def runTest(self, relative_root, recursive):
"""Tests the output for the given parameters."""
root_dir = os.path.join(self.root_dir, relative_root)
expected_filenames = self.expected_dir_midi_contents[relative_root]
if recursive:
for sub_dir in self.expected_sub_dirs[relative_root]:
for filename in self.expected_dir_midi_contents[
os.path.join(relative_root, sub_dir)]:
expected_filenames.add(os.path.join(sub_dir, filename))
with tempfile.NamedTemporaryFile(
prefix='ConvertMidiDirToSequenesTest') as output_file:
with note_sequence_io.NoteSequenceRecordWriter(
output_file.name) as writer:
convert_midi_dir_to_note_sequences.convert_directory(
root_dir, '', writer, recursive)
actual_filenames = set()
for sequence in note_sequence_io.note_sequence_record_iterator(
output_file.name):
self.assertEquals(
note_sequence_io.generate_id(sequence.filename,
os.path.basename(relative_root),
'midi'),
sequence.id)
self.assertEquals(os.path.basename(root_dir), sequence.collection_name)
self.assertNotEquals(0, len(sequence.notes))
actual_filenames.add(sequence.filename)
self.assertEquals(expected_filenames, actual_filenames)
def run_conversion(melody_encoder_decoder,
note_sequences_file,
train_output,
eval_output=None,
eval_ratio=0.0):
"""Loop that converts NoteSequence protos to SequenceExample protos.
Args:
melody_encoder_decoder: A melodies_lib.MelodyEncoderDecoder object.
note_sequences_file: String path pointing to TFRecord file of NoteSequence
protos.
train_output: String path to TFRecord file that training samples will be
saved to.
eval_output: If set, string path to TFRecord file that evaluation samples
will be saved to. Omit this argument to not produce an eval set.
eval_ratio: Fraction of input that will be saved to eval set. A random
partition is chosen, so the actual train/eval ratio will vary.
"""
reader = note_sequence_io.note_sequence_record_iterator(
note_sequences_file)
train_writer = tf.python_io.TFRecordWriter(train_output)
eval_writer = (tf.python_io.TFRecordWriter(eval_output)
if eval_output else None)
input_count = 0
train_output_count = 0
eval_output_count = 0
tf.logging.info('Extracting melodies...')
for sequence_data in reader:
# Only extract melodies from 4/4 time music.
if (not sequence_data.time_signatures or
not (sequence_data.time_signatures[0].numerator == 4
and sequence_data.time_signatures[0].denominator == 4)):
continue
extracted_melodies = melodies_lib.extract_melodies(sequence_data)
for melody in extracted_melodies:
sequence_example = melody_encoder_decoder.encode(melody)
serialized = sequence_example.SerializeToString()
if eval_writer and random.random() < eval_ratio:
eval_writer.write(serialized)
eval_output_count += 1
else:
train_writer.write(serialized)
train_output_count += 1
input_count += 1
if input_count % 10 == 0:
tf.logging.info('Extracted %d melodies from %d sequences.',
eval_output_count + train_output_count,
input_count)
tf.logging.info('Done. Extracted %d melodies from %d sequences.',
eval_output_count + train_output_count, input_count)
tf.logging.info('Extracted %d melodies for training.', train_output_count)
if eval_writer:
tf.logging.info('Extracted %d melodies for evaluation.',
eval_output_count)
def main(unused_argv):
if not FLAGS.tfrecord_file:
tf.logging.fatal('--tfrecord_file required')
return
if not FLAGS.output_dir:
tf.logging.fatal('--output_dir required')
return
for note_sequence in note_sequence_io.note_sequence_record_iterator(FLAGS.tfrecord_file):
pm = midi_io.sequence_proto_to_pretty_midi(note_sequence)
pm.write(os.path.join(FLAGS.output_dir, note_sequence.filename))
def run_conversion(melody_encoder_decoder, note_sequences_file, train_output,
eval_output=None, eval_ratio=0.0):
"""Loop that converts NoteSequence protos to SequenceExample protos.
Args:
melody_encoder_decoder: A melodies_lib.MelodyEncoderDecoder object.
note_sequences_file: String path pointing to TFRecord file of NoteSequence
protos.
train_output: String path to TFRecord file that training samples will be
saved to.
eval_output: If set, string path to TFRecord file that evaluation samples
will be saved to. Omit this argument to not produce an eval set.
eval_ratio: Fraction of input that will be saved to eval set. A random
partition is chosen, so the actual train/eval ratio will vary.
"""
reader = note_sequence_io.note_sequence_record_iterator(note_sequences_file)
train_writer = tf.python_io.TFRecordWriter(train_output)
eval_writer = (tf.python_io.TFRecordWriter(eval_output)
if eval_output else None)
input_count = 0
train_output_count = 0
eval_output_count = 0
tf.logging.info('Extracting melodies...')
for sequence_data in reader:
# Only extract melodies from 4/4 time music.
if (not sequence_data.time_signatures or
not (sequence_data.time_signatures[0].numerator == 4 and
sequence_data.time_signatures[0].denominator == 4)):
continue
extracted_melodies = melodies_lib.extract_melodies(sequence_data)
for melody in extracted_melodies:
sequence_example = melody_encoder_decoder.encode(melody)
serialized = sequence_example.SerializeToString()
if eval_writer and random.random() < eval_ratio:
eval_writer.write(serialized)
eval_output_count += 1
else:
train_writer.write(serialized)
train_output_count += 1
input_count += 1
if input_count % 10 == 0:
tf.logging.info('Extracted %d melodies from %d sequences.',
eval_output_count + train_output_count,
input_count)
tf.logging.info('Done. Extracted %d melodies from %d sequences.',
eval_output_count + train_output_count,
input_count)
tf.logging.info('Extracted %d melodies for training.', train_output_count)
if eval_writer:
tf.logging.info('Extracted %d melodies for evaluation.', eval_output_count)
def run_conversion(encoder, sequences_file, train_output, eval_output="", eval_ratio=0.0):
"""Loop that converts NoteSequence protos to SequenceExample protos.
