ERROR when using conv3d

[vickichen97]

Traceback (most recent call last):
...
return tf.nn.conv3d(inputs, filter=[3, 3, 3, inchannel, outputchannel], strides=[1, 1, 1, 1, 1], padding='SAME', name=None)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 1361, in conv3d
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3414, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1756, in init
control_input_ops)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1592, in _create_c_op
raise ValueError(str(e))
ValueError: Shape must be rank 5 but is rank 1 for 'generator/Conv3D' (op: 'Conv3D') with input shapes: [4,4,256,256,3], [5].

The input tensor shape has 5 dimensions [4,4,256,256,3], Can you tell me where the problem is? Thanks a lot !
tensorflow——1.9.0