{"id":14958098,"url":"https://github.com/sakura2233565548/TabPedia","last_synced_at":"2025-10-24T14:30:46.933Z","repository":{"id":254409565,"uuid":"846449768","full_name":"sakura2233565548/TabPedia","owner":"sakura2233565548","description":"This repository is the codebase of TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","archived":false,"fork":false,"pushed_at":"2024-10-16T02:43:04.000Z","size":2408,"stargazers_count":24,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-31T01:58:02.606Z","etag":null,"topics":["deep-learning","large-vision-language-models","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sakura2233565548.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-23T08:29:04.000Z","updated_at":"2025-01-23T09:43:16.000Z","dependencies_parsed_at":"2025-01-01T18:13:09.570Z","dependency_job_id":"76ffa5ba-e588-4355-98ab-3e57d4ef371c","html_url":"https://github.com/sakura2233565548/TabPedia","commit_stats":{"total_commits":6,"total_committers":1,"mean_commits":6.0,"dds":0.0,"last_synced_commit":"7b730944659606f1cf81f7c35bd792dc83ddbc0e"},"previous_names":["zhaowc-ustc/tabpedia-towards-comprehensive-visual-table-understanding-with-concept-synergy","zhaowc-ustc/tabpedia","sakura2233565548/tabpedia"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sakura2233565548%2FTabPedia","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sakura2233565548%2FTabPedia/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sakura2233565548%2FTabPedia/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sakura2233565548%2FTabPedia/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sakura2233565548","download_url":"https://codeload.github.com/sakura2233565548/TabPedia/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":237982075,"owners_count":19397193,"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","large-vision-language-models","pytorch"],"created_at":"2024-09-24T13:16:13.742Z","updated_at":"2025-10-24T14:30:45.031Z","avatar_url":"https://github.com/sakura2233565548.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":" # TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"assets/framework.png\" width=\"800\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n     📃 \u003ca href=\"https://arxiv.org/pdf/2406.01326\" target=\"_blank\"\u003ePaper\u003c/a\u003e | 🤗 \u003ca href=\"https://huggingface.co/datasets/ByteDance/ComTQA\" target=\"_blank\"\u003eComTQA Dataset\u003c/a\u003e | 🤗 \u003ca href=\"https://huggingface.co/Zhaowc/TabPedia_v1.0/tree/main\" target=\"_blank\"\u003eTabPedia_v1.0\u003c/a\u003e\n\n\u003c/p\u003e\n\n## News\n\n- [2024/08/27] 🔥 The training code is coming soon.\n- [2024/08/27] 🔥 Released inference code for visual table understanding tasks. Due to company copyright restrictions, we utilize [InternLM-7B-chat](https://huggingface.co/internlm/internlm2-chat-7b) as the LLM.\n\n## Installation\n- This codebase is tested on CUDA 11.8 and A100-SXM-80G.\n    ```bash\n    conda create -n TabPedia python=3.10 -y \u0026\u0026 conda activate TabPedia\n    pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118\n    pip install packaging \u0026\u0026  pip install ninja \u0026\u0026 pip install flash-attn==2.3.6 --no-build-isolation --no-cache-dir\n    pip install -r requirements.txt\n    git clone https://github.com/InternLM/xtuner.git -b v0.1.15\n    cd xtuner\n    pip install -e '.[all]'\n    ```\n\n## Quick Start\n\n* You need to download the official ViT-L/224 from [🤗 Huggingface](https://huggingface.co/openai/clip-vit-large-patch14/tree/main) and save it into ``./pretrained_pth/CLIP-ViT-Large``.\n* You need to download our pretrained model from [🤗 TabPedia_v1.0](https://huggingface.co/Zhaowc/TabPedia_v1.0) and save it into ``./pretrained_pth``.\n* Change the configuration of **CLIP_L_224px_pretrained_pth** and **llm_name_or_path** in ``tools/configs/Internlm2_7b_chat_TabPedia.py``\n* Finally, you can perform evaluation shell to coduct prediction. The results could be found in ``./results``.\n    ```bash\n    bash eval_TabPedia.sh\n    ```\n\n## Citation\n\nIf you find this work useful, please consider citing our paper:\n```\n@inproceedings{zhao2024tabpedia,\n title={TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy},\n author = {Weichao Zhao, Hao Feng, Qi Liu, Jingqun Tang, Binghong Wu, Lei Liao, Shu Wei, Yongjie Ye, Hao Liu, Wengang Zhou, Houqiang Li, Can Huang},\n booktitle = {Advances in Neural Information Processing Systems},\n year = {2024}\n}\n```\n\n## Acknowledgement\n- [Xtuner](https://github.com/InternLM/xtuner): the codebase we built upon. \n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsakura2233565548%2FTabPedia","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsakura2233565548%2FTabPedia","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsakura2233565548%2FTabPedia/lists"}