mobilenet_075_cls(pretrained: bool = False, overrides: object = {})MobileNet-v1 image classifier at width multiplier .
Builds a MobileNetForImageClassification with the
paper-cited 0.75-width topology — approximately 2.6M parameters
and 68.4% ImageNet-1k top-1 in Howard et al., 2017 (Table 6).
Model Size
Parameters
pretrainedbool= FalseNo checkpoint is published for
mobilenet_075_cls, so True raises
NotImplementedError rather than return randomly initialised weights.
mobilenet_cls is the checkpointed variant.**overridesobject= {}Keyword overrides forwarded into
MobileNetConfig.Returns
MobileNetForImageClassificationClassifier with the MobileNet-v1 ()
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 6.
Examples
>>> import lucid
>>> from lucid.models.vision.mobilenet import mobilenet_075_cls
>>> model = mobilenet_075_cls()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)