Swin Transformer (base-sized model)

Swin Transformer model pre-trained on ImageNet-1k using the SimMIM objective at resolution 192x192. It was introduced in the paper SimMIM: A Simple Framework for Masked Image Modeling by Xie et al. and first released in this repository .

Intended use cases

This model is pre-trained only, it's meant to be fine-tuned on a downstream dataset.

Usage

Refer to the documentation .