lucid-dl/mobilenet-v1

MobileNet V1

Howard et al., 2017 — MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861)

Lucid port of timm/mobilenetv1_100.ra4_e3600_r224_in1k, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
RA4_E3600_R224_IN1K (default)	0.0	0.0	4.2M	—	16.24 MB	timm

Usage

import lucid.models as models
from lucid.models.weights import MobileNetV1Weights

# default tag
model = models.mobilenet_v1_cls(pretrained=True)

# explicit tag (enum or string)
model = models.mobilenet_v1_cls(weights=MobileNetV1Weights.RA4_E3600_R224_IN1K)
model = models.mobilenet_v1_cls(pretrained="RA4_E3600_R224_IN1K")

# preprocessing travels with the weights
weights = MobileNetV1Weights.RA4_E3600_R224_IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/mobilenetv1_100.ra4_e3600_r224_in1k via python -m tools.convert_weights mobilenet_v1 --tag RA4_E3600_R224_IN1K. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@article{howard2017mobilenets,
  title={MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
  author={Howard, Andrew G. and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig},
  journal={arXiv preprint arXiv:1704.04861}, year={2017}
}