ywwhxxtw opened a new issue #15101: Operator ConstantFill not implemented URL: https://github.com/apache/incubator-mxnet/issues/15101 ## Description I trained a Tacotron model in pytorch and exported to onnx. And now I would like to import the model to mxnet, but I met **NotImplementedError: Operator ConstantFill not implemented.** this error. ## Environment info (Required) Ubuntu 16.04, python 3.7.3, mxnet 1.4.1 with onnx 1.5.0, all in anaconda env Build config: mxnet installed using pip and onnx installed using conda ## Error Message: ``` Traceback (most recent call last): File "<stdin>", line 1, in <module> File "/home/myname/.conda/envs/mxnet/lib/python3.7/site-packages/mxnet/contrib/onnx/onnx2mx/import_model.py", line 59, in import_model sym, arg_params, aux_params = `graph.from_onnx(model_proto.graph)` File "/home/myname/.conda/envs/mxnet/lib/python3.7/site-packages/mxnet/contrib/onnx/onnx2mx/import_onnx.py", line 115, in from_onnx mxnet_sym = self._convert_operator(node_name, op_name, onnx_attr, inputs) File "/home/myname/.conda/envs/mxnet/lib/python3.7/site-packages/mxnet/contrib/onnx/onnx2mx/import_onnx.py", line 63, in _convert_operator raise NotImplementedError("Operator {} not implemented.".format(op_name)) NotImplementedError: Operator ConstantFill not implemented. ``` ## Minimum reproducible example I think the problem is most likely because of this padding %276 : Float(128!, 74!) = onnx::Pad[mode="constant", pads=[0, 0, 0, 0], value=0](%275), scope: Tacotron/Encoder[encoder]/EncoderCBHG[cbhg]/CBHG[cbhg]/BatchNormConv1d/ConstantPad1d[padder] ## What have you tried to solve it? 1. At first I got the same issue in this [link](https://github.com/apache/incubator-mxnet/issues/13949) with mxnet 1.2.1, then I update my mxnet version and here comes the present `issue`
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
