Hello, great work on this toolkit. I really love it. I have a question. Which model would be the best according to you to extract titles and subtitles?
Thanks! You might want to take a look at the installation instruction for the detectron2 backend: layout-parser.readthedocs.io/en/latest/notes/installation.html#additional-instruction-install-detectron2-layout-model-backend
Thanks! I have installed the package and use the demo code but it always returns me Invalid argument: 'C:\\Users\\xxxx/.torch/iopath_cache\\s/f3b12qc4hc0yh4m\\config.yml?dl=1.lock'. Do you have any idea why that happened?
AMAZING ! I've been looking for something similar to this for a while. Thank you ! I can't wait to dive into it and leverage in my processing.
Excellent toolkit
Great job
Great job! how about latest progress?
This is amazing! Any suggestion to only grabbing questions off an image of an test using this?
Is the code for fine tuning the same as retraining after annotation ?
Hello, great work on this toolkit. I really love it.
I have a question.
Which model would be the best according to you to extract titles and subtitles?
Thank you! I'd say the PubLayNet models might be helpful for your task github.com/Layout-Parser/platform/issues/5
Can we use this on binary images ?
Hi
Is posible to detect the police and the style of the document
Hi, great work indeed!
Can it extract buttons from the document, e.g. buttons in emails?
Thanks! I would say yes -- though you might want to customize the layout detection models based on your samples.
Hey, thank you for sharing this.
I have a problem about AttributeError: module layoutparser has no attribute Detectron2LayoutModel
Anyone solved this?
Thanks! You might want to take a look at the installation instruction for the detectron2 backend: layout-parser.readthedocs.io/en/latest/notes/installation.html#additional-instruction-install-detectron2-layout-model-backend
Does it support OCR for Ukrainian language?
Can we extract paragraph as it is in image file?
Yes -- and perhaps the PubLayNet model can help with your task github.com/Layout-Parser/platform/issues/5
Thanks! I have installed the package and use the demo code but it always returns me Invalid argument: 'C:\\Users\\xxxx/.torch/iopath_cache\\s/f3b12qc4hc0yh4m\\config.yml?dl=1.lock'. Do you have any idea why that happened?