Why run the demo with pre-trained weights in python is slower than through darknet.exe? #7867
Unanswered
KevinSalmeron
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I'm testing Darknet with Yolo v4 with CUDA.
i'm get better performance executing the darknet.exe (average 11 fps) but when i run darknet_video.py i get a maximum of 3 fps.
My rig is: AMD Ryzen 5 4600h with GTX 1650 with 4GB, 16GB of RAM memory in my sistem and SSD nvme storage.
Can you give me some tips for improve my performance via Python without decrease the accuracy?
Beta Was this translation helpful? Give feedback.
All reactions