Add LiteRT converted beit_large_patch16_384.in22k_ft_in22k_in1k

b72e032 verified about 1 month ago

2.17 kB

library_name: litert
base_model: timm/beit_large_patch16_384.in22k_ft_in22k_in1k
license: apache-2.0
tags:
  - vision
  - image-classification
  - timm
datasets:
  - imagenet-1k

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}}
}