Tensorflow LSTM实现

# 定义LSTM模型
class LSTM_Model():
    def __init__(self, embedding_size, rnn_size, batch_size, learning_rate,
                 training_seq_len, vocab_size, infer_sample=False):
        self.embedding_size = embedding_size
        self.rnn_size = rnn_size #LSTM单元隐层的神经元个数
        self.vocab_size = vocab_size
        self.infer_sample = infer_sample
        self.learning_rate = learning_rate#学习率

        if infer_sample:#如果是inference，则batch size设为1
            self.batch_size = 1
            self.training_seq_len = 1
        else:
            self.batch_size = batch_size
            self.training_seq_len = training_seq_len

        ‘‘‘建立LSTM单元和初始化state‘‘‘
        self.lstm_cell = tf.contrib.rnn.BasicLSTMCell(self.rnn_size)
        self.initial_state = self.lstm_cell.zero_state(self.batch_size, tf.float32)

       ‘‘‘进行输入和输出的占位‘‘‘
        self.x_data = tf.placeholder(tf.int32, [self.batch_size, self.training_seq_len])
        self.y_output = tf.placeholder(tf.int32, [self.batch_size, self.training_seq_len])

        with tf.variable_scope(‘lstm_vars‘):
            # Softmax 部分的权重
            W = tf.get_variable(‘W‘, [self.rnn_size, self.vocab_size], tf.float32, tf.random_normal_initializer())
            b = tf.get_variable(‘b‘, [self.vocab_size], tf.float32, tf.constant_initializer(0.0))

            # Define Embedding
            embedding_mat = tf.get_variable(‘embedding_mat‘, [self.vocab_size, self.embedding_size],
                                            tf.float32, tf.random_normal_initializer())

            embedding_output = tf.nn.embedding_lookup(embedding_mat, self.x_data)
            rnn_inputs = tf.split(axis=1, num_or_size_splits=self.training_seq_len, value=embedding_output)
            rnn_inputs_trimmed = [tf.squeeze(x, [1]) for x in rnn_inputs]

        # If we are inferring (generating text), we add a ‘loop‘ function
        # Define how to get the i+1 th input from the i th output
        def inferred_loop(prev, count):
            # Apply hidden layer
            prev_transformed = tf.matmul(prev, W) + b
            # Get the index of the output (also don‘t run the gradient)
            prev_symbol = tf.stop_gradient(tf.argmax(prev_transformed, 1))
            # Get embedded vector
            output = tf.nn.embedding_lookup(embedding_mat, prev_symbol)
            return(output)

        decoder = tf.contrib.legacy_seq2seq.rnn_decoder
        outputs, last_state = decoder(rnn_inputs_trimmed,
                                      self.initial_state,
                                      self.lstm_cell,
                                      loop_function=inferred_loop if infer_sample else None)
        # Non inferred outputs
        output = tf.reshape(tf.concat(axis=1, values=outputs), [-1, self.rnn_size])
        # Logits and output
        self.logit_output = tf.matmul(output, W) + b
        self.model_output = tf.nn.softmax(self.logit_output)

        loss_fun = tf.contrib.legacy_seq2seq.sequence_loss_by_example
        loss = loss_fun([self.logit_output],[tf.reshape(self.y_output, [-1])],
                [tf.ones([self.batch_size * self.training_seq_len])],
                self.vocab_size)
        self.cost = tf.reduce_sum(loss) / (self.batch_size * self.training_seq_len)
        self.final_state = last_state
        gradients, _ = tf.clip_by_global_norm(tf.gradients(self.cost, tf.trainable_variables()), 4.5)
        optimizer = tf.train.AdamOptimizer(self.learning_rate)
        self.train_op = optimizer.apply_gradients(zip(gradients, tf.trainable_variables()))

    def sample(self, sess, words=ix2vocab, vocab=vocab2ix, num=10, prime_text=‘thou art‘):
        state = sess.run(self.lstm_cell.zero_state(1, tf.float32))
        word_list = prime_text.split()
        for word in word_list[:-1]:
            x = np.zeros((1, 1))
            x[0, 0] = vocab[word]
            feed_dict = {self.x_data: x, self.initial_state:state}
            [state] = sess.run([self.final_state], feed_dict=feed_dict)

        out_sentence = prime_text
        word = word_list[-1]
        for n in range(num):
            x = np.zeros((1, 1))
            x[0, 0] = vocab[word]
            feed_dict = {self.x_data: x, self.initial_state:state}
            [model_output, state] = sess.run([self.model_output, self.final_state], feed_dict=feed_dict)
            sample = np.argmax(model_output[0])
            if sample == 0:
                break
            word = words[sample]
            out_sentence = out_sentence + ‘ ‘ + word
        return(out_sentence)

# 定义训练阶段的lstm
lstm_model = LSTM_Model(embedding_size, rnn_size, batch_size, learning_rate,
                        training_seq_len, vocab_size)

# 定义测试阶段的lstm
with tf.variable_scope(tf.get_variable_scope(), reuse=True):
    test_lstm_model = LSTM_Model(embedding_size, rnn_size, batch_size, learning_rate,
                                 training_seq_len, vocab_size, infer_sample=True)

# Train model
train_loss = []
iteration_count = 1
for epoch in range(epochs):
    # Shuffle word indices
    random.shuffle(batches)
    # Create targets from shuffled batches
    targets = [np.roll(x, -1, axis=1) for x in batches]
    # Run a through one epoch
    print(‘Starting Epoch #{} of {}.‘.format(epoch+1, epochs))
    # Reset initial LSTM state every epoch
    state = sess.run(lstm_model.initial_state)
    for ix, batch in enumerate(batches):
        training_dict = {lstm_model.x_data: batch, lstm_model.y_output: targets[ix]}
        ‘‘‘每个batch的LSTM中初始化状态c和h，其状态被赋值为上一个batch的LSTM的最终状态的c和h ‘‘‘
        ‘‘‘也就是前后相接 ‘‘‘
        c, h = lstm_model.initial_state
        training_dict[c] = state.c
        training_dict[h] = state.h
        
        temp_loss, state, _ = sess.run([lstm_model.cost, lstm_model.final_state, lstm_model.train_op],
                                       feed_dict=training_dict)
        train_loss.append(temp_loss)
        
        # Print status every 10 gens
        if iteration_count % 10 == 0:
            summary_nums = (iteration_count, epoch+1, ix+1, num_batches+1, temp_loss)
            print(‘Iteration: {}, Epoch: {}, Batch: {} out of {}, Loss: {:.2f}‘.format(*summary_nums))
        
        if iteration_count % eval_every == 0:
            for sample in prime_texts:
                print(test_lstm_model.sample(sess, ix2vocab, vocab2ix, num=10, prime_text=sample))
                
        iteration_count += 1