TensorFlow Tutorial - Inception Model
Notes by Magnus Erik Hvass Pedersen: https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/07_Incept...
This tutorial shows how to use a pre-trained Deep Neural Network called Inception v3 for image classification.
The Inception v3 model takes weeks to train on a monster computer with 8 Tesla K40 GPUs and probably costing $30,000 so it is impossible to train it on an ordinary PC. We will instead download the pre-trained Inception model and use it to classify images.
The Inception v3 model has nearly 25 million parameters and uses 5 billion multiply-add operations for classifying a single image. On a modern PC without a GPU this can be done in a fraction of a second per image.
This tutorial hides the TensorFlow code so it may not require much experience with TensorFlow, although a basic understanding of TensorFlow from the previous tutorials might be helpful, especially if you want to study the implementation details in the inception.py file.