/mxnet_VanillaCNN

VanillaCNN for face alignment

Primary LanguageJupyter Notebook

VanillaCNN

This is a mxnet implementation of the Vanilla CNN.

VanillaCNN is used to detect facial landmarks.

Result

Original image:

origin

Landmarks:

landmark

Reference

Yue Wu and Tal Hassner, "Facial Landmark Detection with Tweaked Convolutional Neural Networks", arXiv preprint arXiv:1511.04031, 12 Nov. 2015.

See project page for more information:

http://www.openu.ac.il/home/hassner/projects/tcnn_landmarks/