Add LiteRT converted xcit_tiny_24_p8_224

4ae8a9c verified about 2 months ago

1.03 kB

library_name: litert
base_model: timm/xcit_tiny_24_p8_224.fb_in1k
tags:
  - vision
  - image-classification
datasets:
  - imagenet-1k

xcit_tiny_24_p8_224

Converted TIMM image classification model for LiteRT.

Source architecture: xcit_tiny_24_p8_224
File: model.tflite

Model Details

Model Type: Image classification / feature backbone
Model Stats:
- Params (M): 12.1
- GMACs: 9.2
- Activations (M): 45.4
- Image size: 224 x 224
Papers:
- XCiT: Cross-Covariance Image Transformers: https://arxiv.org/abs/2106.09681
Dataset: ImageNet-1k
Original: https://github.com/facebookresearch/xcit

Citation

@article{el2021xcit,
  title={XCiT: Cross-Covariance Image Transformers},
  author={El-Nouby, Alaaeldin and Touvron, Hugo and Caron, Mathilde and Bojanowski, Piotr and Douze, Matthijs and Joulin, Armand and Laptev, Ivan and Neverova, Natalia and Synnaeve, Gabriel and Verbeek, Jakob and others},
  journal={arXiv preprint arXiv:2106.09681},
  year={2021}
}