class

EfficientNetB1Weights

extendsWeightsEnum

EfficientNetB1Weights()

Pretrained weights for lucid.models.efficientnet_b1_cls.

compound-scaled B1 at 240 (7.8 M params, 0.69 GFLOPs, top-1 78.64%).

IMAGENET1K_V1WeightEntry

ImageNet-1k V1 checkpoint (top-1 78.642% / top-5 94.186%), sourced from torchvision/EfficientNet_B1_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_b1_cls
>>> model = efficientnet_b1_cls(pretrained=True).eval()