How to use Conv2d layers as fully connected layers.

In Deep learning, a convolutional neural network (CNN) is a class of deep NN, that are typically used to recognize patterns present in images but they are also used for spatial data analysis, computer vision, natural language processing, signal processing, and various other purposes. The focus of this article is to demonstrate how do we use Convolutional layers as Fully connected layers or How to convert fully connected layers to Conv layers. I have tried to find relevant material on the internet, but only could find one research paper on this subject, so we will use that to build up on the theoretical part, then we will dive deep into the coding part. What is a Conv layer in Deep networks?. It's nothing but a convolution operation that is done on an image/input. Such an operation requires a kernel (matrix) with values to move on the image (which itself is converted into a matrix) with a set value of stride or steps performing an elementwise multiplication.