mobilenet_v2_075_cls(pretrained: bool = False, overrides: object = {})MobileNet-v2 image classifier at width multiplier .
Builds a MobileNetV2ForImageClassification with the
0.75-width topology — 2.64M parameters. The 69.8% top-1 usually
quoted for this width comes from the TF model zoo, not from
Sandler et al., which tabulates only 1.0 and 1.4.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
MobileNetV2Config.Returns
MobileNetV2ForImageClassificationClassifier with the MobileNet-v2 ()
configuration applied (or with overrides merged on top
of it).
Notes
See Sandler et al., "MobileNetV2: Inverted Residuals and Linear Bottlenecks", CVPR 2018 (arXiv:1801.04381), Table 4.
Examples
>>> import lucid
>>> from lucid.models.vision.mobilenet_v2 import mobilenet_v2_075_cls
>>> model = mobilenet_v2_075_cls()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)