YOLO
Revision as of 22:21, 4 January 2019 by Javi (talk | contribs) (→Installing Darknet (GPU + OpenCV))
Installation
- Fist, we install OpenCV:
OpenCV installation in Ubuntu 16.04
sudo apt-get update sudo apt-get upgrade sudo apt-get install build-essential cmake pkg-config sudo apt-get install libjpeg8-dev libtiff5-dev libjasper-dev libpng12-dev sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev sudo apt-get install libxvidcore-dev libx264-dev sudo apt-get install libgtk-3-dev sudo apt-get install libatlas-base-dev gfortran sudo apt-get install python2.7-dev python3.5-dev
Installing Darknet (GPU + OpenCV)
- In our forked version of the original repository, the GPU & OPENCV flags in the Makefile have already been set to 1, and the darknet/examples/rnn.c has been modified for being able to save the generate your own model. So we only need to do:
git clone https://github.com/mywdka/darknet.git cd darknet make
Using YOLO with Darknet (GPU + OpenCV). Tested on Ubuntu 16.04
- Download the weights:
wget https://pjreddie.com/media/files/yolov3.weights
- Go to the directory:
cd darknet
- Run the detector (image):
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
- Run the detector (video):
./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights <video file>
- Run the detector (webcam):
./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights