README.md

metadata

library_name: litert
base_model: timm/repvit_m0_9.dist_300e_in1k
tags:
  - vision
  - image-classification
datasets:
  - imagenet-1k

repvit_m0_9

Converted TIMM image classification model for LiteRT.

• Source architecture: repvit_m0_9
• Source checkpoint: timm/repvit_m0_9.dist_300e_in1k
• File: model.tflite
• Input: float32 tensor in NCHW layout, shape [1, 3, 224, 224]
• Output: ImageNet-1K logits, shape [1, 1000]

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 5.5
  • GMACs: 0.8
  • Activations (M): 7.4
  • Image size: 224 x 224
• Papers:
  • RepViT: Revisiting Mobile CNN From ViT Perspective: https://arxiv.org/abs/2307.09283
• Original: https://github.com/THU-MIG/RepViT
• Dataset: ImageNet-1k

Citation

@misc{wang2023repvit,
  title={RepViT: Revisiting Mobile CNN From ViT Perspective}, 
  author={Ao Wang and Hui Chen and Zijia Lin and Hengjun Pu and Guiguang Ding},
  year={2023},
  eprint={2307.09283},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}