class

EfficientNetB6Weights

extendsWeightsEnum

EfficientNetB6Weights()

Pretrained weights for lucid.models.efficientnet_b6_cls.

compound-scaled B6 at 528 (43.0 M params, 19.07 GFLOPs, top-1 84.01%).

IMAGENET1K_V1WeightEntry

ImageNet-1k V1 checkpoint (top-1 84.008% / top-5 96.916%), sourced from torchvision/EfficientNet_B6_Weights.IMAGENET1K_V1.

DEFAULTWeightEntry

Alias for IMAGENET1K_V1.

Reference: Tan, Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks", ICML 2019 (arXiv:1905.11946).

>>> from lucid.models import efficientnet_b6_cls
>>> model = efficientnet_b6_cls(pretrained=True).eval()