CNN读取文件函数

class DataLoader():
	def __init__(self):
		path = tf.keras.utils.get_file('nietzsche.txt',	origin='https://s3.amazonaws.com/text-datasets/nietzsche.txt')
		with open(path, encoding='utf-8') as f:
			self.raw_text = f.read().lower()
		self.chars = sorted(list(set(self.raw_text)))
		self.char_indices = dict((c, i) for i, c in enumerate(self.chars))
		self.indices_char = dict((i, c) for i, c in enumerate(self.chars))
		self.text = [self.char_indices[c] for c in self.raw_text]
	def get_batch(self, seq_length, batch_size):
		seq = []
		next_char = []
		for i in range(batch_size):
			index = np.random.randint(0, len(self.text) - seq_length)
			seq.append(self.text[index:index+seq_length])
			next_char.append(self.text[index+seq_length])
		return np.array(seq), np.array(next_char) # [num_batch, seq_length[num_batch]