Using TensorFlow to generate short sequences of music with a Restricted Boltzmann Machine. Do you want to go deep?, see the original technical idea: How to build an RBM neural network in tensorflow.
- Install Tensorflow. If you have trouble running Tensorflow installation it may help:
sudo easy_install pip
sudo pip install --upgrade virtualenv
export PIP_REQUIRE_VIRTUALENV=false
-
Install Anaconda and dependencies
-
Create virtualenv
virtualenv venv
- Activate venv
source venv/bin/activate
- Install python_midi module in normal procedure
git clone [email protected]:vishnubob/python-midi.git
cd python-midi
python setup.py install
- Install remaining dependencies with pip.
- matplotlib
- numpy
- pandas
- msgpack
- glob
- tqdm
pip install [dependencies]
- Make magic happen. First train your model with custom parameters and then wait the output.
python fire.py
Depends of the technical capabilities of your computer, it can take from 5 to 10 minutes.
We need your help feeding and training our current model. If you have reggeaton samples feel free to contribute.