This repository re-implements YOLOv3 objection detection.
YOLO is a popular object detection algorithm known for its speed and accuracy.
https://pjreddie.com/darknet/yolo/
It obsoletes sliding window approaches by finding the bounding box in a regression problem.
Currently, there are three versions.
YOLOv3: https://pjreddie.com/media/files/papers/YOLOv3.pdf
YOLO9000: https://arxiv.org/pdf/1612.08242.pdf
YOLO: https://arxiv.org/pdf/1506.02640.pdf
Single Shot: https://github.com/weiliu89/caffe/tree/ssd, https://arxiv.org/pdf/1512.02325.pdf
R-CNN: https://github.com/facebookresearch/detectron2, https://arxiv.org/pdf/1703.06870.pdf
This re-implementation follows closely to this reference: https://github.com/wizyoung/YOLOv3_TensorFlow