run.py 文件源码

def read_and_decode(filename_queue):
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)

    features = tf.parse_single_example(serialized_example, features={
        'song_spec': tf.FixedLenFeature([], tf.string),
        'voice_spec': tf.FixedLenFeature([], tf.string),
        'mixed_spec': tf.FixedLenFeature([], tf.string)
        })

    song_spec = transform_spec_from_raw(features['song_spec'])
    voice_spec = transform_spec_from_raw(features['voice_spec'])
    mixed_spec = transform_spec_from_raw(features['mixed_spec'])

    input_spec = stack_spectrograms(mixed_spec)  # this will be the input

    target_spec = tf.concat([song_spec, voice_spec], axis=1) # target spec is going to be a concatenation of song_spec and voice_spec

    return input_spec, target_spec