I also found out that the text2image tool creates null tif images as well, resulting in "Compute CTC targets failed!" error
On Monday, September 18, 2023 at 7:08:30 PM UTC+3 tesseract-ocr wrote: > I am having a lot of null box issue when I run text2image: the same way as > described here: https://github.com/tesseract-ocr/tesseract/issues/2654 > > Since, the issue seems to be contingent with a bug in text2image; I cannot > wait for sb to fix it. As a temporary solution, I have been deleting the > null box files. > (deleting their corresponding images would have been better; but I > couldn't find a way to do it) > > But, the thing is: Tesseract is making lstm files for their pairs (the > tiff files only). As a result, I am getting a lot of "Compute CTC target > for data...." error during the training. > > I don't mind to ignore the error. But, am worried that the images without > corresponding box files (lstm files) might corrupt my training. > > Can sb help me if there are ways to alleviate any of these issues? > -- 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/294ce2ed-4946-4687-a5d6-404a9ff29bfen%40googlegroups.com.
