Shiry Ginosar* , Amir Bar* , Gefen Kohavi, Caroline Chan, Andrew Owens, Jitendra Malik
Back to main project page
python 2.7cuda 9.0cuDNN v7.6.2sudo apt-get install ffmpegpip install -r requirments.txt
- Download the dataset as described here
- Extract training/validation data
- Train a model
- Perform inference using a trained model
Start by extracting training data:
python -m data.train_test_data_extraction.extract_data_for_training --base_dataset_path <base_path> --speaker <speaker_name> -np <number of processes> --speaker <speaker name>`
once done you should see the following directories structure:
(notice train.csv and a train folder within the relevant speaker)
Gestures
├── frames.csv
├── train.csv
├── almaram
├── frames
├── videos
├── keypoints_all
├── keypoints_simple
├── videos
└── train
...
└── shelly
├── frames
├── videos
├── keypoints_all
├── keypoints_simple
├── videos
└── train
train.csv is a csv file in which every row represents a single training sample. Unlike in frames.csv, here, a sample is few seconds long.
audio_fn - path to audio filename associated with training sample
dataset - train/dev/test
start - start time in the video
end - end time in the video
pose_fn - path to .npz file containing training sample
speaker - name of a speaker in the dataset
video_fn - name of the video file
Training run command example:
python -m audio_to_multiple_pose_gan.train --gans 1 --name test_run --arch_g audio_to_pose_gans --arch_d pose_D --speaker oliver --output_path /tmp
During training, example outputs are saved in the define output_path
optionally get a pretrained model here.
Perform inference on a random sample from validation set:
python -m audio_to_multiple_pose_gan.predict_to_videos --train_csv <path/to/train.csv>--seq_len 64 --output_path </tmp/my_output_folder> --checkpoint <model checkpoint path> --speaker <speaker_name> -ag audio_to_pose_gans --gans 1
Perform inference on an audio sample:
python -m audio_to_multiple_pose_gan.predict_audio --audio_path <path_to_file.wav> --output_path </tmp/my_output_folder> --checkpoint <model checkpoint path> --speaker <speaker_name> -ag audio_to_pose_gans --gans 1
If you found this code useful, please cite the following paper:
@InProceedings{ginosar2019gestures,
author={S. Ginosar and A. Bar and G. Kohavi and C. Chan and A. Owens and J. Malik},
title = {Learning Individual Styles of Conversational Gesture},
booktitle = {Computer Vision and Pattern Recognition (CVPR)}
publisher = {IEEE},
year={2019},
month=jun
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent