project/generate.py

@@ -48,18 +48,14 @@ output_path = sys.argv[2]
 # this dictionary is generated with model
 print('Loading... {}'.format(trained_model_path))
 model = pickle.load(open(trained_model_path, 'rb'))
-int_to_note = pickle.load(open('{}_dict'.format(trained_model_path), 'rb'))
-
-# TODO: 16 it should a variable by integrated with model seq_len
-# TODO: random.randint(0,50), the range should be a variable of lenght of vocab size
-seed = [random.randint(0,250) for x in range(16)] 
+int_to_note, n_vocab, seq_len = pickle.load(open('{}_dict'.format(trained_model_path), 'rb'))
 
+seed = [random.randint(0,n_vocab) for x in range(seq_len)] 
 music = []
 
 print('Generating...')
 for i in trange(124):
-    #TODO: 16 it should a variable by integrated with model seq_len
-    predicted_vector = model.predict(np.array(seed).reshape(1,16,1))
+    predicted_vector = model.predict(np.array(seed).reshape(1,seq_len,1))
     # using best fitted note
     # predicted_index = np.argmax(predicted_vector)
     # using propability distribution for choosing note
@@ -67,14 +63,14 @@ for i in trange(124):
     predicted_index = choose_by_prob(predicted_vector)
     music.append(int_to_note[predicted_index])
     seed.append(predicted_index)
-    #TODO: 16 it should a variable by integrated with model seq_len
-    seed = seed[1:1+16]
+    seed = seed[1:1+seq_len]
 
 
 print('Saving...')
 offset = 0
 output_notes = []
-for event in tqdm(music):
+for _event in tqdm(music):
+    event, note_len = _event.split(';')
     if (' ' in event) or event.isdigit():
         notes_in_chord = event.split(' ')
         notes = []
@@ -91,7 +87,7 @@ for event in tqdm(music):
         new_note.storedInstrument = instrument.Piano()
         output_notes.append(new_note)
 
-    offset += 0.5
+    offset += float(note_len)
 
 midi_stream = stream.Stream(output_notes)
 

project/midi.py

@@ -8,8 +8,7 @@ that is prepared for model training.
     output_path - the output path where will be created samples of data
 
     Usage:
-        >>> ./midi.py <midi_folder_path> <output_path>
-
+        >>> ./midi.py <midi_folder_path> <output_path> <sequence_lenth>
 '''
 
 import settings
@@ -24,9 +23,22 @@ import pickle
 from music21 import converter, instrument, note, chord, stream
 import music21
 
-midi_folder_path = sys.argv[1]
-output_path = sys.argv[2]
-seq_len = int(sys.argv[3])
+class MidiParseError(Exception):
+   """Error that is raised then midi file cannot be parsed"""
+   pass
+
+
+def parse_argv(argv):
+    '''This function is parsing given arguments when running a midi script.
+    Returns a tuple consinting of  midi_folder_path, output_path, seq_len'''
+    try:
+        midi_folder_path = argv[1]
+        output_path = argv[2]
+        seq_len = int(argv[3])
+        return midi_folder_path, output_path, seq_len
+    except IndexError:
+        raise AttributeError('You propably didnt pass parameters to run midi.py script.\
+                             >>> ./midi.py <midi_folder_path> <output_path> <sequence_lenth>')
 
 def to_sequence(midi_path, seq_len):
     ''' This function is supposed to be used on one midi file in directory loop.
@@ -40,22 +52,24 @@ def to_sequence(midi_path, seq_len):
             - midi_path: path to midi file
             - seq_len: lenght of sequance before prediction
             
-        Returns: Tuple of train_X, train_y directories'''
+        Returns: Tuple of train_X, train_y dictionaries consisinting of samples of song grouped by instruments
+    '''
         
     seq_by_instrument = defaultdict( lambda : [] )
-    midi_file = music21.converter.parse(midi_path)
+    
+    try:
+        midi_file = music21.converter.parse(midi_path)
+    except music21.midi.MidiException:
+        raise MidiParseError
     stream = music21.instrument.partitionByInstrument(midi_file)
     for part in stream:
         for event in part:
             if part.partName != None:
-                # TODO: add note lenght as parameter
                 if isinstance(event, music21.note.Note):
-                    # to_export_event = (str(event.pitch), event.quarterLength)
-                    to_export_event = str(event.pitch)
+                    to_export_event = '{};{}'.format(str(event.pitch), float(event.quarterLength))
                     seq_by_instrument[part.partName].append(to_export_event)
                 elif isinstance(event, music21.chord.Chord):
-                    to_export_event = ' '.join(str(note) for note in event.pitches)
-                    # to_export_event = (' '.join(str(note) for note in event.pitches), event.quarterLength)
+                    to_export_event = '{};{}'.format(' '.join(str(note) for note in event.pitches), float(event.quarterLength))
                     seq_by_instrument[part.partName].append(to_export_event)
 
