eva_large_patch14_336.in22k_ft_in1k

Converted TIMM image classification model for LiteRT.

• Source architecture: eva_large_patch14_336
• Source checkpoint: timm/eva_large_patch14_336.in22k_ft_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, 336, 336]
• Output: ImageNet-1K logits, shape [1, 1000]
• Converted artifact size: 1.13 GiB
• Weight storage: inline

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 304.5
  • GMACs: 191.1
  • Activations (M): 270.2
  • Image size: 336 x 336
• Papers:
  • EVA: Exploring the Limits of Masked Visual Representation Learning at Scale: https://arxiv.org/abs/2211.07636
• Pretrain Dataset: ImageNet-22k
• Dataset: ImageNet-1k
• Original:
  • https://github.com/baaivision/EVA
  • https://huggingface.co/BAAI/EVA

Citation

@article{EVA,
  title={EVA: Exploring the Limits of Masked Visual Representation Learning at Scale},
  author={Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
  journal={arXiv preprint arXiv:2211.07636},
  year={2022}
}

@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}}
}