mobilenet_v1_025_cls

→MobileNetV1ForImageClassification

mobilenet_v1_025_cls(pretrained: bool = False, overrides: object = {})

source edit

MobileNet-v1 image classifier at width multiplier $\alpha = 0.25$ .

Builds a MobileNetV1ForImageClassification with the paper-cited 0.25-width topology — approximately 0.5M parameters and 50.6% ImageNet-1k top-1 in Howard et al., 2017 (Table 7). The smallest variant in the family, targeted at extreme edge deployments.

Model Size

Parameters

pretrainedbool= False

Reserved for future pretrained-weight loading. Currently ignored.

**overridesobject= {}

Keyword overrides forwarded into MobileNetV1Config.

Returns

MobileNetV1ForImageClassification

Classifier with the MobileNet-v1 ( $\alpha = 0.25$ ) configuration applied (or with overrides merged on top of it).

Notes

See Howard et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications", arXiv:1704.04861, 2017, Table 7.

Examples

>>> import lucid
>>> from lucid.models.vision.mobilenet import mobilenet_v1_025_cls
>>> model = mobilenet_v1_025_cls()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)

Used by 1

lucid.models.vision.mobilenet

>>> import lucid >>> from lucid.models.vision.mobilenet import mobilenet_v1_025_cls >>> model = mobilenet_v1_025_cls() >>> x = lucid.randn(1, 3, 224, 224) >>> out = model(x) >>> out.logits.shape (1, 1000)