Code Samples & Demo Applications
Code Samples
The release package of the toolkit includes simple console applications and sample codes that demonstrate how to integrate deep learning inference into your solutions.
Hello Classification
Perform inference of image classification networks like AlexNet and GoogLeNet using the Synchronous Inference Request API.
Image Classification Async
This sample shows how to use the asynchronous API for classification networks and get more performance.
Object Detection for SSD
This sample demonstrates the inference of object detection networks that are based on the SSD.
Automatic Speech Recognition
This acoustic model inference is based on Kaldi neural networks and speech feature vectors.
Hello Query Device
Query for available inference engine devices and their metrics and configuration values.
Hello Reshape SSD
Resize an inference of SSD networks using the ShapeInfer API according to an input size.
Demo Applications
The Open Model Zoo demo applications show how you can use the inference engine in your AI solutions to solve specific use cases.
Crossroad Camera C++
Use this inference pipeline to detect, recognize, and re-identify people. The application uses the Person Detection Network followed by the Person Attributes Recognition and Person Reidentification Retail networks applied on top of the detection results.
Smart Classroom C++
This example shows a joint use of several neural networks to detect student actions (sitting, standing, raising hand, lying on a desk, and more) and recognize people by faces in a classroom environment.
Text Detection C++
Learn how to use neural networks to detect and recognize printed text rotated at any angle in various environment.
Object Detection SSD with Python*, Async API Performance Showcase
This demo showcases object detection with SSD and the Async API. Async API use can improve the overall frame-rate of the application. Rather than wait for inference to complete, the app can continue performing tasks on the host while the accelerator is also at work, hiding the latency of frame capture.
Super Resolution C++
This demo reconstructs the high-resolution image from the original low-resolution image.
OpenCV
Included in the installation, these examples showcase capabilities for the Intel® Distribution of OpenVINO™ toolkit. Find them under: <install_dir>\opencv\samples\. For documentation, see the README.md file in the Samples directory.
OpenCV Version
This application prints the OpenCV library version and build configuration.
People Detection
Learn how to use the built-in feature descriptor (a histogram of oriented gradients) to detect pedestrians.
Colorization
This sample demonstrates recoloring grayscale images using a DNN. For more information on the Caffe* model and .prototxt file, see GitHub*.
Custom OpenCL™ Kernel
Implement and run this kernel via the Transparency Application Programming Interface (TAPI).
Dense Optical Flow
Run a dense optical flow using TAPI with the Farnebäck and TV-L1 algorithms.
Информация о продукте и производительности
1
Компиляторы Intel могут не обеспечивать для процессоров других производителей уровень оптимизации, который не является присущим только процессорам Intel. В состав этих оптимизаций входят наборы команд SSE2, SSE3 и SSSE3, а также другие оптимизации. Корпорация Intel не гарантирует доступность, функциональность или эффективность работы любых приложений оптимизации для микропроцессоров других производителей. Содержащиеся в данной продукции оптимизации, предназначены для использования с конкретными микропроцессорами Intel. Некоторые оптимизации, не относящиеся к микроархитектуре Intel, зарезервированы для микропроцессоров Intel. Пожалуйста, см. соответствующее руководство пользователя или справочные руководства для получения дополнительной информации о конкретных наборах команд, к которым относится данное уведомление.
Редакция уведомления № 20110804