# ConvNeXt Architecture

UPerNet semantic segmentation model based on ConvNeXt-Large encoder, suitable for scene parsing tasks like ADE20K

ConvNeXt-Nano face recognition model trained on the MS1MV3 dataset, compatible with the timm framework

This model is an image classification model fine-tuned on the huggan/wikiart dataset based on facebook/convnext-tiny-224, primarily used for artwork classification tasks.

CLIP model based on ConvNeXt-Base architecture, trained on the LAION-5B aesthetic subset, supporting 320x320 resolution image classification

CLIP model based on ConvNeXt-Base architecture, trained on a subset of LAION-5B using OpenCLIP, focusing on zero-shot image classification tasks

This model is a fine-tuned image classification model based on the ConvNeXt-Tiny architecture, trained on the EuroSAT dataset with albumentations for data augmentation, achieving 98.48% accuracy on the evaluation set.

A vision model based on the ConvNeXt-Tiny architecture, fine-tuned for image classification tasks

This model is an image classification model based on the ConvNeXt-Tiny architecture, trained on the Dogs vs Food dataset, specifically designed to distinguish between images of dogs and food.

An image classification model based on the ConvNeXt architecture, specifically designed for manuscript image classification tasks