# Food Recognition

This is a food classification model fine-tuned on the food101 dataset based on Google's ViT model, achieving an accuracy of 89.5%.

A simple image classification model for identifying whether a picture is a hot dog

A snack image classification model based on ViT architecture, fine-tuned on the Matthijs/snacks dataset with an accuracy of 93.9%

A Vision Transformer model pre-trained on ImageNet-21k and fine-tuned specifically for snack image classification tasks