Official implementation for our paper Back to MLP: A Simple Baseline for Human Motion Prediction, a simple-yet-effective network achieving SOTA performance.
In this paper, we propose a naive MLP-based network for human motion prediction. The network consists of only FCs, LayerNorms and Transpose. There is no non-linear activation in our network.
- PyTorch >= 1.5
- Numpy
- CUDA >= 10.1
- Easydict
- pickle
- einops
- scipy
- six
Download all the data and put them in the ./data directory.
Directory structure:
data
|-- h36m
| |-- S1
| |-- S5
| |-- S6
| |-- ...
| |-- S11Directory structure:
data
|-- amass
| |-- ACCAD
| |-- BioMotionLab_NTroje
| |-- CMU
| |-- ...
| |-- Transitions_mocapDirectory structure:
data
|-- 3dpw
| |-- sequenceFiles
| | |-- test
| | |-- train
| | |-- validationcd exps/baseline_h36m/
sh run.shcd exps/baseline_amass/
sh run.shcd exps/baseline_h36m/
python test.py --model-pth your/model/pathcd exps/baseline_amass/
#Test on AMASS
python test.py --model-pth your/model/path
#Test on 3DPW
python test_3dpw.py --model-pth your/model/path If you find this project useful in your research, please consider cite:
@article{guo2022back,
title={Back to MLP: A Simple Baseline for Human Motion Prediction},
author={Guo, Wen and Du, Yuming and Shen, Xi and Lepetit, Vincent and Xavier, Alameda-Pineda and Francesc, Moreno-Noguer},
journal={arXiv preprint arXiv:2207.01567},
year={2022}
}Feel free to contact Wen or Me or open a new issue if you have any questions.