No find path model_optimization

[Megamind-5]

Hi,

I'm mind.

I'm trying to convert model YOLOv3 from .pb to .XML.  http://www.keymolen.com/2020/04/run-yolov3-on-raspberry-pi-with-intel.html 

But I didn't find path

/opt/intel/openvino/deployment_tools/model_optimization/mo.py

In my understanding, it should have model_optimization on deployment_tool, but it has just inference_engine and ngram in deployment_tools.

I use  l_openvino_toolkit_runtime_raspbian_p_2020.1.023.tgz

on Raspbian any suggestions about this or can I convert YOLOv3 for NSC2.

Thank you in advance.

[Alberto_Sykes]

Megamind-5, Thank you for posting in the Intel® Communities Support.

Just to let you know, in order for us to be able to provide the most accurate assistance on this scenario, I just moved your thread to the proper department, they will further assist you with this topic as soon as possible.

Regards,

Albert R.

Intel Customer Support Technician

[Peh_Intel · Accepted solution]

Hi Megamind-5,

Thanks for reaching out to us.

For your information, OpenVINO™ Toolkit package does not include the Model Optimizer. As such, you need to install Intel® Distribution of OpenVINO™ toolkit on your host machine (Windows 10 or Linux) in order for you to convert the models to Intermediate Representation (IR). Then, you can transfer the IR format files to your Raspberry Pi for use.

Furthermore, the yolo-v3-tf model only added to support since OpenVINO™ Toolkit version 2020.2 while the yolo-v3-tiny-tf model only added to support since OpenVINO™ Toolkit version 2021.1. Thus, I would suggest you download the latest OpenVINO™ Toolkit which is l_openvino_toolkit_runtime_raspbian_p_2021.3.394.tgz.

Regards,

Peh

[Megamind-5]

Thank you so much

[Peh_Intel]

Hi Megamind-5,

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,

Peh