class

EfficientNetB0Weights

extendsWeightsEnum

EfficientNetB0Weights()

Pretrained weights for lucid.models.efficientnet_b0_cls.

baseline B0 at 224 (5.3 M params, 0.39 GFLOPs, top-1 77.69%).

IMAGENET1K_V1WeightEntry

ImageNet-1k V1 checkpoint (top-1 77.692% / top-5 93.532%), sourced from torchvision/EfficientNet_B0_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_b0_cls
>>> model = efficientnet_b0_cls(pretrained=True).eval()