{"id":13610135,"url":"https://github.com/jisungk/deepjazz","last_synced_at":"2025-05-15T13:08:36.531Z","repository":{"id":44102429,"uuid":"55271222","full_name":"jisungk/deepjazz","owner":"jisungk","description":"Deep learning driven jazz generation using Keras \u0026 Theano!","archived":false,"fork":false,"pushed_at":"2025-05-14T15:33:38.000Z","size":12223,"stargazers_count":2886,"open_issues_count":12,"forks_count":445,"subscribers_count":108,"default_branch":"master","last_synced_at":"2025-05-14T16:46:16.528Z","etag":null,"topics":["deep-learning","jazz","keras","lstm","machine-learning","music","neural-networks","rnn","theano"],"latest_commit_sha":null,"homepage":"http://deepjazz.io","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/jisungk.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":"2016-04-02T01:00:05.000Z","updated_at":"2025-05-14T15:33:42.000Z","dependencies_parsed_at":"2022-09-17T16:00:32.310Z","dependency_job_id":null,"html_url":"https://github.com/jisungk/deepjazz","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/jisungk%2Fdeepjazz","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jisungk%2Fdeepjazz/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jisungk%2Fdeepjazz/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jisungk%2Fdeepjazz/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jisungk","download_url":"https://codeload.github.com/jisungk/deepjazz/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254346624,"owners_count":22055808,"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","jazz","keras","lstm","machine-learning","music","neural-networks","rnn","theano"],"created_at":"2024-08-01T19:01:41.600Z","updated_at":"2025-05-15T13:08:31.484Z","avatar_url":"https://github.com/jisungk.png","language":"Python","funding_links":[],"categories":["Python","Code without articles","Examples/Notebooks"],"sub_categories":[],"readme":"Note: deepjazz is no longer being actively developed. It may be refactored at some point in the future. Goodbye and thank you for your interest 😢\n\n***\n\n![deepjazz](https://cloud.githubusercontent.com/assets/9053987/16575656/901989da-424f-11e6-9f54-6a04199e69f5.png)\n\n### Using Keras \u0026 Theano for deep learning driven jazz generation\n\nI built [*deepjazz*](https://deepjazz.io) in 36 hours at a hackathon. It uses Keras \u0026 Theano, two deep learning libraries, to generate jazz music. Specifically, it builds a two-layer [LSTM](http://deeplearning.net/tutorial/lstm.html), learning from the given MIDI file. It uses deep learning, the AI tech that powers [Google's AlphaGo](https://deepmind.com/alpha-go.html) and [IBM's Watson](https://www.ibm.com/smarterplanet/us/en/ibmwatson/what-is-watson.html), **to make music -- something that's considered as deeply human**.\n\n[![SoundCloud](https://jisungk.github.io/deepjazz/img/button_soundcloud.png)](https://soundcloud.com/deepjazz-ai)  \nCheck out deepjazz's music on **[SoundCloud](https://soundcloud.com/deepjazz-ai)**!\n\n### Dependencies\n\n* [Keras](http://keras.io/#installation)\n* [Theano](http://deeplearning.net/software/theano/install.html#bleeding-edge-install-instructions) (\"bleeding-edge\" version on GitHub)\n* [music21](http://web.mit.edu/music21/doc/installing/index.html)\n\n### Instructions\n\nRun on CPU with command:  \n```\npython generator.py [# of epochs]\n```\n\nRun on GPU with command:  \n```\nTHEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python generator.py [# of epochs]\n```\n\nNote: running Keras/Theano on GPU is formally supported for only NVIDIA cards (CUDA backend).\n\nNote: `preprocess.py` must be modified to work with other MIDI files (the relevant \"melody\" MIDI part needs to be selected). The ability to handle this natively is a planned feature.\n\n### Author\n\n[Ji-Sung Kim](https://jisungkim.com)  \nPrinceton University, Department of Computer Science  \nhello (at) jisungkim.com  \n\n### Citations\n\nThis project develops a lot of preprocessing code (with permission) from Evan Chow's [jazzml](https://github.com/evancchow/jazzml). Thank you [Evan](https://www.linkedin.com/in/evancchow)! Public examples from the [Keras documentation](https://github.com/fchollet/keras) were also referenced.\n\n### Code License, Media Copyright\n\nCode is licensed under the Apache License 2.0  \nImages and other media are copyrighted (Ji-Sung Kim)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjisungk%2Fdeepjazz","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjisungk%2Fdeepjazz","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjisungk%2Fdeepjazz/lists"}