mxnet_VanillaCNN
mxnet_VanillaCNN copied to clipboard
VanillaCNN for face alignment
VanillaCNN
This is a mxnet implementation of the Vanilla CNN.
VanillaCNN is used to detect facial landmarks.
Result
Original image:
Landmarks:
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/