{"id":20575241,"url":"https://github.com/ayumiymk/aster.pytorch","last_synced_at":"2025-04-04T20:14:29.699Z","repository":{"id":41086505,"uuid":"196689396","full_name":"ayumiymk/aster.pytorch","owner":"ayumiymk","description":"ASTER in Pytorch","archived":false,"fork":false,"pushed_at":"2021-12-09T11:26:06.000Z","size":120,"stargazers_count":676,"open_issues_count":23,"forks_count":168,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-03-28T19:10:03.929Z","etag":null,"topics":["aster","computer-vision","ocr","pytorch","scene-text","text-recognition","text-rectification"],"latest_commit_sha":null,"homepage":"","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/ayumiymk.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":"2019-07-13T06:56:34.000Z","updated_at":"2025-03-24T06:57:32.000Z","dependencies_parsed_at":"2022-09-04T14:23:16.192Z","dependency_job_id":null,"html_url":"https://github.com/ayumiymk/aster.pytorch","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayumiymk%2Faster.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayumiymk%2Faster.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayumiymk%2Faster.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayumiymk%2Faster.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ayumiymk","download_url":"https://codeload.github.com/ayumiymk/aster.pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247242680,"owners_count":20907134,"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":["aster","computer-vision","ocr","pytorch","scene-text","text-recognition","text-rectification"],"created_at":"2024-11-16T05:38:43.032Z","updated_at":"2025-04-04T20:14:29.674Z","avatar_url":"https://github.com/ayumiymk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ASTER: Attentional Scene Text Recognizer with Flexible Rectification\n\nThis repository implements the ASTER in pytorch. Origin software could be found in [here](https://github.com/bgshih/aster).\n\nASTER is an accurate scene text recognizer with flexible rectification mechanism. The research paper can be found [here](https://ieeexplore.ieee.org/abstract/document/8395027/).\n\n![ASTER Overview](overview.png)\n\n## Installation\n\n```\nconda env create -f environment.yml\n```\n\n## Train\n\n[**NOTE**] Some users say that they can't reproduce the reported performance with minor modification, like [1](https://github.com/ayumiymk/aster.pytorch/issues/17#issuecomment-527380815) and [2](https://github.com/ayumiymk/aster.pytorch/issues/17#issuecomment-528718596). I haven't try other settings, so I can't guarantee the same performance with different settings. The users should just run the following script without any modification to reproduce the results.\n```\nbash scripts/stn_att_rec.sh\n```\n\n## Test\n\nYou can test with .lmdb files by\n```\nbash scripts/main_test_all.sh\n```\nOr test with single image by\n```\nbash scripts/main_test_image.sh\n```\n\n## Pretrained model\nThe pretrained model is available on our [release page](https://github.com/ayumiymk/aster.pytorch/releases/download/v1.0/demo.pth.tar). Download `demo.pth.tar` and put it to somewhere. Before running, modify the `--resume` to the location of this file.\n\n## Reproduced results\n\n|               | IIIT5k |  SVT |  IC03 |  IC13 |  IC15 | SVTP  |  CUTE |\n|:-------------:|:------:|:----:|:-----:|:-----:|:-----:|:-----:|:-----:|\n|  ASTER (L2R)  |  92.67 |   -  | 93.72 | 90.74 |    -  | 78.76 | 76.39 |\n| ASTER.Pytorch |  93.2  | 89.2 | 92.2  |   91  |  78.0 |  81.2 |  81.9 |\n\nAt present, the bidirectional attention decoder proposed in ASTER is not included in my implementation. \n\nYou can use the codes to bootstrap for your next text recognition research project.\n\n\n## Data preparation\n\nWe give an example to construct your own datasets. Details please refer to `tools/create_svtp_lmdb.py`.\n\nWe also provide datasets for [training](https://pan.baidu.com/s/1BMYb93u4gW_3GJdjBWSCSw\u0026shfl=sharepset) (password: wi05) and [testing](https://drive.google.com/open?id=1U4mGLlsm9Ade1-gQOyd6He5R0yiaafYJ).\n\n## Citation\n\nIf you find this project helpful for your research, please cite the following papers:\n\n```\n@article{bshi2018aster,\n  author    = {Baoguang Shi and\n               Mingkun Yang and\n               Xinggang Wang and\n               Pengyuan Lyu and\n               Cong Yao and\n               Xiang Bai},\n  title     = {ASTER: An Attentional Scene Text Recognizer with Flexible Rectification},\n  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, \n  volume    = {41},\n  number    = {9},\n  pages     = {2035--2048},\n  year      = {2019},\n}\n\n@inproceedings{ShiWLYB16,\n  author    = {Baoguang Shi and\n               Xinggang Wang and\n               Pengyuan Lyu and\n               Cong Yao and\n               Xiang Bai},\n  title     = {Robust Scene Text Recognition with Automatic Rectification},\n  booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition,\n               {CVPR} 2016, Las Vegas, NV, USA, June 27-30, 2016},\n  pages     = {4168--4176},\n  year      = {2016}\n}\n```\n\nIMPORTANT NOTICE: Although this software is licensed under MIT, our intention is to make it free for academic research purposes. If you are going to use it in a product, we suggest you [contact us](xbai@hust.edu.cn) regarding possible patent issues.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayumiymk%2Faster.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fayumiymk%2Faster.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayumiymk%2Faster.pytorch/lists"}