Intel Neural Compute Stick2

[Yifan02]

 

When I used NCS2 to accelerate the YOLOv5 network, an error occurred in the reasoning process.

Error:output item should have 7 as a last dimension.

[Hairul_Intel]

Hi Yifan02,

Thank you for reaching out to us.

For your information, the error occurs due to the Object Detection SSD sample not supporting YOLO models.

You can try using the Object Detection Demo from Open Model Zoo. However, do note that there's no guarantee that the demo can run as YOLOv5 models are not officially validated for the demo as it is not listed in the Supported Model lists.

Here is the command for you to try running the Object Detection Demo with YOLOv5 model:

python3 object_detection_demo.py -at yolov4 -d MYRIAD -m yolov5.xml -i <input_image>

To clone the Open Model Zoo repository for 2021.4.2, run the following command:

git clone --depth 1 -b 2021.4.2 https://github.com/openvinotoolkit/open_model_zoo.git

Regards,

Hairul

[Hairul_Intel]

Hi Yifan02,

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