analyzer.py 文件源码

def read(
    file_pattern,
    batch_size,
    record_bytes=RECORD_BYTES,
    capacity=256,
    min_after_dequeue=128,
    num_threads=8,
    format='NCHW',
    normalizer=None,
    ):
    ''' 
    Read only `sp` and `speaker` 
    Return:
        `feature`: [b, c]
        `speaker`: [b,]
    '''
    with tf.name_scope('InputSpectralFrame'):
        files = tf.gfile.Glob(file_pattern)
        filename_queue = tf.train.string_input_producer(files)


        reader = tf.FixedLengthRecordReader(record_bytes)
        _, value = reader.read(filename_queue)
        value = tf.decode_raw(value, tf.float32)

        value = tf.reshape(value, [FEAT_DIM,])
        feature = value[:SP_DIM]   # NCHW format

        if normalizer is not None:
            feature = normalizer.forward_process(feature)

        if format == 'NCHW':
            feature = tf.reshape(feature, [1, SP_DIM, 1])
        elif format == 'NHWC':
            feature = tf.reshape(feature, [SP_DIM, 1, 1])
        else:
            pass
        speaker = tf.cast(value[-1], tf.int64)
        return tf.train.shuffle_batch(
            [feature, speaker],
            batch_size,
            capacity=capacity,
            min_after_dequeue=min_after_dequeue,
            num_threads=num_threads,
            # enqueue_many=True,
        )