MobileNet-v4-Conv-Large

Qin et al., 2024 — MobileNetV4: Universal Models for the Mobile Ecosystem (arXiv:2404.10518)

Lucid port of timm/mobilenetv4_conv_large.e600_r384_in1k, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
E600_R384_IN1K (default)	82.974	96.244	32.6M	—	124.96 MB	timm

Usage

import lucid.models as models
from lucid.models.weights import MobileNetV4ConvLargeWeights

# default tag
model = models.mobilenet_v4_conv_large_cls(pretrained=True)

# explicit tag (enum or string)
model = models.mobilenet_v4_conv_large_cls(weights=MobileNetV4ConvLargeWeights.E600_R384_IN1K)
model = models.mobilenet_v4_conv_large_cls(pretrained="E600_R384_IN1K")

# preprocessing travels with the weights
weights = MobileNetV4ConvLargeWeights.E600_R384_IN1K
preprocess = weights.transforms()
out = model(preprocess(image)[None])
logits = out.logits  # (B, num_classes)

Conversion

Converted from timm/mobilenetv4_conv_large.e600_r384_in1k via python -m tools.convert_weights mobilenet_v4_conv_large --tag E600_R384_IN1K. Key set, tensor shapes and a strict load verified against a freshly built Lucid model.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{qin2024mobilenetv4,
  title={MobileNetV4: Universal Models for the Mobile Ecosystem},
  author={Qin, Danfeng and Leichner, Chas and Delakis, Manolis and Fornoni, Marco and Luo, Shixin and Yang, Fan and Wang, Weijun and Banbury, Colby and Ye, Chengxi and Akin, Berkin and others},
  booktitle={ECCV}, year={2024}
}