mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-11-28 05:13:49 +08:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

allow user specified box/tiff pairs with tesstrain.sh

Browse Source
This commit is contained in:
Shree Devi Kumar 2019-01-31 19:03:05 +00:00
parent 31c48a04d4
commit 323361b902
2 changed files with 22 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/training/tesstrain.sh
View File

@ -28,7 +28,15 @@ echo -e "USAGE: tesstrain.sh
--run_shape_clustering # Run shape clustering (use for Indic langs).
--maxpages # Specify maximum pages to output (default:0=all)
--save_box_tiff # Save box/tiff pairs along with lstmf files.
<<<<<<< HEAD
--x_size # Specify width of output image (default:3600)
=======
--xsize # Specify width of output image (default:3600)
OPTIONAL flag for specifying directory with user specified box/tiff pairs.
Files should be named similar to ${LANG_CODE}.${fontname}.exp${EXPOSURE}.box/tif
--my_boxtiff_dir MY_BOXTIFF_DIR # Location of user specified box/tiff files.
>>>>>>> c7cd112... allow box/tiff pairs for LSTM training
OPTIONAL flags for input data. If unspecified we will look for them in
the langdata_dir directory.
@ -60,6 +68,14 @@ ARGV=("$@")
parse_flags
mkdir -p ${TRAINING_DIR}
if [[ ${MY_BOXTIFF_DIR} != "" ]]; then
tlog "\n=== Copy existing box/tiff pairs from '${MY_BOXTIFF_DIR}'"
cp ${MY_BOXTIFF_DIR}/*.box ${TRAINING_DIR} | true
cp ${MY_BOXTIFF_DIR}/*.tif ${TRAINING_DIR} | true
ls -l ${TRAINING_DIR}
fi
tlog "\n=== Starting training for language '${LANG_CODE}'"
source "$(dirname $0)/language-specific.sh"
@ -72,8 +88,8 @@ phase_UP_generate_unicharset
if ((LINEDATA)); then
phase_E_extract_features " --psm 6 lstm.train " 8 "lstmf"
make__lstmdata
tlog "\nCreated starter traineddata for language '${LANG_CODE}'\n"
tlog "\nRun lstmtraining to do the LSTM training for language '${LANG_CODE}'\n"
tlog "\nCreated starter traineddata for LSTM training of language '${LANG_CODE}'\n"
tlog "\nRun 'lstmtraining' comman next to continue LSTM training for language '${LANG_CODE}'\n"
else
phase_D_generate_dawg
phase_E_extract_features "box.train" 8 "tr"

4
src/training/tesstrain_utils.sh
View File

@ -36,6 +36,7 @@ fi
X_SIZE=3600
MAX_PAGES=0
SAVE_BOX_TIFF=0
MY_BOXTIFF_DIR=""
OUTPUT_DIR="/tmp/tesstrain/tessdata"
OVERWRITE=0
LINEDATA=0
@ -157,6 +158,9 @@ parse_flags() {
--maxpages)
parse_value "MAX_PAGES" ${ARGV[$j]:-}
i=$j ;;
--my_boxtiff_dir)
parse_value "MY_BOXTIFF_DIR" ${ARGV[$j]:-}
i=$j ;;
--output_dir)
parse_value "OUTPUT_DIR" ${ARGV[$j]:-}
i=$j ;;