If industry leaders in the tech world are to be believed, Artificial Intelligence and Deep Learning are the future of mobile. Smartphones currently play a central role in our lives, assisting us when we perform many of our daily tasks. In the future, smartphones would be able to predict our tasks and perform them, and we are starting to see glimpses of this future with advancements in machine learning and neural networks. Furthermore, such methods allow the ongoing improvement of technologies like self-driving vehicles and augmented reality.
To promote work on this end, Qualcomm has announced the availability of the Qualcomm Snapdragon Neural Processing Engine Software Development Kit, offered to developers through Qualcomm's Developer Network.
The Snapdragon NPE is the first deep learning software framework designed for Snapdragon's Mobile Platforms. NPE is engineered to provide developers with the software tools needed to accelerate deep neural network workloads on mobile and other edge devices powered by Snapdragon processors. Developers can choose the optimal Snapdragon core for the desired user experience, including the Qualcomm Kryo CPU, Qualcomm Adreno GPU or the Qualcomm Hexagon DSP. The NPE provides the tools needed to deliver on-device neural network-driven user experiences.
Developers can take advantage of deep learning user experiences like style transfers and filters for augmented reality, scene detection, facial recognition, natural language understanding, object tracking and avoidance, gesturing, and text recognition, among other functions. The Snapdragon Neural Processing Engine is already being utilized by several industry majors — for example, Facebook recently integrated the Snapdragon NPE into the camera of the official Facebook app to accelerate Caffe2-powered AR features. Through the NPE, Facebook managed to achieve five times better performance on the Adreno GPU, compared to a generic CPU implementation.
"The Snapdragon NPE was created to give developers the tools to easily migrate intelligence from the cloud to edge devices, and affords them the flexibility to target the appropriate Snapdragon core with the power and performance profile for a given user experience.""
The Snapdragon Neural Processing Engine is compatible with Snapdragon 600 and 800 Series Mobile Platforms, and is designed to support common deep learning frameworks such as Caffe, Caffe2 and Tensorflow, and also offers support for custom layers. The SDK includes runtime software, libraries, APIs, offline model conversion tools, sample code, documentation, and debugging and benchmarking tools. Once again, the NPE SDK can be found at the Qualcomm Developer Network page.
What are your thoughts on the SDK release of Qualcomm's Snapdragon NPE? Let us know in the comments below!
from xda-developers http://ift.tt/2uw46EZ
via IFTTT
No comments:
Post a Comment