Deep learning is a booming field at the current time, most of the projects and problem statement uses deep learning in any sort of work. If you have to pick a deep learning technique for solving any computer vision problem statement then many of you including myself will go with a conventional neural network. In this article, we will build our first image processing project using CNN and understand its power and why it has become so popular. In this article, we will walk through every step of developing our own convolutional model and build our first amazing project. Image classification is a task where the system takes an input image and classifies it with an appropriate label.

I think implementing papers is a good approach. Depending on the paper, this might involve just constructing a network of standard layers in the proposed architecture, or it could involve creating custom layers / operations / training loops. Most papers will claim results on standard / openly available datasets, so you can see if you can reproduce their claimed accuracy. Check out Papers with Code: Image Classification subtasks dataset ideas.