vgg_11_cls(pretrained: bool | str = False, weights: VGG11Weights | None = None, overrides: object = {})VGG-11 image classifier (config A, no BatchNorm).
Builds a VGGForImageClassification with the paper-cited
VGG-11 topology (arch=(1, 1, 2, 2, 2)) followed by the two
4096-dim fully-connected layers and a final linear projection to
config.num_classes. Approximately 132.9 M parameters total
(≈124 M of which sit in the two large FC layers). Reaches a top-1
ImageNet validation accuracy of 69.02% (torchvision eval).
Model Size
Parameters
pretrainedbool or str= FalsePretrained-weight selector.
False → random init; True
→ the DEFAULT tag (VGG11Weights.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
VGGConfig — use
num_classes=N to retarget the head.Returns
VGGForImageClassificationClassifier with the VGG-11 configuration applied (or with
overrides merged on top of it), optionally initialised from
pretrained weights.
Notes
Pretrained weights are converted from torchvision's VGG11_Weights
and hosted on the Hugging Face Hub under lucid-dl/vgg-11.
Examples
>>> import lucid
>>> from lucid.models.vision.vgg import vgg_11_cls
>>> model = vgg_11_cls(pretrained=True)
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)