Ir para o conteúdo
ModelListadosExterno
Baixar

Uniformer S Coco Pose

Pure-PyTorch port of UniFormer-S (top-down COCO 17-keypoint pose at 256x192) hosted under CondadosAI/ for use with the acaua computer vision library.

Fontehuggingface.co/CondadosAI/uniformer_s_coco_pose/tree/81f38ba453fab3dcaf011d87180a7feb4b8531a4
TipoOtherVersãoRevision 81f38baBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
96,3 MB
Versão
vRevision 81f38ba
Atualizado
20 de out. de 2026
Downloads
10
Fonte
Hugging Face

Descrição da fonte

UniFormer-S COCO top-down pose — acaua mirror (pure-PyTorch port)

Pure-PyTorch port of UniFormer-S (top-down COCO 17-keypoint pose at 256x192) hosted under CondadosAI/ for use with the acaua computer vision library.

The architecture has been re-implemented in pure PyTorch under acaua.adapters.uniformer.pose — no mmcv, no mmengine, no mmpose, no trust_remote_code, no timm runtime dependency. The backbone reuses UniFormer2DDense (already shipped via PR #9 for the Stage 1.5 dense-prediction work); the pose head is a fresh port of mmpose's TopDownSimpleHead. Decode is the upstream post_process='default' path (argmax + 0.25-pixel shift, NOT the DARK unbiased decoder). Inverse-warp uses the shared acaua.pose.topdown_utils module (introduced in PR #8 ahead of this stage).

Provenance

Upstream codeSense-X/UniFormer @ main (Apache-2.0); files derived: pose_estimation/mmpose/models/backbones/uniformer.py (backbone, identical to detection variant up to module-class identity) + pose_estimation/mmpose/models/keypoint_heads/top_down_simple_head.py (head)
Upstream weightsGoogle Drive file id 162R0JuTpf3gpLe1IK6oxRoQK7JSj4ylx, filename top_down_256x192_global_small.pth (101MB)
Upstream SHA256d77059e3e9322c0e20dc89dc0cf2a583ffe2ced7d3e9b350233738add570bc30
Upstream reportAP 74.0 / AP@50 90.3 / AP@75 82.2 on COCO val 2017, 256x192, single-scale
ArchitectureUniFormer-S backbone (hybrid=False, windows=False, depth=[3,4,8,3], embed_dims=[64,128,320,512], head_dim=64) + TopDownSimpleHead (3x ConvTranspose2d-stride-2 + BN+ReLU upsample, 1x1 conv to 17 channels)
Total params25.23M (backbone 21.04M + head 4.19M)
Mirrored on2026-04-25
Mirrored byCondadosAI/acaua

Usage via acaua

import acaua

# MIT-declared weights -> explicit opt-in (same posture as RTMPose +
# UniFormer image / video classifications). The bundled RTMDet-tiny
# detector is loaded automatically from CondadosAI/rtmdet_t_coco.
model = acaua.Model.from_pretrained(
    "CondadosAI/uniformer_s_coco_pose", allow_non_apache=True
)

result = model.predict("image.jpg")
print(result.keypoints.shape)        # (N_persons, 17, 2)
print(result.keypoint_scores.shape)  # (N_persons, 17)

# COCO skeleton edges are surfaced on the adapter:
import supervision as sv
sv.EdgeAnnotator(edges=model.skeleton).annotate(scene, result.to_supervision())

Files in this mirror

  • model.safetensors — full pose model weights (backbone + head, 352 tensors). Loaded under load_state_dict(strict=True) at adapter init time.
  • config.json — acaua_task=pose, COCO-17 keypoint_names + skeleton, detector_repo_id=CondadosAI/rtmdet_t_coco. Adapter surfaces these as model.keypoint_names / model.skeleton.
  • NOTICE — attribution chain (code AND weights).
  • LICENSE — Apache-2.0.

