malinna/caffe-ml

Caffe with support for multiple labels in image data layer. The original Caffe version, which is base for this modification, is from March 12th, 2017. Direct link to it is https://github.com/BVLC/caffe/tree/e687a71fac81718d40d4e0e98d29eab34f784b5b.

Changes to the original

The base Caffe version for this modification is from March 12th, 2017 and can be found here: https://github.com/BVLC/caffe/tree/e687a71fac81718d40d4e0e98d29eab34f784b5b.

Multiple labels in image data layer

The image data layer in current Caffe supports only one integer label to be defined in the text file for a single image.

0001.jpg 0
0002.jpg 1
0003.jpg 2

With the modifications done in this version, you can define multiple floating-point numbers, as in the example below.

0001.jpg 0.345 1.364 -4.124
0002.jpg 6.321 5.246 6.235
0003.jpg 4.135 -5.356 1.345

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

• DIY Deep Learning for Vision with Caffe
• Tutorial Documentation
• BVLC reference models and the community model zoo
• Installation instructions

and step-by-step examples.

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}
}