Releases: dlstreamer/edge-ai-extension
v0.7.1-beta
The Intel® DL Streamer – Edge AI Extension is a microservice based on DL Streamer Pipeline Server that provides video analytics pipelines built with OpenVINO™ DL Streamer. Developers can send decoded video frames to the AI Extension which performs detection, classification, or tracking and returns the results. The AI Extension exposes gRPC and HTTP APIs that are compatible with Azure Video Analyzer (AVA). Powered by OpenVINO™ toolkit, the AI Extension enables developers to build, optimize and deploy deep learning inference workloads for maximum performance across Intel® architectures.
New and Changed in Release v0.7.1-beta
| Title | Description |
|---|---|
| Branding change | Aligned names to Intel® Deep Learning Streamer suite. |
| Documentation update | Additional documentation to enable HDDL-R in AVA framework |
Known Issues
Known issues can be found as GitHub issues. If you encounter defects in functionality, please submit an issue.
* Other names and brands may be claimed as the property of others.
v0.7.0-beta
The Intel® DL Streamer – Edge AI Extension is a microservice based on Video Analytics Serving that provides video analytics pipelines built with OpenVINO™ DL Streamer. Developers can send decoded video frames to the AI Extension which performs detection, classification, or tracking and returns the results. The AI Extension exposes gRPC and HTTP APIs that are compatible with Azure Video Analyzer (AVA). Powered by OpenVINO™ toolkit, the AI Extension enables developers to build, optimize and deploy deep learning inference workloads for maximum performance across Intel® architectures.
New and Changed in Release v0.7.0-beta
| Title | Description |
|---|---|
| Moved to new repo | For improved support the Edge AI Extension now has its own repo and imports Video Analytics Serving v0.7.0 as an external dependency. Docker hub images can now be found at intel/dlstreamer-edge-ai-extension. |
| Added support for AVA HTTP protocol | The Edge AI Extension now supports both gRPC and HTTP AVA protocols. The supported protocol is selected at launch time. |
| Improved gRPC performance | Processing rate has been increased by up to 2x by performing frame transfer and processing simultaneously. |
| Updated pipelines | Added people and vehicle specific detection pipelines. Renamed existing pipelines to better match their purpose. |
| HDDL-R accelerator support | HDDL-R requires additional dependencies no longer in the the OpenVINO base image – these have been added to the VA Serving docker layer. |
| OpenVINO 2021.4.2 support | Updated DL Streamer base image to openvino/ubuntu20_data_runtime:2021.4.2. |
Known Issues
Known issues can be found as GitHub issues. If you encounter defects in functionality, please submit an issue.
* Other names and brands may be claimed as the property of others.