Constantin Lehenmeier

Hey @Simonwep, no problem and thank you for you response! Unfortunately, I still get the same error with the new version 1.0.3. I'll download the source and maybe I can...

@Simonwep Thank you for the new release. The download seems to work now.

+1 Would be really helpful to see how custom ground truth data can be created (i.e. annotation tools)

@marcelodiaz558 It seems that the ICDAR2019 dataset is not in PascalVOC. I think you need to manually annotate the images from the ICDAR2019 dataset as it is stated in the...

@RiyazAina-DeepML how many classes do you have in your dataset? I have the same problem with one class.

You can try to import the `BaseDetector` and use its `show_result` method: ``` from mmdet.models.detectors import BaseDetector BaseDetector.show_result(img='data/VOCdevkit/VOC2007/JPEGImages/15.jpg', result=result, self=model, score_thr=score_thr, out_file="result.jpg") ```

I receive the same error, but with a non-empty PageXML file. I use the _Party_ version from commit [c7b7e41](https://github.com/mittagessen/party/commit/c7b7e41f1e1ff1cbbdf8644df49d271c5a873159) Here is the file: ``` dhSegment 2025-03-21T16:54:28.549676 2025-03-21T16:54:28.549676 ... ``` Thank...

Many thanks for the quick feedback! I have subsequently added the baselines automatically and now the recognition works.

@mittagessen sorry to bring up the issue again. But I'm just unsure about the following question: As I want to train a custom kraken model for detecting text lines and...

Thanks for the quick response! > Yes, you can train/predict with `--promt-mode boxes/--boxes` to use only bbox information computed from the bounding polygons. You'll still need to add the dummy...