Snapdragon Neural Processing Engine
The Qualcomm® Snapdragon™ Neural Processing Engine (NPE) SDK is designed to help developers run one or more neural network models trained in Caffe/Caffe2 or Tensorflow on any Qualcomm® Snapdragon™ processor, whether that is the CPU, GPU, and DSP.
The NPE is engineered to help developers save time and effort in optimizing performance of trained neural networks on Snapdragon devices. It does this by providing tools for model conversion and execution as well as APIs for targeting the core with the power and performance profile to match the desired user experience. The NPE supports convolutional neural networks, Long Short Term Memory networks (LSTMs) and custom layers.
The NPE does a lot of the heavy lifting needed to run neural networks on Snapdragon, which can help provide developers with more time and resources to focus on building new and innovative user experiences.
The SDK includes runtime software, libraries, APIs, offline model conversion tools, debugging and benchmarking tools, sample code, and documentation. The NPE can be used in multiple verticals including mobile, automotive, IoT, drones, and robotics.
Scheduled for availability in July, 2017. Please fill out the form below to be notified when this tool is available for download (availability subject to change).