     X_train_by_instrument = defaultdict( lambda : [] )
@@ -65,39 +79,54 @@ def to_sequence(midi_path, seq_len):
         for i in range(len(sequence)-(seq_len)) :
             X_train_by_instrument[instrument].append(np.array(sequence[i:i+seq_len])) # <seq lenth
             y_train_by_instrument[instrument].append(np.array(sequence[i+seq_len]))
-            # TODO: Notes to integers
 
     return X_train_by_instrument, y_train_by_instrument
 
-def main():
-    print('Exporting...')
-
+def colect_samples(midi_folder_path, seq_len):
+    '''This function is looping throuth given directories and
+    collecting samples from midi files.
+    
+        Parameters: midi_folder_path - a path to directory with midi files
+                    seq_len - a lenth of train_X sample that tells 
+                    how many notes is given do LSTM to predict the next note.
+        
+        Returns: Tuple of train_X, train_y dictionaries consisinting
+        of samples of all songs in directory grouped by instruments.
+    '''
+    
+    print('Collecting samples...')
     train_X = defaultdict( lambda : [] )
     train_y = defaultdict( lambda : [] )
 
     for directory, subdirectories, files in os.walk(midi_folder_path):
         for midi_file in tqdm(files):
             midi_file_path = os.path.join(directory, midi_file)
-            
-            # some midi files can be corupted, and cannot be parsed
-            # so we just omit corupted files, and go to the next file.
             try:
                 _X_train, _y_train = to_sequence(midi_file_path, seq_len)
-            except music21.midi.MidiException:
+            except MidiParseError:
                 continue
-
             for (X_key, X_value), (y_key, y_value) in zip(_X_train.items(), _y_train.items()):
                 train_X[X_key].extend(np.array(X_value))
                 train_y[y_key].extend(np.array(y_value))
 
-    # this is for intrument separation
+    return train_X, train_y
+
+def save_samples(output_path, samples):
+    '''This function save samples to npz packages, splitted by instrument.'''
+    
     print('Saving...')
+    
     if not os.path.exists(output_path):
         os.makedirs(output_path)
+        
+    train_X, train_y = samples
     for (X_key, X_value), (y_key, y_value) in tqdm(zip(train_X.items(), train_y.items())):
         if X_key == y_key:
             np.savez_compressed('{}/{}.npz'.format(output_path, X_key), np.array(X_value), np.array(y_value))
 
+def main():
+    midi_folder_path, output_path, seq_len = parse_argv(sys.argv)
+    save_samples(output_path, colect_samples(midi_folder_path, seq_len))
     print('Done!')
 
 if __name__ == '__main__':

project/train.py

@@ -1,15 +1,14 @@
 #!python3
 #!/usr/bin/env python3
-
-import tensorflow as tf
+import sys
+import pickle
 import settings
-#from tensorflow.keras import layers
+
+import numpy as np
 from keras.layers import Input, Dense, Conv2D, Flatten, LSTM, Dropout, TimeDistributed, RepeatVector, Activation, Bidirectional, Reshape
 from keras.models import Model, Sequential
 from keras.utils.np_utils import to_categorical
-import numpy as np
-import sys
-import pickle
+
 
 def load_data(samples_path):
     print('Loading... {}'.format(train_data_path))
@@ -25,7 +24,6 @@ def preprocess_samples(train_X, train_y):
     n_vocab = vocab.shape[0]
     note_to_int = dict((note, number) for number, note in enumerate(vocab))
     int_to_note = dict((number, note) for number, note in enumerate(vocab))
-
     _train_X = []
     _train_y = []
     for sample in train_X:
@@ -58,12 +56,13 @@ model.add(Dense(n_vocab))
 model.add(Activation('softmax'))
 model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
 
-# model training
+# This code will train our model, with given by parameter number of epochs
 print('Training...')
 model.fit(train_X, train_y, epochs=epochs, batch_size=64)
 
-# save trained model
+# it saves model, and additional informations of model 
+# that is needed to generate music from it 
 pickle.dump(model, open(save_model_path,'wb'))
-pickle.dump(int_to_note, open('{}_dict'.format(save_model_path),'wb'))
+pickle.dump((int_to_note, n_vocab, train_X.shape[1]), open('{}_dict'.format(save_model_path),'wb'))
 print('Done!')
 print("Model saved to: {}".format(save_model_path))