# ConvNeXt architecture

An image classification model built based on the timm library, with zoobot-encoder-convnext_nano as the base model, capable of image classification.

CLIP ConvNeXt-XXLarge model trained on LAION-2B dataset, implemented with OpenCLIP framework, the first non-ViT architecture achieving >79% ImageNet zero-shot accuracy

CLIP model based on ConvNeXt-Large architecture, trained on LAION-2B dataset, supporting zero-shot image classification and image-text retrieval tasks.

Large-scale ConvNeXt-Large CLIP model trained on LAION-2B dataset, supporting zero-shot image classification and image-text retrieval tasks

This is a multi-category image classification model trained using AutoTrain, based on the ConvNeXt architecture, suitable for general image classification tasks.

A CLIP model based on the ConvNeXt-Base architecture, trained on a subset of LAION-5B, suitable for zero-shot image classification and image-text retrieval tasks.

CLIP model with ConvNeXt-Base architecture trained on the LAION-Aesthetic dataset, supporting zero-shot image classification and cross-modal retrieval tasks

CLIP model based on ConvNeXt-Base architecture, trained on a subset of LAION-5B, supporting zero-shot image classification and image-text retrieval tasks

An image classification model fine-tuned for binary classification tasks based on facebook/convnext-small-224, achieving an F1 score of 0.9620 on the evaluation set

This is a computer vision model based on the ConvNeXt-Tiny architecture, fine-tuned on unsupervised data using pseudo-labels generated by Snorkel

Cat and dog image classification model based on ConvNeXt architecture, fine-tuned on the cats_vs_dogs dataset with an accuracy of 99.73%

An image classification model based on the ConvNeXt architecture, fine-tuned on an image folder dataset, excelling in high-precision image classification tasks

A mask detection model using the ConvNeXt architecture, trained on the Face-Mask18K dataset with an accuracy rate of 99.61%.