Input and output shapes from trtexec

Hi Nvidia,

I am using trtexec to benchmark a tensorRT engine. The engine has fixed size input. I am
wondering if there is a way to get the input and output shapes. This information should be available since the engine performs inference on dummy inputs to benchmark the engine, but I don’t see it in the logs.

Thank you

  • Fatma

Hi @fatma.tlili,

Have you tried --verbose option and verified in the verbose logs ?
Please check verbose logs.

Thank you.