LSTM tensorflow shape error? - tensorflow

Question

I have a Class for RNN that can classify the sentences into positive or negative for sentiment analysis. Because the length of sentences are different, so I used placeholder named text_len to be a vector of sentence lengths in one batch when feeding the training batch data:
class TextRNN:
def __init__(self, hidden_size, num_classes, text_length, vocab_size,
embed_size, l2_lambda=0.001):
self.input_data = tf.placeholder(tf.int32,[None,text_length],name="input_data")
self.output_label = tf.placeholder(tf.float32,[None,num_classes],name="output_label")
self.dropout_rate = tf.placeholder(tf.float32,name="dropout_rate")
self.text_len = tf.placeholder(tf.int32, [None])
with tf.name_scope("embedding"):
self.W = tf.Variable(tf.random_uniform([vocab_size,embed_size],-1.0,1.0),trainable=True,name="W")
self.word_embeddings = tf.nn.embedding_lookup(self.W, self.input_data)
with tf.name_scope("hidden"):
lstm_fw_cell=rnn.BasicLSTMCell(hidden_size)
lstm_bw_cell=rnn.BasicLSTMCell(hidden_size)
lstm_fw_cell=rnn.DropoutWrapper(lstm_fw_cell,output_keep_prob=self.dropout_rate)
lstm_bw_cell=rnn.DropoutWrapper(lstm_bw_cell,output_keep_prob=self.dropout_rate)
outputs,_=tf.nn.bidirectional_dynamic_rnn(lstm_fw_cell,lstm_bw_cell,inputs=self.word_embeddings,sequence_length=self.text_len,dtype=tf.float32)
In my main method:
for ex in range(1,3):
with tf.Graph().as_default():
sess = tf.Session()
with sess.as_default():
rnn = TextRNN(
hidden_size=100,
num_classes=2,
text_length=160,
vocab_size=len(vocab_processor.vocabulary_),
embed_size=100,
l2_lambda=0.001)
global_step = tf.Variable(0, name="global_step", trainable=False)
optimizer = tf.train.AdamOptimizer(1e-3)
grads_and_vars = optimizer.compute_gradients(rnn.loss)
train_op = optimizer.apply_gradients(grads_and_vars,global_step=global_step)
sess.run(tf.global_variables_initializer())
vocabulary = vocab_processor.vocabulary_
initW = None
initW = loadw2v.convert_glove(vocabulary, pretrained_embeddings, 100)
sess.run(rnn.W.assign(initW))
#training step
def train_step(x_batch, y_batch, start_index, end_index):
feed_dict = {rnn.input_data:x_batch,rnn.output_label:y_batch,rnn.dropout_rate:0.5,rnn.text_len:x_train_len[start_index:end_index]}
_, step, loss, test = sess.run([train_op, global_step, rnn.loss, rnn.text_len], feed_dict)
because I want to feed a vector of sequence length into RNN model, so there is a rnn.text_len:x_train_len[start_index:end_index] when using tf.nn.bidirectional_dynamic_rnn, x_train_len[start_index:end_index] is a vector that saves the length of sequence, start_index is the index of batch start, end_index is the index of batch end. The error is:
Traceback (most recent call last):
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call
return fn(*args)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1306, in _run_fn
status, run_metadata)
File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/contextlib.py", line 88, in __exit__
next(self.gen)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: seq_lens(45) > input.dims(1)
[[Node: hidden/bidirectional_rnn/bw/ReverseSequence = ReverseSequence[T=DT_FLOAT, Tlen=DT_INT32, batch_dim=0, seq_dim=1, _device="/job:localhost/replica:0/task:0/cpu:0"](embedding/embedding_lookup, _arg_Placeholder_0_0)]]
I don't understand this error, any idea?