timprepscius opened a new issue #20659:
URL: https://github.com/apache/incubator-mxnet/issues/20659
I know this is a bit vague- however:
I have:
built with torch
exported it into onnx
loaded that network into mxnet
run the network with a np.ones(input_shape)
with both torch and mxnet
the outputs are completely different.
does onnx_mxnet.import_model have any test suite?
My suspicion is that the exported torch weights are in a different column
format than the mxnet weights.
Does anyone have any experience with this?
Is onnx_mxnet.import_model supposed to work?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
