Training Yolo on custom dataset to detect Rubik's Cube
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.

README.md

Building a custom object detector using YOLO

In this repository, I put the code and the dataset of my rubik's cube to building a custom object detector to detect rubik's cube using the tiny YOLO v2.

In the next table, I briefly described the contents of this repository.

Name Its Function
Dataset Folder contains the images and annotation files.
YoloTrainer.java Training Yolo with our custom dataset.
RubixDetector.java Real-time rubik's cube detector, it reads a stream of frames from the webcam the then detects the rubik's cube in each one.
YoloModel.java Loading the trained model by the class YoloTrainer and make the detection given an image.
NonMaxSuppression.java Implementation of the non-maximum suppression algorithm to cope the problem of detecting the same object multiple times by the yolo algorithm.
model.data Pre-trained model to detect rubik's cube, can be downloaded from here.



For more info

http://emaraic.com/blog/yolo-custom-object-detector

Note

In case you have a GPU, you can uncomment the CUDA dependency in pom.xml file. https://deeplearning4j.org/docs/latest/deeplearning4j-config-cudnn

Video

https://www.youtube.com/watch?v=kacQ4vSrEsU

IMAGE ALT TEXT HERE

Screenshot