tesseract-ocr / tesstrain

Train Tesseract LSTM with make
Apache License 2.0
599 stars 178 forks source link

Empty list.train and eval.train #361

Closed sifdinNh closed 7 months ago

sifdinNh commented 7 months ago

Hello guys. i have an issue with tesstrain i prepared all the ground-truth text with it .tif images and box file when i come to train it with : make training MODEL_NAME=ara_new TESSDATA=../tesseract/tessdata START_MODEL=ara MAX_ITERATIONS=100 LANG_TYPE=RTL

i got this error :

 oaded unicharset of size 191 from file data/ara_new/unicharset
Setting unichar properties
Mirror { of } is not in unicharset
Setting script properties
Failed to load script unicharset from:data/langdata/Inherited.unicharset
Warning: properties incomplete for index 16 = َ
Warning: properties incomplete for index 20 = ُ
Warning: properties incomplete for index 44 = ٍ
Warning: properties incomplete for index 48 = ّ
Warning: properties incomplete for index 65 = ِ
Warning: properties incomplete for index 66 = ْ
Warning: properties incomplete for index 69 = ً
Warning: properties incomplete for index 71 = ٌ
Config file is optional, continuing...
Failed to read data from: data/langdata/ara_new/ara_new.config
Created data/ara_new/ara_new.traineddatalstmtraining \
  --debug_interval 0 \
  --traineddata ../tesseract/tessdata/ara.traineddata \
  --old_traineddata ../tesseract/tessdata/ara.traineddata \
  --continue_from data/ara/ara_new.lstm \
  --learning_rate 0.0001 \
  --model_output data/ara_new/checkpoints/ara_new \
  --train_listfile data/ara_new/list.train \
  --eval_listfile data/ara_new/list.eval \
  --max_iterations 400 \
  --target_error_rate 0.01
Failed to load list of training filenames from data/ara_new/list.train
make: *** [Makefile:327: data/ara_new/checkpoints/ara_new_checkpoint] Error 1

and the list.train and eval.train files are empty any solution for this?

zdenop commented 7 months ago

provide input data for replicating problems, otherwise you are alone with your problems...

sifdinNh commented 7 months ago

my bad i just needed to install bc and ther was no error exception for that