Skip to content

Simple baselines and RNNs for predicting human motion in tensorflow. Presented at CVPR 17.

License

Notifications You must be signed in to change notification settings

Gloriabhsfer/human-motion-prediction

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

human-motion-prediction

This is the code for the paper

Julieta Martinez, Michael J. Black, Javier Romero. On human motion prediction using recurrent neural networks. In CVPR 17.

It can be found on arxiv as well: https://arxiv.org/pdf/1705.02445.pdf

The code in this repository was written by Julieta Martinez and Javier Romero.

Dependencies

Get this code and the data

First things first, clone this repo and get the human3.6m dataset on exponential map format.

git clone https://github.com/una-dinosauria/human-motion-prediction.git
cd human-motion-prediction
mkdir data
cd data
wget http://www.cs.stanford.edu/people/ashesh/h3.6m.zip
unzip h3.6m.zip
rm h3.6m.zip
cd ..

Quick demo and visualization

For a quick demo, you can train for a few iterations and visualize the outputs of your model.

To train, run

python src/translate.py --action walking --seq_length_out 25 --iterations 10000

To save some samples of the model, run

python src/translate.py --action walking --seq_length_out 25 --iterations 10000 --sample --load 10000

Finally, to visualize the samples run

python src/forward_kinematics.py

This should create a visualization similar to this one



Running average baselines

To reproduce the running average baseline results from our paper, run

python src/baselines.py

RNN models

To train and reproduce the results of our models, use the following commands

model arguments training time (gtx 1080) notes
Sampling-based loss (SA) python src/translate.py --action walking --seq_length_out 25 45s / 1000 iters Realistic long-term motion, loss computed over 1 second.
Residual (SA) python src/translate.py --residual_velocities --action walking 35s / 1000 iters
Residual unsup. (MA) python src/translate.py --residual_velocities --learning_rate 0.005 --omit_one_hot 65s / 1000 iters
Residual sup. (MA) python src/translate.py --residual_velocities --learning_rate 0.005 65s / 1000 iters best quantitative.
Untied python src/translate.py --residual_velocities --learning_rate 0.005 --architecture basic 70s / 1000 iters

You can substitute the --action walking parameter for any action in

["directions", "discussion", "eating", "greeting", "phoning",
 "posing", "purchases", "sitting", "sittingdown", "smoking",
 "takingphoto", "waiting", "walking", "walkingdog", "walkingtogether"]

or --action all (default) to train on all actions.

The code will log the error in Euler angles for each action to tensorboard. You can track the progress during training by typing tensorboard --logdir experiments in the terminal and checking the board under http://127.0.1.1:6006/ in your browser (occasionally, tensorboard might pick another url).

Citing

If you use our code, please cite our work

@inproceedings{julieta2017motion,
  title={On human motion prediction using recurrent neural networks},
  author={Martinez, Julieta and Black, Michael J. and Romero, Javier},
  booktitle={CVPR},
  year={2017}
}

Acknowledgments

The pre-processed human 3.6m dataset and some of our evaluation code (specially under src/data_utils.py) was ported/adapted from SRNN by @asheshjain399.

Licence

MIT

About

Simple baselines and RNNs for predicting human motion in tensorflow. Presented at CVPR 17.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%