Deep Learning & Tensor Flow , Enterprise Use Case Example - Part 1

[vikas_ohri2]

While reading this blog on Machine learning ( Tensor Flow) model with SAP HANA and recollecitng some of my previous work  and some more recent learning experience on Tensor Flow computational library by Google ,I  started wondering on what could be business use case of  using these readily available technology solutions.

For example ,

1. Use image or take picture of a anything around you that is of interest and then  find if and what are similar things available in your favorite retail shop(s) and save the trouble of a shopping trip(s) and able to transact or place order products 


2. Based on the images uploaded by user on  any external or internal social media platform , suggest or recommed product or readings to the user

There could be many more examples.

Thought of creating a quick prototype working example of use case 1  and share the findings currently available, on what is (now) possible thanks to deep learning models on some common perceptual tasks involving image, voice , text or natural language analysis.

Shared example uses, Google Cloud Vision which offers both pre-trained models via an API and the ability to build custom models using AutoML Vision to provide flexibility depending on your use case. It quickly classifies images into thousands of categories (such as, “sailboat”), detects individual objects and faces within images, and reads printed words contained within images.

User flow  Picture(s)

Launch the App from Phone - either take new picture or use existing image



Take picture of say for example , Laptop or anything of interest and get the recommended options