No description, website, or topics provided.
Switch branches/tags
Clone or download
sachinravi14 Merge pull request #23 from leomrocha/unit_test
code fixes: fix issue with summary writer and checkpt_dir
Latest commit dcc3709 Jul 9, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
src code fixes Jul 8, 2018
.gitignore Add gitignore Mar 22, 2018 Add MIDI tutorial to reading list. Dec 30, 2017 Update project status in README Jun 27, 2018
proposal.pdf Add readme, proposal, and reading list. Dec 1, 2017
requirements.txt Update README with instructions for data and running models Jun 18, 2018

Few-Shot Music Generation

Few-Shot Distribution Learning for Music Generation

  • Tagline: Learning a generative model for music data using a small amount of examples.
  • Date: December 2017
  • Category: Fundamental Research
  • Author(s): Hugo Larochelle, Chelsea Finn, Sachin Ravi

Project Status

  • Brainstorming for datasets phase: Currently collecting ideas for dataset collection for lyrics and MIDI data. See the Issues page for details.
  • Collecting actual data for lyrics and MIDI.
  • Decide and implement pre-processing scheme for data (specifically for MIDI).
  • Release training script and model API code.
  • Experiment with new models on both datasets.

Community Links

Problem description:

See Introduction section of the proposal.

Why this problem matters:

See Introduction section of the proposal.

How to measure success:

See Experiments section of the proposal.


See Datasets subsection of the proposal.

Relevant Work:

See Related Work section of the proposal.


  • Please begin by reading papers from the Reading List to familiarize yourself with work in this area.


Both the lyrics and freemidi data can be downloaded here. Place the raw-data directory in the home folder of the repository and make sure to unzip both .zip files in the data sub-directories.

For example, for the lyrics data, make sure in the given path the following files and directories exist:

ls Few-Shot-Music-Generation/raw-data/lyrics/
>> lyrics_data test.csv  train.csv  val.csv

Training Models

Sample run (check the different yaml files for different ways to run):

$ CONFIG=lyrics.yaml
$ MODEL=lstm_baseline.yaml
$ TASK=5shot.yaml
python -um train.train --data=config/${CONFIG} --model=config/${MODEL} --task=config/${TASK} --checkpt_dir=/tmp/fewshot/lstm_baseline

To view the tensorboard (only works for lstm_baseline.yaml model):

$ tensorboard --logdir=/tmp/fewshot

If you have any trouble running the code, please create an issue describing your problem.

Logging results

Please log all your results in this spreadsheet.