| .. |
|
convolve.cpp
|
Added ADAM optimizer, unless git screwed it up, cos there is no diff
|
2017-08-02 14:03:50 -07:00 |
|
convolve.h
|
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
|
2017-05-03 16:09:44 -07:00 |
|
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
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
fullyconnected.h
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
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
|
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
|
2017-05-03 16:09:44 -07:00 |
|
input.h
|
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
|
2017-05-03 16:09:44 -07:00 |
|
lstm.cpp
|
lstm: Use MS C intrinsic function for faster calculation of log2 (#1369)
|
2018-03-10 20:52:39 +01:00 |
|
lstm.h
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
lstmrecognizer.cpp
|
Added ability to randomly rotate images upside-down during training for training OSD
|
2017-09-08 12:42:57 +01:00 |
|
lstmrecognizer.h
|
Added ability to randomly rotate images upside-down during training for training OSD
|
2017-09-08 12:42:57 +01:00 |
|
lstmtrainer.cpp
|
Remove old code for string class (no longer needed) (#1354)
|
2018-03-03 14:36:28 +01:00 |
|
lstmtrainer.h
|
Remove old code for string class (no longer needed) (#1354)
|
2018-03-03 14:36:28 +01:00 |
|
Makefile.am
|
Remove macro USE_STD_NAMESPACE (#1360)
|
2018-03-04 14:43:28 +01:00 |
|
maxpool.cpp
|
fix filenames in comments
|
2017-07-02 17:35:47 -04:00 |
|
maxpool.h
|
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
|
2017-05-03 16:09:44 -07:00 |
|
network.cpp
|
Corrected SetEnableTraining for recovery from a recognize-only model.
|
2017-05-05 16:39:43 -07:00 |
|
network.h
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
networkbuilder.cpp
|
fix filenames in comments
|
2017-07-02 17:35:47 -04:00 |
|
networkbuilder.h
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
networkio.cpp
|
Added intsimdmatrix as a generic integer matrixdotvector function with AVX2 and SSE specializations
|
2017-09-08 15:06:19 +01:00 |
|
networkio.h
|
Added intsimdmatrix as a generic integer matrixdotvector function with AVX2 and SSE specializations
|
2017-09-08 15:06:19 +01:00 |
|
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
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
plumbing.h
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
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
|
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
|
2017-05-03 16:09:44 -07:00 |
|
reconfig.h
|
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
|
2017-05-03 16:09:44 -07:00 |
|
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
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
series.h
|
Updated comments on RemapOutputs
|
2017-09-08 10:24:00 +01:00 |
|
static_shape.h
|
Fix typos in new LSTM code
|
2016-11-22 08:25:43 +01:00 |
|
stridemap.cpp
|
Fewer g++ -Wsign-compare warnings
|
2017-05-11 23:14:52 +02:00 |
|
stridemap.h
|
Fixes to training process to allow incremental training from a recognition model
|
2016-11-30 15:51:17 -08:00 |
|
tfnetwork.cpp
|
fix filenames in comments
|
2017-07-02 17:35:47 -04:00 |
|
tfnetwork.h
|
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
|
2017-05-03 16:09:44 -07:00 |
|
tfnetwork.proto
|
Added new LSTM-based neural network line recognizer
|
2016-11-07 15:38:07 -08:00 |
|
weightmatrix.cpp
|
Replace log2(n) by local functions (#1353)
|
2018-03-02 06:54:43 +01:00 |
|
weightmatrix.h
|
Added intsimdmatrix as a generic integer matrixdotvector function with AVX2 and SSE specializations
|
2017-09-08 15:06:19 +01:00 |
