Skip to content
pytorch version of Generating Recognizable Long-term Articulated Objects Motion via Spatio-Temporal Hierarchical Recurrent Network
Python Shell
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
src
.gitignore
LICENSE
README.md
fig2.png

README.md

Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network

This is the pytorch version, python code of our paper Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network.
Please follow the introduction below to reproduce our results .

Paper and revisions

Our paper is available at arXiv

Based on the version V1 at arXiv, we have several revisions.

  • Redrew Figure 4:

    Fig 4

  • Modified the caption of Figure 4:

    exchange the locations of the word 'orange' and 'blue'.

Required packages

  • Anaconda is highly recommend

  • Pytorch >= 1.2

  • Matplotlib = 3.0.1

  • FFMPEG

    Note that any Matplotlib version > 3.0.1 cannot guarantee the correct operation of the program due to some compatibility issues.

Dataset download

  • H3.6m dataset

    cd src
    sh ./data/h3.6m/download_h3.6m.sh
  • Mouse dataset

    cd src
    sh ./data/Mouse/download_mouse.sh

Reproduce our results

We save our model in the checkpoint folder. Our code will search a checkpoint automatically according to your settings.

cd src
python train.py --dataset Human --training False --visualize True

Train our network

The main file can be found in train.py.

cd src
python train.py

This command will train our network with default settings, i.e. Human dataset and all actions.

All settings are listed below:

setting default values help
--gpu [0] [.., .., ..] GPU device ids, list
--training True True, False train or test
--action all all, walking, .... see more in the code
--dataset Human Human, Mouse choose dataset
--visualize False True, False visualize predictions or not, only usable for testing

For more detail configurations, you could refer config.py

Acknowledge

Some code is adopted or modified from BII-wushuang, una-dinosauria, and asheshjain399.

Thanks for their great workings! :)

Citation

If you find this useful, please cite our work as follows:

Not available.

Questions

If you have any question or bug in my code, you can contact me with issues or email: hjf@cqu.edu.cn

You can’t perform that action at this time.