{"id":13827035,"url":"https://github.com/jyotidabass/document_text_recognition","last_synced_at":"2025-07-09T02:33:15.851Z","repository":{"id":109565171,"uuid":"467890962","full_name":"jyotidabass/document_text_recognition","owner":"jyotidabass","description":null,"archived":false,"fork":false,"pushed_at":"2022-03-09T11:12:43.000Z","size":200,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-08-04T09:06:12.427Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/jyotidabass.png","metadata":{"files":{"readme":"README.md","changelog":"changelog.rst","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2022-03-09T11:02:36.000Z","updated_at":"2022-03-09T15:29:12.000Z","dependencies_parsed_at":"2023-04-08T06:36:02.590Z","dependency_job_id":null,"html_url":"https://github.com/jyotidabass/document_text_recognition","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/jyotidabass%2Fdocument_text_recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jyotidabass%2Fdocument_text_recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jyotidabass%2Fdocument_text_recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jyotidabass%2Fdocument_text_recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jyotidabass","download_url":"https://codeload.github.com/jyotidabass/document_text_recognition/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225481176,"owners_count":17481167,"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":"2024-08-04T09:01:48.871Z","updated_at":"2024-11-20T06:30:46.152Z","avatar_url":"https://github.com/jyotidabass.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Text recognition\n\nThe sample training script was made to train text recognition model with docTR.\n\n## Setup\n\nFirst, you need to install `doctr` (with pip, for instance)\n\n```shell\npip install -e . --upgrade\npip install -r references/requirements.txt\n```\n\n## Usage\n\nYou can start your training in TensorFlow:\n\n```shell\npython references/recognition/train_tensorflow.py crnn_vgg16_bn --train_path path/to/your/train_set --val_path path/to/your/val_set  --epochs 5\n```\nor PyTorch:\n\n```shell\npython references/recognition/train_pytorch.py crnn_vgg16_bn --train_path path/to/your/train_set --val_path path/to/your/val_set --epochs 5 --device 0\n```\n\n\n\n## Data format\n\nYou need to provide both `train_path` and `val_path` arguments to start training.\nEach of these paths must lead to a 2-elements folder:\n\n```shell\n├── images\n    ├── img_1.jpg\n    ├── img_2.jpg\n    ├── img_3.jpg\n    └── ...\n├── labels.json\n```\n\nThe JSON files must contain word-labels for each picture as a string.\nThe order of entries in the json does not matter.\n\n```shell\nlabels = {\n    'img_1.jpg': 'I',\n    'img_2.jpg': 'am',\n    'img_3.jpg': 'a',\n    'img_4.jpg': 'Jedi',\n    'img_5.jpg': '!',\n    ...\n}\n```\n\n## Advanced options\n\nFeel free to inspect the multiple script option to customize your training to your own needs!\n\n```python\npython references/recognition/train_pytorch.py --help\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjyotidabass%2Fdocument_text_recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjyotidabass%2Fdocument_text_recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjyotidabass%2Fdocument_text_recognition/lists"}