carlb15 / jazz_improvisation_with_lstm

Generating a Jazz Music Sample with a LSTM

NOTE: Implementation hidden due to Coursera Terms of Service.

Jazz Improvisation with LSTM

Generating Jazz music with a Long-Short-Term-Memory (LSTM) using Keras.

Implementation

Music has been pre-processed to render into musical values. The RNN model will train on the dataset to generate a sequence of musical values that are post-processed into midi music. The post-processing ensures the same sound isn't repeated too many times, two notes aren't far part in pitch, etc.

Lessons Learned

1. A sequence model can be used to generate musical values, which are then post-processed into midi music.
2. Fairly similar models can be used to generate dinosaur names or to generate music, with the major difference being the input fed to the model.
3. In Keras, sequence generation involves defining layers with shared weights, which are then repeated for the different time steps 1, ..., T_x.

Credit:

Sequence Models Course for Deep Learning Specialization

jazz_improvisation_with_lstm's Issues

NOne type iterable

your main file has an error that is
`TypeError Traceback (most recent call last)
in
----> 1 model = djmodel(Tx = 30 , n_a = 64, n_values = 78)

in djmodel(Tx, n_a, n_values)
35 x = None
36 # Step 2.C: Perform one step of the LSTM_cell
---> 37 a, _, c = None
38 # Step 2.D: Apply densor to the hidden state output of LSTM_Cell
39 out = None

TypeError: 'NoneType' object is not iterable
`

see to it