Deploy high-performance, deep learning inference
Explore the Intel® Distribution of OpenVINO™ toolkit.
Harness the full potential of AI and computer vision across multiple Intel® architectures to enable new and enhanced use cases in health and life sciences, retail, industrial, and more.
Your AI and Computer Vision Apps...Now Faster
Develop applications and solutions that emulate human vision with the Intel® Distribution of OpenVINO™ toolkit. Based on convolutional neural networks (CNN), the toolkit extends workloads across Intel® hardware (including accelerators) and maximizes performance.
- Enables deep learning inference from edge to cloud
- Accelerates AI workloads, including computer vision, audio, speech, language, and recommendation systems
- Supports heterogeneous execution across Intel® architecture and AI accelerators—CPU, iGPU, Intel® Movidius™ Vision Processing Unit (VPU), FPGA, and Intel® Gaussian & Neural Accelerator (Intel® GNA)—using a common API
- Speeds up time to market via a library of functions and preoptimized kernels
- Includes optimized calls for OpenCV, OpenCL™ kernels, and other industry tools and libraries
Discover the Capabilities
Deep Learning Inference
Accelerate and deploy neural network models across Intel® platforms with a built-in model optimizer for pretrained models and an inference engine runtime for hardware-specific acceleration.
Traditional Computer Vision
Develop and optimize classic computer vision applications built with the OpenCV library and other industry tools.
Hardware Acceleration
Harness the performance of Intel®-based accelerators: CPUs, iGPUs, FPGAs, VPUs, Intel® Gaussian & Neural Accelerators, and IPUs.
Intel offers a powerful portfolio of scalable hardware and software solutions, powered by the Intel Distribution of OpenVINO toolkit, to meet the various performance, power, and price requirements of any use case. See how the toolkit can boost your inference applications across multiple deep neural networks with high throughput and efficiency.
Who Needs This Product
AI researchers, application developers, data scientists, and implementers who require:
- High-performance, deep learning deployments
- Streamlined development and an ease-of-use workflow
- Cross-platform flexibility and scalability with their solutions across Intel® architecture, CPUs, iGPUs, VPUs, Intel® Gaussian & Neural Accelerators, and FPGAs
Medical Imaging Powered by AI
Intel teamed up with Philips to deliver high performance, efficient deep-learning inference on X-rays and computed tomography (CT) scans without the need for accelerators. The solution runs on servers powered by Intel® Xeon® Scalable processors and was optimized by Intel Distribution of OpenVINO toolkit.
what's new in the 2020.1 release
- Introduces post-training optimization to enable significant acceleration improvement with little or no degradation in accuracy. It uses a model quantization technique that streamlines the development process with no model retraining or fine-tuning required.
- Extends support for custom layers on the Intel® Movidius™ Vision Processing Unit (VPU), which enables greater flexibility and customizability for dedicated edge, media, and vision inferencing.
- New low-precision runtime for INT8 includes native support for “fake quantization” and support for 3D convolution layers along with a reduced memory footprint, which enables developers to add more deep learning models to their applications.
- Leverages maximized performance optimizations and cross-platform flexibility with the Deep Learning Workbench. It streamlines and simplifies the development and deployment workflow, now with support for the new Post-training Optimization tool, COCO dataset, new algorithms, and improvements in developer experience and interfaces.
For more information, watch the webinar on the Deep Learning Workbench.
- Added support for new public models, which includes:
- For computer vision: MobileNet* v3, Yolo* v3 (from MXNet GluonCV*)
- For speech and language: LibriSpeech, Automatic Speech Recognition in Reverberant Environments (ASpIRE)
- Added support for new demos and preoptimized, ready-to-deploy models on Open Model Zoo to reduce time to production. They include:
- End-to-end speech recognition
- American Sign Language (ASL) recognition
- Character and text detection with Mask R-CNN
- 3D human pose estimation
What You Can Do
Intelligent Classroom
Track and conduct an analysis on classroom metrics, such as attendance, participation, and engagement.
People Counter Reference Implementation
Create a smart video application using models and inference to run single-class object detection.
Interactive Face Recognition
This example demonstrates face detection capabilities, featuring the ability to determine age, gender, and the position of a head.
Awarded by the
Embedded Vision Alliance*
Support
The developer community and our tech experts provide the help you need in this public forum.
Open Source Software
The OpenVINO toolkit is an open source product. It contains the Intel DLDT for Intel® processors (for CPUs), Intel® Processor Graphics (for GPUs), and heterogeneous support. It includes an open model zoo with pretrained models, samples, and demos.
For more complete information about compiler optimizations, see our optimization notice.
