Retraining the model

To create an image classifier, we need to go through many things and do a lot of coding. To keep it simple, we will be showing you how to create it using the Google Code Lab provided code. The following content was taken from Google's Code Lab tutorial.

This was made using CNNs. Explaining all of this is outside the scope of this book. We briefly explored CNN in the introduction of this chapter. However that is very less, compared to what is an ocean. For more information, interested readers can check out https://colah.github.io/posts/2014-07-Conv-Nets-Modular/.

Let's see how easily we can create an image classifier in tensorflow. To get started, we need to install anaconda and then run the following commands:

conda create ...

Get Machine Learning for Mobile now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.