How to get "yolo_v3.xml"?

[SHK]

Hi,

I would like to try below sample.

-----------------

Object Detection YOLO* V3 C++ Demo, Async API Performance Showcase

./object_detection_demo_yolov3_async -i <path_to_video>/inputVideo.mp4 -m <path_to_model>/yolo_v3.xml -d GPU

https://docs.openvinotoolkit.org/2020.4/omz_demos_object_detection_demo_yolov3_async_README.html

----------------

I can't find yolo_v3.xml from the directory --   C:\Program Files (x86)\IntelSWTools\openvino_2020.3.194\deployment_tools\open_model_zoo\tools\downloader\intel

Could you explain how to get this model?

Regards, SHK

[Vladimir_Dudnik]

Please note in HTML page your refer to, just a little bit below:

To run the demo, you can use public or pre-trained models. To download the pre-trained models, use the OpenVINO Model Downloader 

Regards,
  Vladimir

[SHK]

Hi Vladimir,

I ran Model Downloader as follows:

C:\Program Files (x86)\IntelSWTools\openvino_2020.3.194\deployment_tools\open_model_zoo\tools\downloader

Downloader.py --all

But "yolo_v3" was not downloaded. Pls refer to attached screen capture. Do you have any other suggestion?

Rgds, SHK

[IntelSupport · Accepted solution]

Hi SHK,

Thanks for reaching out. You have to download the Yolo V3 model from the Model Downloader and you can find the file located in C:\Program Files (x86)\Intel\openvino_2021.1.110\deployment_tools\tools\model_downloader\public\yolo-v3-tf

The Yolo-v3-tf is a public model and you need to specify the model name: ./downloader.py --name yolo-v3-tf

Therefore, the downloaded model will be in the .pb file. To obtain the .xml and .bin file of the Yolo V3 model, you have to convert the model into the Intermediate Representation using the Model Optimizer. Please refer to the following link for the conversion guideline.

https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html

Regards,

Aznie

[IntelSupport]

Hi SHK,

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,

Aznie