ResNeSt-101

Zhang et al., 2022 — ResNeSt: Split-Attention Networks (arXiv:2004.08955)

Lucid port of timm/resnest101e.in1k, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
IN1K (default)	82.8	—	48.3M	—	184.74 MB	timm

Usage

import lucid.models as models
from lucid.models.weights import ResNeSt101Weights

# default tag
model = models.resnest_101_cls(pretrained=True)

# explicit tag (enum or string)
model = models.resnest_101_cls(weights=ResNeSt101Weights.IN1K)
model = models.resnest_101_cls(pretrained="IN1K")

# preprocessing travels with the weights
weights = ResNeSt101Weights.IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/resnest101e.in1k via python -m tools.convert_weights resnest_101 --tag IN1K. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{zhang2022resnest,
  title={ResNeSt: Split-Attention Networks},
  author={Zhang, Hang and Wu, Chongruo and Zhang, Zhongyue and Zhu, Yi and Lin, Haibin and Zhang, Zhi and Sun, Yue and He, Tong and Mueller, Jonas and Manmatha, R. and Li, Mu and Smola, Alexander},
  booktitle={CVPR Workshops}, year={2022}
}