ResNet-152 feature-extracting backbone (no classification head).
Builds a ResNet with the paper-cited ResNet-152 topology:
_Bottleneck blocks stacked [3, 8, 36, 3] over four
stages, yielding approximately 60.2M parameters. Reaches 78.31%
ImageNet-1k top-1 in He et al., 2015 (Table 4) — the highest of
the canonical ResNet variants from the original paper.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
ResNetConfig to
customise individual fields without writing a config by hand.Returns
ResNetBackbone with the ResNet-152 configuration applied (or with
overrides merged on top of it).
Notes
See He et al., "Deep Residual Learning for Image Recognition", CVPR 2016 (arXiv:1512.03385), Table 1. The 36-block stage-3 is the defining feature; stages 1 and 4 are unchanged from ResNet-50/101, and stage-2 widens from 4 to 8 blocks. Final-stage output is 2048 channels.
Examples
>>> import lucid
>>> from lucid.models.vision.resnet import resnet_152
>>> model = resnet_152()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.last_hidden_state.shape # (B, 2048, H/32, W/32)
(1, 2048, 7, 7)