hi every body thank you for the incredible work I always have the same file after training (ara.traineddata) always the same size and the same result i only need to train tesseract for three fonts only for test purpose I train tesseract just for number in one font also get the same output training data the same as the original I give the tesseract to get the files needed to train my command as follow did I do some think wrong pleas help me
training/tesstrain.sh \ --fonts_dir /home/idris/mylot \ --lang ara --linedata_only \ --noextract_font_properties --langdata_dir ./langdata \ --tessdata_dir ./tessdata \ --output_dir ~/mylottutorial \ --fontlist "mylotus Bold" training/combine_tessdata -e ./tessdata/ara.traineddata \ ~/mylottutorial/ara.lstm training/lstmtraining --model_output ~/mylottutorial/plusminus/ \ --continue_from ~/mylottutorial/ara.lstm \ --train_listfile ~/mylottutorial/ara.training_files.txt \ --traineddata ./tessdata/ara.traineddata \ --old_traineddata ./tessdata/ara.traineddata \ --max_iterations 1000 training/lstmtraining --stop_training \ --continue_from ~/mylottutorial/plusminus/_checkpoint \ --model_output ~/mylottutorial/plusminus/aranew.traineddata \ --traineddata ./tessdata/ara.traineddata I notice the the deferent size of best and fast data file dos the size reflect in the speed ? -- 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 post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/a95a8213-48b5-480b-8476-4c7eec376bd3%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
