SE-ResNet-152

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

Lucid port of timm/legacy_seresnet152.in1k, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
IN1K (default)	78.66	—	66.8M	—	255.59 MB	timm

Usage

import lucid.models as models
from lucid.models.weights import SEResNet152Weights

# default tag
model = models.se_resnet_152_cls(pretrained=True)

# explicit tag (enum or string)
model = models.se_resnet_152_cls(weights=SEResNet152Weights.IN1K)
model = models.se_resnet_152_cls(pretrained="IN1K")

# preprocessing travels with the weights
weights = SEResNet152Weights.IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/legacy_seresnet152.in1k via python -m tools.convert_weights se_resnet_152 --tag 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}
}