Select device to run model optimizer on

[Nemes__Adam]

I would like to run a model optimizer on a multi GPU system.

In case the first GPU is in use (not enough memory availble to load the model),

I would like the script to use the other GPU.

How can i select the CUDA Device in such case?

[Nemes__Adam]

Ok.

I found a solution:

Simply setting 

os.environ["CUDA_VISIBLE_DEVICES"] to the desired GPU does the job

[Iffa_Intel]

Greetings,

Glad to know that you had found a solution.

If you have no further inquiries, shall I close this thread?

Sincerely,

Iffa

[Nemes__Adam]

Yes, feel free to close it.

Thank you

[Iffa_Intel]

Greetings,

Intel will no longer monitor this thread since this issue has been resolved. If you need any additional information from Intel, please submit a new question.

Sincerely,

Iffa