# ImageNet pretrained

A self-supervised feature representation model based on ConvNeXt-V2, pre-trained using the Fully Convolutional Masked Autoencoder (FCMAE) framework

MobileNet V2 is a small, low-latency, low-power vision model specifically optimized for mobile devices

A Vision Transformer model pretrained on ImageNet-21k, featuring an extra-large architecture suitable for visual tasks like image classification.

ViT-tiny model converted from timm codebase, suitable for image classification tasks