Premium tier Qualcomm® Snapdragon™ mobile platforms have extensive heterogeneous computing capabilities that are engineered to allow the running of trained neural networks on device without a need for connection to the cloud. 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 Snapdragon mobile platforms, whether that is the CPU, GPU or DSP.
高級版Qualcomm®Snapdragon™移動平臺具有廣泛的異構計算功能，旨在允許在設備上運行受過訓練的神經網絡，而無需連接到雲端。 Qualcomm®Snapdragon™神經處理引擎（NPE）SDK旨在幫助開發人員在Snapdragon移動平臺上運行Caffe / Caffe2或TensorFlow培訓的一個或多個神經網絡模型，無論是CPU，GPU還是DSP。
The Snapdragon NPE is engineered to help developers save time and effort in optimizing performance of trained neural networks on devices with Snapdragon. 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 Snapdragon NPE supports convolutional neural networks and custom layers.
Snapdragon NPE旨在幫助開發人員節省時間和精力來優化使用Snapdragon的設備上訓練有素的神經網絡的性能。 它通過提供用於模型轉換和執行的工具以及針對核心的API，通過功能和性能配置文件來匹配所需的用戶體驗。 Snapdragon NPE支持卷積神經網絡和用戶自定義層。
The Snapdragon NPE does a lot of the heavy lifting needed to run neural networks on Snapdragon mobile platforms, which can help provide developers with more time and resources to focus on building new and innovative user experiences.
Snapdragon NPE在Snapdragon移動平臺上運行神經網絡所需的大量工作，可以幫助開發人員更多的時間和資源，專注於建立新的和創新的用戶體驗。
If you would like a more in-depth introduction to artificial intelligence and the Neural Processing SDK, we encourage you to view our Snapdragon and Artificial Intelligence at the Edge webinar, which provides an overview of what we have to offer.
如果您想更深入地介紹人工智能和神經處理SDK，我們鼓勵您在“邊緣”網絡研討會上查看我們的Snapdragon和人工智能，其中概述了我們提供的內容。
What’s in the SDK?（SDK中有什麼？）
Android and Linux runtimes for neural network model execution
Android和Linux運行時神經網絡模型執行Acceleration support for Qualcomm® Hexagon™ DSPs, Qualcomm® Adreno™ GPUs and Qualcomm® Kryo™, CPUs
加速支持Qualcomm®Hexagon™DSP，Qualcomm®Adreno™GPU和Qualcomm®Kryo™，CPUsSupport for models in Caffe, Caffe2 and TensorFlow formats
支持Caffe，Caffe2和TensorFlow格式的模型APIs for controlling loading, execution and scheduling on the runtimes
用於控制運行時的加載，執行和調度的APIDesktop tools for model conversion
用於模型轉換的桌面工具Performance benchmark for bottleneck identification
瓶頸識別的性能基準Sample code and tutorials
示例代碼和教程HTML Documentation
HTML文檔
To make the AI developer’s life easier, the Snapdragon NPE SDK does not define yet another library of network layers; instead it gives developers the freedom to design and train their networks using familiar frameworks, with Caffe/Caffe2 and TensorFlow being supported at launch. The development workflow is the following:
爲了使AI開發人員的生活更輕鬆，Snapdragon NPE SDK還沒有定義另一個網絡層庫; 相反，它使開發人員可以自由地使用熟悉的框架設計和訓練他們的網絡，Caffe / Caffe2和TensorFlow在啓動時得到支持。 開發工作流程如下：
After designing and training, the model file needs to be converted into a “.dlc” (Deep Learning Container) file to be used by the Snapdragon NPE runtime. The conversion tool will output conversion statistics, including information about unsupported or non-accelerated layers, that the developer can use to adjust the design of the initial model.
在設計和培訓之後，模型文件需要轉換爲“.dlc”（深度學習容器）文件供Snapdragon NPE運行時使用。 轉換工具將輸出轉換統計信息，包括有關不受支持或非加速層的信息，開發人員可以使用這些信息來調整初始模型的設計。
Is the Snapdragon NPE SDK Right for You?（Snapdragon NPE SDK是否適合您？）
Developing for artificial intelligence using the Snapdragon NPE SDK does require a few prerequisites before you can get started creating solutions.
使用Snapdragon NPE SDK開發人造智能需要幾個先決條件，才能開始創建解決方案。
You need to run a convolutional modell in one or multiple verticals, including mobile, automotive, IoT, AR, drones, and robotics
您需要在一個或多個垂直方向運行卷積模型，包括移動，汽車，IoT，AR，無人機和機器人You know how to design and train a model or already have a pre-trained model file
您知道如何設計和訓練一個模型，或者已經有一個預先訓練的模型文件Your framework of choice is Caffe/Caffe2 or TensorFlow
您選擇的框架是Caffe / Caffe2或TensorFlowYou make JAVA APPs for Android or native applications for Android or Linux
您可以爲Android或Android或Linux的本機應用程序製作JAVA應用程序You have an Ubuntu 14.04 development environment
您有一個Ubuntu 14.04開發環境You have a supported device to test your application on
您有一個支持的設備來測試您的應用程序