resnet_269_cls(pretrained: bool = False, overrides: object = {})ResNet-269 image classifier (backbone + GAP + linear head).
Builds a ResNetForImageClassification with the very deep
bottleneck topology [3, 30, 48, 8]. Approximately 102.1M
parameters — primarily useful as a high-capacity teacher in
knowledge distillation pipelines.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
ResNetConfig.Returns
ResNetForImageClassificationClassifier with the ResNet-269 configuration applied (or with
overrides merged on top of it).
Examples
>>> import lucid
>>> from lucid.models.vision.resnet import resnet_269_cls
>>> model = resnet_269_cls()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)