resnext_101_64x4d_cls(pretrained: bool = False, overrides: object = {})ResNeXt-101 (64x4d) image classifier — the paper's headline model.
Builds a ResNeXtForImageClassification with cardinality
and width per group , plus a
lucid.nn.Linear classifier projecting 2048 →
config.num_classes.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
ResNeXtConfig.Returns
ResNeXtForImageClassificationClassifier with the ResNeXt-101 (64x4d) configuration applied
(or with overrides merged on top of it).
Notes
Xie et al., CVPR 2017, Table 4: 20.4% top-1 / 5.3% top-5 error at 224x224 — the result §5.1's headline refers to, and the basis of the 2nd-place ILSVRC-2016 submission.
Examples
>>> import lucid
>>> from lucid.models.vision.resnext import resnext_101_64x4d_cls
>>> model = resnext_101_64x4d_cls(num_classes=10)
>>> model(lucid.randn(1, 3, 224, 224)).logits.shape
(1, 10)