def _parse_nsynth(example):
"""Parsing function for NSynth dataset."""
wave, label = example['audio'], example['pitch']
wave = spectral_ops.crop_or_pad(wave[tf.newaxis, :, tf.newaxis],
length, channels)[0]
one_hot_label = tf.one_hot(label_index_table.lookup(label),
depth=len(pitches))
return wave, one_hot_label
def _parse_nsynth(record):
"""Parsing function for NSynth dataset."""
features = {
'pitch': tf.FixedLenFeature([1], dtype=tf.int64),
'audio': tf.FixedLenFeature([length], dtype=tf.float32),
'qualities': tf.FixedLenFeature([10], dtype=tf.int64),
'instrument_source': tf.FixedLenFeature([1], dtype=tf.int64),
'instrument_family': tf.FixedLenFeature([1], dtype=tf.int64),
}
example = tf.parse_single_example(record, features)
wave, label = example['audio'], example['pitch']
wave = spectral_ops.crop_or_pad(wave[tf.newaxis, :, tf.newaxis],
length, channels)[0]
one_hot_label = tf.one_hot(label_index_table.lookup(label),
depth=len(pitches))[0]
return wave, one_hot_label, label, example['instrument_source']
def _parse_nsynth(record):
"""Parsing function for NSynth dataset."""
features = {
'pitch': tf.FixedLenFeature([1], dtype=tf.int64),
'audio': tf.FixedLenFeature([length], dtype=tf.float32),
'qualities': tf.FixedLenFeature([10], dtype=tf.int64),
'instrument_source': tf.FixedLenFeature([1], dtype=tf.int64),
'instrument_family': tf.FixedLenFeature([1], dtype=tf.int64),
}
example = tf.parse_single_example(record, features)
wave, label = example['audio'], example['pitch']
wave = spectral_ops.crop_or_pad(wave[tf.newaxis, :, tf.newaxis],
length,
channels)[0]
one_hot_label = tf.one_hot(
label_index_table.lookup(label), depth=len(pitches))[0]
return wave, one_hot_label, label, example['instrument_source']
def _parse_reverbsynth(record_batch):
n_samples = 64000
# Create a description of the features
feature_description = {
'audio': tf.io.FixedLenFeature([n_samples], tf.float32),
'pitch': tf.io.FixedLenFeature(1, tf.int64),
}
# Parse the input `tf.Example` proto using the dictionary above
example = tf.io.parse_example(record_batch, feature_description)
wave, label = example['audio'], example['pitch'][0]
wave = spectral_ops.crop_or_pad(wave[tf.newaxis, :, tf.newaxis],
length,
channels)[0]
one_hot_label = tf.one_hot(
label_index_table.lookup(label), depth=len(pitches))
return wave, one_hot_label