Ray Smith
77c44cdecd
Added convert to int and directory listing to combine_tessdata
2017-08-02 14:53:07 -07:00
Ray Smith
39b168a0b6
Removed errors introduced by git merge
2017-08-02 14:12:45 -07:00
Ray Smith
4e9665debf
Added ADAM optimizer, unless git screwed it up, cos there is no diff
2017-08-02 14:03:50 -07:00
Ray Smith
2633fef0b6
Part 2 of separating out the unicharset from the LSTM model, fixing command line for training
2017-08-02 13:29:23 -07:00
rays
f4f66f8fa9
Fixed regression of issue #644
2017-07-15 17:21:47 -07:00
Ray Smith
dc8745e6fd
Move LSTM unicharset and recoder to traineddata with version string part1. Backwards compatible - maybe.
2017-07-14 11:14:23 -07:00
Ray Smith
8e79297dce
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
2017-05-03 16:09:44 -07:00
Ray Smith
d55f462c9c
More clang-tidy from previous commits
2016-12-06 13:45:49 -08:00
Stefan Weil
f3e8895a6a
lstm: Pass big parameter by reference (performance)
...
Coverity report:
CID 1366448 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter recoder of type
tesseract::UnicharCompress const (size 240 bytes) by value.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
2016-12-01 14:42:54 +01:00
Ray Smith
ce76d1c569
Fixes to training process to allow incremental training from a recognition model
2016-11-30 15:51:17 -08:00
Ray Smith
c1c1e426b3
Added new LSTM-based neural network line recognizer
2016-11-07 15:38:07 -08:00
