cvt_13_cls

→CvTForImageClassification

cvt_13_cls(pretrained: bool | str = False, weights: CvT13Weights | None = None, overrides: object = {})

source edit

CvT-13 image classifier (Wu et al., 2021).

Combines the cvt_13 backbone with a mean pool + LayerNorm

single nn.Linear classification head. Default output is num_classes=1000 (ImageNet-1k). Approximately 20M parameters.

Model Size

Parameters

pretrainedbool= False

If True, loads ImageNet-1k pretrained weights when available. Defaults to False.

weights(CvT13Weights, optional, keyword - only)= None

Explicit weights enum member; takes precedence over pretrained.

**overridesobject= {}

Keyword overrides on top of the canonical CvT-13 config.

Returns

CvTForImageClassification

Classifier returning ImageClassificationOutput whose logits has shape (B, num_classes).

Notes

CvT-13 reaches 81.6% top-1 on ImageNet-1k at 224x224 (Wu et al., 2021, Table 1).

Examples

>>> import lucid
>>> from lucid.models.vision.cvt import cvt_13_cls
>>> model = cvt_13_cls(num_classes=1000)
>>> x = lucid.randn(1, 3, 224, 224)
>>> model(x).logits.shape
(1, 1000)

Used by 1

lucid.models.vision.cvt