/caffe-heatmap

Caffe with heatmap regression & spatial fusion layers. Useful for any CNN image position regression task.

Primary LanguageC++OtherNOASSERTION

Caffe-heatmap

This is a fork of Caffe that enables training of heatmap regressor ConvNets for the general problem of regressing (x,y) positions in images.
Multiple implementations are provided, using the PyCaffe interface for Python3, the MatCaffe interface for Matlab, and the standard C++ Caffe API.

Pretrained models

Pre-cropped images and training labels for FLIC

  • Training
  • Testing
  • Note these files require multfact=282 in both training and testing data layers

Testing instructions

For example codes for running the FLIC model on a video, use the following:
demo.m (on Matlab version 2015 or earlier)
python python/pose/demo.py
./build/examples/cpp_heatmap/demo.bin (generated automatically on running "make")

Paper

Please cite our ICCV'15 paper in your publications if this code helps your research:

  @InProceedings{Pfister15a,
    author       = "Pfister, T. and Charles, J. and Zisserman, A.",
    title        = "Flowing ConvNets for Human Pose Estimation in Videos",
    booktitle    = "IEEE International Conference on Computer Vision",
    year         = "2015",
  }

Caffe

Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by 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.

Join the chat at https://gitter.im/BVLC/caffe

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!

License and Citation

Caffe is released under the BSD 2-Clause license. The 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}
}