ishay2b/VanillaCNN
Implementation of the Vanilla CNN described in the paper: 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 about this project. http://www.openu.ac.il/home/hassner/projects/tcnn_landmarks/ Written by Ishay Tubi : ishay2b [at] gmail [dot] com https://www.l
Jupyter Notebook
Issues
- 0
Input expected by caffe model
#24 opened by marcobarnobi - 1
question about the code
#23 opened by jj21770 - 0
Activation function
#22 opened by marcobarnobi - 0
Speed performance
#21 opened by marcobarnobi - 1
How to generate /caffeData/test.txt ?
#20 opened by sunmengnan - 0
Visualization Problem
#19 opened by SunnyDp - 6
68 landmark process
#4 opened by fishman2008 - 10
VanillaCNN and TweakedCNN
#2 opened by wuqiangch - 10
some questions about the paper "Facial Landmark Detection with Tweaked Convolutional Neural Networks"
#18 opened by MrBeandou - 1
- 1
Why the conv1 layer has padding 2?
#16 opened by huinsysu - 3
Why normalized-MSE? not Euclidean distance
#11 opened by gicheonkang - 1
In which layer do I extract the feature for GMM?
#15 opened by huinsysu - 1
train error,Creating layer loss
#14 opened by janicevidal - 0
Some little bugs
#13 opened by cmd10 - 0
- 7
how to run this code...
#10 opened by gicheonkang - 0
- 3
learning rate
#8 opened by laoreja - 0
Data augmentation
#7 opened by rexnxiaobai - 0
Gtk-ERROR **
#6 opened by rexnxiaobai - 1
Mean and STD images
#5 opened by fishman2008 - 1
How to generate mean data of the train set?
#3 opened by wuqiangch - 1