Me too, I generated my own version of MNIST throwing in whatever fonts I found in my system (https://gist.github.com/marypwchin/7f4c7e57aebce5b68270cdb88d39bfed). Not just numbers but A, B, C
, … and a, b, c
, too. I use the same dataset from 3 learning sessions:
-
Classifying alphanumerics
1, 2, 3, ..., 9
andA, B, C, ..., Z
anda, b, c, ..., z
. - Classifying font type.
- Classifying font style.
Alphanumerics aside, I also tried face recognition and donkey-mule-horse recognition. Blessed be all donkeys, mules and horses (and all alphanumerics).