efficientnet_b5

→EfficientNet

efficientnet_b5(pretrained: bool = False, overrides: object = {})

source edit

EfficientNet-B5 feature-extracting backbone (compound coefficient $\phi = 4$ ).

Builds an EfficientNet with width multiplier 1.6 and depth multiplier 2.2. Approximately 30M parameters and 83.6% ImageNet-1k top-1 accuracy at the 456×456 native resolution (Tan & Le, 2019, Table 2).

Model Size

Parameters

pretrainedbool= False

Reserved for future pretrained-weight loading. Currently ignored.

**overridesobject= {}

Keyword overrides forwarded into EfficientNetConfig.

Returns

EfficientNet

Backbone with the B5 configuration applied (or with overrides merged on top of it).

Notes

See Tan & Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks", ICML 2019 (arXiv:1905.11946), Table 2. Head expansion: round(1280 · 1.6) = 2048 channels.

Examples

>>> import lucid
>>> from lucid.models.vision.efficientnet import efficientnet_b5
>>> model = efficientnet_b5()
>>> x = lucid.randn(1, 3, 456, 456)
>>> out = model(x)
>>> out.last_hidden_state.shape
(1, 2048, 1, 1)

Used by 1

lucid.models.vision.efficientnet

>>> import lucid >>> from lucid.models.vision.efficientnet import efficientnet_b5 >>> model = efficientnet_b5() >>> x = lucid.randn(1, 3, 456, 456) >>> out = model(x) >>> out.last_hidden_state.shape (1, 2048, 1, 1)