PyTorch-GAN-master.zip

  • Orekikirito
    了解作者
  • Python
    开发工具
  • 30MB
    文件大小
  • zip
    文件格式
  • 0
    收藏次数
  • 1 积分
    下载积分
  • 5
    下载次数
  • 2020-10-09 09:19
    上传日期
基于Pytorch的GAN实现以及数据集
PyTorch-GAN-master.zip
  • PyTorch-GAN-master
  • data
  • download_pix2pix_dataset.sh
    221B
  • download_cyclegan_dataset.sh
    1KB
  • implementations
  • cluster_gan
  • clustergan.py
    17.8KB
  • dualgan
  • models.py
    3.8KB
  • datasets.py
    947B
  • dualgan.py
    8.9KB
  • wgan_div
  • wgan_div.py
    6.4KB
  • wgan_gp
  • wgan_gp.py
    6.7KB
  • sgan
  • sgan.py
    7.6KB
  • stargan
  • stargan.py
    10.9KB
  • models.py
    3.7KB
  • datasets.py
    1.5KB
  • gan
  • gan.py
    5.3KB
  • dcgan
  • dcgan.py
    6.3KB
  • wgan
  • wgan.py
    5.1KB
  • pix2pix
  • models.py
    4.2KB
  • datasets.py
    1KB
  • pix2pix.py
    6.9KB
  • cogan
  • cogan.py
    8.1KB
  • mnistm.py
    4.9KB
  • esrgan
  • test_on_image.py
    1.4KB
  • models.py
    4.6KB
  • datasets.py
    1.5KB
  • esrgan.py
    7.6KB
  • dragan
  • dragan.py
    7.2KB
  • cyclegan
  • models.py
    3.7KB
  • cyclegan.py
    10KB
  • datasets.py
    1.3KB
  • utils.py
    1.4KB
  • infogan
  • infogan.py
    10.5KB
  • bgan
  • bgan.py
    5.6KB
  • unit
  • models.py
    4.6KB
  • datasets.py
    992B
  • unit.py
    10.3KB
  • cgan
  • cgan.py
    6.9KB
  • lsgan
  • lsgan.py
    6.3KB
  • relativistic_gan
  • relativistic_gan.py
    6.6KB
  • ccgan
  • models.py
    3.6KB
  • ccgan.py
    6KB
  • datasets.py
    716B
  • munit
  • models.py
    10.5KB
  • munit.py
    10.8KB
  • datasets.py
    1KB
  • discogan
  • models.py
    3.9KB
  • discogan.py
    8.2KB
  • datasets.py
    942B
  • acgan
  • acgan.py
    8.2KB
  • bicyclegan
  • models.py
    5.3KB
  • datasets.py
    1.1KB
  • bicyclegan.py
    9.4KB
  • began
  • began.py
    6.7KB
  • aae
  • aae.py
    6.5KB
  • pixelda
  • mnistm.py
    5.6KB
  • pixelda.py
    10.2KB
  • softmax_gan
  • softmax_gan.py
    5.2KB
  • srgan
  • models.py
    3.7KB
  • datasets.py
    1.3KB
  • srgan.py
    6.2KB
  • ebgan
  • ebgan.py
    6.9KB
  • context_encoder
  • models.py
    2.2KB
  • datasets.py
    1.7KB
  • context_encoder.py
    6.3KB
  • assets
  • dcgan.gif
    742.5KB
  • munit.png
    860KB
内容介绍
<p align="center"></p> ## PyTorch-GAN Collection of PyTorch implementations of Generative Adversarial Network varieties presented in research papers. Model architectures will not always mirror the ones proposed in the papers, but I have chosen to focus on getting the core ideas covered instead of getting every layer configuration right. Contributions and suggestions of GANs to implement are very welcomed. <b>See also:</b> [Keras-GAN](https://github.com/eriklindernoren/Keras-GAN) ## Table of Contents * [Installation](#installation) * [Implementations](#implementations) + [Auxiliary Classifier GAN](#auxiliary-classifier-gan) + [Adversarial Autoencoder](#adversarial-autoencoder) + [BEGAN](#began) + [BicycleGAN](#bicyclegan) + [Boundary-Seeking GAN](#boundary-seeking-gan) + [Cluster GAN](#cluster-gan) + [Conditional GAN](#conditional-gan) + [Context-Conditional