LSTM-RNN, CNN, Simple NeuralNetworks
This repo is meant to provide simple and straightforward starter codes to those beginning a project in music Genre Classification using Deep Learning Techniques like LSTM, CNN, and just plain old-school Neural Networks. This model can classify new audio files into four categories: Latin American, Asian, Middle Eastern, and African Music.
I hope that this work can help in several Deep Learning, Machine Learning projects in Music Genre Classification. The training data isn't provided here.
The three main model construction/training/evaluation algorithms as below: NN, CNN, LSTM.
- NN_Music_Classification.py -> Simple Neural Network Made with TensorFlow
- CNN_Music_Classification.py -> Convolutional Neural Network Made with TensorFlow
- LSTM_Music_Classification.py -> RNN-LSTM Made with TensorFlow
Below: NN_Music_Classification.py
Below: CNN_Music_Classification.py
Below: LSTM_Music_Classification.py
- main.py -> Make predictions using saved models from running the above codes
- test_data -> Provided for use in main.py