Does OpenVINO 2021.1 has TF2 Extensions to support Efficientdet and Faster-RCNN Models?

[Vicky_Rama]

I was adviced to roll back to OpenVINO 2021.1 from 2021.4 (which I was using before uninstalling to roll back to 2021.1), by ADLINK to make my off-line conversions using MO and deploying them on their Edge device.....I installed the Version 2021.1, ran all the pre-requisites, but could not find any Extensions (TF2 Front) related to Efficientdet Models, as well as other TF models later to TF1.7.....A quick feed back will help me to write to ADLINK to make them create an app compatible to OpenVINO 2021.4.....Looking forward

[Peh_Intel]

Hi Vicky,

Thanks for reaching out to us.

For your information, config files are added to support automl EfficientDet models and TensorFlow 2.0 Faster R-CNN models starting from OpenVINO 2021.2 onwards.

Regards,

Peh

[Vicky_Rama]

Thanks Khun-Peh........I will get back and probably post a new query, based on the outcome of my discussions with ADLINK (who are one of Intel's Channel Partner and use Intel Movidius in their Edge Hardware)....

[Peh_Intel]

Hi Vicky,

This thread will no longer be monitored since we have provided answers. If you need any additional information from Intel, please submit a new question. 

Regards,

Peh