cspdarknet_53_cls(pretrained: bool | str = False, weights: CSPDarknet53Weights | None = None, overrides: object = {})CSPDarknet-53 image classifier — paper Table 1, 27.6M
params, ImageNet-1k acc@1 ~80.1% (timm ra_in1k recipe).
Model Size
Parameters
pretrainedbool or str= FalseFalse returns randomly-initialised weights; True loads
the default entry of CSPDarknet53Weights; a string
selects a named entry from that enum.Explicit weight-enum member overriding
pretrained.**overridesobject= {}Per-field overrides forwarded to
CSPNetConfig.Returns
CSPNetForImageClassificationThe configured classifier.
Notes
Reference: Wang et al., "CSPNet: A New Backbone that can Enhance Learning Capability of CNN", CVPRW 2020 (arXiv:1911.11929).
Examples
>>> import lucid
>>> from lucid.models.vision.cspnet import cspdarknet_53_cls
>>> model = cspdarknet_53_cls()
>>> out = model(lucid.randn(1, 3, 224, 224))
>>> out.logits.shape
(1, 1000)