In this section, we shall look at the finer details of the cost function with a triplet loss. We will train network weights using the triplet cost function or the triplet loss. The idea was introduced in the paper by Schroff in 2015, FaceNet: A unified embedding for face recognition and clustering. We shall also explore the areas to choose the triplet so that our network will learn to achieve really high accuracy.
We begin by choosing the base or anchor image, which will be used as a sample for other comparts. The base image is as follows:
We shall now select a different image that represents the same person; this is known as the positive image, shown as follows:
AS we have seen in the previous section, we want the similarity function d as close to zero as possible. It is mathematically expressed as:
Having this value close to zero means that the...
