# ImageNet-22k pretrained

ConvNeXT is a pure convolutional model inspired by vision Transformer designs, pretrained on ImageNet-22k and fine-tuned on ImageNet-1k, outperforming traditional Transformers.

ConvNeXT is a pure convolutional model inspired by Vision Transformers, claiming superior performance over them. This model was trained on ImageNet-22k dataset at 224x224 resolution.

ConvNeXT is a pure convolutional model inspired by Vision Transformers, claiming superior performance over Vision Transformers. This model was trained on the ImageNet-22k dataset at 224x224 resolution.