/yolo2_light

Light version of convolutional neural network Yolo v3 & v2 for objects detection with a minimum of dependencies (INT8-inference, BIT1-XNOR-inference)

Primary LanguageCMIT LicenseMIT

yolo2_light

Light version of convolutional neural network Yolo v3 & v2 for objects detection with a minimum of dependencies (INT8-inference, BIT1-XNOR-inference)

This repository supports:

  • both Windows and Linux
  • both OpenCV <= 3.3.0 and OpenCV 2.4.13
  • both cuDNN >= 7.1.1
  • CUDA >= 8.0

How to compile:

  • To compile for CPU just do make on Linux or build yolo_cpu.sln on Windows

  • To compile for GPU set flag GPU=1 in the Makefile on Linux or build yolo_gpu.sln on Windows

    Required both CUDA >= 8.0 and cuDNN >= 7.1.1

How to start:

  • Download yolov3.weights to the bin directory and run ./yolo.sh on Linux (or yolo_cpu.cmd / yolo_gpu.cmd on Windows)
  • Download yolov3-tiny.cfg to the bin directory and run ./tiny-yolo.sh

How to use INT8-inference:

How to use BIT1-XNOR-inference - only for custom models (you should train it by yourself):

  • You should base your cfg-file on tiny-yolo-obj_xnor.cfg and train it by using this repository as usual https://github.com/AlexeyAB/darknet
  • Then use it for Detection-test or for getting Accuracy (mAP):
    • ./darknet detector test data/obj.names tiny-yolo-obj_xnor.cfg data/tiny-yolo-obj_xnor_5000.weights -thresh 0.15 dog.jpg
    • ./darknet detector map data/obj.data tiny-yolo-obj_xnor.cfg data/tiny-yolo-obj_xnor_5000.weights -thresh 0.15

Other models by the link: https://pjreddie.com/darknet/yolo/