other versions
- testing 4.0.0-2
- stretch-backports 4.00~git2439-c3ed6f03-1~bpo9+1
- unstable 4.0.0-2
LSTMEVAL(1) | LSTMEVAL(1) |
NAME¶
lstmeval - Evaluation program for LSTM-based networks.SYNOPSIS¶
lstmeval --model lang.lstm|langtrain_checkpoint|pluscharsN.NNN_NN.checkpoint [--traineddata lang/lang.traineddata] --eval_listfile lang.eval_files.txt [--verbosity N] [--max_image_MB NNNN]DESCRIPTION¶
lstmeval(1) evaluates LSTM-based networks. Either a recognition model or a training checkpoint can be given as input for evaluation along with a list of lstmf files. If evaluating a training checkpoint, --traineddata should also be specified.OPTIONS¶
--model FILEName of model file (training or recognition) (type:string
default:)
--traineddata FILE
If model is a training checkpoint, then traineddata must
be the traineddata file that was given to the trainer (type:string
default:)
--eval_listfile FILE
File listing sample files in lstmf training format.
(type:string default:)
--max_image_MB INT
Max memory to use for images. (type:int
default:2000)
--verbosity INT
Amount of diagnosting information to output (0-2).
(type:int default:1)
HISTORY¶
lstmeval(1) was first made available for tesseract4.00.00alpha.RESOURCES¶
Main web site: https://github.com/tesseract-ocr Information on training tesseract LSTM: https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00SEE ALSO¶
tesseract(1)COPYING¶
Copyright (C) 2012 Google, Inc. Licensed under the Apache License, Version 2.0AUTHOR¶
The Tesseract OCR engine was written by Ray Smith and his research groups at Hewlett Packard (1985-1995) and Google (2006-present).05/18/2018 |