{"id":20447331,"url":"https://github.com/snowkylin/rnn-handwriting-generation","last_synced_at":"2025-04-13T01:08:00.518Z","repository":{"id":112690527,"uuid":"77225828","full_name":"snowkylin/rnn-handwriting-generation","owner":"snowkylin","description":"Handwriting generation by RNN with TensorFlow, based on \"Generating Sequences With Recurrent Neural Networks\" by Alex Graves","archived":false,"fork":false,"pushed_at":"2017-01-17T06:34:26.000Z","size":139281,"stargazers_count":108,"open_issues_count":4,"forks_count":38,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-04-13T01:07:49.533Z","etag":null,"topics":["deep-learning","generative-model","handwriting","handwriting-synthesis","rnn","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/snowkylin.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2016-12-23T13:02:25.000Z","updated_at":"2025-03-07T10:20:04.000Z","dependencies_parsed_at":null,"dependency_job_id":"eadbdb15-4e34-413e-8e3d-e8f83e174189","html_url":"https://github.com/snowkylin/rnn-handwriting-generation","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/snowkylin%2Frnn-handwriting-generation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowkylin%2Frnn-handwriting-generation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowkylin%2Frnn-handwriting-generation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snowkylin%2Frnn-handwriting-generation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/snowkylin","download_url":"https://codeload.github.com/snowkylin/rnn-handwriting-generation/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248650766,"owners_count":21139681,"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":["deep-learning","generative-model","handwriting","handwriting-synthesis","rnn","tensorflow"],"created_at":"2024-11-15T10:25:51.033Z","updated_at":"2025-04-13T01:08:00.508Z","avatar_url":"https://github.com/snowkylin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Generating handwriting with LSTM, Mixture Gaussian \u0026 Bernoulli distribution and TensorFlow\n\nThis is a TensorFlow implementation of *[Generating Sequences With Recurrent Neural Networks](https://arxiv.org/abs/1308.0850)* by Alex Graves.\n\nIt have two functions:\n\n* **Handwriting Prediction**: Randomly generate a line of handwriting (set `mode=predict`). \n* **Handwriting Synthesis**: Given a string, generate the corresponding handwriting (set `mode=synthesis`).\n\nThis project is adapted from [hardmaru's great work](https://github.com/hardmaru/write-rnn-tensorflow). The `util.py` is just from there and before running `train.py` and `sample.py` you need to follow [the instruction](https://github.com/hardmaru/write-rnn-tensorflow#training) and download the necessary files.\n\nI hope to make this model simple, just **show the main algorithm as clear as possible** without struggling with bundles of optimization methods in deep learning. But if you wish, you can add them easily by yourself.\n\n### Sample Result\n\n#### Handwriting Prediction\n\n![sample.normal.svg](https://cdn.rawgit.com/snowkylin/rnn-handwriting-generation/master/sample.normal.svg)\nThis is the result with default setting:\n* rnn state size = 256\n* rnn length = 300\n* num of layers = 2\n* number of mixture gaussian = 20\n\nand 20+ epochs. Not so fancy but can be recognized as something like handwritting, huh?\n\n#### Handwriting Synthesis\n\n![sample.normal.biased.3.svg](https://cdn.rawgit.com/snowkylin/rnn-handwriting-generation/master/sample.normal.biased.3.svg)\n\nThis is the result with the string \"a quick brown fox jumps over the lazy dog\".\n\nIn addition, [the scribe project by greydanus](https://github.com/greydanus/scribe) also helps me a lot, expecially the use of `tf.batch_matmul()`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnowkylin%2Frnn-handwriting-generation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsnowkylin%2Frnn-handwriting-generation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnowkylin%2Frnn-handwriting-generation/lists"}