How to create multiple Conv3DLSTMCell in tensorflow - python-2.7

Question

I'm trying to create my model with several conv3d lstm cell layers:
I run the following code:
conv1, state1 = conv3d('conv1', _X, [8,112,112,1], [3,3,3], 64)
pool1 = max_pool('pool1', conv1, k=1)
conv2, state2 = conv3d('conv2', pool1, [8, 56, 56, 64], [3, 3, 3], 128)
pool2 = max_pool('pool2', conv2, k=2)
The conv3d functions:
def conv3d(myname, l_input, shape, kernel, outchan):
cell = contrib_rnn_cell.Conv3DLSTMCell(input_shape=shape, output_channels=out$
hidden = cell.zero_state(array_ops.shape(l_input)[0], dtypes.float32)
output, state = cell(l_input, hidden)
print(output.shape)
return output, state
My code runs OK for the conv1 and pool1 but for conv2 layer it shows me an error:
Traceback (most recent call last):
File "conv3dlstm.py", line 272, in <module>
run(16)
File "conv3dlstm.py", line 199, in run
biases)
File "/home/user/projects/model_conv3dlstm.py", line 47, in inference_c3d
conv2, state2 = conv3d('conv2', pool1, [8, 56, 56, 64], [3, 3, 3], 128)
File "/home/user/projects/model_conv3dlstm.py", line 32, in conv3d
output, state = cell(l_input, hidden)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 190, in __call__
return super(RNNCell, self).__call__(inputs, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/layers/base.py", line 696, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/rnn/python/ops/rnn_cell.py", line 2110, in call
4 * self._output_channels, self._use_bias)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/rnn/python/ops/rnn_cell.py", line 2200, in _conv
"kernel", filter_size + [total_arg_size_depth, num_features], dtype=dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 1297, in get_variable
constraint=constraint)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 1093, in get_variable
constraint=constraint)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 431, in get_variable
return custom_getter(**custom_getter_kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 193, in _rnn_get_variable
variable = getter(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 408, in _true_getter
use_resource=use_resource, constraint=constraint)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 747, in _get_single_variable
name, "".join(traceback.format_list(tb))))
ValueError: Variable conv_lstm_cell/kernel already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/rnn/python/ops/rnn_cell.py", line 2200, in _conv
"kernel", filter_size + [total_arg_size_depth, num_features], dtype=dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/rnn/python/ops/rnn_cell.py", line 2110, in call
4 * self._output_channels, self._use_bias)
File "/home/user/projects/model_conv3dlstm.py", line 32, in conv3d
output, state = cell(l_input, hidden)
I saw the code in run_cell.py at line 2200 which is:
kernel = vs.get_variable(
"kernel", filter_size + [total_arg_size_depth, num_features], dtype=dtype)
Which is getting variable with fixed name "kernel". If I understand it correctly, it is supposed to be unique. But it means I can't create more of Conv3DLSTMCells than one? Is it a bug or am I using it incorrectly?