We are proud to share with you that our CDNN2 deep learning software framework is the recipient of another award! This time, Embedded Computing Design named CDNN2 the 2017 Top Innovative Product in the Software category. We congratulate the other two winners in the Systems and Silicon categories, and the honorable mentions in all three categories. You can read the full announcement here on the Embedded Computing website.
The judges cited the toolkit’s ability to eliminate months of development time. Earlier this year, the CDNN2 was awarded the China Electronics Market (CEM) Editor’s Choice Award. We are pleased that the embedded industry recognizes the innovation of the CDNN2 and are very proud to receives these accolades.
Cutting Development Time from Months to Minutes
Supporting deep learning on mobile and embedded systems is part of our mission to make the world smarter, connected, and accessible to everyone. This is quite a difficult task, as I wrote about in a column titled Deep Learning Challenges in Embedded Platforms. Hence, we developed the CDNN2 as a comprehensive toolkit to streamline the development process on low-power embedded systems. It enables push button conversion of neural networks (NNs) from the leading frameworks like TensorFlow and Caffe to our CEVA-XM family of DSP cores. For embedded developers, this means that the effort of porting from a PC environment to a CEVA vision DSP is cut from months to minutes! After the conversion, the NNs are set to run on a fixed-point embedded environment that uses just a fraction of the power. You can read more about how we achieve this here on our blog. After the conversion, the NNs can be applied to a wide variety of use cases, including smartphones, virtual and augmented reality, ADAS, drones and surveillance.
If you want to find out more about how you can benefit from this innovative product, you can find lots of useful resources on our CDNN2 product page.
You might also like
More from Deep Learning
As demand for artificial intelligence (AI) increases, chip makers strive to create more powerful and more efficient processors. The goal …
On Demand Webinar: Challenges of Vision Based Autonomous Driving & Facilitation of An Embedded Neural Network Platform
The automotive market is seeing accelerated growth and rapid adoption of vision applications that will lead the way to autonomous …