注意：这个代码是我学习时候写的，里面有很多问题，欢迎大家pull request

It is a TensorFlow implementation of《Facial Landmark Detection by Deep Multi-task Learning》

Instead of treating the detection task as a single and independent problem, we investigate the possibility of improving detection robustness through multi-task learning.

You need to install OpenCV3 for image processing.

You can read my blog for more information:

http://blog.csdn.net/tinyzhao/article/details/52730553