Skip to content
An AI for Music Generation
Python Shell
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
docs Change arxiv link from http to https Jan 28, 2019
exp Add results for accompaniment models Nov 5, 2018
scripts
src
v1 delete links of old training data Aug 23, 2018
v2 Suppress Numpy run time errors Nov 2, 2018
.gitattributes Add archived v2 folder Oct 26, 2018
.gitignore Add .backup and .recycle Oct 26, 2018
LICENSE.txt
Pipfile
Pipfile.lock Add environment related file Oct 26, 2018
README.md Add some descriptions for npz-to-MIDI conversion Jul 30, 2019
requirements.txt Add environment related file Oct 26, 2018

README.md

MuseGAN

MuseGAN is a project on music generation. In a nutshell, we aim to generate polyphonic music of multiple tracks (instruments). The proposed models are able to generate music either from scratch, or by accompanying a track given a priori by the user.

We train the model with training data collected from Lakh Pianoroll Dataset to generate pop song phrases consisting of bass, drums, guitar, piano and strings tracks.

Sample results are available here.

Prerequisites

Below we assume the working directory is the repository root.

Install dependencies

  • Using pipenv (recommended)

    Make sure pipenv is installed. (If not, simply run pip install pipenv.)

    # Install the dependencies
    pipenv install
    # Activate the virtual environment
    pipenv shell
  • Using pip

    # Install the dependencies
    pip install -r requirements.txt

Prepare training data

The training data is collected from Lakh Pianoroll Dataset (LPD), a new multitrack pianoroll dataset.

# Download the training data
./scripts/download_data.sh
# Store the training data to shared memory
./scripts/process_data.sh

You can also download the training data manually (train_x_lpd_5_phr.npz).

Scripts

We provide several shell scripts for easy managing the experiments. (See here for a detailed documentation.)

Below we assume the working directory is the repository root.

Train a new model

  1. Run the following command to set up a new experiment with default settings.

    # Set up a new experiment
    ./scripts/setup_exp.sh "./exp/my_experiment/" "Some notes on my experiment"
  2. Modify the configuration and model parameter files for experimental settings.

  3. You can either train the model:

    # Train the model
    ./scripts/run_train.sh "./exp/my_experiment/" "0"

    or run the experiment (training + inference + interpolation):

    # Run the experiment
    ./scripts/run_exp.sh "./exp/my_experiment/" "0"

Use pretrained models

  1. Download pretrained models

    # Download the pretrained models
    ./scripts/download_models.sh

    You can also download the pretrained models manually (pretrained_models.tar.gz).

  2. You can either perform inference from a trained model:

    # Run inference from a pretrained model
    ./scripts/run_inference.sh "./exp/default/" "0"

    or perform interpolation from a trained model:

    # Run interpolation from a pretrained model
    ./scripts/run_interpolation.sh "./exp/default/" "0"

Outputs

By default, samples will be generated alongside the training. You can disable this behavior by setting save_samples_steps to zero in the configuration file (config.yaml). The generated will be stored in the following three formats by default.

  • .npy: raw numpy arrays
  • .png: image files
  • .npz: multitrack pianoroll files that can be loaded by the Pypianoroll package

You can disable saving in a specific format by setting save_array_samples, save_image_samples and save_pianoroll_samples to False in the configuration file.

The generated pianorolls are stored in .npz format to save space and processing time. You can use the following code to write them into MIDI files.

from pypianoroll import Multitrack

m = Multitrack('./test.npz')
m.write('./test.mid')

Sample Results

Some sample results can be found in ./exp/ directory. More samples can be downloaded from the following links.

Papers

Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
Hao-Wen Dong and Yi-Hsuan Yang
in Proceedings of the 19th International Society for Music Information Retrieval Conference (ISMIR), 2018.
[website] [arxiv] [paper] [slides(long)] [slides(short)] [poster] [code]

MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
Hao-Wen Dong,* Wen-Yi Hsiao,* Li-Chia Yang and Yi-Hsuan Yang, (*equal contribution)
in Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), 2018.
[website] [arxiv] [paper] [slides] [code]

MuseGAN: Demonstration of a Convolutional GAN Based Model for Generating Multi-track Piano-rolls
Hao-Wen Dong,* Wen-Yi Hsiao,* Li-Chia Yang and Yi-Hsuan Yang (*equal contribution)
in Late-Breaking Demos of the 18th International Society for Music Information Retrieval Conference (ISMIR), 2017. (two-page extended abstract)
[paper] [poster]

You can’t perform that action at this time.