{"id":19957273,"url":"https://github.com/the-black-knight-01/tabulo","last_synced_at":"2025-05-12T17:25:26.638Z","repository":{"id":39699812,"uuid":"205170519","full_name":"the-black-knight-01/Tabulo","owner":"the-black-knight-01","description":"Table Detection and Extraction Using Deep Learning ( It is built in Python, using Luminoth, TensorFlow\u003c2.0 and Sonnet.)","archived":false,"fork":false,"pushed_at":"2022-11-24T18:54:27.000Z","size":11130,"stargazers_count":197,"open_issues_count":15,"forks_count":40,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-05-11T02:43:05.328Z","etag":null,"topics":["deep-learning","detection","faster-r-cnn","luminoth","ocr","pdf-table-extraction","python","sonnet","ssd","table-data-extraction","table-detection","table-detection-using-deep-learning","table-recognition","tabulo","tensorflow","tesseract"],"latest_commit_sha":null,"homepage":"https://interviewbubble.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/the-black-knight-01.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-08-29T13:29:43.000Z","updated_at":"2025-04-29T05:30:01.000Z","dependencies_parsed_at":"2023-01-22T02:36:00.925Z","dependency_job_id":null,"html_url":"https://github.com/the-black-knight-01/Tabulo","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-black-knight-01%2FTabulo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-black-knight-01%2FTabulo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-black-knight-01%2FTabulo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-black-knight-01%2FTabulo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/the-black-knight-01","download_url":"https://codeload.github.com/the-black-knight-01/Tabulo/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253785802,"owners_count":21964030,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","detection","faster-r-cnn","luminoth","ocr","pdf-table-extraction","python","sonnet","ssd","table-data-extraction","table-detection","table-detection-using-deep-learning","table-recognition","tabulo","tensorflow","tesseract"],"created_at":"2024-11-13T01:37:07.371Z","updated_at":"2025-05-12T17:25:26.609Z","avatar_url":"https://github.com/the-black-knight-01.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Tabulo](https://github.com/interviewBubble/Tabulo/raw/master/docs/images/Tabulo_logo.png)](https://github.com/interviewBubble/Tabulo)\n\n---\n\nTabulo is an open source toolkit for **computer vision**. Currently, we support table detection, but we are aiming for much more. It is built in Python, using [Luminoth](https://github.com/tryolabs/luminoth), [TensorFlow](https://www.tensorflow.org/) and [Sonnet](https://github.com/deepmind/sonnet).\n\n### Table of Contents\n1. **[Installation Instructions](#1-installation-instructions)**\u003cbr\u003e\n2. **[Avaiable API's](#2-avaiable-apis)**\u003cbr\u003e\n3. **[Working with pretrained Models](#3-working-with-pretrained-models)**\u003cbr\u003e\n4. **[Runnning Tabulo](#4-runnning-tabulo)**\u003cbr\u003e\n5. **[Runnning Tabulo As Service](#5-runnning-tabulo-as-service)**\u003cbr\u003e\n6. **[Supported models ](#6-supported-models)**\u003cbr\u003e\n7. **[Usage](#7-usage)**\u003cbr\u003e\n8. **[Working with datasets](#8-working-with-datasets)**\u003cbr\u003e\n9. **[Training](#9-training)**\u003cbr\u003e\n10. **[LICENSE](#10-license)**\u003cbr\u003e\n## 1. Installation Instructions\nTabulo currently supports Python 2.7 and 3.4–3.6. \n\n### 1.1 Pre-requisites\n\nTo use Tabulo, [TensorFlow](https://www.tensorflow.org/install/) must be installed beforehand. If you want **GPU support**, you should install the GPU version of TensorFlow with `pip install tensorflow-gpu`, or else you can use the CPU version using `pip install tensorflow`.