layout-parser

layout-parser copied to clipboard

Challanges with table data parasing.

1

Hi , I am trying to detect the tables inside PDF and the trying to parse the table without changing the positions. I am able to detect the table as...

SAIVENKATARAJU

Add layout export documentation in the doc

1

lolipopshock

I'm trying to run a Docker file and install layoutparser using the following pip command RUN pip3 install layoutparser torchvision && pip install "git+https://github.com/facebookresearch/[email protected]#egg=detectron2" I get the following error message...

solidHeroLink

Is there any way to preserve heading and content together.

3

Hi, Thanks for your library. I have below screenshot with headers and text, is there any way to get the heading together with text. 

SAIVENKATARAJU

AttributeError: module layoutparser has no attribute Detectron2LayoutModel on conversion to exe

1

**Describe the bug** Exe file keeps throwing an error AttributeError: module layoutparser has no attribute Detectron2LayoutModel. Python file works fine on virtualenv when trying to run. **Checklist** 1. I have...

frederick0291

PaddleDetectionLayoutModel requires the PaddlePaddle library but it was not found in your environment.

2

**Describe the bug** I'm trying to use Paddle model: `model = lp.AutoLayoutModel("lp://paddledetection/TableBank/ppyolov2_r50vd_dcn_365e")` I'm getting an error: `ImportError: PaddleDetectionLayoutModel requires the PaddlePaddle library but it was not found in your environment....

mzhadigerov

table parse using tesseract

2

Hi, first I would like to thank you for this amazing project , I am asking if you could provide some details about how can I run the ocr table...

ziodos

Example, ``` lp.AutoLayoutModel("lp://detectron1/PubLayNet") --> returns None ```

lolipopshock

**Motivation** Support for Amazon Textract in ocr **Related resources** https://docs.aws.amazon.com/textract/latest/dg/API_DetectDocumentText.html

kaushal-idx

lolipopshock