BinaryMuseGAN is a follow-up project of the MuseGAN project. In this project, we first investigate how the real-valued piano-rolls generated by the generator may lead to difficulties in training the discriminator for CNN-based models. To overcome the binarization issue, we propose to append to the generator an additional refiner network, which try to refine the real-valued predictions generated by the pretrained generator to binary-valued ones. The proposed model is able to directly generate binary-valued piano-rolls at test time.

We trained the network with training data collected from Lakh Pianoroll Dataset. We used the model to generate four-bar musical phrases consisting of eight tracks: Drums, Piano, Guitar, Bass, Ensemble, Reed, Synth Lead and Synth Pad. Audio samples are available here.

Modify config.py for configuration.

• Quick setup

  Change the values in the dictionary SETUP for a quick setup. Documentation is provided right after each key.

• More configuration options

  Four dictionaries EXP_CONFIG, DATA_CONFIG, MODEL_CONFIG and TRAIN_CONFIG define experiment-, data-, model- and training-related configuration variables, respectively.

  The automatically-determined experiment name is based only on the values defined in the dictionary SETUP, so remember to provide the experiment name manually (so that you won't overwrite a trained model).

python main.py

• Prepare your own data

  The array will be reshaped to (-1, num_bar, num_timestep, num_pitch, num_track). These variables are defined in config.py.

• Download our training data with this script or download it manually here.

Please cite the following paper if you use the code provided in this repository.

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