NotImplementedError: Operator RandomUniform not implemented.

[mnboos]

The following problem occures when trying to compile an ONNX model in a linux environment. Are there any plans when this operator will be implemented?

Shape: Differently implemented in NNVM as a bypass (dummy operator)
Traceback (most recent call last):
  File "compile_model.py", line 54, in <module>
    sym, params = nnvm.frontend.from_onnx(onnx_model)
  File "/usr/tvm/nnvm/python/nnvm/frontend/onnx.py", line 967, in from_onnx
    sym, params = g.from_onnx(graph, opset)
  File "/usr/tvm/nnvm/python/nnvm/frontend/onnx.py", line 822, in from_onnx
    op = self._convert_operator(op_name, inputs, attr, opset)
  File "/usr/tvm/nnvm/python/nnvm/frontend/onnx.py", line 926, in _convert_operator
    "Operator {} not implemented.".format(op_name))
NotImplementedError: Operator RandomUniform not implemented.

[mnboos]

I assume no answer means you have other priorities at the moment?

[yidawang]

As of now, I am not aware of a concrete plan of supporting the randomization ops. You can refer to the release roadmap (latest #2623) for major features being (going to be) implemented. You are also highly encouraged to contribute. BTW, normally please go to https://discuss.tvm.ai for discussion. Thanks.

[tqchen]

Move to #6813