for engtrain and engeval they almost have the same command but for eval you 
specify the font using the argument --font-list, while in train you define 
the fonts in language-specifics.sh , I ran both command and I noticed that 
they produce the same results files, except in engtrain case there will be 
lstmf file for each font in language-specific.sh.

but now there is another question, in the fine tuning 
command is:
training/lstmtraining --model_output ~/tesstutorial/impact_from_small/impact 
  --continue_from ~/tesstutorial/engoutput/base_checkpoint \
  --train_listfile ~/tesstutorial/engeval/eng.training_files.txt \
  --max_iterations 1200

and for evaluating its also uses:
training/lstmeval --model ~/tesstutorial/impact_from_small/impact_checkpoint 
  --eval_listfile ~/tesstutorial/engeval/eng.training_files.txt

for me it seems its a typo at the fine tuning command since the argument 
--eval_listfile  *~/tesstutorial/engeval*
so in both cases the commands contains engeval, my question, since I don't 
want to run the fine tuning many times, so can I use the training files 
that exists in the engtrain ? instead to create files for the engeval for 
every font and then run the fine tune against its training files.


You received this message because you are subscribed to the Google Groups 
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit 
For more options, visit https://groups.google.com/d/optout.

Reply via email to