InceptionNeXt-Small

Yu et al., 2024 — InceptionNeXt: When Inception Meets ConvNeXt (arXiv:2303.16900)

Lucid port of timm/inception_next_small.sail_in1k, converted to Lucid-native safetensors.

Available weights

Tag acc@1 acc@5 Params GFLOPs Size Source
SAIL_IN1K (default) 83.5 96.6 49.4M — 188.52 MB timm

Usage

import lucid.models as models
from lucid.models.weights import InceptionNeXtSmallWeights

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

# explicit tag (enum or string)
model = models.inception_next_small_cls(weights=InceptionNeXtSmallWeights.SAIL_IN1K)
model = models.inception_next_small_cls(pretrained="SAIL_IN1K")

# preprocessing travels with the weights
weights = InceptionNeXtSmallWeights.SAIL_IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/inception_next_small.sail_in1k via python -m tools.convert_weights inception_next_small --tag SAIL_IN1K. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{yu2024inceptionnext,
  title={InceptionNeXt: When Inception Meets ConvNeXt},
  author={Yu, Weihao and Zhou, Pan and Yan, Shuicheng and Wang, Xinchao},
  booktitle={CVPR}, year={2024}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train lucid-dl/inception-next-small

Paper for lucid-dl/inception-next-small

Evaluation results