Fixed C++ inference tutorial

[NRauschmayr]

Description

Tutorial did not properly preprocess images and as such produce incorrect predictions. The example would set default values for mean but not for std_dev. So if the user does not provide the file that contains those values, the example would crash. The C++ example predicts now the same class as in the Python example. However, the probabilities differ (9.72 versus 10.411) and we should to look into that

[wkcn]

Thank you for the fix! LGTM: )

[Roshrini]

@NRauschmayr Thank you for fixing the example. Can you please fix failing CI?
@leleamol Can you take a look?

[NRauschmayr]

I think we have to update the unit-test: it is using an outdated and not maintained model https://github.com/apache/incubator-mxnet/blob/a9458caec285d3c28d16588fef6aef5e219c7472/cpp-package/example/inference/unit_test_inception_inference.sh
The test should rather use a model from the official model zoo. According to https://mxnet.incubator.apache.org/api/python/gluon/model_zoo.html pre-processing has to be done the following way

image = image/255
normalized = mx.image.color_normalize(image,
                                      mean=mx.nd.array([0.485, 0.456, 0.406]),
                                      std=mx.nd.array([0.229, 0.224, 0.225]))

[karan6181]

@NRauschmayr Could you please resolve the merge conflicts??

@nswamy @szha Could you please review it? Thanks!

[piyushghai]

@NRauschmayr Can you rebase with the latest master please ?

@leleamol Gentle ping for review.

[NRauschmayr]

Sorry for the late reply. I have not done the rebase yet, because I saw that the files I modified were deleted by the following commit #15164 I wanted to check first whether or not it makes sense to re-add those files, but I did not have the time yet to compile the latest c++ tutorial of the master branch.

[szha]

@mxnet-bot run ci [all]

[szha]

OK looks like this part is already refactored into the imagenet_inference.cpp example and it's handling the mean values correct. Still, thanks for proposing the patch.