hello all. i am running YOLOv3 on QEMUx86-64 using opencv::dnn module. at the moment it takes 5 minutes for a very small model. how can i accelerate this processing of application?
Consider using the Mobile Net version of YOLO. This contributor provides a good brief on MobileNets architecture and you can find the paper here. A simple Google search yields a lot of readily-available options. According to this benchmark, it has a 217 milliseconds inference time on an i5. Keep in mind, what you gain in speed, you loose in accuracy.
That is great. It is definitely worth a try for my embedded device. Just one question: this also uses opencv::dnn module?
Yes it does. The DNN module just loads the model weights and performs the respective operations. MobileNets still perform convolutions, subsampling, etc and these are operations already supported by DNN module. The setup should still be the same regardless but refer to this tutorial for guidance.
Well - if you are in the lucky situation that you have a nvidiea gpu avaible you could compile opencv dnn module with cuda support. Or you could use yolo directly(this repo https://github.com/AlexeyAB/darknet has .dll / .so avaible - so you can include it in your app.
Or you could have a strong machine in the network and your client communicates to the server - which does the heavy lifting for the client)
Or you could try convert the yolo model and run it on special hardware like nvidea jetson / google coral / intel movideos.
No nvidia support for now but i can try these. How about opencl framework? And how to use it for opencv::dnn module based application
Asked: 2020-02-18 03:52:36 -0600
Seen: 427 times
Last updated: Feb 19 '20
