Cont'd Attention OCR
zuphilip opened this issue · comments
Mentioned in #13, cont'd here:
The synth 90k text recognition dataset is probably a useful addition to the list.
Also of interest: https://github.com/edward-zhu/umaru
Related: Deriving LaTeX source code from rendered formulas: https://github.com/harvardnlp/im2markup (Demo: http://lstm.seas.harvard.edu/latex/) by @da03, @srush
General purpose attention-ocr implementation will live here http://github.com/opennmt/im2text as part of http://opennmt.net .