EfficientNet-B0

Tan & Le, 2019 — EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946)

Lucid port of torchvision/EfficientNet_B0_Weights.IMAGENET1K_V1, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
IMAGENET1K_V1 (default)	77.692	93.532	5.3M	0.386	20.37 MB	torchvision

Usage

import lucid.models as models
from lucid.models.weights import EfficientNetB0Weights

# default tag
model = models.efficientnet_b0_cls(pretrained=True)

# explicit tag (enum or string)
model = models.efficientnet_b0_cls(weights=EfficientNetB0Weights.IMAGENET1K_V1)
model = models.efficientnet_b0_cls(pretrained="IMAGENET1K_V1")

# preprocessing travels with the weights
weights = EfficientNetB0Weights.IMAGENET1K_V1
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from torchvision/EfficientNet_B0_Weights.IMAGENET1K_V1 via python -m tools.convert_weights efficientnet_b0 --tag IMAGENET1K_V1. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{tan2019efficientnet,
  title={EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks},
  author={Tan, Mingxing and Le, Quoc},
  booktitle={ICML}, year={2019}
}