Python-caffe simplified implementation of the R-CNN object detection method. I have taken as a starting point the caffe ipython-notebook available at http://nbviewer.ipython.org/github/BVLC/caffe/blob . The tutorial requires the use of matlab code for calculating selective search bounding boxes. This make it hard to use and slow. Thus, I have implemented bounding boxes proposal with a pythonized BING that I have implemented in another repository. I have also changed the interaction with the script so that the result is a nicer demo.