W1 A3: list(Y) is a list with 30 items, where each of the list items is of shape (60,90)

Course Q&A Deep Learning Specialization Sequence Models
1

Why is the shape (60,90)?

I thought 90 was length of 1-hot vector (90 difference possible values).

Where did this 60 come from?

2

These numbers come from Section 1.1 “Dataset”, where the “original_metheny.mid” file is pre-preprocessed. You can see the values in the 3rd cell in the notebook.

The MIDI file is about 8 minutes of music. The pre-processing cuts it into 60 separate segments of about 7 seconds each. These segments form the 60 members of the training set. Each example has 30 ‘notes’, and each note is one of 90 values.

Later in the notebook, at cell 11, the value is hard-coded “m = 60”, but I don’t think that was really necessary if they had saved it as a global value earlier.