efficientformer_l3_cls(pretrained: bool | str = False, weights: EfficientFormerL3Weights | None = None, overrides: object = {})EfficientFormer-L3 image classifier (Li et al., 2022).
Combines the efficientformer_l3 backbone (depths= (4, 4, 12, 6), embed_dims=(64, 128, 320, 512)) with a final
LayerNorm, mean pool, and a distilled dual head (head +
head_dist) averaged at inference. ~31.4M parameters.
Model Size
Parameters
pretrainedbool or str= FalsePretrained-weight selector.
False → random init; True
→ the DEFAULT tag
(EfficientFormerL3Weights.SNAP_DIST_IN1K); a tag string
→ that specific checkpoint. Mutually exclusive with weights
(which wins if both are given).Explicit weights enum member. Takes precedence over
pretrained.**overridesobject= {}Keyword overrides on top of the canonical L3 config.
Returns
EfficientFormerForImageClassificationClassifier whose logits has shape (B, num_classes).
Notes
EfficientFormer-L3 reaches 82.4% top-1 on ImageNet-1k (Li
et al., 2022, Table 4). Pretrained weights are converted from
timm's efficientformer_l3.snap_dist_in1k and hosted under
lucid-dl/efficientformer-l3.
Examples
>>> import lucid
>>> from lucid.models.vision.efficientformer import efficientformer_l3_cls
>>> model = efficientformer_l3_cls(num_classes=1000)
>>> x = lucid.randn(1, 3, 224, 224)
>>> model(x).logits.shape
(1, 1000)