GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → pfnet-research → tgan

pfnet-research / tgan

Licence: MIT license
The implementation of Temporal Generative Adversarial Nets with Singular Value Clipping

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

machine-learningdeep-learninggenerative-adversarial-networkneural-networks

Projects that are alternatives of or similar to tgan

tiny-pix2pix
Redesigning the Pix2Pix model for small datasets with fewer parameters and different PatchGAN architecture
Stars: ✭ 21 (-70%)
Mutual labels:  generative-adversarial-network
Exemplar-GAN-Eye-Inpainting-Tensorflow
Tensorflow implement of "Eye In-Painting with Exemplar Generative Adversarial Networks"
Stars: ✭ 98 (+40%)
Mutual labels:  generative-adversarial-network
BicycleGAN
Tensorflow implementation of the NIPS paper "Toward Multimodal Image-to-Image Translation"
Stars: ✭ 30 (-57.14%)
Mutual labels:  generative-adversarial-network
WGAN-GP-TensorFlow
TensorFlow implementations of Wasserstein GAN with Gradient Penalty (WGAN-GP), Least Squares GAN (LSGAN), GANs with the hinge loss.
Stars: ✭ 42 (-40%)
Mutual labels:  generative-adversarial-network
gan
A 1D toy example of optimizing a generative model using the WGAN-GP model.
Stars: ✭ 21 (-70%)
Mutual labels:  generative-adversarial-network
GAN-Anime-Characters
Applied several Generative Adversarial Networks (GAN) techniques such as: DCGAN, WGAN and StyleGAN to generate Anime Faces and Handwritten Digits.
Stars: ✭ 43 (-38.57%)
Mutual labels:  generative-adversarial-network
ArtGAN
Tensorflow codes for our ICIP-17 and arXiv-1708.09533 works: "ArtGAN: Artwork Synthesis with Conditional Categorial GAN" & "Learning a Generative Adversarial Network for High Resolution Artwork Synthesis "
Stars: ✭ 16 (-77.14%)
Mutual labels:  generative-adversarial-network
BicycleGAN-pytorch
Pytorch implementation of BicycleGAN with implementation details
Stars: ✭ 99 (+41.43%)
Mutual labels:  generative-adversarial-network
face inpainting
No description or website provided.
Stars: ✭ 27 (-61.43%)
Mutual labels:  generative-adversarial-network
CWR
Code and dataset for Single Underwater Image Restoration by Contrastive Learning, IGARSS 2021, oral.
Stars: ✭ 43 (-38.57%)
Mutual labels:  generative-adversarial-network
csgan
Task-Aware Compressed Sensing Using Generative Adversarial Networks (published in AAAI18)
Stars: ✭ 25 (-64.29%)
Mutual labels:  generative-adversarial-network
Keras ile Derin Ogrenmeye Giris
BTK Akademi -1 Milyon İstihdam Projesi için Merve Ayyüce Kızrak tarafından Hazırlanmıştır.
Stars: ✭ 109 (+55.71%)
Mutual labels:  generative-adversarial-network
Deeplearning.ai-GAN-Specialization-Generative-Adversarial-Networks
This repository contains my full work and notes on Deeplearning.ai GAN Specialization (Generative Adversarial Networks)
Stars: ✭ 59 (-15.71%)
Mutual labels:  generative-adversarial-network
pytorch-CycleGAN
Pytorch implementation of CycleGAN.
Stars: ✭ 39 (-44.29%)
Mutual labels:  generative-adversarial-network
tfjs-gan
Simple GAN example using tensorflow JS core
Stars: ✭ 56 (-20%)
Mutual labels:  generative-adversarial-network
adversarial-recommender-systems-survey
The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-…
Stars: ✭ 110 (+57.14%)
Mutual labels:  generative-adversarial-network
CartoonGAN-tensorflow
Simple code implement the paper of CartoonGAN(CVPR2018)
Stars: ✭ 14 (-80%)
Mutual labels:  generative-adversarial-network
CS231n
PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"
Stars: ✭ 47 (-32.86%)
Mutual labels:  generative-adversarial-network
Improved-Wasserstein-GAN-application-on-MRI-images
Improved Wasserstein GAN (WGAN-GP) application on medical (MRI) images
Stars: ✭ 23 (-67.14%)
Mutual labels:  generative-adversarial-network
ganbert-pytorch
Enhancing the BERT training with Semi-supervised Generative Adversarial Networks in Pytorch/HuggingFace
Stars: ✭ 60 (-14.29%)
Mutual labels:  generative-adversarial-network
View All Similar Projects ➔

Temporal Generative Adversarial Nets

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.

Results

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.

Usage

Datasets

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

MovingMNIST

  1. Download mnist_test_seq.npy from here.
  2. 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.

  1. Transforms all the videos in the UCF-101 dataset to the images.
  2. 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.
  3. 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 and weight 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

Quantitative evaluation on UCF101 (2019/08/20)

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.

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},
}

License

MIT License. Please see the LICENSE file for details.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].