swin-base-patch4-window12-384

Model overview

The model is published by microsoft as a base-sized Swin Transformer for image classification. The captured configuration identifies SwinForImageClassification with a swin model type. According to the model card, it was trained on ImageNet-1k at 384x384 resolution and introduced in the Swin Transformer paper on hierarchical vision transformers with shifted windows.

Recorded capabilities

Use cases in the source record

• Raw-model image classification into the 1,000 ImageNet classes using the card's documented Transformers workflow.
• Vision-backbone research building on the card's description of hierarchical feature maps for classification and dense recognition tasks.

Limitations and unknowns

• No parameter count or evaluation metrics were extracted from this record.
• No context-window, hardware requirement, or quantization detail applies to this vision record beyond the extracted fields.
• Training and architecture narrative comes from the publisher-supplied card text and was not independently verified by Ethen.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: microsoft/swin-base-patch4-window12-384

Captured: Unknown. Processed: 2026-09-07T19:34:51.836483+00:00.

Swin Transformer (base-sized model) Swin Transformer model trained on ImageNet-1k at resolution 384x384. It was introduced in the paper Swin Transformer: Hierarchical Vision Transformer using Shifted Windows by Liu et al. and first released in this repository . Disclaimer: The team releasing Swin Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. Model description The Swin Transformer is a type of Vision Transformer. It builds hierarchical feature maps by merging image patches (shown in gray) in deeper layers and has linear computation complexity to input image size du…