{"id":19110159,"url":"https://github.com/zotroneneis/deep_music","last_synced_at":"2025-04-30T20:40:48.459Z","repository":{"id":93478882,"uuid":"98782065","full_name":"zotroneneis/deep_music","owner":"zotroneneis","description":"Recurrent neural network in TensorFlow for generating novel monophonic melodies.","archived":false,"fork":false,"pushed_at":"2019-02-10T08:14:39.000Z","size":86853,"stargazers_count":11,"open_issues_count":0,"forks_count":4,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-03-30T19:41:30.078Z","etag":null,"topics":["neural-network","python3","recurrent-neural-network","recurrent-neural-networks","tensorflow","variational-autoencoder","variational-autoencoders"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/zotroneneis.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":"2017-07-30T07:24:46.000Z","updated_at":"2022-04-20T20:49:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"841c1b54-08c6-4261-9e50-1d29ef4e3f5e","html_url":"https://github.com/zotroneneis/deep_music","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/zotroneneis%2Fdeep_music","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2Fdeep_music/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2Fdeep_music/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2Fdeep_music/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zotroneneis","download_url":"https://codeload.github.com/zotroneneis/deep_music/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251778897,"owners_count":21642443,"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":["neural-network","python3","recurrent-neural-network","recurrent-neural-networks","tensorflow","variational-autoencoder","variational-autoencoders"],"created_at":"2024-11-09T04:23:53.416Z","updated_at":"2025-04-30T20:40:48.439Z","avatar_url":"https://github.com/zotroneneis.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"deepmusic\n==============================\n\nThe main part of this project is based on exploring the ability of different recurrent Long Short-Term Memory architectures to generate novel monophonic melodies. All details about this part of the project can be found in the corresponding [report](https://github.com/zotroneneis/deep_music/blob/master/reports/report_deepmusic.pdf).\n\nIn addition, we trained and tested a variational autoencoder on the same task.\n\nAll code is written in Python and uses TensorFlow. \n\nProject authors: Anna-Lena Popkes, Pascal Wenker\n\nProject Organization\n------------\n\n    ├── Makefile           \u003c- Makefile with commands like `make data` or `make train`\n    ├── README.md          \u003c- The top-level README for developers using this project.\n    ├── data\n    │   ├── midis              \u003c- Original MIDI files \n    │   ├── notesequences      \u003c- Computed notesequence protocols \n    │   └── sequence_examples  \u003c- Sequence examples used to train the model \n    │\n    ├── models             \u003c- Trained and serialized models, model predictions, or model summaries\n    │\n    ├── references         \u003c- Data dictionaries, manuals, and all other explanatory materials.\n    │\n    ├── reports            \u003c- Final latex report for the project \n    │\n    ├── requirements.txt   \u003c- The requirements file for reproducing the analysis environment, e.g.\n    │                         generated with `pip freeze \u003e requirements.txt`\n    │\n    ├── src                \u003c- Source code for use in this project.\n    │   ├── __init__.py    \u003c- Makes src a Python module\n    │   │\n    │   ├── main.py        \u003c- Main method \n    │   ├── config.yaml    \u003c- Config file, storing all network parameters \n    │   │\n    │   ├── data           \u003c- Scripts to transform MIDI files to notesequences and \n    │   │   │                 notesequences to sequence examples\n    │   │   │                 \n    │   │   ├── 01_create_notesequences \n    │   │   └── 02_create_sequenceExampes \n    │   │\n    │   │\n    │   ├── models         \u003c- Scripts to train models and then use trained models to make\n    │   │   │                 predictions\n    │   │   ├── basic_model.py\n    │   │   ├── attention_model.py\n    │   │\n    │   ├── helper         \u003c- Scripts that contain helper functions used by the model \n    │   │   ├── misc.py\n    │   │   └── visualization.py\n    │   │\n    │   ├── scripts        \u003c- Scripts to create exploratory and results oriented visualizations\n    │       ├── create_debug_midis.py \n    │       ├── midi_to_melody.py\n    │       └── tensorboardify.py \n    │   \n    │   \n    ├── vae                 \u003c- Additional project training a variational autoencoder\n    │   │                   to generate music\n    │   │                   \n    │   ├── models          \u003c- Trained and serialized models, model predictions, \n    │   │   │               or model predictions\n    │   │   ├── checkpoints \n    │   │   ├── generated_midis \n    │   │   └── tensorboard \n    │   │                   \n    │   ├── src\n    │       │                 \n    │       ├── main.py      \u003c- Main method \n    │       ├── config.yaml  \u003c- Config file, storing all network parameters\n    │       ├── models       \u003c- Model definition and code to train the model\n    │       └── helper       \u003c- Helper functions used to train the model \n    └── \n\n\n--------\n\n\u003cp\u003e\u003csmall\u003eProject based on the \u003ca target=\"_blank\" href=\"https://drivendata.github.io/cookiecutter-data-science/\"\u003ecookiecutter data science project template\u003c/a\u003e. #cookiecutterdatascience\u003c/small\u003e\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzotroneneis%2Fdeep_music","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzotroneneis%2Fdeep_music","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzotroneneis%2Fdeep_music/lists"}