mobilenet-v3-large

MobileNet V3 Large

Howard et al., 2019 — Searching for MobileNetV3 (arXiv:1905.02244)

Lucid port of torchvision/MobileNet_V3_Large_Weights.IMAGENET1K_V1, converted to Lucid-native safetensors.

Available weights

Usage

import lucid.models as models
from lucid.models.weights import MobileNetV3LargeWeights

# default tag
model = models.mobilenet_v3_large_cls(pretrained=True)

# explicit tag (enum or string)
model = models.mobilenet_v3_large_cls(weights=MobileNetV3LargeWeights.IMAGENET1K_V1)
model = models.mobilenet_v3_large_cls(pretrained="IMAGENET1K_V1")

# preprocessing travels with the weights
weights = MobileNetV3LargeWeights.IMAGENET1K_V1
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from torchvision/MobileNet_V3_Large_Weights.IMAGENET1K_V1 via python -m tools.convert_weights mobilenet_v3_large --tag IMAGENET1K_V1. Key mapping + numerical parity verified against the source.

License

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

Citation

@inproceedings{howard2019searching,
  title={Searching for MobileNetV3},
  author={Howard, Andrew and Sandler, Mark and Chu, Grace and Chen, Liang-Chieh and Chen, Bo and Tan, Mingxing and Wang, Weijun and Zhu, Yukun and Pang, Ruoming and Vasudevan, Vijay and others},
  booktitle={ICCV}, year={2019}
}