Magical OpenVINO Integration with TensorFlow

This video was originally published at Intel’s YouTube channel. It is reprinted here with the permission of Intel.

In this episode, Ragesh and Steph talk about OpenVINO™ Integration with Tensorflow which is used for speeding up inferencing of a TensorFlow based real-time application at the edge. Ragesh pulls and runs a docker image on his Intel® Core™ i7 CPU to showcase what it can do, uses a notebook that covers an object detection use case and demonstrates acceleration of YOLOv4 model, trained on coco dataset. In the end, Steph mentions 4 short training videos for you on Container Playground from Intel® DevCloud: Edge Workloads.

OpenVINO™ integration with TensorFlow GitHub Homepage: https://bit.ly/3QHNxzy

Validated models supported by OpenVINO™ integration with TensorFlow: https://bit.ly/3A5dSlr

Dockerfiles and prebuilt images: https://bit.ly/3neu4co

Sample applications and tutorials on Intel® DevCloud: https://intel.ly/3OgVEBG

Object Detection Jupyter Notebook on GitHub: https://bit.ly/3OznOaG

How OpenVINO™ integration with TensorFlow really works under the hood?: https://intel.ly/3xO1YJK

Video playlist to learn about Intel® DevCloud container playground: https://bit.ly/39NrK8Z

Performance improvement of SSD & Faster-RCNN object detection models are in progress and will be addressed in the upcoming release. Stay tuned to this page: https://bit.ly/3njwg2j

Please submit your questions, feature requests and bug reports via GitHub issues: https://bit.ly/3ni3teu

About Intel Software

The Intel® Developer Zone encourages and supports software developers that are developing applications for Intel hardware and software products. The Intel Software YouTube channel is a place to learn tips and tricks, get the latest news, watch product demos from both Intel, and our many partners across multiple fields. You’ll find videos covering the topics listed below, and to learn more, you can follow the links provided!

Connect with Intel Software:

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top