestly? I don’t know. But I do think WebAssembly is a good target for ML/AI deployment (in the browser and beyond).
The shortest tutorial for deploying ML & AI models efficiently.
We are hardly living up to the promises of AI in healthcare. It’s not because of our training, it’s because of our deployment.