tensorflow 學習筆記13 RNN LSTM結構預測正弦(sin)函式
阿新 • • 發佈:2019-02-05
import tensorflow as tf import numpy as np import matplotlib.pyplot as plt BATCH_START = 0 TIME_STEPS = 20 BATCH_SIZE = 50 INPUT_SIZE = 1 OUTPUT_SIZE = 1 #hidden_unit_size CELL_SIZE = 10 #learning_rate LR = 0.006 #資料輸入函式 #按照序列的順序,每次get_batch()就切出BATCH_SIZE*TIME_STEPS*INPUT_SIZE作為下一次訓練的輸入資料 def get_batch(): global BATCH_START, TIME_STEPS # xs shape (50batch, 20steps) xs = np.arange(BATCH_START, BATCH_START+TIME_STEPS*BATCH_SIZE).reshape((BATCH_SIZE, TIME_STEPS)) / (10*np.pi) seq = np.sin(xs) res = np.cos(xs) BATCH_START += TIME_STEPS # returned seq, res and xs: shape (batch, step, input) return [seq[:, :, np.newaxis], res[:, :, np.newaxis], xs]#np.newaxis 在使用和功能上等價於 None,其實就是 None 的一個別名 class LSTMRNN(object): def __init__(self, n_steps, input_size, output_size, cell_size, batch_size): self.n_steps = n_steps self.input_size = input_size self.output_size = output_size self.cell_size = cell_size self.batch_size = batch_size with tf.name_scope('inputs'): self.xs = tf.placeholder(tf.float32, [None, n_steps, input_size], name='xs') self.ys = tf.placeholder(tf.float32, [None, n_steps, output_size], name='ys') with tf.variable_scope('in_hidden'): self.add_input_layer() with tf.variable_scope('LSTM_cell'): self.add_cell() with tf.variable_scope('out_hidden'): self.add_output_layer() with tf.name_scope('cost'): self.compute_cost() with tf.name_scope('train'): self.train_op = tf.train.AdamOptimizer(LR).minimize(self.cost) def add_input_layer(self,): # reshape 3維變2維 用於矩陣計算 l_in_x (batch, n_steps, input_size)==> (batch*n_step, in_size) l_in_x = tf.reshape(self.xs, [-1, self.input_size], name='2_2D') # Ws (in_size, cell_size) Ws_in = self._weight_variable([self.input_size, self.cell_size]) # bs (cell_size, ) bs_in = self._bias_variable([self.cell_size,]) # l_in_y = (batch * n_steps, cell_size) with tf.name_scope('Wx_plus_b'): l_in_y = tf.matmul(l_in_x, Ws_in) + bs_in #reshape 2維變3維 l_in_y (batch*n_step, in_size)==> (batch, n_steps, cell_size) self.l_in_y = tf.reshape(l_in_y, [-1, self.n_steps, self.cell_size], name='2_3D') def add_cell(self): lstm_cell = tf.contrib.rnn.BasicLSTMCell(self.cell_size, forget_bias=1.0, state_is_tuple=True) with tf.name_scope('initial_state'): self.cell_init_state = lstm_cell.zero_state(self.batch_size, dtype=tf.float32) self.cell_outputs, self.cell_final_state = tf.nn.dynamic_rnn( lstm_cell, self.l_in_y, initial_state=self.cell_init_state, time_major=False) def add_output_layer(self): # reshape 3維變2維 用於矩陣計算 l_out_x (batch, n_steps, cell_size)==> (batch * steps, cell_size) l_out_x = tf.reshape(self.cell_outputs, [-1, self.cell_size], name='2_2D') Ws_out = self._weight_variable([self.cell_size, self.output_size]) bs_out = self._bias_variable([self.output_size, ]) # shape = (batch * steps, output_size) with tf.name_scope('Wx_plus_b'): self.pred = tf.matmul(l_out_x, Ws_out) + bs_out def compute_cost(self): #(logits, targets, weights):針對logits中的每一個num_step,即[batch_size, classes], # 對所有classes個預測結果,得出預測值最大的那個類別,與targets中的值相比較計算Loss值 losses = tf.contrib.legacy_seq2seq.sequence_loss_by_example( [tf.reshape(self.pred, [-1], name='reshape_pred')], [tf.reshape(self.ys, [-1], name='reshape_target')], [tf.ones([self.batch_size * self.n_steps], dtype=tf.float32)], average_across_timesteps=True, softmax_loss_function=self.ms_error, name='losses' ) with tf.name_scope('average_cost'): #對於每一個batch_size計算平均cost self.cost = tf.div(tf.reduce_sum(losses, name='losses_sum'),self.batch_size,name='average_cost') tf.summary.scalar('cost', self.cost) def ms_error(self, labels, logits): return tf.square(tf.subtract(labels, logits)) def _weight_variable(self, shape, name='weights'): initializer = tf.random_normal_initializer(mean=0., stddev=1.,) return tf.get_variable(shape=shape, initializer=initializer, name=name) def _bias_variable(self, shape, name='biases'): initializer = tf.constant_initializer(0.1) return tf.get_variable(name=name, shape=shape, initializer=initializer) if __name__ == '__main__': model = LSTMRNN(TIME_STEPS, INPUT_SIZE, OUTPUT_SIZE, CELL_SIZE, BATCH_SIZE) sess = tf.Session() merged = tf.summary.merge_all() writer = tf.summary.FileWriter("桌面/logs/", sess.graph) init = tf.global_variables_initializer() sess.run(init) plt.ion() plt.show() for i in range(200): seq, res, xs = get_batch() if i == 0: #該LSTM模型所學習到的是sin(x)到cos(x)的對映關係,最後給定一個輸入sin(x0),LSTM能夠預測出相對應的cos(x0) feed_dict = { model.xs: seq, model.ys: res, # create initial state } else: feed_dict = { model.xs: seq, model.ys: res, model.cell_init_state: state # use last state as the initial state for this run } _, cost, state, pred = sess.run([model.train_op, model.cost, model.cell_final_state, model.pred],feed_dict=feed_dict) # plotting plt.plot(xs[0, :], res[0].flatten(), 'r', xs[0, :], pred.flatten()[:TIME_STEPS], 'b--') plt.ylim((-1.2, 1.2)) plt.draw() plt.pause(0.3) if i % 20 == 0: print('cost: ', round(cost, 4)) result = sess.run(merged, feed_dict) writer.add_summary(result, i)
結果: