Often the hardest part of a project is the “final mile” – getting deep learning models into production and yielding results. In order to accelerate this process, you need an effective approach that supports ONNX (open neural network exchange) format models for inferencing — allowing you to leverage trained ONNX format models to implement streaming analytics in the cloud or at the edge.
You can focus on training the most effective model for the problem at hand by simplifying the task of deployment on various supported GPU and CPU hardware with capabilities that remove a lot of the model deployment complexity.
In this latest Data Science Central webinar, you will learn:
• How to inference models like neural nets for computer vision use cases, including object detection and classification.
• How the integration of ONNX Runtime with SAS Event Stream Processing combines streaming analytics with simplified testing and deployment on different GPU and CPU accelerated hardware.
• How you can deploy ONNX format models to gain maximum benefit using sample projects provided through GitHub examples
Steven Allan, Senior Product Manager – SAS
Daniele Cazzari, Global Lead IoT, Edge and Cloud Analytics Solutions – SAS
Sean Welch, Host and Producer – DSC