GAN](#context-conditional-gan) + [Context Encoder](#context-encoder) + [Coupled GAN](#coupled-gan) + [CycleGAN](#cyclegan) + [Deep Convolutional GAN](#deep-convolutional-gan) + [DiscoGAN](#discogan) + [DRAGAN](#dragan) + [DualGAN](#dualgan) + [Energy-Based GAN](#energy-based-gan) + [Enhanced Super-Resolution GAN](#enhanced-super-resolution-gan) + [GAN](#gan) + [InfoGAN](#infogan) + [Least Squares GAN](#least-squares-gan) + [MUNIT](#munit) + [Pix2Pix](#pix2pix) + [PixelDA](#pixelda) + [Relativistic GAN](#relativistic-gan) + [Semi-Supervised GAN](#semi-supervised-gan) + [Softmax GAN](#softmax-gan) + [StarGAN](#stargan) + [Super-Resolution GAN](#super-resolution-gan) + [UNIT](#unit) + [Wasserstein GAN](#wasserstein-gan) + [Wasserstein GAN GP](#wasserstein-gan-gp) + [Wasserstein GAN DIV](#wasserstein-gan-div) ## Installation $ git clone https://github.com/eriklindernoren/PyTorch-GAN $ cd PyTorch-GAN/ $ sudo pip3 install -r requirements.txt ## Implementations ### Auxiliary Classifier GAN _Auxiliary Classifier Generative Adversarial Network_ #### Authors Augustus Odena, Christopher Olah, Jonathon Shlens #### Abstract Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128x128 resolution image samples exhibiting global coherence. We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models. These analyses demonstrate that high resolution samples provide class information not present in low resolution samples. Across 1000 ImageNet classes, 128x128 samples are more than twice as discriminable as artificially resized 32x32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real ImageNet data. [[Paper]](https://arxiv.org/abs/1610.09585) [[Code]](implementations/acgan/acgan.py) #### Run Example ``` $ cd implementations/acgan/ $ python3 acgan.py ``` <p align="center"> </p> ### Adversarial Autoencoder _Adversarial Autoencoder_ #### Authors Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, Brendan Frey #### Abstract n this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution. Matching the aggregated posterior to the prior ensures that generating from any part of prior space results in meaningful samples. As a result, the decoder of the adversarial autoencoder learns a deep generative model that maps the imposed prior to the data distribution. We show how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization. We performed experiments on MNIST, Street View House Numbers and Toronto Face datasets and show that adversarial autoencoders achieve competitive results in generative modeling and semi-supervised classification tasks. [[Paper]](https://arxiv.org/abs/1511.05644) [[Code]](implementations/aae/aae.py) #### Run Example ``` $ cd implementations/aae/ $ python3 aae.py ``` ### BEGAN _BEGAN: Boundary Equilibrium Generative Adversarial Networks_ #### Authors David Berthelot, Thomas Schumm, Luke Metz #### Abstract We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure. [[Paper]](https://arxiv.org/abs/1703.10717) [[Code]](implementations/began/began.py) #### Run Example ``` $ cd implementations/began/ $ python3 began.py ``` ### BicycleGAN _Toward Multimodal