datagenerator.py 文件源码

def __init__(self, data_dir, batch_size):
        '''preprocess the training data
        data_dir: dir containing the training data
                  format:root_dir + speaker_dir + wavfiles'''
        # get dirs for each speaker
        self.speakers_dir = [os.path.join(data_dir, i)
                             for i in os.listdir(data_dir)]
        self.n_speaker = len(self.speakers_dir)
        self.batch_size = batch_size
        self.speaker_file = {}
        self.epoch = 0

        # get the files in each speakers dir
        for i in range(self.n_speaker):
            wav_dir_i = [os.path.join(self.speakers_dir[i], file)
                         for file in os.listdir(self.speakers_dir[i])]
            for j in wav_dir_i:
                if i not in self.speaker_file:
                    self.speaker_file[i] = []
                self.speaker_file[i].append(j)
        # ipdb.set_trace()
        # self.reinit()