This is a copy of the SVHN dataset (http://ufldl.stanford.edu/housenumbers/), that has been formatted to work with both `cuda-convnet2` (https://github.com/akrizhevsky/cuda-convnet2) and `nengo_extras
SVHN is a real-world image dataset for developing machine learning and object recognition algorithms with minimal requirement on data preprocessing and formatting. It can be seen as similar in flavor
