def match_one_midi(midi_file):
'''
Hash and match a single MIDI file against the MSD
:parameters:
- midi_file : str
Path to a MIDI file to match
'''
# Get a beat-synchronous piano roll of the MIDI
pm = pretty_midi.PrettyMIDI(midi_file)
piano_roll = pm.get_piano_roll(times=pm.get_beats()).T
piano_roll = piano_roll[np.newaxis, :, 36:84]
# Make the piano roll look like it does when we trained the hasher
piano_roll = (piano_roll - train_stats['mean'])/train_stats['std']
hashed_piano_roll = hash(
piano_roll[np.newaxis].astype(theano.config.floatX))
# Compute hash sequence
query = hash_match.vectors_to_ints(hashed_piano_roll > 0)
query = query.astype('uint16')
# Get indices of sequences which are within 40% -> 1/40% of this seq length
valid_length_indices = hash_match.filter_by_length(query, sequences, .4)
# Compute MIDI mean chroma vector
query_chroma = pm.get_chroma().mean(axis=1)
# Get sequences less than the mean chroma distance
valid_chroma_indices = hash_match.filter_by_mean_chroma(
query_chroma, mean_chromas, 20)
# Intersect to get valid index set
valid_indices = np.intersect1d(valid_length_indices, valid_chroma_indices)
# Match the MIDI file query hash list against all sequences
matches, scores = hash_match.match_one_sequence(
query, sequences, .9, 4, valid_indices)
return matches, scores
def process_one_file(index_entry, base_path='msd', train_stats=train_stats,
hash=hash):
'''
Hash the features in a single npz file.
:parameters:
- index_entry : dict
Entry in an index with keys 'path', 'artist', and 'title'
- base_path : str
Which dataset are we processing?
- train_stats : dict
Dict where train_stats['mean'] is the training set mean feature
and train_stats['std'] is the per-feature std dev
- hash : theano.function
Theano function which takes in feature matrix and outputs hashes
'''
try:
npz_file = os.path.join(BASE_DATA_PATH, base_path, 'npz',
index_entry['path'] + '.npz')
output_filename = npz_file.replace('npz', 'pkl')
if os.path.exists(output_filename):
return
features = np.load(npz_file)
sync_gram = features['sync_gram']
if sync_gram.shape[0] < 6:
return
mean_cqt = sync_gram.mean(axis=0)
sync_gram = sync_gram[np.newaxis]
sync_gram = (sync_gram - train_stats['mean'])/train_stats['std']
if np.isnan(sync_gram).any():
return
hashed_features = hash(
sync_gram[np.newaxis].astype(theano.config.floatX))
hashes = hash_match.vectors_to_ints(hashed_features > 0)
hashes = hashes.astype('uint16')
output_dict = dict([('hash_list', hashes), ('mean_cqt', mean_cqt)],
**index_entry)
if not os.path.exists(os.path.split(output_filename)[0]):
os.makedirs(os.path.split(output_filename)[0])
with open(output_filename, 'wb') as f:
pickle.dump(output_dict, f)
except Exception as e:
print "Error creating {}: {}".format(index_entry['path'], e)
return