Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6474 Discussions

Output for tensor name 'boxes' is not found.

Farhâd
Novice
1,035 Views

Hello:

Trying to run the sample Hello Object Detection in:

https://docs.openvino.ai/latest/notebooks/004-hello-detection-with-output.html

 

Get the following error:

 

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-13-91d59ca51c94> in <module>
      6 
      7 input_layer_ir = compiled_model.input(0)
----> 8 output_layer_ir = compiled_model.output("boxes")

RuntimeError: Output for tensor name 'boxes' is not found.

 

Please take a look

 

0 Kudos
4 Replies
Hairul_Intel
Moderator
994 Views

Hi Farhâd,

Thank you for reaching out to us.

 

For your information, this error is related to the model's output. For the Hello Object Detection notebook tutorial, it is using the horizontal-text-detection-0001 from Open Model Zoo which has the "boxes" output.

 

Please ensure that the IR model (.xml and .bin) files are included in the following directory when running the notebook:

horizontal text.png

 

 

You can refer to the Outputs section for more information.

 

 

Regards,

Hairul

 

0 Kudos
Farhâd
Novice
978 Views

thanks.

how can i access those IR models ( xml + bin )?

0 Kudos
Hairul_Intel
Moderator
965 Views

Hi Farhâd,

Following the OpenVINO™ Notebooks Windows installation guide, you can access the IR model (.xml and .bin) files for the Hello Object Detection tutorial located in the following directory:

<openvino_notebooks_dir>\notebooks\004-hello-detection\model

 

model.png

 

 

Regards,

Hairul

 

0 Kudos
Hairul_Intel
Moderator
920 Views

Hi Farhâd,

This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.

 

 

Regards,

Hairul


0 Kudos
Reply