Accelerating Neural Network Solutions With Simple APIs

Objective

This Code Lab topic is intended to give an insight to the user about the various APIs and tools provided by Neural SDK. The contents also handholds him/her to prepare and run a neural network model on a Samsung device with the help of a sample native benchmark application.

Overview

Samsung Neural SDK enables developers to efficiently execute the trained neural networks on Samsung devices. The SDK is designed to accelerate neural network models in order to improve performance by making the best use of underlying hardware components.

A deep neural network consists of several computationally intensive operations that increase the latency and impacts the performance of any hand-held device. Samsung Neural SDK bridges the gap between a neural network designer and device performance, allowing network designers to focus on improving the overall user experience.

Developers can integrate their code with simple C++ APIs in order to deploy their trained models on devices. The SDK supports popular Caffe and TensorFlow framework based model formats.