beit_large_patch16_384.in22k_ft_in22k_in1k

Converted TIMM image classification model for LiteRT.

• Source architecture: beit_large_patch16_384
• Source checkpoint: timm/beit_large_patch16_384.in22k_ft_in22k_in1k
• File: model.tflite
• Runtime target: CPU only. GPU delegation is not expected for this converted file.
• Input: float32 tensor in NCHW layout, shape [1, 3, 384, 384]
• Output: ImageNet-1K logits, shape [1, 1000]
• Converted artifact size: 1.61 GiB
• Weight storage: inline

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 305.0
  • GMACs: 191.2
  • Activations (M): 270.2
  • Image size: 384 x 384
• Papers:
  • BEiT: BERT Pre-Training of Image Transformers: https://arxiv.org/abs/2106.08254
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
• Dataset: ImageNet-1k
• Pretrain Dataset: ImageNet-22k
• Original: https://github.com/microsoft/unilm/tree/master/beit

Citation

@article{bao2021beit,
  title={Beit: Bert pre-training of image transformers},
  author={Bao, Hangbo and Dong, Li and Piao, Songhao and Wei, Furu},
  journal={arXiv preprint arXiv:2106.08254},
  year={2021}
}

@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}