SE-ResNet-50

Hu et al., 2018 — Squeeze-and-Excitation Networks (arXiv:1709.01507)

Lucid port of timm/seresnet50.ra2_in1k, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
RA2_IN1K (default)	78.498	—	28.1M	—	107.39 MB	timm

Usage

import lucid.models as models
from lucid.models.weights import SEResNet50Weights

# default tag
model = models.se_resnet_50_cls(pretrained=True)

# explicit tag (enum or string)
model = models.se_resnet_50_cls(weights=SEResNet50Weights.RA2_IN1K)
model = models.se_resnet_50_cls(pretrained="RA2_IN1K")

# preprocessing travels with the weights
weights = SEResNet50Weights.RA2_IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/seresnet50.ra2_in1k via python -m tools.convert_weights se_resnet_50 --tag RA2_IN1K. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{hu2018squeeze,
  title={Squeeze-and-Excitation Networks},
  author={Hu, Jie and Shen, Li and Sun, Gang},
  booktitle={CVPR}, year={2018}
}