http://qiita.com/t_shinmura/items/066b696d82f9919480ae
上のページの
https://github.com/TakuyaShinmura/conv_lstm
にあるソースコードのtrain.pyをそのまま実行した結果、

WARNING:tensorflow:<conv_lstm_cell.ConvLSTMCell object at 0x7f3797af4be0>: Using a concatenated state is slower and will soon be deprecated.  Use state_is_tuple=True.
Traceback (most recent call last):
  File "/home/user/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 563, in merge_with
    self.assert_same_rank(other)
  File "/home/user/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 609, in assert_same_rank
    "Shapes %s and %s must have the same rank" % (self, other))
ValueError: Shapes (?, 64, 64, 3) and (?, ?) must have the same rank

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 639, in with_rank
    return self.merge_with(unknown_shape(ndims=rank))
  File "/home/user/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 570, in merge_with
    (self, other))
ValueError: Shapes (?, 64, 64, 3) and (?, ?) are not compatible

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "train.py", line 137, in <module>
    tf.app.run()
  File "/home/user/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 30, in run
    sys.exit(main(sys.argv))
  File "train.py", line 78, in main
    result = inference(images)
  File "train.py", line 43, in inference
    outputs, state = tf.nn.rnn(cell=cell, inputs=images, dtype=tf.float32)
  File "/home/user/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/rnn.py", line 113, in rnn
    (fixed_batch_size, input_size) = inputs[0].get_shape().with_rank(2)
  File "/home/user/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 641, in with_rank
    raise ValueError("Shape %s must have rank %d" % (self, rank))
ValueError: Shape (?, 64, 64, 3) must have rank 2

とエラーが出ましたが、原因がわかりません。
何故このようなエラーが出るのか教えてくださると助かります。