Shannon Shen

> You may be also interested in this example: > `block_A = lp.Rectangle(40, 50, 150, 150) block_B = lp.Rectangle(40, 120, 140, 151)` Good point. In this case, you might want...

Hi @SAIVENKATARAJU ! Could you please provide more context to your questions? 1. Is it a PDF or just scanned document? 2. What do you mean by "get the heading...

Thanks @DhavalThkkar ! We are working on this topic and you could find some ready-to-use scripts in this repo https://github.com/Layout-Parser/layout-model-training . Please stay tuned for more updates.

Thanks! As mentioned in [the layout-parser paper ](https://arxiv.org/abs/2103.15348), this is the direction we are working on right now. I'll share more information in this thread later when there are more...

Thanks! Typically you just need to try again to download the models and it should be resolved -- but perhaps we will improve the model hosting strategy soon :)

Sure no problem! And thanks @lotfiabdelghafour for the pointer. I assume you are dealing with some image scans, so you might want to perform OCR after running the layout detection...

Thanks for reporting the issue - downloading failure is always annoying! And your suggestions is great - let me try to figure out a solution for fixing this issue.

Thank you @osanseviero ! Yeah, I think this plan looks great! Let me discuss with our teammates and we will get back to you soon.

Thank you @rathorology ! I think this is a combination of lack of documentation as well as OCR API design issues. I am working on this and will let you...

Thank you for your kind words! And sorry for just seeing your issue. Sure, let me write a tutorial or build some exemplar code for the pre-training. Basically you just...