MENU

CEVA adds ONNX support to CDNN neural network compiler

By eeNews Europe


ONNX is an open format created by Facebook, Microsoft and AWS to enable interoperability and portability within the AI community, allowing developers to use the right combinations of tools for their project, without being ‘locked in’ to any one framework or ecosystem. The ONNX standard ensures interoperability between different deep learning frameworks, giving developers complete freedom to train their neural networks using any machine learning framework and then deploy it using another AI framework. Now with support for ONNX, CDNN enables developers to import models generated using any ONNX-compatible framework, and deploy them on the CEVA-XM vision DSPs and NeuPro AI processors.

More information

CEVA Deep Neural Network (CDNN)

Related news

New release gives Matlab and Simulink enhanced AI functions

Intel looks to launch Nervana NN processor next year

CEVA licences Bluetooth LE IP to BlueX Microelectronics

Ceva goes non-DSP with neural processor


Share:

10s