LibreSwinb-cls

Swin Transformer V1 Base image classifier (224px input, ImageNet-1k, 1,000 classes), repackaged for LibreYOLO. 87,768,224 parameters.

Source

Derived from the Microsoft Research Swin Transformer V1 release at commit f82860bfb5225915aca09c3227159ee9e1df874d, with released weight storage at SwinTransformer/storage v1.0.0 (commit 3cc359915d3a6079b176a871f68d5fb0d8dfdea2). Copyright (c) 2021 SwinTransformer. Licensed under the MIT License.

The exact source snapshot is timm/swin_base_patch4_window7_224.ms_in1k at revision 160443c7878650977f11a3a89d4ed685b001a304. Its model.safetensors SHA-256 is 6544e46498082f24e90b3e5269d909dad03aa016db8711777313c162e136420c. Training lineage: ImageNet-1k.

The Apache-2.0 timm v1.0.28 implementation at commit 8ef73809f622e0031bd7f4940265734aef8b9978 is the architecture and parity reference; it does not relicense the MIT weight release.

Modifications

Learned parameters are unchanged. The checkpoint is metadata-wrapped into the LibreYOLO schema with canonical ImageNet-1k class names. LibreYOLO's native Swin V1 implementation matches timm's parameter names and produces bit-exact pretrained logits (max_abs_diff == 0). The converted checkpoint SHA-256 is 3e5172822afef8c813a944617e97cc9402016744dcba2bbda4a923b6e16f8c29.

See weights/convert_swin_weights.py in the LibreYOLO source repository.

Usage

from libreyolo import LibreYOLO

model = LibreYOLO("LibreSwinb-cls.pt")
result = model.predict("image.jpg")[0]
print(result.probs.top1, result.probs.top5)

License

MIT License. See the LICENSE and NOTICE files in this repository.