ohmytable

Name	ohmytable JSON
Version	0.1.0 JSON
	download
home_page	None
Summary	None
upload_time	2024-07-25 14:36:33
maintainer	Sanster
docs_url	None
author	Sanster
requires_python	>=3.8
license	None
keywords	deep-learning table-structure-recognition
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # OhMyTable

![example](./assets/example.jpg)

## Install

```bash
pip install ohmytable
```

## Quick Start

Use as a package

```python
from ohmytable import OhMyTable

image_path = "/path/to/your_image_contains_table"
ohmytable = OhMyTable(device="cpu")  # cpu/mps/cuda
htmls = ohmytable(image_path)
# The entire pipeline outputs table structure represented in HTML.
print(htmls)

# Visualize and save the results of all models in the pipeline.
from ohmytable.callback import VisualizeCallback

ohmytable(image_path, callbacks=[VisualizeCallback(image_path, "./tmp")])
```

Start a gradio web demo:

```bash
git clone https://github.com/Sanster/OhMyTable.git
cd OhMyTable
pip install gradio typer
python3 gradio_demo.py
```

## Limitation

- Table Structure Recognition model is trained with max output length 1024(about 150 table cell boxes.)
- The model effect will be better with less padding around the table image.

## Acknowledgement

- [PaddleOCR2Pytorch](https://github.com/frotms/PaddleOCR2Pytorch)
- [unitable](https://github.com/poloclub/unitable)
- [keremberke/yolov8m-table-extraction)](https://huggingface.co/keremberke/yolov8m-table-extraction)

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "ohmytable",
    "maintainer": "Sanster",
    "docs_url": null,
    "requires_python": ">=3.8",
    "maintainer_email": null,
    "keywords": "deep-learning, table-structure-recognition",
    "author": "Sanster",
    "author_email": null,
    "download_url": "https://files.pythonhosted.org/packages/38/aa/d8273e91d5ce16043edd62933a07e0fc9165da4f86014c74a8ba9a896635/ohmytable-0.1.0.tar.gz",
    "platform": null,
    "description": "# OhMyTable\n\n![example](./assets/example.jpg)\n\n## Install\n\n```bash\npip install ohmytable\n```\n\n## Quick Start\n\nUse as a package\n\n```python\nfrom ohmytable import OhMyTable\n\nimage_path = \"/path/to/your_image_contains_table\"\nohmytable = OhMyTable(device=\"cpu\")  # cpu/mps/cuda\nhtmls = ohmytable(image_path)\n# The entire pipeline outputs table structure represented in HTML.\nprint(htmls)\n\n# Visualize and save the results of all models in the pipeline.\nfrom ohmytable.callback import VisualizeCallback\n\nohmytable(image_path, callbacks=[VisualizeCallback(image_path, \"./tmp\")])\n```\n\nStart a gradio web demo:\n\n```bash\ngit clone https://github.com/Sanster/OhMyTable.git\ncd OhMyTable\npip install gradio typer\npython3 gradio_demo.py\n```\n\n## Limitation\n\n- Table Structure Recognition model is trained with max output length 1024(about 150 table cell boxes.)\n- The model effect will be better with less padding around the table image.\n\n## Acknowledgement\n\n- [PaddleOCR2Pytorch](https://github.com/frotms/PaddleOCR2Pytorch)\n- [unitable](https://github.com/poloclub/unitable)\n- [keremberke/yolov8m-table-extraction)](https://huggingface.co/keremberke/yolov8m-table-extraction)\n",
    "bugtrack_url": null,
    "license": null,
    "summary": null,
    "version": "0.1.0",
    "project_urls": {
        "Bug Reports": "https://github.com/Sanster/ohmytable/issues",
        "Source": "https://github.com/Sanster/ohmytable/"
    },
    "split_keywords": [
        "deep-learning",
        " table-structure-recognition"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "4c5e7412300f6899220b68985f020fc1876bbb6b712ef69eaf420e05ba5c49f4",
                "md5": "78769d704fc4958bf6440918d5cd8032",
                "sha256": "cbe3d65566964cef954fae39aec2338b5b3aa3265b88b57b6696515f21fcc252"
            },
            "downloads": -1,
            "filename": "ohmytable-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "78769d704fc4958bf6440918d5cd8032",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.8",
            "size": 59416,
            "upload_time": "2024-07-25T14:36:31",
            "upload_time_iso_8601": "2024-07-25T14:36:31.420523Z",
            "url": "https://files.pythonhosted.org/packages/4c/5e/7412300f6899220b68985f020fc1876bbb6b712ef69eaf420e05ba5c49f4/ohmytable-0.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "38aad8273e91d5ce16043edd62933a07e0fc9165da4f86014c74a8ba9a896635",
                "md5": "9d4808886dea834bf997f7efa586cbff",
                "sha256": "8eb15eae5c2d3f867a2e6571fd4dfc3ad4123e2caebd4e89179e91341935e579"
            },
            "downloads": -1,
            "filename": "ohmytable-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "9d4808886dea834bf997f7efa586cbff",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8",
            "size": 45195,
            "upload_time": "2024-07-25T14:36:33",
            "upload_time_iso_8601": "2024-07-25T14:36:33.364823Z",
            "url": "https://files.pythonhosted.org/packages/38/aa/d8273e91d5ce16043edd62933a07e0fc9165da4f86014c74a8ba9a896635/ohmytable-0.1.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-07-25 14:36:33",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "Sanster",
    "github_project": "ohmytable",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": false,
    "lcname": "ohmytable"
}