5
$\begingroup$

the model was trained by

net = NetModel["Inception V1 Trained on ImageNet Competition Data"]

Export["model.json",model,"MXNet"]
model.json
 Import["model.json",{"MXNet","Net"}]
During evaluation of Import::invmxlayer: Layer named "1.pool1_3x3_s2_pad$0" couldn't be created, layer type "Pad" is not supported.
$Failed

So sad

So we cann't import many models into Mathematica.

Improve this question
$\endgroup$
4
  • $\begingroup$ Since the documentation here declare it is a invertible convert.then I don't think something wrong. $\endgroup$
    – yode
    Commented Sep 16, 2017 at 8:11
  • $\begingroup$ @yoda bad news. I think Mathematica implements some stat-of-art models, should support this manipulation as new features.. $\endgroup$
    – HyperGroups
    Commented Sep 16, 2017 at 8:15
  • $\begingroup$ You didn't spell @yode 's name correctly. Maybe you can try again? $\endgroup$
    – QuantumDot
    Commented Sep 16, 2017 at 19:36
  • $\begingroup$ @QuantumDot Copy yours. :) $\endgroup$
    – yode
    Commented Sep 16, 2017 at 19:51

1 Answer 1

Reset to default
4
$\begingroup$

There are two function GeneralUtilities`MLExport and GeneralUtilities`MLImport to do export and import thing.But it cannot produce that .params file.Maybe it can help.

net = NetModel["Inception V1 Trained on ImageNet Competition Data"];
GeneralUtilities`MLExport["test.json", net]

"test.json"

Then you can import it.

netin = GeneralUtilities`MLImport["test.json"]

Improve this answer
$\endgroup$
1
  • $\begingroup$ Nice find. I can't wait for ONNX support. $\endgroup$
    – M.R.
    Commented May 18, 2018 at 17:50

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.