What is the VGG 19 neural network?

VGG 19 is a convolutional neural network architecture that is 19 layers deep. The main purpose for which the VGG net was designed was to win the ILSVRC imagenet competition.

Let’s take a brief look at the architecture of VGG19.

  • Input: The VGG-19 takes in an image input size of 224×224.
  • Convolutional Layers: VGG’s convolutional layers leverage a minimal receptive field, i.e., 3×3, the smallest possible size that still captures up/down and left/right. This is followed by a ReLU activation function. ReLU stands for rectified linear unit activation function, it is a piecewise linear function that will output the input if positive otherwise, the output is zero. Stride is fixed at 1 pixel to keep the spatial resolution preserved after convolution
  • Fully-Connected Layers: The VGG19 has 3 fully connected layers. Out of the 3 layers, the first 2 have 4096 nodes each, and the third has 1000 nodes, which is the total number of classes the imagenet dataset has.
Important Notice for college students

If you’re a college student and have skills in programming languages, Want to earn through blogging? Mail us at geekycomail@gmail.com

For more Programming related blogs Visit Us Geekycodes . Follow us on Instagram.

Leave a Reply

%d bloggers like this: