# Fast Image Classification

This is an image classification model built based on PyTorch and HuggingPics, specifically designed to distinguish between Jeep and Toyota vehicles.

LeViT-128 is an image classification model based on the Vision Transformer architecture, achieving efficient inference by combining the advantages of convolutional networks.

LeViT-256 is an efficient vision model based on Transformer architecture, designed for fast inference and pretrained on the ImageNet-1k dataset.