VGG16 AND VGG19

docs link: https://keras.io/api/applications/vgg/

What is a Pre-trained Model?

A pre-trained model has been previously trained on a dataset and contains the weights and biases that represent the features of whichever dataset it was trained on. Learned features are often transferable to different data. For example, a model trained on a large dataset of bird images will contain learned features like edges or horizontal lines that you would be transferable your dataset.

VGG19 and VGG16 are also examples of pre-trained models on a large dataset of images, belonging to 1000 different classes, called ImageNet.

Why use a Pre-trained Model?

Pre-trained models are beneficial to us for many reasons. By using a pre-trained model you are saving time. Someone else has already spent the time and compute resources to learn a lot of features and your model will likely benefit from it.

ABOUT VGG19 AND VGG16

Very Deep Convolutional Networks for Large-Scale Image Recognition. VGG stands for Visual Geometry Group; it is a standard deep Convolutional Neural Network (CNN) architecture with multiple layers. The “deep” refers to the number of layers with VGG-16 or VGG-19 consisting of 16 and 19 convolutional layers.

VGG16 is a convolution neural net (CNN ) architecture that was used to win ILSVR(Imagenet) competition in 2014. It is considered to be one of the excellent vision model architectures till date.

In the end, it has 2 FC(fully connected layers) followed by a softmax for output.

The 16 in VGG16 refers to it has 16 layers that have weights. This network is a pretty large network and it has about 138 million (approx) parameters.

What is CNN?

A Convolutional Neural Network, is a class of neural networks that specializes in processing data that has a grid-like pattern, such as an image. A digital image is a binary representation of visual data. It contains a series of pixels arranged in a grid-like structure that contains pixel values to denote how bright and what color each pixel should be.

In CNN layers are arranged in such a way so that they detect simpler patterns first like lines, curves, etc. And more complex patterns like faces, objects, etc. further.