OpenVINO Error: Demo supports topologies only with 2 outputs

[tsmith]

I am having an issue running the human pose estimation 0001 demo with OpenVINO. I have everything set up, and when I try to actually run the .exe (cpp), an error occurs. 

[ INFO ] Batch size is forced to 1.
[ ERROR ] Demo supports topologies only with 2 outputs

Here is a screenshot of the window, I am using Anaconda Prompt.

 I tried once with a specified output and then without to see if the problem had anything to do with that (it doesn't). Help would be very much appreciated.

[Vladimir_Dudnik]

@tsmith As you may noticed, there are number of different human pose estimation models available in Open Model Zoo. Even though models solve similar task (estimation of human pose) they have different implementation, different architecture/topology (as you may see from reading models descriptions).

Intel pre-trained models:

• human-pose-estimation-0001
• human-pose-estimation-0005
• human-pose-estimation-0006
• human-pose-estimation-0007

Public pre-trained models:

• human-pose-estimation-3d-0001
• single-human-pose-estimation-0001

Because of this (sometime significant) difference we have several demo applications, which support particular models:

• 3D human pose estimation demo Python
• human pose estimation demo C++/Python

So, for 3D human pose estimation model there is a dedicated demo, other human pose estimation models supported in separate C++/Python demos.

Note, each Open Model Zoo demo contains models.lst file, which lists models, supported by the demo. This .LST file also could be used as a parameter for model downloader (and if necessary for model converter). 

Regards,
  Vladimir

[Wan_Intel]

Hi Taber Smith,

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,

Wan