Microsoft and Qualcomm accelerate AI with Developer Kit

Smart Blog

Microsoft and Qualcomm accelerate AI with Developer Kit

Accelerate AI: The combination of hardware, software, and AI models needed to support scenarios on the edge – e. g. on construction sites – can be difficult to organize.

To remove this barrier, Microsoft and Qualcomm announced a developer kit last year, to accelerate AI inferencing at the intelligent edge. Now the companies announced, that the Vision AI Developer Kit is broadly available. It includes a camera, which uses Qualcomm’s Vision Intelligence 300 Platform, and the software needed to develop intelligent edge solutions using Azure IoT Edge and Azure Machine Learning. It supports an end-to-end Azure enabled solution with real-time image processing locally on the edge device, and model training and management on Azure. The Vision AI Developer Kit, which is produced by eInfochips, can now be ordered from Arrow Electronics
With the use of the kit, customers can deploy vision models in minutes, even if they have only low level machine learning skills. The Azure Cognitive Service „Custom Vision“, enables customers to build their own computer vision model through a user-friendly interface that walks users through the process for uploading data, training, and deploying customer vision models, including image tagging. Custom vision models are then accelerated using the camera’s Snapdragon Neural Processing Engine (SNPE), which enables image classification to run quickly even when offline.

Microsoft and Qualcomm accelerate AI with Developer Kit

The Vision AI Developer Kit also enables data scientists to use Azure Machine Learning to build custom models and deploy them to the included camera. Reference implementations provided in Jupyter notebooks walk data scientists through the steps to upload training data to Azure Blob Storage, run a transfer learning experiment, convert the trained model to be compatible with the developer kit platform, and deploy via Azure IoT Edge.
Developers are provided with a single development environment to manage their code and access Azure services through plugins. Developers using Visual Studio Code may use a GitHub repository which includes sample Python modules, pre-built Azure IoT deployment configurations, and Dockerfiles for container creation and deployment. Visual Studio Code can be used to modify sample modules or create custom modules and containerize them to deploy on the camera. The Vision AI Developer Kit is available through the product page from Arrow.

Author: Tim Cole
Image Credit: Qualcomm


Leave a Reply

Your email address will not be published. Required fields are marked *