Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [gan]

GAN refers to Generative Adversarial Networks.

Such networks is made of two networks that compete against each other. The first one generates new samples and the second one discriminates between generated samples and true samples.

GAN refers to Generative Adversarial Networks.

Such networks is made of two networks that compete against each other:

  • The first network generates new samples, based on random input samples to create variability

  • The second network discriminates between generated samples and true samples. It usually entails running the first network to generate a new sample and the discriminator network must tag it as artificial. At the same time, a true sample is passed in the discriminator to and this one must be tagged as non artificial.

By optimizing the first network in alternance with the second one, more and more realistic samples will be created by the generative network which can then be used without the discriminator once trained.

236 questions
17
votes
3 answers

GANs (generative adversarial networks) possible for text as well?

Are GANs (generative adversarial networks) good just for images or can they be used for text as well? Like training a network to generate meaningful text from a summary. UPD - quotes from the GAN inventor Ian Goodfellow. GANs have not been applied…
Open Food Broker
  • 381
  • 1
  • 2
  • 13
6
votes
3 answers

Is it possible for a DCGAN to do regression? What are some examples of this?

I'm currently a student doing some machine learning projects, and I want to use generative adversarial networks to train some data to discern for example, how old someone is. The intended output is a regression continuous output in term of months. I…
lppier
  • 161
  • 1
  • 3
4
votes
2 answers

CapsNet Generative adversarial network

I have a very interesting question. It's one month ago Geoffrey Hinton release his CapsNet paper. It's a complete new way for visual computing in the neural network stack. But my question is. Is it possible to use the CapsNet as a GAN. I only…
Christian Frei
  • 351
  • 1
  • 5
3
votes
0 answers

Explanation of generative adversarial net in Generative adversarial networks by IJ Goodfellow and et at. (2014)

In a paper titled Generative adversarial networks (link in comment - sorry I don't have enough reputation to include more than 2 links), an explanation of generative adversarial net is provided as following: I have 2 questions about the explanation…
Quan Vuong
  • 141
  • 3
2
votes
2 answers

Recommendations for learning DCGANs?

I mean stuff that doesn't use Python, Keras or TensorFlow. I have been looking for an in-depth explanation on how to implement a DCGAN from the ground up so I can have a complete understanding of the concept. Even some literature on GANs from the…
Al G Johnston
  • 21
  • 1
2
votes
1 answer

GAN Loss Function Notation Clarification

In the Generative Adversarial Network loss function, what do these mean?: $E_{x~p_{data}(x)}$ and $E_{z~p_{z}(z)}$ and how are they used in this context?
kareem arab
  • 23
  • 3
2
votes
1 answer

How different should discriminator be from generator in GAN

When training a GAN, the generator $G$ strives to fool the discriminator $D$, while $D$ attempts to catch any output generated $G$ and isolate it from a real data point. They grow together training in turns for each epoche. Assuming $D$ is already…
havakok
  • 143
  • 3
1
vote
0 answers

Training neural network to generate realistic terrain for video games

I've recently had an idea to create a tool that makes it easier for environment artists to generate highly realistic terrain for video games. I've seen approaches using GANs and I'm familiar with the publication by Guérin et al "Interactive…
Max Walczak
  • 111
  • 2
1
vote
1 answer

What is meant by Average Content Distance in Videos generated by GANs?

I'm reading a research paper on generating/synthesizing videos: MoCoGAN: Decomposing Motion and Content for Video Generation To evaluate the generated videos, they have used a metric called 'Average Content Distance'. I couldn't find any material on…
Nagabhushan S N
  • 724
  • 3
  • 8
  • 23
1
vote
2 answers

Value Function of Generative Adversarial Network

My question concerns the notation used in the Value function of a GAN Does $${x ∼ p_{data}}$$ mean $$ E_{x\sim p_{data}}[log(D(x)]= \sum_{x} logD(x)(x)p_{data}(x)$$ ?
midawn98
  • 121
  • 4
1
vote
1 answer

Where is the VGG in Cartoongan?

When I read through the paper of Cartoongan [CartoonGAN: Generative Adversarial Networks for Photo Cartoonization], I was so confused about where is vgg located in the entire network. Based on the paper about GAN [Generative Adversarial Nets], I…
sss
  • 13
  • 3
1
vote
0 answers

Constrain GAN so the subject is always the same

I want to build a face GAN, but I want to be able to control the 'camera angle' of the generated image, and I also want the subject (the generated face) to be the same every time. If the above is possible, then it seems like it could generate the…
Karric
  • 113
  • 4
1
vote
0 answers

Super Resolution GAN with different input image size

I am trying to train a Super Resolution GAN. Following some materials on the web I managed to train the first SRGAN model. To do that I took some high-resolution images (128x128 pixels) and downscale them to 32x32 to train the model. Once I finished…
MattiaMartinelli
  • 11
  • 1
1
vote
1 answer

Random Noise in GANs

What does the "random input" from noise (random noise) mean in GANs? Let's say I want to synthesize data such as name, age, income etc.. Does my generator know the original data sets (and thus the distributions of the data)? How can I think of…
user126861
  • 13
  • 2
0
votes
1 answer

How to implement self attention Generator and Discriminator in Conditional Generative Adversarial Nets

We have a CGAN built with a generator and a discriminator built using neural networks. How can we change the code to implement the same logic using self attention generator and discriminators? Our code.
Rajdeep datta
  • 1
  • 1