lstm training can take weeks, days, hours depending on the options chosen. you have given complete network spec, so that is training from scratch.
Please see the following training wiki page for training related info: https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00 On Tue, Aug 7, 2018 at 12:39 PM May <h...@u.rochester.edu> wrote: > Oh the training started by itself after a long while and still processing. > Does it normally take that long to train 6 images? > > > > > <https://lh3.googleusercontent.com/-S-zqe4mmBWA/W2lFl6LakEI/AAAAAAAAAOY/1g2tCBu6-cUDZjSj8-DsyvMhl3ypueJggCLcBGAs/s1600/Capture.PNG> > > > On Monday, August 6, 2018 at 11:42:40 PM UTC-7, May wrote: >> >> Thanks a lot Shree. I tried the tesseract 4.0 and the training is working >> well until it reaches the lstm-training step and got stuck there. I am >> totally new in the training so hope you don't mind if I am asking silly >> questions. Do you know why I got stuck? Also, would you call this training >> fine-tuning? As I just want to improve the accuracy of existing >> eng.langdata. >> >> >> <https://lh3.googleusercontent.com/-dWRkYql4AKA/W2k9PoNsndI/AAAAAAAAAOM/zWVkkPvUCT44moZPpvt6xgYFnQ0StwxUQCLcBGAs/s1600/Capture.PNG> >> >> >> >> On Monday, August 6, 2018 at 10:26:12 PM UTC-7, shree wrote: >>> >>> Ocr-d scripts are geared towards tesseract 4.0.x. you are trying to use >>> it with tesseract 3.05. >>> >>> On Tue 7 Aug, 2018, 10:50 AM May, <hw...@u.rochester.edu> wrote: >>> >>>> Hey Shree >>>> >>>> I also tried with the orignal script from the github. But faced the >>>> same issue with the process stuck at unicharset_output. >>>> >>>> >>>> <https://lh3.googleusercontent.com/-rFB69WQGLIg/W2krzHUjFfI/AAAAAAAAAOA/SZ4CEzUIEGMIhQUWXHfHMS9H4Yxk-ADGwCLcBGAs/s1600/Capture.PNG> >>>> >>>> >>>> These are the versions: >>>> tesseract 3.05.02 >>>> leptonica-1.75.3 >>>> libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 1.5.3) : libpng 1.6.34 : >>>> libtiff 4.0.9 : zlib 1.2.11 : libwebp 0.6.1 : libopenjp2 2.2.0 >>>> >>>> >>>> On Thursday, August 2, 2018 at 8:52:38 PM UTC-7, shree wrote: >>>>> >>>>> Please use latest scripts from https://github.com/OCR-D/ocrd-train >>>>> >>>>> On Fri, Aug 3, 2018 at 4:41 AM May <hw...@u.rochester.edu> wrote: >>>>> >>>>>> >>>>>> <https://lh3.googleusercontent.com/-LnwUni4-lLw/W2OPUqJpn_I/AAAAAAAAANs/Xd_-CVCdiMk0cjMmxBpVgfOSU1JeAacAgCLcBGAs/s1600/Capture.PNG> >>>>>> >>>>>> >>>>>> >>>>>> <https://lh3.googleusercontent.com/-j3_B1CmVv9w/W2OPbuUYH3I/AAAAAAAAANw/xmBXrNakKuMHm2L9cj-K3sCXCjFxuF80QCLcBGAs/s1600/Capture.PNG> >>>>>> >>>>>> >>>>>> >>>>>> Here are attached photos >>>>>> >>>>>> >>>>>> On Thursday, August 2, 2018 at 4:08:11 PM UTC-7, May wrote: >>>>>>> >>>>>>> Hey all, >>>>>>> >>>>>>> I am following Shree's script for OCR-d in the google groups for >>>>>>> ocrd-training ( >>>>>>> https://groups.google.com/forum/#!topic/tesseract-ocr/be4-rjvY2tQ). >>>>>>> I managed to pass the combine tessdata stage but got stuck at the >>>>>>> unicharset stage: >>>>>>> >>>>>>> >>>>>>> >>>>>>> I have edited the script to direct it to my path: >>>>>>> >>>>>>> I do find a unicharset file named "unicharset" but not as >>>>>>> "my.unicharset". Changing the script by removing "my." also did not >>>>>>> solve >>>>>>> the problem. Do you know what's causing the issue? >>>>>>> >>>>>>> Best >>>>>>> May >>>>>>> >>>>>> -- >>>>>> 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-oc...@googlegroups.com. >>>>>> To post to this group, send email to tesser...@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/48347dd8-7b7e-4d0d-9cb5-b21e3ec23f31%40googlegroups.com >>>>>> <https://groups.google.com/d/msgid/tesseract-ocr/48347dd8-7b7e-4d0d-9cb5-b21e3ec23f31%40googlegroups.com?utm_medium=email&utm_source=footer> >>>>>> . >>>>>> For more options, visit https://groups.google.com/d/optout. >>>>>> >>>>> >>>>> >>>>> -- >>>>> >>>>> ____________________________________________________________ >>>>> 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-oc...@googlegroups.com. >>>> To post to this group, send email to tesser...@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/af43b995-7e24-4dca-827c-080755211544%40googlegroups.com >>>> <https://groups.google.com/d/msgid/tesseract-ocr/af43b995-7e24-4dca-827c-080755211544%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 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/5a1e3259-e0e4-45aa-8eb5-db28f0eba535%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/5a1e3259-e0e4-45aa-8eb5-db28f0eba535%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- ____________________________________________________________ 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 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/CAG2NduX25AQOdRkpRzupSSwiYGWuXdJpNSfHQV9_z7QDbaNAAA%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
