questions about python3.6 and tensorflow1.2 - tensorflow

Question

when i run a program, an error "Shape (10, ?) must have rank at least 3" appeared.
my code is below and maybe the error is "output,_=tf.nn.dynamic_rnn(cell,x_,dtype=tf.float32)"
however I cannot revise.
can you help me?
Traceback (most recent call last):
File "C:/Users/yyb/PycharmProjects/untitled1/myLSTM.py", line 49, in <module>
regressor.fit(train_X,train_y,batch_size=BATCH_SIZE,steps=TRAINING_STEPS)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\util\deprecation.py", line 289, in new_func
return func(*args, **kwargs)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 439, in fit
SKCompat(self).fit(x, y, batch_size, steps, max_steps, monitors)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 1350, in fit
monitors=all_monitors)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\util\deprecation.py", line 289, in new_func
return func(*args, **kwargs)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 455, in fit
loss = self._train_model(input_fn=input_fn, hooks=hooks)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 955, in _train_model
model_fn_ops = self._get_train_ops(features, labels)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 1162, in _get_train_ops
return self._call_model_fn(features, labels, model_fn_lib.ModeKeys.TRAIN)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py", line 1133, in _call_model_fn
model_fn_results = self._model_fn(features, labels, **kwargs)
File "C:/Users/yyb/PycharmProjects/untitled1/myLSTM.py", line 35, in lstm_model
output,_=tf.nn.dynamic_rnn(cell,x_,dtype=tf.float32)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 574, in dynamic_rnn
dtype=dtype)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 637, in _dynamic_rnn_loop
for input_ in flat_input)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 637, in <genexpr>
for input_ in flat_input)
File "C:\Users\yyb\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\tensor_shape.py", line 649, in with_rank_at_least
raise ValueError("Shape %s must have rank at least %d" % (self, rank))
ValueError: Shape (10, ?) must have rank at least 3
#coding=utf-8
import numpy as np
import tensorflow as tf
import matplotlib as mpl
mpl.use('Agg')
from matplotlib import pyplot as plt
learn=tf.contrib.learn
HIDDEN_SIZE=30
NUM_LAYERS=2
TIMESTEPS=10
TRAINING_STEPS=10000
BATCH_SIZE=32
TRAINING_EXAMPLES=10000
TESTING_EXAMPLES=1000
SAMPLE_GAP=0.01
def generate_data(seq):
X=[]
y=[]
for i in range(len(seq)-TIMESTEPS-1):
X.append([seq[i:i+TIMESTEPS]])
y.append([seq[i+TIMESTEPS]])
return np.array(X,dtype=np.float32),np.array(y,dtype=np.float32)
def lstm_model(X,y):
lstm_cell=tf.nn.rnn_cell.BasicLSTMCell(HIDDEN_SIZE)
cell=tf.nn.rnn_cell.MultiRNNCell([lstm_cell]*NUM_LAYERS)
x_=tf.unstack(X,axis=1)
output,_=tf.nn.dynamic_rnn(cell,x_,dtype=tf.float32)
output=output[-1]
prediction,loss=learn.models.linear_regression(output,y)
train_op=tf.contrib.layers.optimize_loss(loss,tf.contrib.framework.get_global_step(),optimizer="Adagrad",learning_rate=0.1)
return prediction,loss,train_op
regressor=learn.Estimator(model_fn=lstm_model)
test_start=TRAINING_EXAMPLES*SAMPLE_GAP
test_end=(TRAINING_EXAMPLES+TESTING_EXAMPLES)*SAMPLE_GAP
train_X,train_y=generate_data(np.sin(np.linspace(0,test_start,TRAINING_EXAMPLES,dtype=np.float32)))
test_X,test_y=generate_data(np.sin(np.linspace(test_start,test_end,TESTING_EXAMPLES,dtype=np.float32)))
regressor.fit(train_X,train_y,batch_size=BATCH_SIZE,steps=TRAINING_STEPS)
predicted=[[pred] for pred in regressor.predict(test_X)]
rmse=np.sqrt(((predicted-test_y)**2).mean(axis=0))
print('Mean square error is: %f'%rmse[0])
fig=plt.figure()
plot_predicted=plt.plot(predicted,label='predicted')
plot_test=plt.plot(test_y,label='real_sin')
plt.legend([plot_predicted,plot_test],['predicted','real_sin'])
fig.savefig('sin.png')