Repository files navigation

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 byJulieta Martinez andJavier Romero.

• h5py -- to save samples
• Tensorflow 1.2 or later.

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.gitcd human-motion-predictionmkdir datacd datawget http://www.cs.stanford.edu/people/ashesh/h3.6m.zipunzip h3.6m.ziprm h3.6m.zipcd ..

For a quick demo, you can train for a few iterations and visualize the outputsof 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

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

python src/baselines.py

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

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 totensorboard. You can track the progress during training by typingtensorboard --logdir experiments in the terminal and checking the board underhttp://127.0.1.1:6006/ in your browser (occasionally, tensorboard might pick another url).

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}}

• Pytorch by@enriccorona

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

MIT