Intel OpenCV 4.7 supports Huawei Ascend CANN

Intel launched OpenCV 4.7 version of its, open source computer vision library and supports Huawei Ascend CANN backend for the DNN module to speed up convolution processing in the DNN module.

Intel OpenCV is a software toolkit for processing real-time images and video and providing analytics and machine learning capabilities.

Huawei Compute Architecture for Neural Networks (CANN) is a heterogeneous computing architecture developed by Huawei for AI scenarios, including the operator library and TBE operator development kit, through which you can improve the development efficiency to better match the Ascend chip enablement.

DNN framework provides basic functionality such as security, user administration, and content management, while modules tailor the website for specific deployment needs.

The DNN module was introduced with OpenCV 3.3. Without any dependencies, the model trained by the deep learning framework can be used after the standard installation of OpenCV. The inference calculation can be realized by borrowing the den interface of OpenCV.

(via)