Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5772 Discussions

Converting OmniScaleNet from PyTorch to Intel IR

Socke__Linux
Beginner
331 Views

Is there already something in the model optimizer to convert a self learned OSNet?

0 Kudos
1 Solution
SuryaPSC_Intel
Employee
331 Views

Hi Linux,

OSNet is not an OpenVINO pytorch supported topology. Kindly refer to Supported Pytorch* Models via ONNX Conversion.

Best Regards,

Surya

View solution in original post

3 Replies
SuryaPSC_Intel
Employee
332 Views

Hi Linux,

OSNet is not an OpenVINO pytorch supported topology. Kindly refer to Supported Pytorch* Models via ONNX Conversion.

Best Regards,

Surya

Socke__Linux
Beginner
331 Views

Ok, thanks.

Can give me some links where I can learn to do it myself then?

Greetings Socke

Max_L_Intel
Moderator
331 Views

Hi Socke, Linux

As Surya mentioned above, OSNet is not the one of officially supported topologies. However, you can try to convert this via ONNX conversion if all the model layers are supported by Model Optimizer, as per https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Supported_Frameworks_Layers.html#o...
and your inference device, as per  https://docs.openvinotoolkit.org/latest/_docs_IE_DG_supported_plugins_Supported_Devices.html#support...

The command is:

python3 mo.py --input_model <INPUT_MODEL>.onnx

Thanks.
Best regards, Max.

Reply