audio_reader.py 文件源码

def __init__(self,
                 audio_dir,
                 noise_dir,
                 coord,
                 N_IN,
                 frame_length,
                 frame_move,
                 is_val):
        '''coord: tensorflow coordinator
        N_IN: number of input frames presented to DNN
        frame_move: hopsize'''
        self.audio_dir = audio_dir
        self.noise_dir = noise_dir
        self.coord = coord
        self.N_IN = N_IN
        self.frame_length = frame_length
        self.frame_move = frame_move
        self.is_val = is_val
        self.sample_placeholder_many = tf.placeholder(
            tf.float32, shape=(None, self.N_IN, 2, frame_length))
        # queues to store the data
        if not is_val:
            self.q = tf.RandomShuffleQueue(
                200000, 5000, tf.float32, shapes=(self.N_IN, 2, frame_length))
        else:
            self.q = tf.FIFOQueue(
                200000, tf.float32, shapes=(self.N_IN, 2, frame_length))
        self.enqueue_many = self.q.enqueue_many(
            self.sample_placeholder_many + 0)
        self.audiofiles = find_files(audio_dir)
        self.noisefiles = find_files(noise_dir)
        print('%d speech found' % len(self.audiofiles))
        print('%d noise found' % len(self.noisefiles))
        # ipdb.set_trace()