Views
No views yet
Liu et al., 2022 — A ConvNet for the 2020s (arXiv:2201.03545)
torchvision/ConvNeXt_Large_Weights.IMAGENET1K_V1,
converted to Lucid-native safetensors.| Tag | acc@1 | acc@5 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|---|
IMAGENET1K_V1 (default) | 84.414 | 96.976 | 197.8M | 34.361 | 754.45 MB | torchvision |
1import lucid.models as models
2from lucid.models.weights import ConvNeXtLargeWeights
3
4# default tag
5model = models.convnext_large_cls(pretrained=True)
6
7# explicit tag (enum or string)
8model = models.convnext_large_cls(weights=ConvNeXtLargeWeights.IMAGENET1K_V1)
9model = models.convnext_large_cls(pretrained="IMAGENET1K_V1")
10
11# preprocessing travels with the weights
12weights = ConvNeXtLargeWeights.IMAGENET1K_V1
13preprocess = weights.transforms()
14logits = model(preprocess(image)[None]).logitstorchvision/ConvNeXt_Large_Weights.IMAGENET1K_V1 via
python -m tools.convert_weights convnext_large --tag IMAGENET1K_V1.
Key mapping + numerical parity verified against the source.bsd-3-clause — inherited from the original weights.@inproceedings{liu2022convnet,
title={A ConvNet for the 2020s},
author={Liu, Zhuang and Mao, Hanzi and Wu, Chao-Yuan and Feichtenhofer, Christoph and Darrell, Trevor and Xie, Saining},
booktitle={CVPR}, year={2022}
}