johnlockejrr
johnlockejrr
"incremental private key cracking mode" has no resume/continue, if you run it one day from a key and the system crashes/is rebooted/whatever how can one resume the work/test? Maybe some...
I'm not sure this is an issue or a missunderstanding, anyway, I finetuned a segmentation model on a small data but kraken picks the first output model although following models...
I try to segment an image under eScriptorium but I get this error and all is messed up ``` [2024-03-01 09:59:49,900: WARNING/ForkPoolWorker-9] Running binary model on non-binary input image (mode...
Seems the IAM dataset is not public anymore, any other location? Trying to download, output: ``` PublicAccessNotPermitted Public access is not permitted on this storage account. RequestId:954279e9-d01e-0066-427a-91a772000000 Time:2024-04-18T10:26:49.5054310Z ```
I have eScriptorium with tesseract and tesserocr, everything ok but when I try to train a model I get some error on API: (https://ub-mannheim.github.io/eScriptorium_Dokumentation/eScriptorium-with-tesseract-extension.html) ``` [2024-03-11 14:11:09,546: WARNING/ForkPoolWorker-6] ['combine_tessdata', '-l',...
I'm not sure if is eScriptorium or kraken related, I just want to poin out, same model, same image on different installs: 1. **eScriptorium with kraken 4.3.13 (python 3.8)** ![esc-kraken-4](https://github.com/mittagessen/kraken/assets/16368414/f959e21b-e4d6-405f-ae0f-38ce2a73b8b9)...
Not an issue but an idea: wouldn't be great to add GPU support with pytorch? Anyone thought about that?