Can I get all kind of ops latency after running a model? #19326
Answered
by
skottmckay
xpmemeda
asked this question in
Performance Q&A
-
|
What I want is a table like this:
|
Beta Was this translation helpful? Give feedback.
Answered by
skottmckay
Feb 21, 2024
Replies: 1 comment
-
|
This will output per-node info that you can process if you need additional statistics. The overall execution time will be meaningless due to the cost of producing this output so ignore that. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
sophies927
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This will output per-node info that you can process if you need additional statistics. The overall execution time will be meaningless due to the cost of producing this output so ignore that.
https://onnxruntime.ai/docs/performance/tune-performance/profiling-tools.html#in-code-performance-profiling