yoloc5s model in 401-object-detection-webcam notebook

[Mostafa-]

Hello All,

I am trying to run yolov5s (already converted to OpenVINO format) in 401-object-detection-webcam notebook;

https://github.com/openvinotoolkit/openvino_notebooks/tree/main/notebooks/401-object-detection-webcam

and I got this error "Can't SetBlob with name: images, because model input (shape={1,3,640,640}) and blob (shape=(1.3.640.3)) are incompatible".

does it because the model and the data have different shapes, if yes, can you help to solve this please?

BR,

Mostafa

[IntelSupport]

Hi Mostafa,

Thanks for reaching out.

Yolov5 is currently not an officially supported topology by the OpenVINO toolkit nor has it been validated by us. It will be supported in future versions of the OpenVINO toolkit.

For sharing purposes, I also tried running this demo using yolo-v3-tf and yolo-v4-tf models from Open Model Zoo (OMZ) and encountered errors as well.

For your information, ssdlite_mobilenet_v2 is the only officially supported model for this demo. I validated this model, and I'm able to successfully run this demo.

Subsequently, I proactively tested with the following ssd models as well, and am able to run the demo successfully too.

•  ssd_mobilenet_v1_coco
•  ssd_mobilenet_v1_fpn_coco

I share the output when running the demo with the ssd_mobilenet_v1_fpn_coco model here.

Regards,

Aznie

[Mostafa-]

Thank you for your reply.

[IntelSupport]

Hi Mostafa,

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

Regards,

Aznie