efficientnet-b7 / README.md
ChanLumerico's picture
Fix usage example: import weights enum from lucid.models.weights
3955faf verified
metadata
library_name: lucid
license: apache-2.0
tags:
  - image-classification
  - efficientnet
  - lucid
datasets:
  - imagenet-1k
pipeline_tag: image-classification
model-index:
  - name: efficientnet-b7
    results:
      - task:
          type: image-classification
        dataset:
          name: ImageNet-1K
          type: imagenet-1k
        metrics:
          - type: acc@1
            value: 84.122
          - type: acc@5
            value: 96.908

EfficientNet-B7

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

Lucid port of torchvision/EfficientNet_B7_Weights.IMAGENET1K_V1, converted to Lucid-native safetensors.

Available weights

Tag acc@1 acc@5 Params GFLOPs Size Source
IMAGENET1K_V1 (default) 84.122 96.908 66.3M 37.746 254.4 MB torchvision

Usage

import lucid.models as models
from lucid.models.weights import EfficientNetB7Weights

# default tag
model = models.efficientnet_b7_cls(pretrained=True)

# explicit tag (enum or string)
model = models.efficientnet_b7_cls(weights=EfficientNetB7Weights.IMAGENET1K_V1)
model = models.efficientnet_b7_cls(pretrained="IMAGENET1K_V1")

# preprocessing travels with the weights
weights = EfficientNetB7Weights.IMAGENET1K_V1
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from torchvision/EfficientNet_B7_Weights.IMAGENET1K_V1 via python -m tools.convert_weights efficientnet_b7 --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}
}