Views
No views yet
Long et al., 2015 — Fully Convolutional Networks for Semantic Segmentation (arXiv:1411.4038)
torchvision/FCN_ResNet101_Weights.COCO_WITH_VOC_LABELS_V1,
converted to Lucid-native safetensors.| Tag | miou | pixel_acc | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|---|
COCO_WITH_VOC_LABELS_V1 (default) | 63.7 | 91.9 | 54.3M | 232.738 | 207.67 MB | torchvision |
1import lucid.models as models
2from lucid.models.weights import FCNResNet101Weights
3
4# default tag
5model = models.fcn_resnet101(pretrained=True)
6
7# explicit tag (enum or string)
8model = models.fcn_resnet101(weights=FCNResNet101Weights.COCO_WITH_VOC_LABELS_V1)
9model = models.fcn_resnet101(pretrained="COCO_WITH_VOC_LABELS_V1")
10
11# preprocessing travels with the weights
12weights = FCNResNet101Weights.COCO_WITH_VOC_LABELS_V1
13preprocess = weights.transforms()
14out = model(preprocess(image)[None])
15# SemanticSegmentationOutput: per-pixel class logits (B, C, H, W)
16seg = out.logits.argmax(axis=1) # (B, H, W) class indicestorchvision/FCN_ResNet101_Weights.COCO_WITH_VOC_LABELS_V1 via
python -m tools.convert_weights fcn_resnet101 --tag COCO_WITH_VOC_LABELS_V1.
Key mapping + numerical parity verified against the source.bsd-3-clause — inherited from the original weights.@inproceedings{long2015fully,
title={Fully Convolutional Networks for Semantic Segmentation},
author={Long, Jonathan and Shelhamer, Evan and Darrell, Trevor},
booktitle={CVPR}, year={2015}
}