Error: Must specify at least one target to fetch or execute

[triton-inference-server]

Error: Must specify at least one target to fetch or execute

[Tabrizian]

It looks like your model doesn't have any output. Is it expected? I think this error comes from Tensorflow side. Can you generate a single request using Triton clients to make sure that it works properly?

[belugum]

Thanks! I've added the outputs and it works now. How long is it supposed to take? It's been stuck for 15 minutes now.
We're using the --strict-model-config=false option for tritonserver, that's why the outputs were not set at first, is there a similar option with model-analyser? The outputs aren't relevant for the analysis, right?

[Tabrizian]

It can take a while to complete depending on your model. The add_sub model takes around 45 minutes on a TITAN RTX GPU. You can pass triton-server-flags in the Model Analyzer Config. You can read more about it below:

https://github.com/triton-inference-server/model_analyzer/blob/main/docs/config.md#triton-server-flags