Skip to content

jamt9000/matconvnet-rcnn

 
 

Repository files navigation

R-CNN Implementation for MatConvnet

An implementation of selective search[1] and R-CNN[2] for the MatConvnet CNN library.

Code in examples/rcnn

For the Selective Search implementation see vl_regionproposals which is a wrapper around mexfile vl_selectivesearch.cpp itself wrapping the pure C++ version selectivesearch.cpp.

[1] Uijlings, Jasper RR, et al. "Selective search for object recognition." International journal of computer vision 104.2 (2013): 154-171.

[2] Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.

About

R-CNN for Matconvnet

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • C++ 34.2%
  • Cuda 27.8%
  • MATLAB 19.9%
  • Protocol Buffer 6.4%
  • C 3.8%
  • Python 3.3%
  • Other 4.6%