News for hackers. Stuff that matters.
Re:Welcome to the New AWS AI Blog by allenz on Tuesday February 21, 2017 @05:39AM (#13694657)
You would just use pixel values as inputs, see https://www.tensorflow.org/get_started/mnist/beginners

You can make it more performant by downsizing the documents, but obviously this is incredibly GPU-intensive to train. I second the suggestions to just use OCR.

There are no comments on this comment yet.