TNT

Paper：Transformer in Transformer
Origin Repo：huawei-noah/noah-research
Code：tnt.py

Evaluate Transforms：

# backend: pil
# input_size: 224x224
transforms = T.Compose([
    T.Resize(248, interpolation='bicubic'),
    T.CenterCrop(224),
    T.ToTensor(),
    T.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

Model Details：

Model Model Name Params (M) FLOPs (G) Top-1 (%) Top-5 (%) Pretrained Model

TNT-S tnt_s 23.8 5.2 81.53 95.74 Download

Citation：

@misc{han2021transformer,
    title={Transformer in Transformer}, 
    author={Kai Han and An Xiao and Enhua Wu and Jianyuan Guo and Chunjing Xu and Yunhe Wang},
    year={2021},
    eprint={2103.00112},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}