Hello Jozef, Thank you for this tool. It is very helpful to have a visual look at inttemp.
I tried it with hin.traineddata (devanagri script) as well as some custom trained data. The inttemp display does not seem to correspond to the titles for the boxes. When I checked for eng.traineddata they seem ok. I am wondering whether the problem is in the Training or in the inspector UI for this unicode range. I would appreciate if you can allow for hin, nep, mar, san from https://github.com/tesseract-ocr/tessdata - all devanagari script based languages. ShreeDevi ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Wed, Sep 9, 2015 at 2:08 PM, jm <[email protected]> wrote: > > > On Tuesday, September 8, 2015 at 4:02:21 AM UTC+2, Tom Morris wrote: >> >> On Thursday, September 3, 2015 at 5:33:33 AM UTC-4, jm wrote: >>> >>> Dear all, >>> >>> you can use the following web app to inspect some of the internals of >>> traineddata files: >>> https://te-traineddata-ui.herokuapp.com >>> >>> Few notes: >>> - this version does not parse cube specifics and some of the newer files; >>> - free hosting limits apply which means several parallel requests will >>> kill it, be patient. >>> >> >> That looks interesting. Is the source available? >> > > No (or not yet, reused code from our co., this needs to be solved). > > >> What's the significance of the different colors in the feature plots for >> characters? >> > > Different colour for each protoset (the same colour for protos in a > protoset). > > >> >> The ambigs data looks suspect because the source and target for the >> replacements all seems to be the same which seems unlikely. >> >> For example, >> >> m -> m >> rn -> rn >> m -> m >> >> >> I would expect to be something more like: >> >> m -> rn >> rn -> m >> >> Is there a bug causing it to print the source instead of the target, or >> vice versa? >> > > Fixed the typo in the UI, thanks. > > >> >> Tom >> > -- > 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 http://groups.google.com/group/tesseract-ocr. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/c50d5b73-8d96-41f9-becd-ca0fd2d54976%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/c50d5b73-8d96-41f9-becd-ca0fd2d54976%40googlegroups.com?utm_medium=email&utm_source=footer> > . > > For more options, visit https://groups.google.com/d/optout. > -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduV7_%3D9wwQZ-R5CoztMYEaaSNTVqb%3D-HsNPJoiPfYU5Lhw%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
