MaxViT-Small

Tu et al., 2022 — MaxViT: Multi-Axis Vision Transformer (arXiv:2204.01697)

Lucid port of timm/maxvit_small_tf_224.in1k, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
IN1K (default)	84.45	96.98	68.9M	—	263.27 MB	timm

Usage

import lucid.models as models
from lucid.models.weights import MaxViTSmallWeights

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

# explicit tag (enum or string)
model = models.maxvit_small_cls(weights=MaxViTSmallWeights.IN1K)
model = models.maxvit_small_cls(pretrained="IN1K")

# preprocessing travels with the weights
weights = MaxViTSmallWeights.IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/maxvit_small_tf_224.in1k via python -m tools.convert_weights maxvit_small --tag IN1K. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{tu2022maxvit,
  title={MaxViT: Multi-Axis Vision Transformer},
  author={Tu, Zhengzhong and Talebi, Hossein and Zhang, Han and Yang, Feng and Milanfar, Peyman and Bovik, Alan and Li, Yinxiao},
  booktitle={ECCV}, year={2022}
}