Temporal Generative Adversarial Networks

This repository contains a collection of scripts used in the experiments of Temporal Generative Adversarial Nets with Singular Value Clipping.

Requirements

These scripts require the following python libraries.

Chainer 2.0.0+
h5py
numpy
pandas
PIL
PyYAML
matplotlib

Note that they also require ffmpeg to produce a video from a set of images.

Datasets

In order to run our scripts, you need to prepare MovingMNIST and UCF-101 datasets as follows.

MovingMNIST

Download mnist_test_seq.npy from here.
Put it on path-to-tgans/data/mnist_test_seq.npy.

UCF-101

There are two ways to create an UCF-101 dataset for this script.

Transforms all the videos in the UCF-101 dataset to the images.
Resizes these images to the appropriate resolution, and concatenate them into as single hdf5 format represented as (time, channel, rows, cols). In this transformation we used make_ucf101.py in this repository. Note that this script also produces a config file that describes videos and these corresponding label information.
puts them on path-to-tgans/data.

Another way is to simply download these files; please download them from this url, and put them on the same directory.

Training

TGAN with WGAN and Singular Value Clipping

python train.py --config_path configs/moving_mnist/mnist_wgan_svd_zdim-100_no-beta-all_init-uniform-all.yml --gpu 0
python train.py --config_path configs/ucf101/ucf101_wgan_svd_zdim-100_no-beta.yml --gpu 0

TGAN (WGAN, clipping)

python train.py --config_path configs/moving_mnist/mnist_wgan_clip_zdim-100_no-beta-all_init-uniform-all.yml --gpu 0
python train.py --config_path configs/ucf101/ucf101_wgan_clip_zdim-100_no-beta.yml --gpu 0

TGAN (vanilla GAN)

python train.py --config_path configs/ucf101/ucf101_vanilla_zdim-100_no-beta.yml --gpu 0

Citation

Please cite the paper if you are interested in:

@inproceedings{TGAN2017,
    author = {Saito, Masaki and Matsumoto, Eiichi and Saito, Shunta},
    title = {Temporal Generative Adversarial Nets with Singular Value Clipping},
    booktitle = {ICCV},
    year = {2017},
}

mattya/tgan