by alexgkendall

alexgkendall / caffe-posenet

Implementation of PoseNet

433 Stars 190 Forks Last release: Not found Other 3.5K Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:


This is a modified version of Caffe which supports the PoseNet architecture

As described in the ICCV 2015 paper PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization Alex Kendall, Matthew Grimes and Roberto Cipolla []

Getting Started

  • Download the Cambridge Landmarks dataset from here.
  • Download models and trained weights from here.

Create an LMDB localisation dataset with

Change lines 1, 11 & 12 to the appropriate directories.

Test PoseNet with

using the command
python --model your_model.prototxt --weights your_weights.caffemodel --iter size_of_dataset


If you use this software in your research, please cite our publications: Alex Kendall, Matthew Grimes and Roberto Cipolla "PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization." Proceedings of the International Conference on Computer Vision (ICCV), 2015. Alex Kendall and Roberto Cipolla "Modelling Uncertainty in Deep Learning for Camera Relocalization." The International Conference on Robotics and Automation, 2015.


This extension to the Caffe library and the PoseNet models are released under a creative commons license which allows for personal and research use only. For a commercial license please contact the authors. You can view a license summary here:

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.