posts

In this post, I will share what I learnt about Transformers into the world of

The success of object detection models, such as YOLO (You Only Look Once) and Faster R-CNN (Region-based Convolutional Neural Network), heavily relies on the quality of the datasets used for training. These models are at the forefront of computer vision applications, enabling tasks like real-time object identification, tracking, and localization. The importance of high-quality datasets in their training can’t be overstated, as they serve as the foundation upon which these models learn to understand and recognize objects within images or video streams.

This post is written as a summary of my university lectures in deep learning, with the purpose of helping me revise and understand the concept of RNNs. If you are looking for a detailed introduction to RNNs then this post might offer just that.