New Toolkit Helps Developers Streamline Deep Learning Inference & Deployment
Just released as part of Intel's Vision products lineup, Intel announces the new OpenVINO™ toolkit (Open Visual Inference and Neural Network Optimization, and formerly the Intel® Computer Vision SDK) to help developers bring vision intelligence into their applications from edge to cloud.
The toolkit is a free download that helps fast-track development of high-performance computer vision and deep learning inference solutions, and deliver fast and efficient deep learning workloads across multiple types of Intel® platforms (CPU, CPU with integrated graphics, FPGA, and Movidius™ vision processing units (VPUs). Vision systems hold incredible promise to change the world and help us solve problems—whether they’re making homes safer or discovering new medical cures—affording great opportunities for developers.
What's Inside the OpenVINO™ toolkit
The toolkit has a common API and is based on common development standards, such as OpenCL™, OpenCV and OpenVX.
Intel® Deep Learning Deployment Toolkit, which has:
- A Model Optimizer to import trained models from various frameworks (like Caffe*, TensorFlow*, MXNet*), optimize topologies and convert them to a unified intermediate representation file
- An Inference Engine, a simple and unified API for inference across many types of Intel® processors (CPU, GPU (CPUs with integrated graphics/Intel® Processor Graphics), FPGA, VPU (Intel Movidius™ Neural Compute Stick), providing easy heterogeneous processing and asynchronous execution to save developers time.
Optimized computer vision libraries for OpenCV and OpenVX and Photography Vision for CPUs and Intel® Processor Graphics.
Components to increase performance of Intel Processor Graphics for Linux*, including the Intel® Media SDK open source version and OpenCL graphics drivers and runtimes.
FPGA Runtime Environment (RTE) (from the Intel® FPGA SDK for OpenCL™) and bitstreams for Linux FPGA.
Versions for the OpenVINO™ toolkit has three versions:
Gain Significant Performance for Deep Learning Workloads
Depending on workload, quality/resolution for FP16 may be marginally impacted. A performance/quality tradeoff from FP32 to FP16 can affect accuracy; customers are encouraged to experiment to find what works best for their situation. The benchmark results reported in this deck may need to be revised as additional testing is conducted. The results depend on the specific platform configurations and workloads utilized in the testing, and may not be applicable to any particular user’s components, computer system or workloads. The results are not necessarily representative of other benchmarks and other benchmark results may show greater or lesser impact from mitigations.For more complete information about performance and benchmark results, visit www.intel.com/benchmarks. Configuration: Intel® Core™ i7-6700K CPU @ 2.90GHz fixed, GPU GT2 @ 1.00GHz fixed Internal ONLY testing, performed 4/10/2018 Test v312.30 – Ubuntu* 16.04, OpenVINO™ 2018 RC4. Tests were based on various parameters such as model used (these are public), batch size, and other factors. Different models can be accelerated with different Intel hardeware solutions, yet use the same Intel software tools. Benchmark Source: Intel Corporation. See Optimization Notice below.
Intel also has development kits that work with the OpenVINO™ toolkit.
- Intel Vision Intelligence Transforms IoT Industry
- OpenVINO™ toolkit website and technical specifications
- Developer resources to get started
- Intel® Tech.Decoded program, which houses online computer vision webinars (beginning May 25), how-to’s and quick tips to using OpenVINO™ toolkit
- Hands-on trainings and in-person computer vision events
- OpenVINO™ toolkit - Community Forum/public support
Innovate data visualization today!
Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice revision #20110804
OpenVX and the OpenVX logo are trademarks of the Khronos Group Inc.
OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos