How to set multiple outputs using python API?

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Hi,
I have a model which has multiple outputs.
for example, outPut1 and outPut2

If I try to set these outputs using TRT python API e.g.
network.mark_output(outPut1)
network.mark_output(outPut2)

The engine gets built but results in error at runtime as
[TRT] [E] 3: [executionContext.cpp::enqueueInternal::342] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::enqueueInternal::342, condition: (mEngine.bindingIsInput(x) && hasZeroVolume(dims)) || bindings[x]

How can I set multiple outputs using TensorRT python API?

TensorRT version used: 8.4.1.5

2

Hi,
Please check the below link, as they might answer your concerns

Thanks!

4

Hi,

Could you please share with us a minimal issue repro script/model to try from our end for better debugging? Also could you please share with us the complete logs?

Thank you.