DeepPose-caffe
A general Riemannian formulation of the pose estimation problem to train CNNs directly on SO(3) and SE(3) equipped with a left-invariant Riemannian metric.
This package requires building Caffe with Intel MKL.
cmake/Summary.cmake
cmake/Dependencies.cmake
cmake/Modules/FindMKL.cmake
include/caffe/layers/base_data_layer.hpp
src/caffe/layers/data_layer.cpp
src/caffe/layers/dropout_layer.cpp
src/caffe/layers/dropout_layer.cu
src/caffe/proto/caffe.proto
include/caffe/layers/normalize_layer.hpp
include/caffe/layers/se3_geodesic_loss_layer.hpp
include/caffe/layers/so3_quaternion_loss2.hpp
include/caffe/layers/so3_quaternion_loss3.hpp
include/caffe/layers/so3_quaternion_loss4.hpp
src/caffe/layers/normalize_layer.cpp
src/caffe/layers/normalize_layer.cu
src/caffe/layers/se3_geodesic_loss_layer.cpp
src/caffe/layers/se3_geodesic_loss_layer.cu
src/caffe/layers/so3_quaternion_loss2.cpp
src/caffe/layers/so3_quaternion_loss2.cu
src/caffe/layers/so3_quaternion_loss3.cpp
src/caffe/layers/so3_quaternion_loss3.cu
src/caffe/layers/so3_quaternion_loss4.cpp
src/caffe/layers/so3_quaternion_loss4.cu
src/caffe/test/test_normalize_layer.cu
src/caffe/test/test_se3_geodesic_loss_layer.cpp
src/caffe/test/test_so3_quaternion_loss2.cpp
src/caffe/test/test_so3_quaternion_loss3.cpp
src/caffe/test/test_so3_quaternion_loss4.cpp
These loss functions optimises on the manifold
SE3 Geodesic Loss (Rotation + Translation)
SO3 Quaternion Loss (Rotations only)
Instance Normalisation Layer
See DeepPose/README.md
Benjamin Hou
Nina Miolane
Bishesh Khanal
Bernhard Kainz
If you like our work and found it useful for your research, please cite our paper. Thanks! :)
@inproceedings{hou2018computing, title={Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry}, author={Hou, Benjamin and Miolane, Nina and Khanal, Bishesh and Lee, Matthew and Alansary, Amir and McDonagh, Steven and Hajnal, Jo V and Rueckert, Daniel and Glocker, Ben and Kainz, Bernhard}, booktitle={ International Conference on Medical Image Computing and Computer-Assisted Intervention}, year={2018}, organization={Springer} }
@misc{miolane2018geomstats, title={Geomstats: Computations and Statistics on Manifolds with Geometric Structures.}, url={https://github.com/ninamiolane/geomstats}, journal={GitHub}, author={Miolane, Nina and Mathe, Johan and Pennec, Xavier}, year={2018}, month={Feb} }
Miolane et al. Geomstats
Kendall et al. - Kings College Dataset
Du Q. Hyunh et al. - Metrics for 3D Rotations: Comparison and Analysis
Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR)/The Berkeley Vision and Learning Center (BVLC) and community contributors.
Check out the project site for all the details like
and step-by-step examples.
Intel Caffe (Optimized for CPU and support for multi-node), in particular Xeon processors (HSW, BDW, SKX, Xeon Phi).
OpenCL Caffe e.g. for AMD or Intel devices.
Please join the caffe-users group or gitter chat to ask questions and talk about methods and models. Framework development discussions and thorough bug reports are collected on Issues.
Happy brewing!
Caffe is released under the BSD 2-Clause license. The BAIR/BVLC reference models are released for unrestricted use.
Please cite Caffe in your publications if it helps your research:
@article{jia2014caffe, Author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor}, Journal = {arXiv preprint arXiv:1408.5093}, Title = {Caffe: Convolutional Architecture for Fast Feature Embedding}, Year = {2014} }
还没有评论,说两句吧!
热门资源
Keras-ResNeXt
Keras ResNeXt Implementation of ResNeXt models...
seetafaceJNI
项目介绍 基于中科院seetaface2进行封装的JAVA...
spark-corenlp
This package wraps Stanford CoreNLP annotators ...
capsnet-with-caps...
CapsNet with capsule-wise convolution Project ...
inferno-boilerplate
This is a very basic boilerplate example for pe...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com