Python API? Speedup?

[lars-ek]

Hi,

I have a question: I want to detect the frames of two cameras simultaneously and currently use the darknet python wrapper (AlexeyAB-Version) and just feed one frame to the network at once. Is it possible to speed up the detection by using batch detection (batch=2) within python wrapper (e.g. darknet_video.py)? How does the speed compare (2 frames with batch=1 vs. batch=2)?

Thank you.

[lars-ek]

@vincentgong7 Sorry to ask again, but do you have any hint if there is an speedup using batch detection? In AlexeyAB-Version, the batch-inference function does not offer any performance gain. Is it different with your fork?

Thank you.

[vincentgong7]

Hi, I have not yet used the batch-inference function in the AlexeyAB version. The batch function in my version is different I think. Have you tried the batch function in my version? The performance should be fine. Regards, Vincent X. Gong

…

On Sun, Oct 4, 2020 at 8:13 AM lars-ek ***@***.***> wrote: @vincentgong7 <https://github.com/vincentgong7> Sorry to ask again, but do you have any hint if there is an speedup using batch detection? In AlexeyAB-Version, the batch-inference function does not offer any performance gain. Is it different with your fork? Thank you. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#21 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEI2JRGHITU6ANFM7IGLSJAHBPANCNFSM4PORBS6A> .