densenet_121

→DenseNet

densenet_121(pretrained: bool = False, overrides: object = {})

source edit

DenseNet-121 feature-extracting backbone (no classification head).

Builds a DenseNet with the paper-cited DenseNet-121 topology: per-block dense-layer counts (6, 12, 24, 16), growth rate $k = 32$ , initial conv channels 64. Approximately 8.0 M parameters total — by far the most parameter-efficient of the ImageNet DenseNets, reaching a top-1 error of 25.0% (Huang et al., 2017, Table 2).

Model Size

Parameters

pretrainedbool= False

Reserved for future pretrained-weight loading. Currently ignored — the returned model is randomly initialised.

**overridesobject= {}

Keyword overrides forwarded into DenseNetConfig (growth_rate, dropout_rate, in_channels, etc.).

Returns

DenseNet

Backbone with the DenseNet-121 configuration applied (or with overrides merged on top of it).

Notes

See Huang et al., "Densely Connected Convolutional Networks", CVPR 2017, Table 1.

Examples

>>> import lucid
>>> from lucid.models.vision.densenet import densenet_121
>>> model = densenet_121()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.last_hidden_state.shape   # (B, 1024, 1, 1)
(1, 1024, 1, 1)

Used by 1

lucid.models.vision.densenet

>>> import lucid >>> from lucid.models.vision.densenet import densenet_121 >>> model = densenet_121() >>> x = lucid.randn(1, 3, 224, 224) >>> out = model(x) >>> out.last_hidden_state.shape # (B, 1024, 1, 1) (1, 1024, 1, 1)