GoogLeNet

Szegedy et al., 2015 — Going Deeper with Convolutions (arXiv:1409.4842)

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

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
IMAGENET1K_V1 (default)	69.778	89.53	13.0M	1.498	49.71 MB	torchvision

Usage

import lucid.models as models
from lucid.models.weights import GoogLeNetWeights

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

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

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

Conversion

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

License

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

Citation

@inproceedings{szegedy2015going,
  title={Going Deeper with Convolutions},
  author={Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andrew},
  booktitle={CVPR}, pages={1--9}, year={2015}
}