{"id":21327735,"url":"https://github.com/bdshrk/neuraldrummer","last_synced_at":"2026-05-20T15:12:35.377Z","repository":{"id":182912965,"uuid":"638691107","full_name":"bdshrk/neuraldrummer","owner":"bdshrk","description":"A neural network for generating drum tracks for songs using Python and TensorFlow.","archived":false,"fork":false,"pushed_at":"2024-02-06T19:26:55.000Z","size":10246,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-22T12:45:55.431Z","etag":null,"topics":["computational-creativity","creativity","deep-learning","drum-machine","drumkit","drums","machine-learning","neural-network","python","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bdshrk.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}},"created_at":"2023-05-09T22:35:30.000Z","updated_at":"2023-08-14T23:01:42.000Z","dependencies_parsed_at":"2025-01-22T12:44:53.168Z","dependency_job_id":"39843d80-0d61-47b3-aad5-6c9f012825c3","html_url":"https://github.com/bdshrk/neuraldrummer","commit_stats":null,"previous_names":["bdshrk/neuraldrummer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdshrk%2Fneuraldrummer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdshrk%2Fneuraldrummer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdshrk%2Fneuraldrummer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bdshrk%2Fneuraldrummer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bdshrk","download_url":"https://codeload.github.com/bdshrk/neuraldrummer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243806084,"owners_count":20350775,"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":["computational-creativity","creativity","deep-learning","drum-machine","drumkit","drums","machine-learning","neural-network","python","tensorflow"],"created_at":"2024-11-21T21:19:24.789Z","updated_at":"2026-05-20T15:12:30.347Z","avatar_url":"https://github.com/bdshrk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NeuralDrummer\n\n**A neural network for generating drum tracks for songs.**\n\nPractical project for the COMP6590: Computational Creativity module.\n\n## Usage\n\nThe code can be run from the Jupyter notebook file `main.ipynb`.\n\nYou will need `TensorFlow` installed in your Python environment and\nalso `PrettyMIDI`, `Mido`, `numpy`, and `matplotlib`. \nPlease use `requirements.txt` or the following command:\n\n```\npip install pretty_midi mido numpy tensorflow matplotlib\n```\n\nEach cell in the notebook should be executed consecutively with the\nexception of the `nn.train()` and `nn.plot()` cells (which are for training\nthe network if you wish.) The model saves its weights to the\n`/saved/` directory and can be loaded in the cell `nn.load()`.\n\nFeel free to modify the `INPUT_PATH` in the final cell to point to a MIDI\nfile of your choosing. You can also modify the cut-off parameter of the\n`tokeniser.add_drum_track()` within the same cell to adjust the sensitivity\nof the result. You should find the output as a file named `combined.mid`.\n\nIn order for the model to learn, you will require a collection of MIDI files\ncontaining drum tracks.\nDuring development, I used the *\"Lakh MIDI Dataset Clean\"*, available\n[here](https://colinraffel.com/projects/lmd/). Once the MIDI files have been\npre-processed, the original files are no longer needed. The result of the \npre-processing is stored in a file named `saved.txt`.\n\nNote: You will need a fair amount of memory to load the neural network and\nthe inputs from the saved file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbdshrk%2Fneuraldrummer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbdshrk%2Fneuraldrummer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbdshrk%2Fneuraldrummer/lists"}