\n\nWe are using tesseract to extract data from table so you have to install tesseract also. [Follow this link to install tessersact](https://interviewbubble.com/install-tesseract-on-mac-linux-windows-centos/)\n\n### 1.2 Installing Tabulo\n\nFirst, clone the repo on your machine and then install with `pip`:\n\n```bash\ngit clone https://github.com/interviewBubble/Tabulo.git\ncd tabulo\npip install -e .\n```\n\n\n### 1.3 Check that the installation worked\n\nSimply run `tabulo --help`.\n\n## 2. Avaiable API's\n* `localhost:5000/api/fasterrcnn/predict/`   - To detect table in the image\n* `localhost:5000/api/fasterrcnn/extract/`   - Extract table content from detected tables\n\n## 3. Working with pretrained Models:\n* DOWNLOAD pretrained model from [Google drive](https://drive.google.com/drive/folders/1aUh9RfGn2XGgG2EtpKFh7P6PmcC3Q48z?usp=sharing)\n* Unzip and Copy downloaded luminoth folder inside ```luminoth/utils/pretrained_models``` folder\n* Hit this command to list all check points: ```tabulo checkpoint list```\n* You will get output like this:\n![Checkpoints](https://github.com/interviewBubble/Tabulo/raw/master/docs/images/Checkpoints.png)\n* Now run server using this command: ```tabulo server web --checkpoint 6aac7a1e8a8e```\n\n## 4. Runnning Tabulo\n\n### 4.1 Running Tabulo as Web Server:\n![Running Tabulo](https://github.com/interviewBubble/Tabulo/blob/master/docs/images/tabulo_server.png)\n\n### 4.2 Example of Table Detection with Faster R-CNN By Tabulo:\n![Example of Table Detection with Faster R-CNN By Tabulo](https://github.com/interviewBubble/Tabulo/blob/master/docs/images/table_detect.png)\n\n### 4.3 Example of Table Data Extraction with tesseract By Tabulo:\n![Example of Table Data Extraction with tesseract By Tabulo](https://github.com/interviewBubble/Tabulo/blob/master/docs/images/table_data_extract.png)\n\n## 5. Runnning Tabulo As Service:\n\n### 5.1 Using Curl command\n```Curl command to detect tabel\ncurl -X POST \\\n  http://localhost:5000/api/fasterrcnn/predict/ \\\n  -H 'Content-Type: application/x-www-form-urlencoded' \\\n  -H 'Postman-Token: 70478bd2-e1e8-442f-b0bf-ea5ecf7bf4d8' \\\n  -H 'cache-control: no-cache' \\\n  -H 'content-type: multipart/form-data; boundary=----WebKitFormBoundary7MA4YWxkTrZu0gW' \\\n  -F image=@/path/to/image/page_8-min.jpg\n``` \n### 5.2 With PostMan\n#### Header Section:\n![Table Detection using Postman](https://github.com/interviewBubble/Tabulo/blob/master/docs/images/tabulo_resquest_header.png)\n\n#### Data Section:\n![Table Detection using Postman](https://github.com/interviewBubble/Tabulo/raw/master/docs/images/table_detect_API.png)\n\n## 6. Supported models\n\nCurrently, we support the following models:\n\n* **Object Detection**\n  * [Faster R-CNN](https://arxiv.org/abs/1506.01497)\n  * [SSD](https://arxiv.org/abs/1512.02325)\n\nWe also provide **pre-trained checkpoints** for the above models trained on popular datasets such as [COCO](http://cocodataset.org/) and [Pascal](http://host.robots.ox.ac.uk/pascal/VOC/).\n\n## 7. Usage\n\nThere is one main command line interface which you can use with the `tabulo` command. Whenever you are confused on how you are supposed to do something just type:\n\n`tabulo --help` or `tabulo \u003csubcommand\u003e --help`\n\nand a list of available options with descriptions will show up.\n\n## 8. Working with datasets\n\n [DataSet to train your custom model](https://github.com/interviewBubble/Table-Detection-using-Deep-Learning/tree/master/data).\n\n## 9. Training\n\nSee [Training your own model](https://github.com/interviewBubble/Table-Detection-using-Deep-Learning) to learn how to train locally or in Google Cloud.\n\n## 10. LICENSE\nReleased under the [BSD 3-Clause](LICENSE).\n\n--------------\n# References\n* https://github.com/Sargunan/Table-Detection-using-Deep-learning\n* https://github.com/tryolabs/luminoth\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthe-black-knight-01%2Ftabulo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthe-black-knight-01%2Ftabulo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthe-black-knight-01%2Ftabulo/lists"}