Hello, To train Indian Rupee symbol(Symbol <https://www.google.com/search?rlz=1C1GCEU_enIN885IN885&sxsrf=ALeKk034nEHGOJT-j61Opjn5K9LBiGGyJg:1583302461857&q=indian+rupee+symbol&stick=H4sIAAAAAAAAAOPgE-LUz9U3MEovLsvWks9OttLPLojPKdcvzy_KSYlPLi0qSs1LrrQqrsxNys9ZxCqcmZeSmZinUFRakJqqABEFANwI_TNEAAAA&sa=X&ved=2ahUKEwi_972mlYDoAhXm7nMBHXc8BpcQ6BMoADAlegQIEBAC> : ₹) i added it in multiple places in eng.training_text file. Around 20 places i added. I then ran tesstrain.sh using various arguments. I am running tesseract(4.1.1) in Ubuntu so used /usr/share/fonts as default fonts directory. After some time, i got the result without error . Message was "run lstmtraing". After this i ran lstmtraining command
training/lstmtraining --debug_interval 100 \ --traineddata ~/tesstutorial/engtrain/eng/eng.traineddata \ --net_spec '[1,36,0,1 Ct3,3,16 Mp3,3 Lfys48 Lfx96 Lrx96 Lfx256 O1c111]' \ --model_output ~/tesstutorial/engoutput/base --learning_rate 20e-4 \ --train_listfile ~/tesstutorial/engtrain/eng.training_files.txt \ I now got base_checkpoint file. I ran above command for 5000 iterations. After this, i again ran lstmtraining with stop_training command as argument. training/lstmtraining --stop_training \ --continue_from ~/tesstutorial/eng_from_chi/base_checkpoint \ --traineddata ~/tesstutorial/engtrain/eng/eng.traineddata \ Any other stop do i need to perform ? Regards PD -- 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 [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/5755776c-8446-4ecc-a2c2-920b467a2f40%40googlegroups.com.
