{"id":23739859,"url":"https://github.com/p1atdev/mangalineextraction-hf","last_synced_at":"2026-03-02T16:30:15.987Z","repository":{"id":223673598,"uuid":"761018175","full_name":"p1atdev/MangaLineExtraction-hf","owner":"p1atdev","description":"MangaLineExtraction in transformers library format ","archived":false,"fork":false,"pushed_at":"2024-02-21T11:35:12.000Z","size":2164,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-12-31T09:39:28.968Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://huggingface.co/p1atdev/MangaLineExtraction-hf","language":"Jupyter Notebook","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/p1atdev.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}},"created_at":"2024-02-21T04:43:09.000Z","updated_at":"2024-02-21T11:43:34.000Z","dependencies_parsed_at":"2024-02-21T13:58:02.815Z","dependency_job_id":null,"html_url":"https://github.com/p1atdev/MangaLineExtraction-hf","commit_stats":null,"previous_names":["p1atdev/mangalineextraction-hf"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p1atdev%2FMangaLineExtraction-hf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p1atdev%2FMangaLineExtraction-hf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p1atdev%2FMangaLineExtraction-hf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/p1atdev%2FMangaLineExtraction-hf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/p1atdev","download_url":"https://codeload.github.com/p1atdev/MangaLineExtraction-hf/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239880901,"owners_count":19712486,"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":[],"created_at":"2024-12-31T09:39:34.443Z","updated_at":"2026-03-02T16:30:15.858Z","avatar_url":"https://github.com/p1atdev.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MangaLineExtraction-hf\n\nA huggingface transformers compatible implementation of MangaLineExtraction (https://github.com/ljsabc/MangaLineExtraction_PyTorch).\n\n\nThe converted weights are avaiable on [🤗 HuggingFace](https://huggingface.co/p1atdev/MangaLineExtraction-hf).\n\n## Example usage with transformers\n\n```py\nfrom PIL import Image\nimport torch\n\nfrom transformers import AutoModel, AutoImageProcessor\n\nREPO_NAME = \"p1atdev/MangaLineExtraction-hf\"\n\nmodel = AutoModel.from_pretrained(REPO_NAME, trust_remote_code=True)\nprocessor = AutoImageProcessor.from_pretrained(REPO_NAME, trust_remote_code=True)\n\nimage = Image.open(\"./sample.jpg\")\n\ninputs = processor(image, return_tensors=\"pt\")\n\nwith torch.no_grad():\n    outputs = model(inputs.pixel_values)\n\nline_image = Image.fromarray(outputs.pixel_values[0].numpy().astype(\"uint8\"), mode=\"L\")\nline_image.save(\"./line_image.png\")\n```\n\n## Acknowledgements\n\nWe extend our gratitude to the authors of the  [Deep Extraction of Manga Structural Lines](https://www.cse.cuhk.edu.hk/~ttwong/papers/linelearn/linelearn.html) and the contributors to the  [MangaLineExtraction_PyTorch](https://github.com/ljsabc/MangaLineExtraction_PyTorch) for their pioneering work that served as the foundation for our adaptation. Our thanks also go to HuggingFace for developing [transformers](https://github.com/huggingface/transformers), enabling us to enhance this project further.\n\nFor detailed information, please refer to:\n- https://www.cse.cuhk.edu.hk/~ttwong/papers/linelearn/linelearn.html\n- https://github.com/huggingface/transformers\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fp1atdev%2Fmangalineextraction-hf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fp1atdev%2Fmangalineextraction-hf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fp1atdev%2Fmangalineextraction-hf/lists"}