layout-parser

layout-parser copied to clipboard

**Describe the bug** A clear and concise description of what the bug is. Thanks for this great work, it really very good. But when I try to use Google Cloud...

wr0124

gcv_agent.py bugs: 'google.cloud.vision' has no attribute 'types'

1

**Describe the bug** On initializing the gcv_agent, the following error occurs: `AttributeError: module 'google.cloud.vision' has no attribute 'types'` This error is thrown at line 119 of layoutparser/ocr/gcv_agent.py: `self._context = _vision.types.ImageContext(language_hints=languages)`...

Andrew-Kao

When I use LayoutParser on scientific documents that have watermarks, the generation of bounding boxes completely falls apart, and the information in the entire region covered by the watermark is...

KeshavBalaji

**Describe the bug** code: `ocr_agent = lp.TesseractAgent(languages='eng')` Error: ContextualVersionConflict: (google-api-core 2.11.0 (/usr/local/lib/python3.10/dist-packages), Requirement.parse('google-api-core[grpc]=1.14.0'), {'google-cloud-vision'}) **Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug...

mlbrothers

Cannot Usage lp.models. Detectron2LayoutModel

1

**Describe the bug** I cannot use Decetron2LayoutModel despite successfully install. Usage of LP ``` lp.models.Detectron2LayoutModel(...) ``` ``` lp.Detectron2LayoutModel(...) ``` **Environment** 1. On MacOS having M1 chip 2. '0.3.4' Version 3....

mertakcay

Train (fine-tune) LayoutParser pre-trained model using custom dataset

3

**Motivation** I want to fine-tune the pre-train model from LayoutParser by using my own dataset images. But I don't find any way in the documentation where I can train the...

ammarsaf

Hello, thanks for this very useful toolkit. According to the [official PubLayNet docs](https://github.com/ibm-aur-nlp/PubLayNet/tree/master/pre-trained-models#convert-pre-trained-model-for-fine-tuning-on-another-target-dataset), they had this mapping: | Category id | Label | | :---: | :--- | | 0...

opyate

The configuration for the `PrimaLayout` MRCNN Detectron2 model … https://github.com/Layout-Parser/layout-parser/blob/04e28168d820eea3a1ff1e098078323e7b48648b/src/layoutparser/models/detectron2/catalog.py#L57 … contains a setting `MODEL.ROI_HEADS.NUM_CLASSES: 7`. But LP's actual runtime config for the label map of the region types contains...

bertsky

Update constructor to specify the type of input parameter in the `blocks` argument to Layout class

kairi003

At `layoutparser.io`, the type hint `Image.Image` is used, but it is not imported.

kairi003