fork of Alex Krizhevsky's convolutional neural network. The original project is in https://code.google.com/p/cuda-convnet/

It is a version from Sijin. A paper(3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network) implementation.

Thanks to him very much!

How ro use:

First, it is a convnet, so you need install cuda.

Learn more from https://code.google.com/p/cuda-convnet/wiki/Compiling

However, install pip, numpy, matplotlib and atlas, do not install python-magic! or it will be conflict.

Then, compile jpeg in libs, and install PIL. Note that PIL is an old package, It is recommended that you use virtualenv to install.

At last, you can run as tips from accvdemo.py.

Enjoy!