CondadosAI/uniformer_b_in1k

UniFormer-B — acaua mirror (pure-PyTorch port)

Pure-PyTorch port of UniFormer-B hosted under CondadosAI/ for use with the acaua computer vision library.

The architecture has been re-implemented in pure PyTorch under acaua.adapters.uniformer — no mmcv, no mmengine, no mmseg, no trust_remote_code, no timm runtime dependency. The weights in this mirror are converted from the upstream .pth checkpoint to safetensors with acaua's state‑dict key naming (backbone.* + head.fc.*). They are not drop-in compatible with timm or Sense-X/UniFormer loaders — they are designed to load cleanly into acaua's nn.Module tree under load_state_dict(strict=True).

Provenance

Upstream code	Sense-X/UniFormer @ main (Apache-2.0)
Upstream weights	Sense-X/uniformer_image at revision ae70a7dc23e2d85972370501db47717efcd2c6f1 (MIT)
Upstream file	uniformer_base_in1k.pth
Upstream SHA256	82c01015818cb897b00a29352043053df53ce4c02c2d012226b3a8a12ccb60eb
Upstream factory	uniformer_base() in image_classification/models/uniformer.py
Conversion script	scripts/convert_uniformer.py
Paper	Li et al., UniFormer: Unifying Convolution and Self-attention for Visual Recognition, ICLR 2022
Params	50M
Top-1 (ImageNet-1k, 224×224)	83.8%
FLOPs (224×224)	8.3G
Mirrored on	2026-04-24
Mirrored by	CondadosAI/acaua

Usage via acaua

import acaua
model = acaua.Model.from_pretrained("CondadosAI/uniformer_b_in1k")
result = model.predict("image.jpg")
print(result.labels)  # tuple of top-5 ImageNet class names
print(result.scores)  # aligned float32 probabilities

Files in this mirror

• model.safetensors — acaua-format weights (key-remapped, verified round-trip under load_state_dict(strict=True) at conversion time).
• labels.json — JSON array of 1000 ImageNet-1k class names in index order. Read by the adapter at load time.
• NOTICE — attribution chain (code AND weights).
• LICENSE — Apache-2.0.

License and attribution

The adapter code (this mirror) is redistributed under Apache-2.0. The underlying weights carry upstream's MIT declaration (compatible, permissively re-distributable). The acaua UniFormer adapter is itself a derivative work of the upstream PyTorch implementation — see NOTICE for the required attribution chain.

Citation

@inproceedings{li2022uniformer,
  title     = {UniFormer: Unifying Convolution and Self-attention for Visual Recognition},
  author    = {Li, Kunchang and Wang, Yali and Zhang, Junhao and Gao, Peng and Song, Guanglu and Liu, Yu and Li, Hongsheng and Qiao, Yu},
  booktitle = {ICLR},
  year      = {2022},
}