What are default settings for Java spring/image model for concurrent detections? Is it possible to improve performance on one CPU? (without cluster) #840
Replies: 2 comments 2 replies
-
|
Does setting several "api_key string required Face Verification Api Key in UUID format" mean that i will increase concurrency? Why do we need different services and different api_keys? |
Beta Was this translation helpful? Give feedback.
-
|
What are default concurrent setting? How many simultaneous detects can it do? Does it start workers or some analogy for each CPU core? What are config files/environment variables that i can tweak? Does it work sequentially? Does setting several "api_key string required Face Verification Api Key in UUID format" mean that i will increase concurrency? |
Beta Was this translation helpful? Give feedback.

Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I am not really familiar with java spring - and it seems that REST API and CompreFace Python SDK works using call to Java spring.
What are default concurrent setting? How many simultaneous detects can it do?
Does it start workers or some analogy for each CPU core?
What are config files/environment variables that i can tweak ?
Or does it work sequentially?
When I send several detect requests using CompreFace Python SDK I see that the server's cpu doesn't reach 100% utilization.
Only some core.
So I am curious, is it possible to improve concurrent perfomance.
And a little bit of repetition but I want to fully understand this:
if I call compreface-python-sdk detect from several separate applications - will they be worked on simultaneously?
Does compreface work on compreface-python-sd requests at the same time (using workers or threads) or does it use something like a queue and work on the tasks sequentially?
Beta Was this translation helpful? Give feedback.
All reactions