This is the code for the paper
Wei Mao, Miaomiao Liu, Mathieu Salzmann. History Repeats Itself: Human Motion Prediction via Motion Attention. In ECCV 20.
- cuda 10.0
- Python 3.6
- Pytorch >1.0.0 (Tested on 1.1.0 and 1.3.0)
Human3.6m in exponential map can be downloaded from here.
Directory structure:
H3.6m
|-- S1
|-- S5
|-- S6
|-- ...
`-- S11AMASS from their official website..
Directory structure:
amass
|-- ACCAD
|-- BioMotionLab_NTroje
|-- CMU
|-- ...
`-- Transitions_mocap3DPW from their official website.
Directory structure:
3dpw
|-- imageFiles
| |-- courtyard_arguing_00
| |-- courtyard_backpack_00
| |-- ...
`-- sequenceFiles
|-- test
|-- train
`-- validationPut the all downloaded datasets in ./datasets directory.
All the running args are defined in opt.py. We use following commands to train on different datasets and representations. To train,
python main_h36m_3d.py --kernel_size 10 --dct_n 20 --input_n 50 --output_n 10 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 66python main_h36m_ang.py --kernel_size 10 --dct_n 20 --input_n 50 --output_n 10 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 48python main_amass_3d.py --kernel_size 10 --dct_n 35 --input_n 50 --output_n 25 --skip_rate 5 --batch_size 128 --test_batch_size 128 --in_features 54 To evaluate the pretrained model,
python main_h36m_3d_eval.py --is_eval --kernel_size 10 --dct_n 20 --input_n 50 --output_n 25 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 66 --ckpt ./checkpoint/pretrained/h36m_3d_in50_out10_dctn20/python main_h36m_ang_eval.py --is_eval --kernel_size 10 --dct_n 20 --input_n 50 --output_n 25 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 48 --ckpt ./checkpoint/pretrained/h36m_ang_in50_out10_dctn20/python main_amass_3d_eval.py --is_eval --kernel_size 10 --dct_n 35 --input_n 50 --output_n 25 --skip_rate 5 --batch_size 128 --test_batch_size 128 --in_features 54 --ckpt ./checkpoint/pretrained/amass_3d_in50_out25_dctn30/If you use our code, please cite our work
@inproceedings{wei2020his,
title={History Repeats Itself: Human Motion Prediction via Motion Attention},
author={Wei, Mao and Miaomiao, Liu and Mathieu, Salzemann},
booktitle={ECCV},
year={2020}
}
The overall code framework (dataloading, training, testing etc.) is adapted from 3d-pose-baseline.
The predictor model code is adapted from LTD.
Some of our evaluation code and data process code was adapted/ported from Residual Sup. RNN by Julieta.
MIT
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent