Use real image input in demo colab notebook

[GregoryComer]

📚 The doc issue

We have a Colab notebook which we link to in the Getting Started documentation, which illustrates exporting, lowering, and running (with Pybindings) MobileNet V2. It would be nice to have it load a real image and print the top predicted classes, as opposed to current behavior of using random inputs and printing PASS. It would make a nice demo and illustrate it working end to end. It also forces us to include some of the practical bits for input transformations, matching the "real" user experience. We can also align with the content in the getting started section to ideally make them match up.

Suggest a potential alternative/fix

No response

cc @mergennachin @iseeyuan @lucylq @helunwencser @tarun292 @kimishpatel @jackzhxng @byjlw

[byjlw]

I think it would be best to have the notebook fully atomic (no need to navigate to other URLs for required instructions)