Image-to-Image Translation_ #### Authors Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A. Efros, Oliver Wang, Eli Shechtman #### Abstract Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. In this work, we aim to model a \emph{distribution} of possible outputs in a conditional generative modeling setting. The ambiguity of the mapping is distilled in a low-dimensional latent vector, which can be randomly sampled at test time. A generator learns to map the given input, combined with this latent code, to the output. We explicitly encourage the connection between output and the latent code to be invertible. This helps prevent a many-to-one mapping from the latent code to the output during training, also known as the problem of mode collapse, and produces more diverse results. We explore several variants of this approach by employing different training objectives, network architectures, and methods of injecting the latent code. Our proposed method encourages bijective consistency between the latent encoding and output modes. We present a systematic comparison of our method and other variants on both perceptual realism and diversity. [[Paper]](https://arxiv.org/abs/1711.11586) [[Code]](implementations/bicyclegan/bicyclegan.py) <p align="center"> </p> #### Run Example ``` $ cd data/ $ bash download_pix2pix_dataset.sh edges2shoes $ cd ../implementations/bicyclegan/ $ python3 bicyclegan.py ``` <p align="center"> </p> <p align="center"> Various style translations by varying the latent code. </p> ### Boundary-Seeking GAN _Boundary-Seeking Generative Adversarial Networks_ #### Authors R Devon Hjelm, Athul Paul Jacob, Tong Che, Adam Trischler, Kyunghyun Cho, Yoshua Bengio #### Abstract Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs wit
评论
    相关推荐
    • CycleGAN:Pytorch实现CycleGAN
      Pytorch实现CycleGAN :star:在GitHub上为这个项目加注星标-它会有所帮助! 是将一个图像的到另一个图像的任务。它通过使用一些预训练模型的功能来实现。在这种情况下,使用在ImageNet上预训练的VGG19这样的基本...
    • image_generator:GAN pytorch实施
      GAN.py python GAN.py所在的目录中GAN.py python GAN.py 它学习,使用结果生成图像,并将生成的结果输出到img目录下。 根据环境的不同,学习可能需要10个小时或更长时间。输入图像的大小调整为64x64,并用于学习。...
    • 3D-GAN-pytorch:3D-GANpytorch实现
      3D-GAN-火炬 Pytorch实现。 数据集 wget http://3dshapenets.cs.princeton.edu/3DShapeNetsCode.zip unzip 3DShapeNetsCode.zip mv 3DShapeNetsCode ModelNet
    • PytorchGAN:人脸-使用GANPytorch正面实现
      派托克·甘(PytorchGAN) 人脸-使用GANPytorch正面实现
    • InfoGAN:InfoGANPyTorch实现
      InfoGANPyTorch实现 此仓库为玩具2D数据集实现了简单的InfoGAN。 但是,可以通过修改网络设计轻松地进行扩展。 带有玩具数据集的Experimenet 我想在MSE和InfoGAN下测试生成的样本配置。 数据生成函数来自半径为...
    • cafe_gan_pytorch
      基于Cafe-gan的AttGAN的非官方代码 仅用于UESTC-zjw进行实验 如果您想使用它或发现一些错误,可以告诉我们。谢谢。 不同之处: 添加关注分支 加输 由于STGAN其他没有注入层相同 AttGAN-PyTorch AttGAN的PyTorch...
    • ode-gan-pytorch
      Pytorch 实现。 用法 只需将ode_gan.py放入您的项目目录中,导入 ode_gan,然后实例化您选择的优化器(目前仅实现了RK2 [Heun 的方法]),传递生成器和鉴别器参数以及损失函数。 在训练循环中调用step()方法以执行...
    • NICE-GAN-pytorch:NICE-GANPyTorch正式实施
      NICE-GAN —官方PyTorch实施 重用鉴别符进行编码:实现无监督的图像到图像的翻译 重用鉴别符进行编码:实现无监督的图像到图像的翻译 摘要无监督的图像到图像转换是计算机视觉中的中心任务。 培训过程完成后,当前的...
    • Python-BigGANPyTorch实现
      Pytorch实现高保真自然图像合成的大规模GAN训练(BigGAN)'
    • matlabcnhelp.rar
      matlab中文帮助很难找的,快速下载