Operator {} not implemented.".format(op_name

  When I deployed the Tensorflow model using TVM, I encountered the following error according to the routine of the official website:
   1, Traceback (most recent call last):
                 File "pb_test.py", line 65, in <module>
                  Sym, params = nnvm.frontend.from_tensorflow(graph_def)
                 File "/home/yan/Files/tvm/nnvm/python/nnvm/frontend/tensorflow.py", line 774, in from_tensorflow
                  Sym, params = g.from_tensorflow(graph)
                 File "/home/yan/Files/tvm/nnvm/python/nnvm/frontend/tensorflow.py", line 627, in from_tensorflow
                  Op = self._convert_operator(node.op, inputs, attr)
                 File "/home/yan/Files/tvm/nnvm/python/nnvm/frontend/tensorflow.py", line 741, in _convert_operator
                   Raise NotImplementedError("Operator {} not implemented.".format(op_name))
                 NotImplementedError: Operator RandomUniform not implemented.,
          How is it solved?

This operator not supported now, but it’s not difficult to implement.

I would see 2 options here.
We could either support this operator directly in TVM
Or
Let frontend convert this to Placeholder and (Variable) and user feed the data as graph input.

Can you share use case of this operator (model details) ?

In my experimental environment, the version used by tensorflow is 1.4.0. Is there a problem with the version of tensorflow? I sent my pb file to your mailbox, can you tell me the specific solution? thank you very much

please use public url or pastbin for reproducibility so everyone can come and help

My pb file url is : https://github.com/yzhao065/tvm_tf_pb_file

Has this problem been solved? I have the same problem mow