class

EfficientNetB7Weights

extendsWeightsEnum

EfficientNetB7Weights()

Pretrained weights for lucid.models.efficientnet_b7_cls.

compound-scaled B7 at 600 (66.3 M params, 37.75 GFLOPs, top-1 84.12%).

IMAGENET1K_V1WeightEntry

ImageNet-1k V1 checkpoint (top-1 84.122% / top-5 96.908%), sourced from torchvision/EfficientNet_B7_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_b7_cls
>>> model = efficientnet_b7_cls(pretrained=True).eval()