Views
No views yet
He et al., 2015 — Deep Residual Learning for Image Recognition (arXiv:1512.03385)
torchvision/ResNet101_Weights.IMAGENET1K_V1,
converted to Lucid-native safetensors.| Tag | acc@1 | acc@5 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|---|
IMAGENET1K_V1 (default) | 77.374 | 93.546 | 44.5M | 7.801 | 170.4 MB | torchvision |
1import lucid.models as models
2from lucid.models.weights import ResNet101Weights
3
4# default tag
5model = models.resnet_101_cls(pretrained=True)
6
7# explicit tag (enum or string)
8model = models.resnet_101_cls(weights=ResNet101Weights.IMAGENET1K_V1)
9model = models.resnet_101_cls(pretrained="IMAGENET1K_V1")
10
11# preprocessing travels with the weights
12weights = ResNet101Weights.IMAGENET1K_V1
13preprocess = weights.transforms()
14logits = model(preprocess(image)[None]).logitstorchvision/ResNet101_Weights.IMAGENET1K_V1 via
python -m tools.convert_weights resnet_101 --tag IMAGENET1K_V1.
Key mapping + numerical parity verified against the source.bsd-3-clause — inherited from the original weights.@inproceedings{he2016deep,
title={Deep Residual Learning for Image Recognition},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={CVPR}, year={2016}
}