Issue to read IR model (OpenVINO IR from zoo) on NCS2+Raspberry Pi4

[fredf]

Error when reading a model from DL Workbench on RPi4 (OpenVino 2021.4.2):

1. >>> net = ie.read_network(model="face-detection-0200.xml", weights="face-detection-0200.bin")
2. Traceback (most recent call last):
3. File "<stdin>", line 1, in <module>
4. File "ie_api.pyx", line 357, in openvino.inference_engine.ie_api.IECore.read_network
5. File "ie_api.pyx", line 400, in openvino.inference_engine.ie_api.IECore.read_network
6. RuntimeError: Unknown model format! Cannot find reader for model format: xml and read the model: face-detection-0200.xml. Please check that reader library exists in your PATH.

OpenVino 2022.1 for Raspberry not found on repo

[Hairul_Intel · Accepted solution]

Hi fredf,

Thank you for reaching out to us.

This error is due to the difference in version for Intermediate Representation (IR) model and OpenVINO™ Toolkit.

If you're using OpenVINO™ Toolkit 2021.4.2 for Raspbian OS Package, git clone the same version of Open Model Zoo and download the model again:

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

cd open_model_zoo/tools/downloader

python3 -m pip install -r requirements.in

python3 downloader.py --name face-detection-0200

On another note, OpenVINO™ DL Workbench is only supported on Linux, Windows and Mac OS. OpenVINO™ DL Workbench is not validated on Raspbian OS.

Additionally, DL Workbench requires 8GB of available RAM space to ensure all features are available. You can refer to the DL Workbench Recommended Requirements for more information.

Regards,

Hairul

[Wan_Intel]

Hi Fredf,

Thanks for your question.

This thread will no longer be monitored since this issue has been resolved. 

If you need any additional information from Intel, please submit a new question.

Regards,

Hairul