Contents

• Contents
  • Wave-MLP Description
  • Model architecture
  • Dataset
  • Environment Requirements
  • Script description
    • Script and sample code
  • Eval process
    • Usage
    • Launch
    • Result
  • Description of Random Situation
  • ModelZoo Homepage

Wave-MLP Description

To dynamically aggregate tokens, Wave-MLP proposes to represent each token as a wave function with two parts, amplitude and phase. Amplitude is the original feature and the phase term is a complex value changing according to the semantic contents of input images.

Paper: Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu, Yunhe Wang. An Image Patch is a Wave: Phase-Aware Vision MLP. arxiv 2111.12294.

Model architecture

A block of Wave-MLP is shown below:

Dataset

Dataset used: [ImageNet2012]

• Dataset size 224*224 colorful images in 1000 classes
  • Train：1,281,167 images
  • Test： 50,000 images
• Data format：jpeg
  • Note：Data will be processed in dataset.py

Environment Requirements

• Hardware(Ascend/GPU)
  • Prepare hardware environment with Ascend or GPU.
• Framework
  • MindSpore
• For more information, please check the resources below£º
  • MindSpore Tutorials
  • MindSpore Python API

Script description

Script and sample code

WalveMlp
├── eval.py # inference entry
├── fig
│   └── wavemlp.png # the illustration of wave_mlp network
├── readme.md # Readme
└── src
    ├── dataset.py # dataset loader
    └── wave_mlp.py # wave_mlp network

Eval process

Usage

After installing MindSpore via the official website, you can start evaluation as follows:

Launch

# infer example
  # python
  GPU: python eval.py --dataset_path dataset --platform GPU --checkpoint_path [CHECKPOINT_PATH]
  # shell
  bash ./scripts/run_eval.sh [DATA_PATH] [PLATFORM] [CHECKPOINT_PATH]

checkpoint can be downloaded at https://download.mindspore.cn/model_zoo/research/cv/wavemlp/.

Result

result: {'acc': 0.807} ckpt= ./WaveMLP_T.ckpt

Inference Performance

WaveMlp infer on ImageNet2012

Description of Random Situation

In dataset.py, we set the seed inside "create_dataset" function. We also use random seed in train.py.

ModelZoo Homepage

Please check the official homepage.