# ViT fine-tuning

This is a fine-tuned ViT (Vision Transformer) model specifically designed for Pokémon image classification. The model has been trained to classify Pokémon images up to the ninth generation (1025 species).

An image classification model fine-tuned based on Google's ViT-base-patch16-224 model, achieving an accuracy of 68.97% on the evaluation set

A NSFW (Not Safe For Work) content detection model fine-tuned based on Google Vision Transformer, capable of identifying 5 types of image content

A multi-label classification model fine-tuned from google/vit-base-patch16-224-in21k with an accuracy of 73.7%

Image classification model fine-tuned on EuroSAT remote sensing image dataset based on Google's ViT base architecture

This is a binary classification model based on the ViT architecture, designed to distinguish between male and female eye images.

An image anti-counterfeiting detection model based on ViT architecture, achieving 70.88% accuracy after fine-tuning on an unknown dataset

This is a MNIST handwritten digit classification model based on the Vision Transformer (ViT) architecture, achieving 99.23% accuracy after fine-tuning on the MNIST dataset.

A ViT-based image classification model for Roman numerals, fine-tuned on the farleyknight/roman_numerals dataset with an accuracy of 83.09%

This is a Vision Transformer (ViT) model fine-tuned on an image classification task based on the tiny-random-vit architecture, achieving 66.47% accuracy on the evaluation set.