Darknet YOLO slowing down when using Jetpack4.4's cuDNN(8.0.0) on Jetson Xavier NX and Jetson Nano

Autonomous Machines Jetson & Embedded Systems Jetson Xavier NX
#1

Hi.

In general, FPS increases when using darknet Yolo’s cuDNN(8.0.0). However, in the new Jetpack 4.4, FPS is decreases when using cuDNN.

  1. Jetson Xavier NX
    nvpmodel -m2, jetson_clock

  • Used yolov3-tiny weights
    Not use cuDNN : 45.2 fps
    Use cuDNN : 40.4 fps

  • Used yolov3(320*320) weights
    Not use cuDNN : 8.5 fps
    Use cuDNN : 7.2 fps

  1. Jetson Nano
    nvpmodel -m0, jetson_clock

  • Used yolov3-tiny weights
    Not use cuDNN : 11.3 fps
    Use cuDNN : 6.6 fps

  • Used yolov3(320*320) weights
    Not use cuDNN : 3.1 fps
    Use cuDNN : 2.9 fps

  1. Jetson Nano (Use Jetpack 4.3, cuDNN 7.6.3)
    nvpmodel -m0, jetson_clock
  • Used yolov3-tiny weights
    Not use cuDNN : 11.3 fps
    Use cuDNN : 13.9 fps

I got the same results at GitHub - AlexeyAB/darknet: YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet ) as well as GitHub - pjreddie/darknet: Convolutional Neural Networks.

I hope this problem will be solved quickly.
Thanks.

1 Like
#3

Hi,

We found that darknet run slower with cuDNN 8.0 but the root cause is still under investigation.
https://forums.developer.nvidia.com/t/121579

By the way, our DeepstreamSDK also has YOLO related sample.
It’s recommended to give it a try. Deepstream has optimized for the Jetson device.

/opt/nvidia/deepstream/deepstream-4.0/sources/objectDetector_Yolo/

Thanks.

#5

Hi yacad,

I can only achieve to 7fps when test Jetson Xavier NX with yolov3-tiny weights. I see that you have achieved to 40.4 fps and 45.2 fps. could you give me instruction to achieve that?

#6

I can only get 60fps，when i use deepstream_yolo3_tiny_int8 on the xavier nx。why is so slow? how get higher fps that above 100fps in many nvidia advertisment?

#7

Hi chang-quan,

Please help to open a new topic if it’s still an issue to support.

Thanks

#8