YOLO-NAS : A Makeover for a trained deep learning model

YOLO(You Only Look Once) has always been a go-to model for Object detection tasks. with YOLO-NAS on board it has even more gained popularity with Data Scientist for object detection tasks.

YOLO-NAS What's New:

While previous YOLO models were leading in innovation and performance when it comes to object detection, they did have some limitations such as lack of proper quantization support, which aims to decrease the model’s memory and computation requirements.

By leveraging a concept called neural architecture search (NAS) researchers addressed these limitations head-on.

Traditionally, neural network architectures were manually designed by human experts which has always been very time-consuming and cumbersome. NAS, on the other hand, automatically re-designs the model’s architecture in order to boost its performance when it comes to things like speed, memory usage, and throughput. It typically involves a search space that defines the set of possible architectural choices, such as the number of layers, layer types, kernel sizes, and connectivity patterns. The search algorithm then assesses different architectures by training and evaluating them on a given task and dataset. Based on these evaluations, the algorithm iteratively explores and refines the architecture space, ultimately returning the one that yields the best performance.

The results of this novel methodology speak for themselves. As can be seen in the graph below.