wide_resnet_101_cls(pretrained: bool | str = False, weights: WideResNet101Weights | None = None, overrides: object = {})Wide ResNet-101-2 image classifier (backbone + GAP + linear head).
Builds a ResNetForImageClassification with the Wide
ResNet-101-2 configuration: ResNet-101's [3, 4, 23, 3]
bottleneck layout with a 2x inner-channel multiplier.
Approximately 126.9M parameters; from Zagoruyko & Komodakis,
"Wide Residual Networks", BMVC 2016 (arXiv:1605.07146).
Model Size
Parameters
pretrainedbool or str= FalsePretrained-weight selector.
False → random init; True
→ the DEFAULT tag
(WideResNet101Weights.IMAGENET1K_V1); a tag string →
that specific checkpoint. Mutually exclusive with weights
(which wins if both are given).Explicit weights enum member. Takes precedence over
pretrained.**overridesobject= {}Keyword overrides forwarded into
ResNetConfig.Returns
ResNetForImageClassificationClassifier with the Wide ResNet-101-2 configuration applied
(or with overrides merged on top of it), optionally
initialised from pretrained weights.
Notes
Pretrained weights are converted from torchvision's
Wide_ResNet101_2_Weights and hosted on the Hugging Face Hub
under lucid-dl/wide-resnet-101-2.
Examples
>>> import lucid
>>> from lucid.models.vision.resnet import wide_resnet_101_cls
>>> model = wide_resnet_101_cls()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)