AlexNet for cifar from " Understanding deep learning requires rethinking generalization"

I wanted to train an AlexNet model on cifar with the architecture from:

“Understanding deep learning requires rethinking generalization”

Is the following the recommended way to do it:

or is there a standard way to do this in pytorch for cifar?

(note I don’t need pre-trained models)

That looks like a reasonable way to initialize it, though your model is not exactly the same as AlexNet both in the layer definitions and the fully connected layers.

There is also torchvision which has a pre-setup version of the model -

is the alexnet on that paper the alex net on Cifar 10 or Imagenet? (I want one for Cifar 10, I know the original one was on imagenet)