Lightweight NAS CNN

Overview

A computer-vision project exploring neural architecture search for compact convolutional networks. It focuses on finding a practical balance between model size and predictive performance, so a selected network can be efficient as well as capable. The repository demonstrates a search-based approach to designing lightweight CNN architectures for image-classification tasks.

Source code

Black and white diagram for Lightweight NAS CNN: candidate convolutional networks are compared and a compact image model is selected