ResNeSt-26 feature-extracting backbone (no classification head).
Builds a ResNeSt with block repeats [2, 2, 2, 2]
over four stages — a middle-ground variant between the
lightweight ResNeSt-14 and the canonical ResNeSt-50. Uses
radix = 2 and stem_width = 32. Approximately 17.1M
parameters.
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored.
**overridesobject= {}Keyword overrides forwarded into
ResNeStConfig.Returns
ResNeStBackbone with the ResNeSt-26 configuration applied (or
with overrides merged on top of it).
Notes
See Zhang et al., "ResNeSt: Split-Attention Networks", CVPR Workshops 2022 (arXiv:2004.08955).
Examples
>>> import lucid
>>> from lucid.models.vision.resnest import resnest_26
>>> model = resnest_26()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.last_hidden_state.shape
(1, 2048, 7, 7)