Hi, I'm new to tesseract and wondered why the lstm dataset creation for the training process has to write the file again and again in TrainLineRecognizer. I've seen 200MB/s IO on the disk while creating the training data set. As far I can see for the training case it would be sufficient to just load it once and write it at the end. The same applies to the box and tif file - but these are only read and not written...
Thanks, Jens Weibler -- 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 https://groups.google.com/d/msgid/tesseract-ocr/ea35cf15-f53a-47f4-afdb-801e8745eb93%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
