# 224x224 Resolution

PVT is a Transformer-based vision model that employs a pyramid structure for image processing, pre-trained on ImageNet-1K, suitable for image classification tasks.

This model is a tiny version based on the ConvNeXT architecture, fine-tuned on the CIFAR10 dataset, suitable for image classification tasks.

LeViT-128S is a vision Transformer model pretrained on the ImageNet-1k dataset, combining the advantages of convolutional networks for faster inference.

LeViT-384 is a vision Transformer model pre-trained on the ImageNet-1k dataset, combining the advantages of convolutional networks for faster inference speed.

A deep residual network model pre-trained on the ImageNet-1k dataset for image classification tasks

BEiT is a Vision Transformer (ViT)-based image classification model, pre-trained in a self-supervised manner on ImageNet-22k and fine-tuned on the same dataset.

ConvNeXT is a pure convolutional model inspired by vision Transformers, trained on the ImageNet-1k dataset at 224x224 resolution.

The distilled version of the Efficient Data Image Transformer (DeiT) model was pre-trained and fine-tuned on ImageNet-1k at 224x224 resolution, extracting knowledge from a teacher model through distillation learning.