1LSTMEVAL(1) 2=========== 3:doctype: manpage 4 5NAME 6---- 7lstmeval - Evaluation program for LSTM-based networks. 8 9SYNOPSIS 10-------- 11*lstmeval* --model 'lang.lstm|modelname_checkpoint|modelname_N.NN_NN_NN.checkpoint' [--traineddata lang/lang.traineddata] --eval_listfile 'lang.eval_files.txt' [--verbosity N] [--max_image_MB NNNN] 12 13DESCRIPTION 14----------- 15lstmeval(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. Intermediate training checkpoints can also be used. 16 17OPTIONS 18------- 19'--model FILE':: 20 Name of model file (training or recognition) (type:string default:) 21 22'--traineddata FILE':: 23 If model is a training checkpoint, then traineddata must be the traineddata file that was given to the trainer (type:string default:) 24 25'--eval_listfile FILE':: 26 File listing sample files in lstmf training format. (type:string default:) 27 28'--max_image_MB INT':: 29 Max memory to use for images. (type:int default:2000) 30 31'--verbosity INT':: 32 Amount of diagnosting information to output (0-2). (type:int default:1) 33 34HISTORY 35------- 36lstmeval(1) was first made available for tesseract4.00.00alpha. 37 38RESOURCES 39--------- 40Main web site: <https://github.com/tesseract-ocr> + 41Information on training tesseract LSTM: <https://tesseract-ocr.github.io/tessdoc/TrainingTesseract-4.00.html> 42 43SEE ALSO 44-------- 45tesseract(1) 46 47COPYING 48------- 49Copyright \(C) 2012 Google, Inc. 50Licensed under the Apache License, Version 2.0 51 52AUTHOR 53------ 54The Tesseract OCR engine was written by Ray Smith and his research groups 55at Hewlett Packard (1985-1995) and Google (2006-present). 56