gan生成图像at 1024² 的 代码 论文

2017 年 10 月 31 日 CreateAMind
gan生成图像at 1024² 的 代码 论文

Progressive Growing of GANs for Improved Quality, Stability, and Variation

https://github.com/tkarras/progressive_growing_of_gans

Tero Karras (NVIDIA), Timo Aila (NVIDIA), Samuli Laine (NVIDIA), Jaakko Lehtinen (NVIDIA and Aalto University)

Picture: Two imaginary celebrities that were dreamed up by a random number generator.

Abstract: 
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024². We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

Links

  • Paper (NVIDIA research)

  • Paper (arXiv)

  • Result video (YouTube)

  • One hour of imaginary celebrities (YouTube)

  • Pre-trained networks (Google Drive)

  • Datasets (currently unavailable)

License

The source code is available under the CC BY-NC license:

# Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
#
# This work is licensed under the Creative Commons Attribution-NonCommercial
# 4.0 International License. To view a copy of this license, visit
# http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to
# Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.

Compatibility

We have tested the implementation on the following system:

  • NVIDIA DGX-1 with Tesla P100

  • BaseOS 2.1.0, 4.4.0-92-generic kernel

  • NVIDIA driver 384.81, CUDA Toolkit 9.0

  • Python 2.7.11

  • Bleeding-edge version of Theano and Lasagne from Oct 17, 2017

We are planning to add support for TensorFlow and multi-GPU in the near future.




https://github.com/tkarras/progressive_growing_of_gans

登录查看更多
4

相关内容

Previous works \citep{donahue2018adversarial, engel2019gansynth} have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques. Subjective evaluation metric (Mean Opinion Score, or MOS) shows the effectiveness of the proposed approach for high quality mel-spectrogram inversion. To establish the generality of the proposed techniques, we show qualitative results of our model in speech synthesis, music domain translation and unconditional music synthesis. We evaluate the various components of the model through ablation studies and suggest a set of guidelines to design general purpose discriminators and generators for conditional sequence synthesis tasks. Our model is non-autoregressive, fully convolutional, with significantly fewer parameters than competing models and generalizes to unseen speakers for mel-spectrogram inversion. Our pytorch implementation runs at more than 100x faster than realtime on GTX 1080Ti GPU and more than 2x faster than real-time on CPU, without any hardware specific optimization tricks. Blog post with samples and accompanying code coming soon.

0
5
下载
预览

In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes. Following the two-step (layout-image) generation process, a novel object-driven attentive image generator is proposed to synthesize salient objects by paying attention to the most relevant words in the text description and the pre-generated semantic layout. In addition, a new Fast R-CNN based object-wise discriminator is proposed to provide rich object-wise discrimination signals on whether the synthesized object matches the text description and the pre-generated layout. The proposed Obj-GAN significantly outperforms the previous state of the art in various metrics on the large-scale COCO benchmark, increasing the Inception score by 27% and decreasing the FID score by 11%. A thorough comparison between the traditional grid attention and the new object-driven attention is provided through analyzing their mechanisms and visualizing their attention layers, showing insights of how the proposed model generates complex scenes in high quality.

0
6
下载
预览

Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick", allowing fine control over the trade-off between sample fidelity and variety by truncating the latent space. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128x128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.3 and Frechet Inception Distance (FID) of 9.6, improving over the previous best IS of 52.52 and FID of 18.65.

0
4
下载
预览

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

0
3
下载
预览
小贴士
相关资讯
【ICML2019】IanGoodfellow自注意力GAN的代码与PPT
GAN生成式对抗网络
13+阅读 · 2019年6月30日
带你读论文 | 生成对抗网络GAN论文TOP 10
微软研究院AI头条
22+阅读 · 2019年4月11日
必读!生成对抗网络GAN论文TOP 10
全球人工智能
5+阅读 · 2019年3月19日
2018 年最棒的三篇 GAN 论文
AI科技评论
4+阅读 · 2019年1月14日
【深度】Ian Goodfellow 强推:GAN 进展跟踪 10 大论文(附下载)
条件GAN重大改进!cGANs with Projection Discriminator
CreateAMind
6+阅读 · 2018年2月7日
Auto-Encoding GAN
CreateAMind
5+阅读 · 2017年8月4日
相关VIP内容
专知会员服务
20+阅读 · 2020年4月6日
专知会员服务
40+阅读 · 2020年2月26日
专知会员服务
25+阅读 · 2020年1月10日
专知会员服务
19+阅读 · 2020年1月10日
八篇 ICCV 2019 【图神经网络(GNN)+CV】相关论文
专知会员服务
26+阅读 · 2020年1月10日
生成式对抗网络GAN异常检测
专知会员服务
61+阅读 · 2019年10月13日
计算机视觉最佳实践、代码示例和相关文档
专知会员服务
8+阅读 · 2019年10月9日
【ICLR2020】五篇Open代码的GNN论文
专知会员服务
39+阅读 · 2019年10月2日
相关论文
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Kundan Kumar,Rithesh Kumar,Thibault de Boissiere,Lucas Gestin,Wei Zhen Teoh,Jose Sotelo,Alexandre de Brebisson,Yoshua Bengio,Aaron Courville
5+阅读 · 2019年10月8日
Object-driven Text-to-Image Synthesis via Adversarial Training
Wenbo Li,Pengchuan Zhang,Lei Zhang,Qiuyuan Huang,Xiaodong He,Siwei Lyu,Jianfeng Gao
6+阅读 · 2019年2月27日
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
David Bau,Jun-Yan Zhu,Hendrik Strobelt,Bolei Zhou,Joshua B. Tenenbaum,William T. Freeman,Antonio Torralba
11+阅读 · 2018年12月8日
Andrew Brock,Jeff Donahue,Karen Simonyan
4+阅读 · 2018年9月28日
Han Zhang,Ian Goodfellow,Dimitris Metaxas,Augustus Odena
5+阅读 · 2018年5月21日
Jianxin Lin,Yingce Xia,Tao Qin,Zhibo Chen,Tie-Yan Liu
5+阅读 · 2018年5月1日
Ruoqi Sun,Chen Huang,Jianping Shi,Lizhuang Ma
4+阅读 · 2018年4月24日
Hao Ge,Yin Xia,Xu Chen,Randall Berry,Ying Wu
3+阅读 · 2018年3月23日
Zhou Yin,Wei-Shi Zheng,Ancong Wu,Hong-Xing Yu,Hai Wang,Jianhuang Lai
7+阅读 · 2018年2月6日
Tero Karras,Timo Aila,Samuli Laine,Jaakko Lehtinen
3+阅读 · 2017年11月3日
Top