Incorrect reading of MNIST Images

[benvcutilli]

This may be considered a minor quibble by most, but I do want to be accurate when using the MNIST dataset.

The documentation for chainer.datasets.get_mnist(...) implies that you do something like derive the 0 to scale values by just dividing the raw pixel value by 255. However, from the MNIST site (under "FILE FORMATS FOR THE MNIST DATABASE):

Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black).

The same goes for the testing images. So, I believe you should be inverting your values output by get_mnist(...). Actually it would be best to give the option to invert them seeing as one may need to compare their results to other research that used the wrong method. I know there are workaround(s) for this, but this is technically a bug.

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed after 30 days if no further activity occurs. Thank you for your contributions.