{"id":15027859,"url":"https://github.com/meijieru/crnn.pytorch","last_synced_at":"2025-05-15T01:08:01.937Z","repository":{"id":18079671,"uuid":"83292099","full_name":"meijieru/crnn.pytorch","owner":"meijieru","description":"Convolutional recurrent network in pytorch","archived":false,"fork":false,"pushed_at":"2024-09-19T06:50:05.000Z","size":38,"stargazers_count":2438,"open_issues_count":103,"forks_count":656,"subscribers_count":53,"default_branch":"master","last_synced_at":"2025-04-11T14:16:51.936Z","etag":null,"topics":["neural-network","recognition","scene-texts"],"latest_commit_sha":null,"homepage":null,"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/meijieru.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2017-02-27T09:26:06.000Z","updated_at":"2025-04-11T11:04:27.000Z","dependencies_parsed_at":"2023-01-11T20:27:58.929Z","dependency_job_id":"85b8a6ef-c4f7-4bcb-bf2c-ec9e16fc5cf7","html_url":"https://github.com/meijieru/crnn.pytorch","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/meijieru%2Fcrnn.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meijieru%2Fcrnn.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meijieru%2Fcrnn.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meijieru%2Fcrnn.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/meijieru","download_url":"https://codeload.github.com/meijieru/crnn.pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254254042,"owners_count":22039792,"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":["neural-network","recognition","scene-texts"],"created_at":"2024-09-24T20:07:11.728Z","updated_at":"2025-05-15T01:07:56.913Z","avatar_url":"https://github.com/meijieru.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Convolutional Recurrent Neural Network\n======================================\n\nThis software implements the Convolutional Recurrent Neural Network (CRNN) in pytorch.\nOrigin software could be found in [crnn](https://github.com/bgshih/crnn)\n\nRun demo\n--------\nA demo program can be found in ``demo.py``. Before running the demo, download a pretrained model\nfrom [Baidu Netdisk](https://pan.baidu.com/s/1pLbeCND) or [Dropbox](https://www.dropbox.com/s/dboqjk20qjkpta3/crnn.pth?dl=0). \nThis pretrained model is converted from auther offered one by ``tool``.\nPut the downloaded model file ``crnn.pth`` into directory ``data/``. Then launch the demo by:\n\n    python demo.py\n\nThe demo reads an example image and recognizes its text content.\n\nExample image:\n![Example Image](./data/demo.png)\n\nExpected output:\n    loading pretrained model from ./data/crnn.pth\n    a-----v--a-i-l-a-bb-l-ee-- =\u003e available\n\nDependence\n----------\n* [warp_ctc_pytorch](https://github.com/SeanNaren/warp-ctc/tree/pytorch_bindings/pytorch_binding)\n* lmdb\n\nTrain a new model\n-----------------\n1. Construct dataset following [origin guide](https://github.com/bgshih/crnn#train-a-new-model). If you want to train with variable length images (keep the origin ratio for example), please modify the `tool/create_dataset.py` and sort the image according to the text length.\n2. Execute ``python train.py --adadelta --trainRoot {train_path} --valRoot {val_path} --cuda``. Explore ``train.py`` for details.\n\nCite\n----\n```tex\n@article{shi2016end,\n  title={An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition},\n  author={Shi, Baoguang and Bai, Xiang and Yao, Cong},\n  journal={IEEE transactions on pattern analysis and machine intelligence},\n  volume={39},\n  number={11},\n  pages={2298--2304},\n  year={2016},\n  publisher={IEEE}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmeijieru%2Fcrnn.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmeijieru%2Fcrnn.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmeijieru%2Fcrnn.pytorch/lists"}