SK-ResNet-101 feature-extracting backbone (no classification head).
Builds an SKNet with ResNet-101 bottleneck topology
(_SelectiveKernelBottleneck blocks stacked
[3, 4, 23, 3]). Approximately 45M parameters. Deeper
variant of SK-ResNet-50 for higher-accuracy budgets.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
SKNetConfig.Returns
SKNetBackbone with the SK-ResNet-101 configuration applied (or
with overrides merged on top of it).
Notes
See Li et al., "Selective Kernel Networks", CVPR 2019 (arXiv:1903.06586).
Examples
>>> import lucid
>>> from lucid.models.vision.sknet import sk_resnet_101
>>> model = sk_resnet_101()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.last_hidden_state.shape
(1, 2048, 7, 7)