Add LiteRT converted swin_small_patch4_window7_224

d321bda verified 13 days ago

1.93 kB

library_name: litert
base_model: timm/swin_small_patch4_window7_224.ms_in22k_ft_in1k
tags:
  - vision
  - image-classification
datasets:
  - imagenet-1k

swin_small_patch4_window7_224

Converted TIMM image classification model for LiteRT.

Source architecture: swin_small_patch4_window7_224
Source checkpoint: timm/swin_small_patch4_window7_224.ms_in22k_ft_in1k
File: model.tflite
Input: float32 tensor in NCHW layout, shape [1, 3, 224, 224]
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): 49.6
- GMACs: 8.8
- Activations (M): 27.5
- Image size: 224 x 224
Papers:
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows: https://arxiv.org/abs/2103.14030
Original: https://github.com/microsoft/Swin-Transformer
Dataset: ImageNet-1k
Pretrain Dataset: ImageNet-22k

Citation

@inproceedings{liu2021Swin,
  title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  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}}
}