The original training scripts in tesseract repo is `tesstrain.sh` and all training tutorials refer to that.
Make based `tesstrain` repo is a later addition and tesseract documentation has not been updated for it. You can contribute by creating a PR to add missing info regarding training for the `tessdoc` repo. On Fri, Jan 8, 2021 at 9:05 PM Keith <kmo...@gmail.com> wrote: > Shree, > > Thank you for your reply. I should have gone to bed (it was like 2 AM my > time on a work night) instead of continuing to bang my head. > > When I saw your message this morning, I was thinking, "What tesstrain > folder? There's no tesstrain folder in the repo." Which was exactly when it > occurred to me that tesstrain is a separate repo and needs checked out > individually. > > All is well. It's working. > > The phrase "tesstrain" doesn't show up on any of the (4) Compiling and > Installation pages. There's lots of mention about installing the > dependencies to support training, but no mention about actually installing > it. > > Do you think that's worthy of filing an issue? > > I'm probably not the only bonehead out there. > > Thanks, > Keith > > On Fri, Jan 8, 2021 at 3:12 AM Shree Devi Kumar <shreesh...@gmail.com> > wrote: > >> >After placing the groundtruth files in a folder called >> *data/foo-ground-truth* inside the main *tesseract *repo folder, >> >> data/foo-ground-truth needs to be under the tesstrain folder not >> tesseract folder. >> >> You can use ground-truth in a different location, in that case you have >> to refer to it while calling make. >> >> On Fri, Jan 8, 2021 at 12:42 PM Keith M <kmo...@gmail.com> wrote: >> >>> I'm sure I'm making a beginner mistake here, but I'm struggling quite a >>> bit. >>> >>> I've built straight from source, both version 4.1.1 and 5.0.0 on Ubuntu >>> 18.04, and Ubuntu 20.04(fresh install, never used, but properly updated). >>> All exhibit the same behavior. I installed all the dependencies following >>> the build/installation guides. No error during the build that I can see. >>> >>> "make training" and "make training-install" both succeed when run >>> initially. Clearly it's building and finishing without error. >>> >>> At this point, all I'm trying to do is train using the example here: >>> >>> https://github.com/tesseract-ocr/tesstrain >>> >>> using groundtruth files. >>> >>> After placing the groundtruth files in a folder called >>> *data/foo-ground-truth* inside the main *tesseract *repo folder, I >>> unzip the .TIFs and .gt.txt's. >>> >>> When either "make training MODEL_NAME=foo" is run nothing happens. It >>> just returns almost instantly and does nothing. 4.1.1 goes through >>> directories and then says there's nothing that needs done. 5.0.0 reports >>> "make: Nothing to be done for 'training'." >>> >>> Also tried incanting as such " make training MODEL_NAME=<MODEL_NAME> >>> START_MODEL=eng PSM=7 TESSDATA=/usr/local/share/tessdata" >>> >>> Same result. >>> >>> I'm clearly doing something wrong here. I must not have the files in the >>> right directory. I've tried putting data/foo-ground-truth in the root, I >>> tried putting it in tessdata inside the root folder, I tried putting it in >>> /usr/local/share/tessdata. >>> >>> eng.trainneddata has been copied to the tessdata folder. >>> >>> There's something obvious I'm doing wrong, but heck if I can find it..... >>> >>> Help!@# >>> >>> Keith >>> >>> >>> -- >>> 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 view this discussion on the web visit >>> https://groups.google.com/d/msgid/tesseract-ocr/6238fb08-4631-43f0-8e32-29ebb0c8c0f4n%40googlegroups.com >>> <https://groups.google.com/d/msgid/tesseract-ocr/6238fb08-4631-43f0-8e32-29ebb0c8c0f4n%40googlegroups.com?utm_medium=email&utm_source=footer> >>> . >>> >> >> >> -- >> >> ____________________________________________________________ >> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com >> >> -- >> 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 view this discussion on the web visit >> https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduXGkYsM-yr9%3Dbk_KBVrPZS%3DEUcdTHethmyF5Usc4BFnzw%40mail.gmail.com >> <https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduXGkYsM-yr9%3Dbk_KBVrPZS%3DEUcdTHethmyF5Usc4BFnzw%40mail.gmail.com?utm_medium=email&utm_source=footer> >> . >> > -- > 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 view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/CADEyXY-iXvvU6Nrwormy8oFBdp6a%3DZ%3DrAstCLdFuY%3DBqGt1XOw%40mail.gmail.com > <https://groups.google.com/d/msgid/tesseract-ocr/CADEyXY-iXvvU6Nrwormy8oFBdp6a%3DZ%3DrAstCLdFuY%3DBqGt1XOw%40mail.gmail.com?utm_medium=email&utm_source=footer> > . > -- ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduVMyo2%3DRpDekSF%2BCy%2BfLrXMcrh1UKWfCF_y3avw-6YAEQ%40mail.gmail.com.
