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
## i meet a error when train the data while the mnist example is ok in the caffe. Could give me some advice, thanks a lot~
I0804 10:07:59.888437 17875 net.cpp:157] Top shape: 30 100 (3000) 3041 I0804 10:07:59.888444 17875 net.cpp:165] Memory required for data: 19890000 3042 I0804 10:07:59.888454 17875 layer_factory.hpp:77] Creating layer Dense2 3043 I0804 10:07:59.888505 17875 net.cpp:100] Creating Layer Dense2 3044 I0804 10:07:59.888520 17875 net.cpp:434] Dense2 <- Abs5 3045 I0804 10:07:59.888548 17875 net.cpp:408] Dense2 -> Dense2 3046 I0804 10:07:59.888748 17875 net.cpp:150] Setting up Dense2 3047 I0804 10:07:59.888782 17875 net.cpp:157] Top shape: 30 10 (300) 3048 I0804 10:07:59.888792 17875 net.cpp:165] Memory required for data: 19891200 3049 I0804 10:07:59.888811 17875 layer_factory.hpp:77] Creating layer loss 3050 3051 (modpython:17875): Gtk-ERROR **: GTK+ 2.x symbols detected. Using GTK+ 2.x and GTK+ 3 in the same process is not supported