densenet_264_cls(pretrained: bool = False, overrides: object = {})DenseNet-264 image classifier (backbone + GAP + linear head).
Builds a DenseNetForImageClassification with the
paper-cited DenseNet-264 topology and a lucid.nn.Linear
classifier projecting 2688 → config.num_classes.
Approximately 33.3 M parameters; the deepest DenseNet evaluated in
the paper, with a top-1 ImageNet error of 22.2% (Huang et al.,
2017, Table 2).
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
DenseNetConfig.Returns
DenseNetForImageClassificationClassifier with the DenseNet-264 configuration applied (or with
overrides merged on top of it).
Examples
>>> import lucid
>>> from lucid.models.vision.densenet import densenet_264_cls
>>> model = densenet_264_cls()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)