License and attribution

The adapter code is redistributed under Apache-2.0. The underlying weights carry upstream's MIT declaration (compatible). The acaua UniFormer-pose adapter is a derivative work of the upstream PyTorch implementation — see NOTICE for the 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},
}

Fontes

1 fonte
Hugging FacePrimárioVersão 81f38ba453fab3dcaf011d87180a7feb4b8531a4
huggingface.co/CondadosAI/uniformer_s_coco_pose/tree/81f38ba453fab3dcaf011d87180a7feb4b8531a4

Verificado 20 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 96,3 MB · SHA-256 5350e36bf09f…5e0c · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme4 de ago.huggingface.co/CondadosAI/uniformer_s_coco_pose

--- license: mit library_name: acaua pipeline_tag: keypoint-detection tags: - pose-estimation - keypoint-detection - vision - acaua - native-pytorch-port datasets: - coco --- # UniFormer-S COCO top-down pose — acaua mirror (pure-PyTorch port) Pure-PyTorch port of **UniFormer-S** (top-down COCO 17-keypoint pose at 256x192) hosted under `CondadosAI/` for use with the [acaua](https://github.com/CondadosAI/acaua) computer vision library. The architecture has been re-implemented in pure PyTorch under `acaua.adapters.uniformer.pose` — no `mmcv`, no `mmengine`, no `mmpose`, no `trust_remote_code`, no `timm` runtime dependency. The backbone reuses `UniFormer2DDense` (already shipped via PR #9 for the Stage 1.5 dense-prediction work); the pose head is a fresh port of mmpose's `TopDownSimpleHead`. Decode is the upstream `post_process='default'` path (argmax + 0.25-pixel shift, NOT the DARK unbiased decoder). Inverse-warp uses the shared `acaua.pose.topdown_utils` module (introduced in PR #8 ahead of this stage). ## Provenance | | | |---|---| | Upstream code | [`Sense-X/UniFormer`](https://github.com/Sense-X/UniFormer) @ `main` (Apache-2.0); files derived: `pose_estimation/mmpose/models/backbones/uniformer.py` (backbone, identical to detection variant up to module-class identity) + `pose_estimation/mmpose/models/keypoint_heads/top_down_simple_head.py` (head) | | Upstream weights | Google Drive file id `162R0JuTpf3gpLe1IK6oxRoQK7JSj4ylx`, filename `top_down_256x192_global_small.pth` (101MB) | | Upstream SHA256 | `d77059e3e9322c0e20dc89dc0cf2a583ffe2ced7d3e9b350233738add570bc30` | | Upstream report | AP 74.0 / AP@50 90.3 / AP@75 82.2 on COCO val 2017, 256x192, single-scale | | Architecture | UniFormer-S backbone (`hybrid=False, windows=False`, depth=[3,4,8,3], embed_dims=[64,128,320,512], head_dim=64) + TopDownSimpleHead (3x ConvTranspose2d-stride-2 + BN+ReLU upsample, 1x1 conv to 17 channels) | | Total params | 25.23M (backbone 21.04M + head 4.19M) | | Mirrored on | 2026-04-25 | | Mirrored by | [CondadosAI/acaua](https://github.com/CondadosAI/acaua) | ## Usage via acaua ```python import acaua # MIT-declared weights -> explicit opt-in (same posture as RTMPose + # UniFormer image / video classifications). The bundled RTMDet-tiny # detector is loaded automatically from CondadosAI/rtmdet_t_coco. model = acaua.Model.from_pretrained( "CondadosAI/uniformer_s_...

Note20 de out.huggingface.co/CondadosAI/uniformer_s_coco_pose

Source context: 10 downloads · 0 likes · Pipeline keypoint-detection · Library acaua · Repo CondadosAI/uniformer_s_coco_pose

Note4 de ago.huggingface.co/CondadosAI/uniformer_s_coco_pose

Source context: 5 downloads · 0 likes · Pipeline keypoint-detection · Library acaua · Repo CondadosAI/uniformer_s_coco_pose