The implementation of Temporal Generative Adversarial Nets with Singular Value Clipping
The new version of TGAN has been published and the code is available: TGANv2.
This repository contains a collection of scripts used in the experiments of Temporal Generative Adversarial Nets with Singular Value Clipping.
Disclaimer: PFN provides no warranty or support for this implementation. Use it at your own risk. See license for details.
These scripts require the following python libraries.
Note that they also require ffmpeg to produce a video from a set of images.
In order to run our scripts, you need to prepare MovingMNIST and UCF-101 datasets as follows.
mnist_test_seq.npy
from here.path-to-tgans/data/mnist_test_seq.npy
.There are two ways to create an UCF-101 dataset for this script.
make_ucf101.py
in this repository.
Note that this script also produces a config file that describes videos and
these corresponding label information.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.
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
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
python train.py --config_path configs/ucf101/ucf101_vanilla_zdim-100_no-beta.yml --gpu 0
We have uploaded mean2.npz
on GitHub because there are many inquiries about the mean file in the UCF101.
If you want to perform a quantitative evaluation, please download it from
this url.
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},
}
MIT License. Please see the LICENSE file for details.