Transfer Learning in Tensorflow: Part 2 – Towards Data Science

This is the second part of the Transfer Learning in Tensorflow (VGG19 on CIFAR-10). The first part can be found here. The previous article has given descriptions about'Transfer Learning', 'Choice of Model', 'Choice of the Model Implementation', 'Know How to Create the Model', and'Know About the Last Layer'. In short, the Part 1 is a kind of preparational step before training and prediction. In this article (Part 2), I will go over how to load pre-trained parameters, how to re-scale input images, how to choose batch-size, and then we will look into the result.