Krzysztof Nowak comments

Results 6 comments of


                                            Krzysztof Nowak

label studio slowes down when importing OCR preannotations

I can confirm. Also multiple boxes cannot be selected with the Shift key as the documentation claims (https://labelstud.io/guide/labeling.html#Select-multiple-regions). Sadly, this makes interface hardly usable for OCR word boxes labeling.

The ocr results and reported model accuracy mismatch

Yes, I am. In fact, the command should read: `kraken -i pagexml_trans.jpg pagexml_trans.txt **segment -bl** ocr -m some_best.mlmodel`. I've experimented with kraken-trained seg models as well, but to no avail....

The ocr results and reported model accuracy mismatch

I've tried that one, too. Running both `train --repolygonize` and `contrib/repolygonize.py` [on the XML](https://github.com/mittagessen/kraken/files/8093542/839309_0026_31120457.txt) I've attached before yields this error: ``` File "repolygonize.py", line 63, in _repl_page pol.attrib['points'] = '...

The ocr results and reported model accuracy mismatch

> I have tried to import your pagexml into eScriptorium. The imagefilename needs to get adapted to the imagename github gave your image but the system also gives another error...

The ocr results and reported model accuracy mismatch

I'm afraid I dont. The error message doesn't point to the input file line. However, I'll try to debug it starting with `the lib/xml.py` which feeds the `repolygonize.py`.

The ocr results and reported model accuracy mismatch

I've gone through the `repolygonize.py`. There's a mismatch between the list of lines retrieved from the XML and the list of normalized polygons: `line 45 lines = doc.findall('.//{*}TextLine') ` `...