Amit Dovev

This issue has not been fixed yet. Every user of the master branch will suffer from the slowness, unless he/she builds with `debug=-1`. A fix in SConstruct is needed.

>How does it encode the images to be used as input to the network? Is it just the raw pixels of the image with varying width/height? Yes. it takes raw...

You might want to look at ocropy's lstm.py code, because I think it will be easier to understand. It was written by the same author who wrote clstm.

Maybe this link will help you: https://github.com/tmbdev/ocropy/issues/17

There are replacements: `clstmfiltertrain` and `clstmfilter`.

They added Ubuntu 14.04 support in Feb 2016. [It's now the Default OS for New Projects](https://circleci.com/blog/ubuntu-14-04-trusty-is-the-default-os-for-new-projects/) g++ 4.8 and 4.9 are available. It's possible to download deb packages for newer...

Currently TensorFlow is not being used.

* QtAndGo * QG * QGo * Go2Qt * Go4Qt * Qpher (Qt+Gopher) * Qter

I don't know if it's related to this issue, but one difference between tesseract and libtesseract is the default psm. The default psm in tesseract is '3', while in libtesseract...

@meh, FYI, the default psm mode for tesseract command line is '3', while for libtesseract it's '6'.