Skip to content

Latest commit

 

History

History
44 lines (37 loc) · 2.42 KB

coat.md

File metadata and controls

44 lines (37 loc) · 2.42 KB
Raw

CoaT

  • Paper：Co-Scale Conv-Attentional Image Transformers

  • Origin Repo：mlpc-ucsd/CoaT

  • Code：coat.py

  • Evaluate Transforms：

    # backend: pil
# input_size: 224x224
transforms = T.Compose([
    T.Resize(248, interpolation='bicubic'),
    T.CenterCrop(224),
    T.ToTensor(),
    T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

  • Model Details：

    Model Model Name Params (M) FLOPs (G) Top-1 (%) Top-5 (%) Pretrained Model
    CoaT-tiny coat_ti 5.5 4.4 78.45 94.07 Download
    CoaT-mini coat_m 10.0 6.8 81.09 95.25 Download
    CoaT-lite-tiny coat_lite_ti 5.7 1.6 77.51 93.92 Download
    CoaT-lite-mini coat_lite_m 11.0 2.0 79.10 94.61 Download

  • Citation：

    @misc{xu2021coscale,
    title={Co-Scale Conv-Attentional Image Transformers}, 
    author={Weijian Xu and Yifan Xu and Tyler Chang and Zhuowen Tu},
    year={2021},
    eprint={2104.06399},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}