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}
}

Face-Resources

Following is a growing list of some of the materials I found on the web for research on face recognition algorithm.

Papers

1. DeepFace.A work from Facebook.
2. FaceNet.A work from Google.
3. One Millisecond Face Alignment with an Ensemble of Regression Trees. Dlib implements the algorithm.
4. DeepID
5. DeepID2
6. DeepID3
7. Learning Face Representation from Scratch
8. Face Search at Scale: 80 Million Gallery

Datasets

1. CASIA WebFace Database. 10,575 subjects and 494,414 images
2. Labeled Faces in the Wild.13,000 images and 5749 subjects
3. Large-scale CelebFaces Attributes (CelebA) Dataset 202,599 images and 10,177 subjects. 5 landmark locations, 40 binary attributes.
4. MSRA-CFW. 202,792 images and 1,583 subjects.
5. MegaFace Dataset 1 Million Faces for Recognition at Scale 690,572 unique people
6. FaceScrub. A Dataset With Over 100,000 Face Images of 530 People.
7. FDDB.Face Detection and Data Set Benchmark. 5k images.
8. AFLW.Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization. 25k images.
9. AFW. Annotated Faces in the Wild. ~1k images. 10.3D Mask Attack Dataset. 76500 frames of 17 persons using Kinect RGBD with eye positions (Sebastien Marcel)
10. Audio-visual database for face and speaker recognition.Mobile Biometry MOBIO http://www.mobioproject.org/
11. BANCA face and voice database. Univ of Surrey
12. Binghampton Univ 3D static and dynamic facial expression database. (Lijun Yin, Peter Gerhardstein and teammates)
13. The BioID Face Database. BioID group
14. Biwi 3D Audiovisual Corpus of Affective Communication. 1000 high quality, dynamic 3D scans of faces, recorded while pronouncing a set of English sentences.
15. Cohn-Kanade AU-Coded Expression Database. 500+ expression sequences of 100+ subjects, coded by activated Action Units (Affect Analysis Group, Univ. of Pittsburgh.
16. CMU/MIT Frontal Faces . Training set: 2,429 faces, 4,548 non-faces; Test set: 472 faces, 23,573 non-faces.

Trained Model

1. openface. Face recognition with Google's FaceNet deep neural network using Torch.
2. VGG-Face. VGG-Face CNN descriptor. Impressed embedding loss.

Tutorial

1. Deep Learning for Face Recognition. Shiguan Shan, Xiaogang Wang, and Ming yang.

Software

1. OpenCV. With some trained face detector models.
2. dlib. Dlib implements a state-of-the-art of face Alignment algorithm.
3. ccv. With a state-of-the-art frontal face detector
4. libfacedetection. A binary library for face detection in images.

Frameworks

1. Caffe
2. Torch7
3. Theano
4. cuda-convnet
5. MXNET
6. Tensorflow

Miscellaneous

1. faceswap Face swapping with Python, dlib, and OpenCV
2. Facial Keypoints Detection Competition on Kaggle.
3. An implementation of Face Alignment at 3000fps via Local Binary Features

---

Created by betars on 27/10/2015.

OpenFace •    

Free and open source face recognition with deep neural networks.

---

• Website: http://cmusatyalab.github.io/openface/
• API Documentation
• Join the cmu-openface group or the gitter chat for discussions and installation issues.
• Development discussions and bugs reports are on the issue tracker.

---

This research was supported by the National Science Foundation (NSF) under grant number CNS-1518865. Additional support was provided by the Intel Corporation, Google, Vodafone, NVIDIA, and the Conklin Kistler family fund. Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and should not be attributed to their employers or funding sources.

What's in this repository?

• batch-represent: Generate representations from a batch of images. Example directory structure.
• demos/web: Real-time web demo.
• demos/compare.py: Demo to compare two images.
• demos/vis-outputs.lua: Demo to visualize the network's outputs.
• demos/classifier.py: Demo to train and use classifiers.
• evaluation: LFW accuracy evaluation scripts.
• openface: Python library code.
• models: Model directory for openface and 3rd party libraries.
• tests: Tests for scripts and library code, including neural network training.
• training: Scripts to train new OpenFace neural network models.
• util: Utility scripts.

Citations

The following is a BibTeX and plaintext reference for the OpenFace GitHub repository. The reference may change in the future. The BibTeX entry requires the url LaTeX package.

@misc{amos2016openface,
    title        = {{OpenFace: Face Recognition with Deep Neural Networks}},
    author       = {Amos, Brandon and Ludwiczuk, Bartosz and Harkes, Jan and
                    Pillai, Padmanabhan and Elgazzar, Khalid and Satyanarayanan, Mahadev},
    howpublished = {\url{http://github.com/cmusatyalab/openface}},
    note         = {Accessed: 2016-01-11}
}

Brandon Amos, Bartosz Ludwiczuk, Jan Harkes, Padmanabhan Pillai,
Khalid Elgazzar, and Mahadev Satyanarayanan.
OpenFace: Face Recognition with Deep Neural Networks.
http://github.com/cmusatyalab/openface.
Accessed: 2016-01-11

Licensing

Unless otherwise stated, the source code and trained Torch and Python model files are copyright Carnegie Mellon University and licensed under the Apache 2.0 License. Portions from the following third party sources have been modified and are included in this repository. These portions are noted in the source files and are copyright their respective authors with the licenses listed.

Project	Modified	License
Atcold/torch-TripletEmbedding	No	MIT
facebook/fbnn	Yes	BSD