VGG-13

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

Lucid port of torchvision/VGG13_Weights.IMAGENET1K_V1, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
IMAGENET1K_V1 (default)	69.928	89.246	133.0M	11.308	507.54 MB	torchvision

Usage

import lucid.models as models
from lucid.models.weights import VGG13Weights

# default tag
model = models.vgg_13_cls(pretrained=True)

# explicit tag (enum or string)
model = models.vgg_13_cls(weights=VGG13Weights.IMAGENET1K_V1)
model = models.vgg_13_cls(pretrained="IMAGENET1K_V1")

# preprocessing travels with the weights
weights = VGG13Weights.IMAGENET1K_V1
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from torchvision/VGG13_Weights.IMAGENET1K_V1 via python -m tools.convert_weights vgg_13 --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}
}