CrossViT-9

Chen et al., 2021 — CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification (arXiv:2103.14899)

Lucid port of timm/crossvit_9_240.in1k, converted to Lucid-native safetensors.

Available weights

Tag	acc@1	acc@5	Params	GFLOPs	Size	Source
IN1K (default)	73.9	—	8.6M	—	32.65 MB	timm

Usage

import lucid.models as models
from lucid.models.weights import CrossViT9Weights

# default tag
model = models.crossvit_9_cls(pretrained=True)

# explicit tag (enum or string)
model = models.crossvit_9_cls(weights=CrossViT9Weights.IN1K)
model = models.crossvit_9_cls(pretrained="IN1K")

# preprocessing travels with the weights
weights = CrossViT9Weights.IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/crossvit_9_240.in1k via python -m tools.convert_weights crossvit_9 --tag IN1K. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{chen2021crossvit,
  title={CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification},
  author={Chen, Chun-Fu (Richard) and Fan, Quanfu and Panda, Rameswar},
  booktitle={ICCV}, year={2021}
}