What are the best image classification models that have a implementation using pytorch or keras? (and generally easy to use?)

What are the best image classification models that have a implementation using pytorch or keras? (and generally easy to use?)

Are all images classifiers have a static input size? What is the best approach if the images if bigger/smaller or have different aspect ratio?

I am just curious what are the best models right now? (I mean available that already have an implementation).

​

I asked this before but in a different manner:

Is it a good idea to use …

classification computervision easy image implementation keras pytorch