-
Notifications
You must be signed in to change notification settings - Fork 2.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Performance]: Latency is much longer than RealTime when using benchmark_app for profiling #24517
Comments
Hi @cold-blue! What device you used for inference? CPU, GPU? |
.take |
Thank you for looking into this issue! Please let us know if you have any questions or require any help. |
hi @cold-blue
How to solve:
Here is an example code to break down the time overhead of each step:
By using this approach, you can get detailed insights into the time taken for each step and perform targeted optimizations. This will help you better understand and resolve the issue of long latency times. |
@cold-blue
|
OpenVINO Version
No response
Operating System
Windows System
Device used for inference
None
OpenVINO installation
PyPi
Programming Language
Python
Hardware Architecture
x86 (64 bits)
Model used
N/A
Model quantization
Yes
Target Platform
No response
Performance issue description
When I am using benchmark_app to profile a model. I find that the latency in the report is much longer than the total RealTime computed in detailed_counter_report.csv.
In report.csv:
In detailed_counter_report.csv:
I wonder whether this is a normal phenomenon and what is the reason?
Step-by-step reproduction
No response
Issue submission checklist
The text was updated successfully, but these errors were encountered: