This page contains code useful to reproduce some of the experiments reported in:
M. Ranzato, V. Mnih, G. Hinton,
Realistic Images Using Gated MRF's". Advances in Neural Information
Processing Systems 23 (NIPS 2010), Vancouver, 2010.
mPoT on image patches
the CUDAMAT version
which requires Volodymyr Mnih's
and a GPU board to run.
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).