Open hexiangquan opened 6 years ago
yolov3 is based on darknet53. This model is not very fast on embedded system. Actually, i am also working on jetson tx2. So i will make custom model like tiny-darknet(darknet-reference). You need to change darknet53(yolov3.cfg) for fast detection.
@springkim i will try use tensorRT
@springkim hi there! how much fps you have on tx2? That's yolo version and height&width you use?
Has anyone really managed to port Yolov2 or v3 to tensorRT? Custom layers make it a pain.
i have done it 10fps
Hi @hexiangquan Did you use YOLOv3 as TensorRT?
yes
发自我的 iPhone
在 2018年4月3日,下午9:46,KimBomm notifications@github.com 写道:
Hi @hexiangquan Did you use YOLOv3 as TensorRT?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.
Could you share some info how you did it?
Hi @hexiangquan,
Could you please share you code?
I have got roughly 14 fps with tiny YOLO v3, that is not satisfactory either.
My main findings were:
Ensure that max frequency is set for GPU: $ ~/jetson_clocks.sh --show
should indicate that current GPU frequency is equal to max GPU frequency
Use 'NCHW' order of input images, convolutions and poolings
@hexiangquan Can you tell me the memory usage of yolo v3 on tx2?
@hexiangquan please reply .. many people are looking on you.... please
I only get 1fps,that sucks.
i have test 416 ssd i can get 15fps. but use yolov3 just get 3 fps