{"id":18735390,"url":"https://github.com/wenmuzhou/segmentation-free_ocr","last_synced_at":"2025-08-10T03:34:37.208Z","repository":{"id":117622076,"uuid":"119379497","full_name":"WenmuZhou/Segmentation-Free_OCR","owner":"WenmuZhou","description":"recognize chinese and english without segmentation ","archived":false,"fork":false,"pushed_at":"2018-08-22T01:48:33.000Z","size":5983,"stargazers_count":11,"open_issues_count":0,"forks_count":6,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-12T19:14:29.822Z","etag":null,"topics":["ocr","python3","tensorflow","text-recognition"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/WenmuZhou.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,"zenodo":null}},"created_at":"2018-01-29T12:27:39.000Z","updated_at":"2022-05-26T11:39:54.000Z","dependencies_parsed_at":null,"dependency_job_id":"9692e421-5d3d-443d-984a-ba1c106614aa","html_url":"https://github.com/WenmuZhou/Segmentation-Free_OCR","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/WenmuZhou/Segmentation-Free_OCR","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WenmuZhou%2FSegmentation-Free_OCR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WenmuZhou%2FSegmentation-Free_OCR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WenmuZhou%2FSegmentation-Free_OCR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WenmuZhou%2FSegmentation-Free_OCR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/WenmuZhou","download_url":"https://codeload.github.com/WenmuZhou/Segmentation-Free_OCR/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WenmuZhou%2FSegmentation-Free_OCR/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269672052,"owners_count":24457112,"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","status":"online","status_checked_at":"2025-08-10T02:00:08.965Z","response_time":71,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["ocr","python3","tensorflow","text-recognition"],"created_at":"2024-11-07T15:16:48.711Z","updated_at":"2025-08-10T03:34:37.194Z","avatar_url":"https://github.com/WenmuZhou.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Convolutional Recurrent Neural Network in Tensorflow (tf.crnn)\n\nthis code is fork from \u003chttps://github.com/solivr/tf-crnn\u003e and modified.\n\nCRNN model in Tensorflow using Estimators\n\nImplementation of the Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition tasks, such as scene text recognition and OCR. Original paper \u003chttp://arxiv.org/abs/1507.05717\u003e and code \u003chttps://github.com/bgshih/crnn\u003e\n\nThis version uses the `tf.estimator.Estimator` to build the model.\n\n### Contents\n* `src/model.py` : definition of the model\n* `src/data_handler.py` :  functions for data loading, preprocessing and data augmentation\n* `src/config.py` : `class Params`  manages parameters of model and experiments\n* `src/decoding.py` :  helper fucntion to transform characters to words\n* `train_info.py` : script to launch for training the model, more info on the parameters and options inside\n* `export_model.py`: script to export a model once trained, i.e for serving\n* Extra : `hlp/numbers_mnist_generator.py` :  generates a sequence of digits to form a number using the MNIST database\n* Extra : `hlp/simple_generate_scene_text.py` : generates  Chinese and English text images\n* Extra : `hlp/get_captcha.py` : draws text to images\n* Extra : `hlp/csv_path_convertor.py` :  converts a csv file with relative paths to a csv file with absolute paths\n\n### How to train a model\nThe main script to launch is `train.py`. To train the model, you should input a csv file with each row containing the filename of the image (full path) and its label (plain text) separated by a delimiting character (let's say ';') :\n\n```\n/full/path/to/image1.{jpg,png} string_label1\n/full/path/to/image2.{jpg,png} string_label2\n...\n```\n\nFor example launch the script using :\n\n```\npython3 train.py -g 1 -ft train_data.csv -o ./export_model_dir\n```\n\n### Dependencies \n* `tensorflow` (1.3)\n* `tensorflow-tensorboard` (0.1.7) \n* `tqdm`  \n* `json`\n* `glob`\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwenmuzhou%2Fsegmentation-free_ocr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwenmuzhou%2Fsegmentation-free_ocr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwenmuzhou%2Fsegmentation-free_ocr/lists"}