OpenVINO™ toolkit 2020.2 Release Available!

OpenVINO™ toolkit 2020.2 Release Available!


What’s New in 2020.2

  • Introduces the new Deep Learning (DL) Streamer component, which uses the GStreamer* multimedia framework. This component enables the creation and deployment of analytic pipelines across Intel architecture from edge to cloud.
  • Includes bug fixes and stability fixes in memory leak issues in the Intel® Threading Building Blocks (Intel® TBB) library.
  • Improves support for noise suppression use cases by adding new layers and bug fixes to the Intel® Gaussian & Neural Accelerators plug-in.
  • Adds support for new FP32 and INT8 models to enable more vision and text use cases:
    • Original models: 3D U-Net, MobileFace
    • Low precision (that is, INT8) models: EAST, OpenPose, RetinaNet, and FaceNet
  • Introduces new pretrained models on Open Model Zoo to reduce time to production, which include:
    • Multi-camera tracking for person reidentification
    • Cascade R-CNN for person detection
  • Published new performance benchmarks

 

Learn more from the release notes, and join the conversation below.
Get Latest Version | Documentation | Tutorials

1 post / 0 new