# Image Classification

ResNet-50 is a deep residual network developed by Microsoft Research, widely used for image classification tasks.

An image classification model built with PyTorch and HuggingPics, capable of accurately distinguishing between pictures of cats and dogs.

A plant identification model fine-tuned based on Google Vision Transformer (ViT) architecture, achieving 80.96% accuracy on the evaluation set

This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset, primarily used for image classification tasks, achieving an accuracy of 84.86% on the evaluation set.

KAT is a novel vision model that replaces the traditional Transformer's channel mixer with Grouped Rational Kolmogorov-Arnold Networks (GR-KAN), trained on the ImageNet-1k dataset.

A font recognition model fine-tuned on ResNet-18, achieving 78.1% accuracy on the test set

A fine-tuned ResNet18 model for font recognition, capable of identifying 48 standard fonts with a test accuracy of 96.33%

A bird image classifier fine-tuned on EfficientNet-B2, capable of recognizing 525 bird species with up to 99% accuracy

A fine-tuned cat-dog image classification model based on ResNet-18, trained on the Kaggle Cats and Dogs dataset with an accuracy of 99.29%

This model is a fine-tuned image classification model based on Google's ViT-base-patch16-224 on an image folder dataset, achieving an accuracy of 85.76% on the evaluation set.

Image classification model generated by HuggingPics, capable of identifying different dog breeds

Pyramid Vision Transformer (PVT) is a vision model based on transformer architecture, specifically designed for image classification tasks.

A vision model fine-tuned based on google/vit-base-patch16-224, suitable for image classification tasks

An image classification model fine-tuned on a letter recognition dataset based on Google's ViT base model, achieving 98.81% accuracy

A face classification model fine-tuned based on Microsoft ResNet-50, achieving 99.84% accuracy on the validation set

This is the OpenVINO version converted from the microsoft/swin-tiny-patch4-window7-224 model, designed to accelerate image classification inference.

Doge is an image classification model generated by HuggingPics, specifically designed to recognize Doge-related images.

A vision model fine-tuned based on microsoft/swin-tiny-patch4-window7-224, achieving 100% accuracy on the evaluation set

This is an image classification model fine-tuned based on Google's ViT model, trained on the fl_image_category_ds dataset with an accuracy of 66.22%.

Art style classification model based on ViT architecture, capable of identifying the art style category of input images

An image classification model fine-tuned based on microsoft/resnet-18, trained on the fl_image_category_ds dataset

A ViT model fine-tuned on the preprocessed 1024 configuration dataset for image classification tasks

This model is a vision classification model fine-tuned on an algae dataset based on Google's ViT model, primarily used for algae image classification tasks.

An image classification model fine-tuned based on microsoft/resnet-50, achieving an accuracy of 64.1% on the evaluation set

A vision classification model fine-tuned based on google/vit-base-patch16-224 for recognizing first-generation Pokémon

A simple image classification model based on PyTorch and HuggingPics, used to determine whether a person in an image is bald.

An image classification model based on YOLOv8 for identifying fog and smoke scenes.

Vision Transformer model based on ViT architecture for gender and age classification tasks

An image classification model based on the BEiT architecture, fine-tuned on the FER2013 dataset for facial expression recognition

This model is an image classification model based on the BEiT architecture, fine-tuned on the FER2013CKPlus dataset for facial expression recognition tasks.

EfficientFormer-L3 is a lightweight vision Transformer model developed by Snap Research, optimized for mobile devices to achieve low latency while maintaining high performance.

A small model based on the Swin Transformer architecture, fine-tuned on the CIFAR-100 dataset for image classification tasks

EfficientFormer-L1 is a vision Transformer model developed by Snap Research, optimized for mobile devices to achieve extremely low latency while maintaining high performance.

Image classification model fine-tuned on CIFAR-100 dataset based on Swin Transformer Tiny architecture

A fine-tuned test version of Google Vision Transformer (ViT) base model on CIFAR-10 dataset

The Hybrid Vision Transformer (ViT) model combines convolutional networks and Transformer architectures for image classification tasks, excelling on ImageNet.

An image classification model based on ViT architecture, fine-tuned on an image folder dataset

This is an image classification model used to determine whether an image is of a 3D-printed object.

A Vision Transformer (ViT) based model fine-tuned on the CIFAR-10 dataset for image classification tasks

This is a model based on the Keras framework, with unspecified functionality, possibly used for image classification or spam detection tasks