mobilevitv2_100

Converted TIMM image classification model for LiteRT.

• Source architecture: mobilevitv2_100
• File: model.tflite

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 4.9
  • GMACs: 1.8
  • Activations (M): 16.1
  • Image size: 256 x 256
• Papers:
  • Separable Self-attention for Mobile Vision Transformers: https://arxiv.org/abs/2206.02680
• Original: https://github.com/apple/ml-cvnets
• Dataset: ImageNet-1k

Citation

@article{Mehta2022SeparableSF,
  title={Separable Self-attention for Mobile Vision Transformers},
  author={Sachin Mehta and Mohammad Rastegari},
  journal={ArXiv},
  year={2022},
  volume={abs/2206.02680}
}