metadata
library_name: lucid
license: bsd-3-clause
tags:
- image-classification
- alexnet
- lucid
datasets:
- imagenet-1k
pipeline_tag: image-classification
model-index:
- name: alexnet-cls
results:
- task:
type: image-classification
dataset:
name: ImageNet-1K
type: imagenet-1k
metrics:
- type: acc@1
value: 56.522
- type: acc@5
value: 79.066
AlexNet
Krizhevsky et al., 2012 — ImageNet Classification with Deep Convolutional Neural Networks (NIPS); single-stream channel widths from Krizhevsky 2014 (arXiv:1404.5997).
Lucid port of torchvision/AlexNet_Weights.IMAGENET1K_V1,
converted to Lucid-native safetensors.
Available weights
| Tag | acc@1 | acc@5 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|---|
IMAGENET1K_V1 (default) |
56.522 | 79.066 | 61.1M | 0.714 | 233.08 MB | torchvision |
Usage
import lucid.models as models
from lucid.models.weights import AlexNetWeights
# default tag
model = models.alexnet_cls(pretrained=True)
# explicit tag (enum or string)
model = models.alexnet_cls(weights=AlexNetWeights.IMAGENET1K_V1)
model = models.alexnet_cls(pretrained="IMAGENET1K_V1")
# preprocessing travels with the weights
weights = AlexNetWeights.IMAGENET1K_V1
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits
Conversion
Converted from torchvision/AlexNet_Weights.IMAGENET1K_V1 via
python -m tools.convert_weights alexnet_cls --tag IMAGENET1K_V1.
Key mapping + numerical parity verified against the source.
License
bsd-3-clause — inherited from the original weights.
Citation
@inproceedings{krizhevsky2012imagenet,
title={ImageNet Classification with Deep Convolutional Neural Networks},
author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},
booktitle={NIPS}, year={2012}
}
@article{krizhevsky2014oneweirdtrick,
title={One weird trick for parallelizing convolutional neural networks},
author={Krizhevsky, Alex},
journal={arXiv preprint arXiv:1404.5997}, year={2014}
}