vgg-16

VGG-16

Simonyan & Zisserman, 2015 — Very Deep Convolutional Networks for Large-Scale Image Recognition (arXiv:1409.1556)

Lucid port of torchvision/VGG16_Weights.IMAGENET1K_V1, converted to Lucid-native safetensors.

Available weights

Usage

import lucid.models as models
from lucid.models.weights import VGG16Weights

# default tag
model = models.vgg_16_cls(pretrained=True)

# explicit tag (enum or string)
model = models.vgg_16_cls(weights=VGG16Weights.IMAGENET1K_V1)
model = models.vgg_16_cls(pretrained="IMAGENET1K_V1")

# preprocessing travels with the weights
weights = VGG16Weights.IMAGENET1K_V1
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from torchvision/VGG16_Weights.IMAGENET1K_V1 via python -m tools.convert_weights vgg_16 --tag IMAGENET1K_V1. Key mapping + numerical parity verified against the source.

License

bsd-3-clause — inherited from the original weights.

Citation

@inproceedings{simonyan2015very,
  title={Very Deep Convolutional Networks for Large-Scale Image Recognition},
  author={Simonyan, Karen and Zisserman, Andrew},
  booktitle={ICLR}, year={2015}
}