Home

(BiGAN)Adversarial Feature Learning - Donahue - ICLR 2017

Info Title: Adversarial Feature Learning Task: Image Generation Author: Jeff Donahue, Philipp Krähenbühl, Trevor Darrell Date: May 2016 Arxiv: 1605.09782 Published: ICLR 2017 Abstract The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitra...

Read more

Common Training Loss Curve of DCGAN and WGAN

DCGAN Implementation Genrator class Generator(nn.Module): def __init__(self): super(Generator, self).__init__() self.init_size = opt.img_size // 4 self.l1 = nn.Sequential(nn.Linear(opt.latent_dim, 128 * self.init_size ** 2)) self.conv_blocks = nn.Sequential( nn.BatchNorm2d(128), nn....

Read more

(ALI)Adversarially Learned Inference - Dumoulin - ICLR 2017

Info Title: Adversarially Learned Inference Task: Image Generation Author: Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Alex Lamb, Martin Arjovsky, Olivier Mastropietro and Aaron Courville Date: June 2016 Arxiv: 1606.00704 Published: ICLR 2017 Abstract We introduce the adversarially learned inference (ALI) model, which jointly...

Read more

GANs in PyTorch: DCGAN, cGAN, LSGAN, InfoGAN, WGAN and more

Deep Convolutional GAN(DCGAN) The deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations. DCGAN in PyTorch Genrator class Genera...

Read more