| .. |
|
convolve.cpp
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
convolve.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
ctc.cpp
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
ctc.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
fullyconnected.cpp
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
fullyconnected.h
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
functions.cpp
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
functions.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
input.cpp
|
lstm: Remove unused variable
|
2017-03-08 07:30:31 +01:00 |
|
input.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
lstm.cpp
|
openmp: Fix build with clang++ and compilers without OpenMP support
|
2016-12-04 18:44:03 +01:00 |
|
lstm.h
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
lstmrecognizer.cpp
|
Added extra Init that takes a memory buffer or a filereader function pointer to enable read of traineddata from memory or foreign file systems. Updated existing readers to use TFile API instead of FILE. This does not yet add big-endian capability to LSTM, but it is very easy from here.
|
2017-04-27 15:48:23 -07:00 |
|
lstmrecognizer.h
|
Added extra Init that takes a memory buffer or a filereader function pointer to enable read of traineddata from memory or foreign file systems. Updated existing readers to use TFile API instead of FILE. This does not yet add big-endian capability to LSTM, but it is very easy from here.
|
2017-04-27 15:48:23 -07:00 |
|
lstmtrainer.cpp
|
Added extra Init that takes a memory buffer or a filereader function pointer to enable read of traineddata from memory or foreign file systems. Updated existing readers to use TFile API instead of FILE. This does not yet add big-endian capability to LSTM, but it is very easy from here.
|
2017-04-27 15:48:23 -07:00 |
|
lstmtrainer.h
|
More clang-tidy from previous commits
|
2016-12-06 13:45:49 -08:00 |
|
Makefile.am
|
openmp: Fix build with clang++ and compilers without OpenMP support
|
2016-12-04 18:44:03 +01:00 |
|
maxpool.cpp
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
maxpool.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
network.cpp
|
Fix Network declarations with GRAPHICS_DISABLED
|
2017-01-27 12:06:15 +01:00 |
|
network.h
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
networkbuilder.cpp
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
networkbuilder.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
networkio.cpp
|
lstm: Remove unused constant and unused local variables
|
2017-01-21 12:32:06 +01:00 |
|
networkio.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
networkscratch.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
parallel.cpp
|
openmp: Fix build with clang++ and compilers without OpenMP support
|
2016-12-04 18:44:03 +01:00 |
|
parallel.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
plumbing.cpp
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
plumbing.h
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
recodebeam.cpp
|
Fixed issue #633 (multi-language mode
|
2017-01-25 15:58:39 -08:00 |
|
recodebeam.h
|
Made LSTM the default engine, pushed cube out
|
2016-12-13 14:37:40 -08:00 |
|
reconfig.cpp
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
reconfig.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
reversed.cpp
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
reversed.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
series.cpp
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
series.h
|
Fix typos in new LSTM code
|
2016-11-22 08:25:43 +01:00 |
|
static_shape.h
|
Fix typos in new LSTM code
|
2016-11-22 08:25:43 +01:00 |
|
stridemap.cpp
|
Fix typos in new LSTM code
|
2016-11-22 08:25:43 +01:00 |
|
stridemap.h
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
tfnetwork.cpp
|
Added std:: to vector
|
2016-11-30 15:45:36 -08:00 |
|
tfnetwork.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
tfnetwork.proto
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
weightmatrix.cpp
|
lstm: Move class SIMDDetect to new source file and improve code
|
2016-12-27 13:25:08 +01:00 |
|
weightmatrix.h
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
