Training our own TensorFlow model 

Building our own custom model requires following a step-by-step procedure. To begin, we are going to use the TensorFlow Hub to feed images using pre-trained models.

Note

TensorFlow Hub is a library for the publication, discovery, and consumption of reusable parts of machine learning models. A module is a self-contained piece of a TensorFlow graph, along with its weights and assets, that can be reused across different tasks in a process known as transfer learning. 

Installing TensorFlow

While writing this book, TensorFlow 1.7.0 was available. The TensorFlow Hub has a dependency on the TensorFlow library and can be installed with pip as follows:

$ pip install "tensorflow>=1.7.0"
$ pip install tensorflow-hub

When the TensorFlow library is installed, we need to start collecting our image dataset before the training process starts. We need to look into a lot of things before beginning our training. 

Training the images

In this step, we will collect the images and...