{"id":13435667,"url":"https://github.com/alleveenstra/attentionocr","last_synced_at":"2025-03-18T11:31:52.783Z","repository":{"id":39734525,"uuid":"219037683","full_name":"alleveenstra/attentionocr","owner":"alleveenstra","description":"Attention OCR in Tensorflow 2.0","archived":false,"fork":false,"pushed_at":"2023-03-25T00:31:08.000Z","size":103,"stargazers_count":46,"open_issues_count":6,"forks_count":11,"subscribers_count":10,"default_branch":"master","last_synced_at":"2024-10-27T18:58:29.780Z","etag":null,"topics":["computer-vision","machine-learning","ocr","python3","tensorflow2"],"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/alleveenstra.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":"2019-11-01T18:04:18.000Z","updated_at":"2023-12-04T08:39:58.000Z","dependencies_parsed_at":"2024-05-02T04:59:16.717Z","dependency_job_id":"4faa419d-3fe5-485d-9eb2-5e10d786ca09","html_url":"https://github.com/alleveenstra/attentionocr","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/alleveenstra%2Fattentionocr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alleveenstra%2Fattentionocr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alleveenstra%2Fattentionocr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alleveenstra%2Fattentionocr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alleveenstra","download_url":"https://codeload.github.com/alleveenstra/attentionocr/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244211103,"owners_count":20416582,"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":["computer-vision","machine-learning","ocr","python3","tensorflow2"],"created_at":"2024-07-31T03:00:37.892Z","updated_at":"2025-03-18T11:31:47.776Z","avatar_url":"https://github.com/alleveenstra.png","language":"Python","funding_links":[],"categories":["Sample Codes / Projects \u003ca name=\"sample\" /\u003e ⛏️📐📁"],"sub_categories":["Reinforcement Learning \u003ca name=\"RL\" /\u003e🔮"],"readme":"# Attention OCR\n\nA clear and maintainable implementation of Attention OCR in Tensorflow 2.0.\n\nThis sequence to sequence OCR model aims to provide a clear and maintainable implementation of attention based OCR.\n\nPlease note that this is currently a work in progress.\nDocumentation is missing, but will be added when the code is stable.\n\nThis repository depends upon the following:\n\n*  Tensorflow 2.0\n*  Python 3.6+\n\n## Training a model\n\nTo train a model, first download the sources for generating synthetic data:\n\n```bash\ncd synthetic\n./download_data_sources.sh\n```\n\nNext, in this project's root folder, run the training script:\n\n```bash\npython3 run.py\n```\n\nThis will run a test training run. \nIf everything went well, you'll find a file named \"trained.h5\" in your directory.\nTo train a real model you should change the training parameters.\nSee run.py its arguments to find out what is configurable.\n\n```bash\npython3 run.py --help\n```\n\n## References\n\nThis work is based on the following work:\n\n*  [Attention Is All You Need](https://arxiv.org/abs/1706.03762)\n\n## To do\n\n*  Make image height variable\n*  Name all input and output tensors \n*  Write unit tests with full coverage\n*  Show a test case on google colab\n*  Perform a grid search on best parameters for a toy dataset\n*  Document the whole API\n\n[![Codacy Badge](https://api.codacy.com/project/badge/Grade/4b136e7c17fb4106a94afa985d03e491)](https://www.codacy.com/manual/alle.veenstra/attentionocr?utm_source=github.com\u0026amp;utm_medium=referral\u0026amp;utm_content=alleveenstra/attentionocr\u0026amp;utm_campaign=Badge_Grade)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falleveenstra%2Fattentionocr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falleveenstra%2Fattentionocr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falleveenstra%2Fattentionocr/lists"}