This project focuses on developing a robust gemstone classification system by employing two cutting-edge deep learning architectures: Convolutional Neural Network (CNN) and Vision Transformer (ViT).

We benchmark the largest array of CNN and ViT models, extensively trained on the largest publicly available COVID-19 dataset to the best of our knowledge. We conducted a detailed comparison of the ...

This study investigates the performance of Transformer-based models (ViT, DeiT) and Convolutional Neural Networks (CNNs) (Simple CNN, VGG16, Xception, InceptionV3, MobileNetV2, DenseNet121) and ...