Args:
encoder: A function that converts Melody to SequenceExample which is fed
into a model. The function takes one input of type melodies_lib.Melody
and outputs a tuple (tf.train.SequenceExample, reconstruction_data)
where reconstruction_data is any extra data that is needed to
reconstruct a Melody from the given SequenceExample.
sequences_file: String path pointing to TFRecord file of NoteSequence
protos.
train_output: String path to TFRecord file that training samples will be
saved to.
eval_output: If set, string path to TFRecord file that evaluation samples
will be saved to. Omit this argument to not produce an eval set.
eval_ratio: Fraction of input that will be saved to eval set. A random
partition is chosen, so the actual train/eval ratio will vary.
"""
reader = note_sequence_io.note_sequence_record_iterator(sequences_file)
train_writer = tf.python_io.TFRecordWriter(train_output)
eval_writer = tf.python_io.TFRecordWriter(eval_output) if eval_output else None
input_count = 0
train_output_count = 0
eval_output_count = 0
for sequence_data in reader:
extracted_melodies = melodies_lib.extract_melodies(sequence_data)
for melody in extracted_melodies:
sequence_example, _ = encoder(melody)
serialized = sequence_example.SerializeToString()
if eval_writer and random.random() < eval_ratio:
eval_writer.write(serialized)
eval_output_count += 1
else:
train_writer.write(serialized)
train_output_count += 1
input_count += 1
tf.logging.log_every_n(
logging.INFO,
"Extracted %d melodies from %d sequences.",
500,
eval_output_count + train_output_count,
input_count,
)
logging.info("Found %d sequences", input_count)
logging.info("Extracted %d melodies for training.", train_output_count)
if eval_writer:
logging.info("Extracted %d melodies for evaluation.", eval_output_count)
def run_conversion(encoder, sequences_file, train_output, eval_output='', eval_ratio=0.0):
"""Loop that converts NoteSequence protos to SequenceExample protos.
Args:
encoder: A function that converts Melody to SequenceExample which is fed
into a model. The function takes one input of type melodies_lib.Melody
and outputs a tuple (tf.train.SequenceExample, reconstruction_data)
where reconstruction_data is any extra data that is needed to
reconstruct a Melody from the given SequenceExample.
sequences_file: String path pointing to TFRecord file of NoteSequence
protos.
train_output: String path to TFRecord file that training samples will be
saved to.
eval_output: If set, string path to TFRecord file that evaluation samples
will be saved to. Omit this argument to not produce an eval set.
eval_ratio: Fraction of input that will be saved to eval set. A random
partition is chosen, so the actual train/eval ratio will vary.
"""
reader = note_sequence_io.note_sequence_record_iterator(sequences_file)
train_writer = tf.python_io.TFRecordWriter(train_output)
eval_writer = (tf.python_io.TFRecordWriter(eval_output)
if eval_output else None)
input_count = 0
train_output_count = 0
eval_output_count = 0
for sequence_data in reader:
extracted_melodies = melodies_lib.extract_melodies(sequence_data)
for melody in extracted_melodies:
sequence_example, _ = encoder(melody)
serialized = sequence_example.SerializeToString()
if eval_writer and random.random() < eval_ratio:
eval_writer.write(serialized)
eval_output_count += 1
else:
train_writer.write(serialized)
train_output_count += 1
input_count += 1
tf.logging.log_every_n(logging.INFO,
'Extracted %d melodies from %d sequences.',
500,
eval_output_count + train_output_count,
input_count)
logging.info('Found %d sequences', input_count)
logging.info('Extracted %d melodies for training.', train_output_count)
if eval_writer:
logging.info('Extracted %d melodies for evaluation.', eval_output_count)
def testNoteSequenceRecordWriterAndIterator(self):
sequences = []
for i in xrange(4):
sequence = music_pb2.NoteSequence()
sequence.id = str(i)
sequence.notes.add().pitch = i
sequences.append(sequence)
with tempfile.NamedTemporaryFile(prefix='NoteSequenceIoTest') as temp_file:
with note_sequence_io.NoteSequenceRecordWriter(temp_file.name) as writer:
for sequence in sequences:
writer.write(sequence)
for i, sequence in enumerate(
note_sequence_io.note_sequence_record_iterator(temp_file.name)):
self.assertEquals(sequence, sequences[i])
def testNoteSequenceRecordWriterAndIterator(self):
sequences = []
for i in xrange(4):
sequence = music_pb2.NoteSequence()
sequence.id = str(i)
sequence.notes.add().pitch = i
sequences.append(sequence)
with tempfile.NamedTemporaryFile(prefix='NoteSequenceIoTest') as temp_file:
with note_sequence_io.NoteSequenceRecordWriter(temp_file.name) as writer:
for sequence in sequences:
writer.write(sequence)
for i, sequence in enumerate(
note_sequence_io.note_sequence_record_iterator(temp_file.name)):
self.assertEquals(sequence, sequences[i])