sk_resnext_50_32x4d_cls(pretrained: bool = False, overrides: object = {})SK-ResNeXt-50 32×4d image classifier — the paper's SKNet-50.
Builds an SKNetForImageClassification with the
ResNeXt-style SK backbone (cardinality = 32,
base_width = 4) followed by global average pooling and a
linear projection to config.num_classes. Approximately
27.5M parameters and 77.5% ImageNet-1k top-1 accuracy in
Li et al., 2019 (Table 1, SKNet-50 row).
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
SKNetConfig.Returns
SKNetForImageClassificationClassifier with the SK-ResNeXt-50-32×4d configuration
applied (or with overrides merged on top of it).
Notes
See Li et al., "Selective Kernel Networks", CVPR 2019 (arXiv:1903.06586), Table 1 (SKNet-50 row).
Examples
>>> import lucid
>>> from lucid.models.vision.sknet import sk_resnext_50_32x4d_cls
>>> model = sk_resnext_50_32x4d_cls()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.logits.shape
(1, 1000)