Hi All, I am an occasional user of ocropy with no knowledge of what it is doing.
I have run training sessions in the past with no problem and I assumed they were doing something. I watched the various library's being built and ran the tools to pick the one with the least errors. To day I am running a session with training data that does not have a .gt.txt file for every .png file. Coincidently I received the subject error, " n 11840 N 5000 input too large for LSTM model." I looked found the source of the error in lstm.py but I don't know what to do about it. Can someone suggest a way to debug this or improve my training files? Ken -- You received this message because you are subscribed to the Google Groups "ocropus" 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/ocropus/c53812d0-b591-4e0c-9e75-8d502d628905%40googlegroups.com.
