Ir para o conteúdo
ModelListadosExterno
Baixar

Uniformer S K400

Pure-PyTorch port of UniFormer-S (video classification, trained on Kinetics-400 with 16-frame clips at sampling stride 8) hosted under CondadosAI/ for use with the acaua computer vision library.

Fontehuggingface.co/CondadosAI/uniformer_s_k400/tree/7c3238d06465a2f02493a85f04afb95962bf9fcb
TipoOtherVersãoRevision 7c3238dBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
81,7 MB
Versão
vRevision 7c3238d
Atualizado
24 de out. de 2026
Downloads
9
Fonte
Hugging Face

Descrição da fonte

UniFormer-S (Kinetics-400) — acaua mirror (pure-PyTorch port)

Pure-PyTorch port of UniFormer-S (video classification, trained on Kinetics-400 with 16-frame clips at sampling stride 8) hosted under CondadosAI/ for use with the acaua computer vision library.

The architecture has been re-implemented in pure PyTorch under acaua.adapters.uniformer.video — no mmcv, no mmengine, no mmaction2, no trust_remote_code, no timm runtime dependency. The weights 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 codeSense-X/UniFormer @ main (Apache-2.0)
Upstream weightsSense-X/uniformer_video at revision f9448914e6161573b14ba47b72fcef170e03a1f9 (MIT)
Upstream fileuniformer_small_k400_16x8.pth
Upstream SHA256d5fd7b0c49ee6a5422ef5d0c884d962c742003bfbd900747485eb99fa269d0db
Upstream factoryuniformer_small() in video_classification/models/uniformer.py
Conversion scriptscripts/convert_uniformer_video.py
PaperLi et al., UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning, 2022
Params22M
Top-1 (Kinetics-400, 16 frames x 1 clip x 1 crop)78.4%
FLOPs41.8G
Training recipe16 input frames, sampling stride 8, 224x224 center-crop, ImageNet-mean/std normalization
Mirrored on2026-04-24
Mirrored byCondadosAI/acaua

Usage via acaua

import acaua

# MIT-declared weights require the explicit opt-in.
model = acaua.Model.from_pretrained(
    "CondadosAI/uniformer_s_k400", allow_non_apache=True
)
result = model.predict("video.mp4")
print(result.labels)   # tuple of top-5 Kinetics-400 action labels
print(result.scores)   # aligned float32 probabilities

Requires pip install 'acaua[video]' for the TorchCodec-backed video decoder and a system-level ffmpeg install.

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 400 Kinetics-400 action labels in index order. Read by the adapter at load time.
  • config.json — minimal metadata: acaua_task=video_classification, num_frames, num_classes.
  • NOTICE — attribution chain (code AND weights).
  • LICENSE — Apache-2.0.

License and attribution

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

Citation

@misc{li2022uniformervideo,
  title        = {UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning},
  author       = {Li, Kunchang and Wang, Yali and Gao, Peng and Song, Guanglu and Liu, Yu and Li, Hongsheng and Qiao, Yu},
  year         = {2022},
  eprint       = {2201.04676},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
}

Fontes

1 fonte
Hugging FacePrimárioVersão 7c3238d06465a2f02493a85f04afb95962bf9fcb
huggingface.co/CondadosAI/uniformer_s_k400/tree/7c3238d06465a2f02493a85f04afb95962bf9fcb

Verificado 24 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 81,7 MB · SHA-256 464eb55c47be…fb9c · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme6 de ago.huggingface.co/CondadosAI/uniformer_s_k400

--- license: mit library_name: acaua pipeline_tag: video-classification tags: - video-classification - vision - acaua - native-pytorch-port datasets: - kinetics-400 --- # UniFormer-S (Kinetics-400) — acaua mirror (pure-PyTorch port) Pure-PyTorch port of **UniFormer-S** (video classification, trained on Kinetics-400 with 16-frame clips at sampling stride 8) 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.video` — no `mmcv`, no `mmengine`, no `mmaction2`, no `trust_remote_code`, no `timm` runtime dependency. The weights 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`](https://github.com/Sense-X/UniFormer) @ `main` (Apache-2.0) | | Upstream weights | [`Sense-X/uniformer_video`](https://huggingface.co/Sense-X/uniformer_video) at revision `f9448914e6161573b14ba47b72fcef170e03a1f9` (MIT) | | Upstream file | `uniformer_small_k400_16x8.pth` | | Upstream SHA256 | `d5fd7b0c49ee6a5422ef5d0c884d962c742003bfbd900747485eb99fa269d0db` | | Upstream factory | `uniformer_small()` in `video_classification/models/uniformer.py` | | Conversion script | [`scripts/convert_uniformer_video.py`](https://github.com/CondadosAI/acaua/blob/main/scripts/convert_uniformer_video.py) | | Paper | Li et al., [*UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning*](https://arxiv.org/abs/2201.04676), 2022 | | Params | 22M | | Top-1 (Kinetics-400, 16 frames x 1 clip x 1 crop) | 78.4% | | FLOPs | 41.8G | | Training recipe | 16 input frames, sampling stride 8, 224x224 center-crop, ImageNet-mean/std normalization | | Mirrored on | 2026-04-24 | | Mirrored by | [CondadosAI/acaua](https://github.com/CondadosAI/acaua) | ## Usage via acaua ```python import acaua # MIT-declared weights require the explicit opt-in. model = acaua.Model.from_pretrained( "CondadosAI/uniformer_s_k400", allow_non_apache=True ) result = model.predict("video.mp4") print(result.labels) # tuple of top-5 Kineti...

Note24 de out.huggingface.co/CondadosAI/uniformer_s_k400

Source context: 9 downloads · 0 likes · Pipeline video-classification · Library acaua · Repo CondadosAI/uniformer_s_k400

Note6 de ago.huggingface.co/CondadosAI/uniformer_s_k400

Source context: 8 downloads · 0 likes · Pipeline video-classification · Library acaua · Repo CondadosAI/uniformer_s_k400