Difference between revisions of "YOLO"

From Interaction Station Wiki
Jump to navigation Jump to search
Line 4: Line 4:
 
*[[OpenCV Installation]]
 
*[[OpenCV Installation]]
  
=== Installing Darknet  (GPU + OpenCV)  ===
+
*Then, we need to install our modified version of Darknet:
*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:
+
*[[Darknet Installation]]
 
 
git clone https://github.com/mywdka/darknet.git
 
cd darknet
 
make
 
 
 
*Guide:
 
*https://pjreddie.com/darknet/install/
 
  
 
== Using YOLO with Darknet (GPU + OpenCV). Tested on Ubuntu 16.04  ==
 
== Using YOLO with Darknet (GPU + OpenCV). Tested on Ubuntu 16.04  ==

Revision as of 22:31, 4 January 2019

Installation

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