search

tesseract-ocr / tesstrain

Train Tesseract LSTM with make
Apache License 2.0
604 stars 178 forks source link

make training hung #277

Closed NeilduToit13 closed 2 years ago

NeilduToit13 commented 2 years ago

I got as far as this part of the documentation: "The repository contains a ZIP archive with sample ground truth, see ocrd-testset.zip. Extract it to ./data/foo-ground-truth and run make training." After unzipping and running make training my terminal displayed this: $ make training unicharset_extractor --output_unicharset "data/foo/unicharset" --norm_mode 2 "data/foo/all-gt for the next 36 hours. At which point I killed it. No logging at all. What is this doing and how long is it supposed to take?

aquino-a commented 2 years ago

When it is training it will leave logs regularly. No logs for 36 hours is not normal

stweil commented 2 years ago

@NeilduToit13, could you please try to run unicharset_extractor --output_unicharset "data/foo/unicharset" --norm_mode 2 "data/foo/all-gt directly from the command line instead of running make training? Does it terminate then?

Please run also ls -l data/foo and show the result here.

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.