Software Package


This page contains code useful to reproduce some of the experiments reported in:

M. Ranzato, V. Mnih, G. Hinton, "Generating More Realistic Images Using Gated MRF's". Advances in Neural Information Processing Systems 23 (NIPS 2010), Vancouver, 2010.



mPoT on image patches


This is the code to train mPoT on image patches (see fig.1 of the paper). 

Download here the CUDAMAT version which requires Volodymyr Mnih's CUDAMAT and a GPU board to run.

Download here the GNUMPY version which is a bit slower but easier to read. This runs both on GPU and CPU.



Tiled mPoT on high-resolution images


This is the code to train TConv mPoT on high-resolution images (see fig.3-A of the paper). 

Download here the CUDAMAT version which requires Volodymyr Mnih's CUDAMAT and a GPU board to run.

The processed images are available here.