I am trying understand implementation of CTC layer in lstm.py but unable to locate decoding algorithm as mentioned in thesis paper by Alex graves like *prefix decoding or token passing algorithm* !!
So where should i look for implementation of Decoding algorithm used in CTC ???? Currently I am running lstm.py on english data for OCR purpose !! Addition to this I have also installed RNNLIB and ran it as black box but I am facing same problem there as I cant see any decoding algorithm implementation in transducer.hpp !!! PS: I have understood the role of Forward-Backward algorithm in CTC layer and I have 2 years of experience on Hidden markov model -- 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 post to this group, send email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/ocropus/5ac31209-dae9-4a7a-8cb1-a059d3ddeb96%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
