mobilevitv2_125

Converted TIMM image classification model for LiteRT.

• Source architecture: mobilevitv2_125
• Source checkpoint: timm/mobilevitv2_125.cvnets_in1k
• File: model.tflite
• Input: float32 tensor in NCHW layout, shape [1, 3, 256, 256]
• Output: ImageNet-1K logits, shape [1, 1000]

Runtime Status

• CPU smoke test: passed with LiteRT CompiledModel.
• GPU delegation: currently blocked for this model by rank-5 tensor patterns in the GPU backend, mostly RESHAPE, TRANSPOSE, and related window/attention operations. The model is published as CPU-ready while GPU support is being improved.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 7.5
  • GMACs: 2.9
  • Activations (M): 20.1
  • 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}
}