Background
In neural networks, Convolutional Neural Networks (CNNs) are one major technique that is being used widely for image classifications, object detection, facial recognition, and so on. A typical CNN algorithm takes an image as an input in an array format and produces its classification as output, for example, a head shot picture of a person of 256 * 256 * 3 (height * width * dimension) an array of matrix of RGB values. Here the number 3 refers to RGB values.
In a typical transfer algorithm, more focus would be given on object recognition, and a CNN would be trained in object recognition. In the CNN processing hierarchy, when the processing level increases, the object information becomes more explicit on higher layers. The transformation ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access