LSTMTRAINING(1) | LSTMTRAINING(1) |
NAME¶
lstmtraining - Training program for LSTM-based networks.
SYNOPSIS¶
lstmtraining --continue_from train_output_dir/continue_from_lang.lstm --old_traineddata bestdata_dir/continue_from_lang.traineddata --traineddata train_output_dir/lang/lang.traineddata --max_iterations NNN --debug_interval 0|-1 --train_listfile train_output_dir/lang.training_files.txt --model_output train_output_dir/newlstmmodel
DESCRIPTION¶
lstmtraining(1) trains LSTM-based networks using a list of lstmf files and starter traineddata file as the main input. Training from scratch is not recommended to be done by users. Finetuning (example command shown in synopsis above) or replacing a layer options can be used instead. Different options apply to different types of training. Read the [training documentation](https://tesseract-ocr.github.io/tessdoc/TrainingTesseract-4.00.html) for details.
OPTIONS¶
'--debug_interval '
'--net_mode '
'--perfect_sample_delay '
'--max_image_MB '
'--append_index '
'--max_iterations '
'--target_error_rate '
'--weight_range '
'--learning_rate '
'--momentum '
'--adam_beta '
'--stop_training '
'--convert_to_int '
'--sequential_training '
'--debug_network '
'--randomly_rotate '
'--net_spec '
'--continue_from '
'--model_output '
'--train_listfile '
'--eval_listfile '
'--traineddata '
'--old_traineddata '
HISTORY¶
lstmtraining(1) was first made available for tesseract4.00.00alpha.
RESOURCES¶
Main web site: https://github.com/tesseract-ocr Information on training tesseract LSTM: https://tesseract-ocr.github.io/tessdoc/TrainingTesseract-4.00.html
SEE ALSO¶
COPYING¶
Copyright (C) 2012 Google, Inc. Licensed under the Apache License, Version 2.0
AUTHOR¶
The Tesseract OCR engine was written by Ray Smith and his research groups at Hewlett Packard (1985-1995) and Google (2006-present).
01/11/2023 |