Add `ResNeXt [50, 101]` to keras.applications about keras-cv HOT 11 CLOSED

Thanks for opening the issue. Can you provide a paragraph as a proposal for justifying adding this model? If you can provide some context of how widely this is used or some citation, that would be helpful.

from keras-cv.

Any update on this?

from keras-cv.

This model was introduced in 2016 and now it's 2022 and still, we don't have it in keras.application even though it's cited by 6697. Same as its too.

from keras-cv.

How can that be?

from keras-cv.

@innat have you tried using ResNext from here? I'm not able to get good accuracies: qubvel/classification_models#73 .

from keras-cv.

I did use SE-ResNeXt most often. It worked well, comparable with DenseNet121.

from keras-cv.

cc @taehoonlee
Mentioning Lee who has once made a PR on ResNeXt HERE, keras-team/keras#11203.

from keras-cv.

Thank you @innat !

from keras-cv.

There are so many different types of deep learning architecture these days, (as I know) so François Chollet wants to add only those with special structural changes among them.

from keras-cv.

@taehoonlee Is the decision still persist? The torchvision provides these models. Models like wide-resnet, shuffle-net, unfortunately are missing as well.

from keras-cv.

You can ask the maintainers. Now I am out of the keras team.

from keras-cv.