vandanavk commented on a change in pull request #12812: [MXNET-886] ONNX
export: HardSigmoid, Less, Greater, Equal, InstanceNorm
URL: https://github.com/apache/incubator-mxnet/pull/12812#discussion_r225747501
##########
File path: tests/python-pytest/onnx/export/backend_rep.py
##########
@@ -72,13 +72,22 @@ def run(self, inputs, **kwargs):
for idx, input_name in enumerate(data_names):
data_shapes.append((input_name, inputs[idx].shape))
- mod = mx.mod.Module(symbol=self.symbol, data_names=data_names,
context=ctx,
- label_names=None)
- mod.bind(for_training=False, data_shapes=data_shapes,
- label_shapes=None)
- mod.set_params(arg_params=self.arg_params, aux_params=self.aux_params)
+ # module bind method requires all data to have same batch size,
Review comment:
This is in the test for export. the changes in onnx_export.py are used with
create_onnx_graph_proto()
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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
