Advanced Deep Learning with Keras
Chapter 5Figure 5.3.4: A side by side comparison of outputs of CGAN and ACGAN conditioned with digits 0 to 9[ 159 ]
Improved GANsConclusionIn this chapter, we've presented various improvements in the original algorithmof GAN, first introduced in the previous chapter. WGAN proposed an algorithmto improve the stability of training by using the EMD or Wassertein 1 loss. LSGANargued that the original cross-entropy function of GAN is prone to vanishinggradients, unlike least squares loss. LSGAN proposed an algorithm to achieve stabletraining and quality outputs. ACGAN convincingly improved the quality of theconditional generation of MNIST digits by requiring the discriminator to performclassification task on top of determining whether the input image is fake or real.In the next chapter, we'll study how to control the attributes of generator outputs.Whilst CGAN and ACGAN are able to indicate the desired digits to produce; wehave not analyzed GANs that can specify the attributes of outputs. For example,we may want to control the writing style of the MNIST digits such as roundness,tilt angle, and thickness. Therefore, the goal will be to introduce GANs withdisentangled representations to control the specific attributes of the generatoroutputs.References1. Ian Goodfellow and others. Generative Adversarial Nets. Advances inneural information processing systems, 2014(http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf).2. Martin Arjovsky, Soumith Chintala, and Léon Bottou, Wasserstein GAN. arXivpreprint, 2017(https://arxiv.org/pdf/1701.07875.pdf).3. Xudong Mao and others. Least Squares Generative Adversarial Networks.2017 IEEE International Conference on Computer Vision (ICCV). IEEE2017(http://openaccess.thecvf.com/content_ICCV_2017/papers/Mao_Least_Squares_Generative_ICCV_2017_paper.pdf).4. Augustus Odena, Christopher Olah, and Jonathon Shlens. Conditional ImageSynthesis with Auxiliary Classifier GANs. ICML, 2017(http://proceedings.mlr.press/v70/odena17a/odena17a.pdf).[ 160 ]
- Page 125 and 126: Generative Adversarial Networks (GA
- Page 127 and 128: Generative Adversarial Networks (GA
- Page 129 and 130: Generative Adversarial Networks (GA
- Page 131 and 132: Generative Adversarial Networks (GA
- Page 133 and 134: Generative Adversarial Networks (GA
- Page 135 and 136: Generative Adversarial Networks (GA
- Page 137 and 138: Generative Adversarial Networks (GA
- Page 139 and 140: Generative Adversarial Networks (GA
- Page 141 and 142: Generative Adversarial Networks (GA
- Page 143 and 144: Improved GANsIn summary, the goal o
- Page 145 and 146: Improved GANsThe intuition behind E
- Page 147 and 148: Improved GANsThis makes sense since
- Page 149 and 150: Improved GANsIn the context of GANs
- Page 151 and 152: Improved GANsFigure 5.1.3: Top: Tra
- Page 153 and 154: Improved GANsThe functions include:
- Page 155 and 156: Improved GANsmodels = (generator, d
- Page 157 and 158: Improved GANsfor layer in discrimin
- Page 159 and 160: Improved GANsFollowing figure shows
- Page 161 and 162: Improved GANsThe preceding table sh
- Page 163 and 164: Improved GANsFollowing figure shows
- Page 165 and 166: Improved GANsEssentially, in CGAN w
- Page 167 and 168: Improved GANslayer = Dense(layer_fi
- Page 169 and 170: Improved GANsx = BatchNormalization
- Page 171 and 172: Improved GANsdiscriminator.compile(
- Page 173 and 174: Improved GANssize=batch_size)real_i
- Page 175: Improved GANsUnlike CGAN, the sampl
- Page 179 and 180: Disentangled Representation GANsIn
- Page 181 and 182: Disentangled Representation GANsInf
- Page 183 and 184: Disentangled Representation GANsFol
- Page 185 and 186: Disentangled Representation GANs# A
- Page 187 and 188: Disentangled Representation GANsif
- Page 189 and 190: Disentangled Representation GANsLis
- Page 191 and 192: Disentangled Representation GANsdat
- Page 193 and 194: Disentangled Representation GANsy[b
- Page 195 and 196: Disentangled Representation GANspyt
- Page 197 and 198: Disentangled Representation GANsThe
- Page 199 and 200: Disentangled Representation GANsSta
- Page 201 and 202: Disentangled Representation GANs( )
- Page 203 and 204: Disentangled Representation GANsThe
- Page 205 and 206: Disentangled Representation GANsfea
- Page 207 and 208: Disentangled Representation GANs# f
- Page 209 and 210: Disentangled Representation GANslat
- Page 211 and 212: Disentangled Representation GANsDis
- Page 213 and 214: Disentangled Representation GANsz_d
- Page 215 and 216: Disentangled Representation GANs2.
- Page 217 and 218: Disentangled Representation GANsFig
- Page 220 and 221: Cross-Domain GANsIn computer vision
- Page 222 and 223: Chapter 7There are many more exampl
- Page 224 and 225: The CycleGAN ModelFigure 7.1.3 show
Chapter 5
Figure 5.3.4: A side by side comparison of outputs of CGAN and ACGAN conditioned with digits 0 to 9
[ 159 ]