{"id":15905737,"url":"https://github.com/18520339/dbnet-tf2","last_synced_at":"2025-03-21T01:31:53.130Z","repository":{"id":46327222,"uuid":"499326477","full_name":"18520339/dbnet-tf2","owner":"18520339","description":"A TensorFlow 2 reimplementation of DBNet available as a Python package for Scene Text Detection, following ICDAR 2015 Dataset format and using TedEval as Evaluation metrics","archived":false,"fork":false,"pushed_at":"2023-05-10T20:59:16.000Z","size":2204,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-16T20:55:32.710Z","etag":null,"topics":["dbnet","differentiable-binarization","icdar","ocr","scene-text-detection","tensorflow"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/tfdbnet","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/18520339.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":"2022-06-02T23:59:58.000Z","updated_at":"2025-02-10T08:01:20.000Z","dependencies_parsed_at":"2024-10-28T09:13:58.854Z","dependency_job_id":"84f86a1e-2592-4d28-b073-f257694658d2","html_url":"https://github.com/18520339/dbnet-tf2","commit_stats":{"total_commits":25,"total_committers":1,"mean_commits":25.0,"dds":0.0,"last_synced_commit":"22cb0134ba3d7d5cdcaa8e3f0a9f168deeb2f736"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/18520339%2Fdbnet-tf2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/18520339%2Fdbnet-tf2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/18520339%2Fdbnet-tf2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/18520339%2Fdbnet-tf2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/18520339","download_url":"https://codeload.github.com/18520339/dbnet-tf2/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244721269,"owners_count":20498922,"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":["dbnet","differentiable-binarization","icdar","ocr","scene-text-detection","tensorflow"],"created_at":"2024-10-06T13:07:52.289Z","updated_at":"2025-03-21T01:31:52.710Z","avatar_url":"https://github.com/18520339.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TFDBNet\nA TensorFlow 2 reimplementation of [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/abs/1911.08947) available as a Python package and using [TedEval](https://github.com/clovaai/TedEval) for evaluation metrics. \n\n## Data Preparation\n![](./demo/preparation.png)\n\nStore images in `imgs` folder and groundtruths in `gts` folder. Then, prepare text files for training and validate data in the following format with '\\t' as a separator:\n- Example for ICDAR 2015 `train.txt`:\n```\n./datasets/train/train_imgs/img_1.jpg\t./datasets/train/train_gts/gt_img_1.txt\n./datasets/train/train_imgs/img_2.jpg\t./datasets/train/train_gts/gt_img_2.txt\n```\n- Example for ICDAR 2015 `validate.txt`:\n```\n./datasets/validate/validate_imgs/img_1.jpg\t./datasets/validate/validate_gts/gt_img_1.txt\n./datasets/validate/validate_imgs/img_2.jpg\t./datasets/validate/validate_gts/gt_img_2.txt\n```\nYou can customize the script in [dir2paths.sh](dir2paths.sh) to generate the above `train.txt` and `validate.txt` for your own dataset. And the groundtruths can be `.txt` files, with the following format:\n```\nx1,y1,x2,y2,x3,y3,x4,y4,annotation\n```\nBelow is the content of `./datasets/train/train_gts/gt_img_1.txt`:\n```\n377,117,463,117,465,130,378,130,Genaxis Theatre\n493,115,519,115,519,131,493,131,[06]\n374,155,409,155,409,170,374,170,###\n492,151,551,151,551,170,492,170,62-03\n376,198,422,198,422,212,376,212,Carpark\n494,190,539,189,539,205,494,206,###\n374,1,494,0,492,85,372,86,###\n```\n\n## Quick Start\n```\npip install tfdbnet\n```\nAfter installation, see the [demo](demo/demo.ipynb) on ICDAR 2015 dataset to know how to use. You can download my example trained weights along with the 2 files `train.txt` and `validate.txt` mentioned above [here](https://drive.google.com/file/d/1rLZiOTwlWtnq_a0v_oa0_2tSg7Mt1CUF).\n\n![](/demo/demo.png)\n\n## Reference\n- https://github.com/MhLiao/DB\n- https://github.com/zonasw/DBNet\n- https://github.com/WenmuZhou/DBNet.pytorch\n- https://github.com/xuannianz/DifferentiableBinarization\n- https://github.com/clovaai/TedEval\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F18520339%2Fdbnet-tf2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F18520339%2Fdbnet-tf2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F18520339%2Fdbnet-tf2/lists"}