SE-ResNet-50 feature-extracting backbone (no classification head).
Builds an SENet with ResNet-50 topology
(_SEBottleneck blocks stacked [3, 4, 6, 3]) plus
squeeze-and-excitation modules at the end of every bottleneck.
Approximately 28.1M parameters — about 10% more than plain
ResNet-50 — and 77.6% ImageNet-1k top-1 accuracy in Hu et al.,
2018 (Table 2) versus 76.2% for plain ResNet-50. The most
widely deployed SE variant.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
SENetConfig.Returns
SENetBackbone with the SE-ResNet-50 configuration applied (or
with overrides merged on top of it).
Notes
See Hu et al., "Squeeze-and-Excitation Networks", CVPR 2018 (arXiv:1709.01507), Table 2. Final-stage output is 2048 channels.
Examples
>>> import lucid
>>> from lucid.models.vision.senet import se_resnet_50
>>> model = se_resnet_50()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.last_hidden_state.shape
(1, 2048, 7, 7)