Transfer learning using feature extraction with the VGG16 model

As we stated in the Visualizing the MNIST dataset using PCA and t-SNE recipe of Chapter 14, Unsupervised Representation Learning, in the case of datasets of important dimensions, the data was transformed into a reduced series of representation functions. This process of transforming the input data into a set of functionalities is named feature extraction. This is because the extraction of the characteristics proceeds from an initial series of measured data and produces derived values that can keep the information contained in the original dataset, but excluded from the redundant data. In the case of images, feature extraction is aimed at obtaining information that can be identified by a computer.

Getting ready

...