OpenVINO Inference Engine uses synchronous or asynchronous inference mode

[nat98]

Hello there,

I am doing some benchmark/comparison for my original (unoptimized) model and the OpenVINO (optimized) model. The performance evaluation of the optimized model is done using DL Workbench.

Now, I would like to know that, what is the default inference mode when I am measuring throughput/accuracy/latency in DL Workbench? Is it synchronous or asynchronous inference mode?

Thanks.

Regards,

nat98

[Wan_Intel · Accepted solution]

Hi Nat98,

Thanks for reaching out to us.

For your information, the default inference mode when measuring throughput/accuracy/latency in DL Workbench is the asynchronous inference mode.

Regards,

Wan

[artyom_tugaryov]

Hello @nat98 ,

DL Workbench runs benchmark application with default inference mode to measure performance of a model. The default inference mode in benchmark application is the asynchronous mode.

To measure accuracy of a model DL Workbench uses  accuracy_checker with the asynchronous mode by default.

[nat98]

Hello Wan_Intel and artyom_tugaryov,

Thanks for answering my question and thanks for both of your replies.

Regards,

Nathaniel Tan

[Wan_Intel]

Hi Nat98,

You are welcome.

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,

Wan