Yolo: PyTorch vs. Darknet

user_13899917 0
Viewed 5161

I have recently found Yolo implementations in PyTorch (e.g. https://github.com/ultralytics/yolov3). What I would like to know if this is really the same (in terms of model accuracy, speed and so on) like the one with Darknet backbone?

I am asking because it is waaaaaay easier with PyTorch (as I am struggling with installing Darknet on windows).

Kind regards, Can

darknet object-detection yolo computer-vision
2 Answers

Follow these step to install darknet framework on window10. I recommend to clone darknet from AlexeyAB repository since it works great on windows10 and a lot of community support.(https://github.com/AlexeyAB/darknet). And now it has a python wrapper so you could implement it on python.

  1. Clone darknet repositoriey.
  2. install vcpkg.(https://github.com/microsoft/vcpkg)
  3. Install visual studio 2017.
  4. Install CUDA and CUDNN.
  5. Add CUDNN into system environment. Variable name = 'CUDNN' , variable value = 'installed path'.
  6. Add 'CUDA_TOOLKIT_ROOT_DIR' into system environment. Variable name = 'CUDNN', variable value = 'installed path\NVIDIA GPU Computing Toolkit\CUDA\v10.2.
  7. build with powershell command '.\build.ps1' in darknet directory.

Hope you find this help :).

user_110628700

YOLO (You Only Look Once) is a one shot detector method to detect object in a certain image. It can work with Darknet, Pytorch, Tensorflow, Keras etc. frameworks. YOLO and darknet complements together pretty well as it has a robust support for CUDA & CUDNN. Use whichever framework you want !!

user_108223700
Related