Serverless model Human Pose Estimation in CVAT

[Thomascloostermans]

I'm trying to add a model from the open model zoo (https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/human-pose-estimation-0006) to the models of CVAT in the serverless setup. However, I can't find how to do so. Do I need nuclio for this? If so, how? When searching for solutions I saw that yolo-v3-tf can be added using the nuctl command. However, yolo-v3-tf has a nuclio directory and a model handler. This is not the case for human-pose-estimation-006. There is also very little information to find to add models to the CVAT UI.

[Hairul_Intel]

Hi Thomascloostermans,

Thank you for reaching out to us.

For your information, CVAT is no longer a part of OpenVINO™ Toolkit. CVAT tool is now under the umbrella of OpenCV.

Referring to the CVAT Serverless Tutorial, it describes using DL models for Image Classification, Object Detection, Semantic, and Instance Segmentation, etc., and since human-pose-estimation-0006 model is used in Human Pose Estimation demo, the model might work with CVAT.

However, we suggest you post your query regarding adding the model into Serverless CVAT on CVAT Community for further support.

Regards,

Hairul

[Hairul_Intel]

Hi Thomascloostermans,

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

Regards,

Hairul