Questions tagged [gan]

Generative Adversarial Networks (GANs) are neural networks that are trained in an adversarial manner to generate data mimicking some distribution.

Filter by
Sorted by
Tagged with
0
votes
0answers
5 views

Combining a neural network classifier with genetic algorithm to do the task likes what generative adversarial network does?

Recently I read some materials about GANs(Generative adversarial network). I know that GANs uses a discriminator network to distinguish the expected output(let's say that it's an image),and a ...
0
votes
0answers
11 views

How to generate a path given a set of input features?

I have set of features for each element of my training set: features = [time, status, speed, on/off, ...]. Such features are just a single value for each element ...
0
votes
0answers
24 views

Can data generated by generative models be used for training unsupervised learning models? [duplicate]

I'm working on a signal denoising problem. Because of not having enough data for training I'm considering using one of the generative models like VAE or GAN to generate data similar to real data for ...
0
votes
1answer
11 views

How to grasp the full entropy of the distribution we want to model in GAN

In pix2pix GAN paper( https://arxiv.org/abs/1611.07004), authors found that the noise vector and the dropout are not efficient in grasping the full entropy of the data distribution we want to model. ...
0
votes
0answers
14 views

How to measure the quality of fakes produced by a digital twin?

I have asked this on stackoverflow, but it was considered too broad, perhaps because there is no specific code involved. I hope this question is more appropriate for crossvalidated. I am developing a ...
1
vote
1answer
24 views

Is it possible to obtain learn specific information about a distribution from a GAN?

If I feed a GAN some images of Gaussian noise with some $\sigma$ and it is successful at generating similar images, is there some way to recover $\sigma$ from the gan or is the generator purely a ...
0
votes
0answers
10 views

Implementing a specific GAN loss

In this paper in section 3.4 they define a GAN loss as (I simplify to the important part): $$\mathcal L_{GAN} = \max_D \min_G E_{x_{1} \sim P_1}[ \Vert D(G(x_{1})) \Vert] + \max_D E_{x_2 \sim P_2}[\...
1
vote
2answers
20 views

Working mechanism of discriminator in text to image synthesis GAN

I have the following architecture of discriminator in text to image synthesis where the image is convolved to lower dimension and concatenated with the text . My question is what is the use of ...
2
votes
1answer
78 views

How does one generate (smooth) varying size output signals with Machine Learning?

I am interested in knowing about generative methods that generate signals (e.g. images) of varying sizes. But the size generation being sort of "smooth/continuous". So for example, generating images ...
1
vote
0answers
33 views

calculate Inception Score and FID in GAN [closed]

Do we calculate Inception Score and Fréchet Inception Distance (FID) on the images generated by generator in parallel during training ? Or do we save the images generated by the generator and later ...
0
votes
0answers
11 views

What is this phenomenon? is this the so called “Model Collapse” phenomenon in a Gan or something completely different?

This is a follow up question which I asked here. I tried to see if my GAN memorized something or not. I'm 100% sure that in my earlier experiments I noticed couple of images that were identical to ...
1
vote
0answers
33 views

How does the number of epochs affecting GANs training?

In CNN training, increasing the number epochs would lead to overfitting. However, to train a GAN, would a too large number of training epochs matter? Indeed, I also do not understand what does it mean ...
1
vote
0answers
17 views

Generating distributions with very small values with generative adverserial networks

I am using a GAN to generate a vector distribution. However, most of the values of this distribution are very close to zero, i.e $1 \times 10^{-7}$. The distribution also have minus values. With ...
1
vote
0answers
82 views

GANs for non image data

I'm looking to narrow down the subject for my bachelor thesis: I am currently working on a project, that only offers a small dataset and there will be no more data incoming for now. What I'm trying to ...
1
vote
1answer
58 views

Increasing image size in pytorch celebrity generating GAN? [closed]

complete newbie here, bear with me. I'm making my way through this tutorial: https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html Upon attempting to make a simple change to the image ...
2
votes
0answers
26 views

Distribution $f$ that minimizes $JSD(f||q) + JSD(f||p)$

What can we say about the distribution $f^*$ that is the solution to the following optimization problem: $$\min_f JSD(f||p)+JSD(f||q) ,$$ where $p,q$ are given distributions over some set, and $JSD$ ...
0
votes
1answer
32 views

Global Minimum solution for the Generator step in the original GAN formulation

I am going through the proof in Goodfellow's original GAN paper. Specifically, I'm at the stage where he did the discriminator step (solve a maximization problem) and now he is doing the generator ...
0
votes
0answers
21 views

Intuition for manifold-diffusion training

Manifold-diffusion training is introduced in the following paper: https://arxiv.org/pdf/1612.02136.pdf The basic idea is that when training a GAN, we try to accomplish two things, which the paper ...
0
votes
0answers
34 views

When to stop training a Auixilary Classifier GAN?

When should I stop training an Auxiliary Classifier GAN? when the discriminator loss converges or when the auxiliary classification accuracy converges or when the Real vs Fake classifier converges to ...
1
vote
0answers
19 views

How do I check my GAN implementation is correct?

I wrote a GAN implementation and I trained that to produce some sample images after training on a dataset. The images looked visually fine. Now I want to test my implementation on the CI and make ...
1
vote
1answer
255 views

Understanding the GAN Loss function from the original paper

I've been reading the paper Generative Adversarial Nets by Ian J. Goodfellow et al., to have a more deeper understanding about the concepts from the author's perspective (I do understand the basics of ...
3
votes
0answers
130 views

Usage of dropout in convolutional GANs with batch norm?

In DCGAN, dropout is not used in either generator or discriminator. When using batch norm, are the benefits of dropout generally so marginal that is is not used? If it is used, in what circumstances?...
1
vote
1answer
420 views

Is a GAN's discriminator loss expected to be twice the generator's?

If a GAN generator has the same (but reversed) hidden layer architecture as the discriminator, is a the discriminator's loss expected to be approximately double the generator's? In the examples I'm ...
1
vote
1answer
146 views

How can we relate the concepts of GAN/cGAN in SRGAN? Is SRGAN a Conditional GAN?

I have been reading and looking at implementations of the SRGAN, from "Photo-realistic Single Image Super Resolution with Generative Adversarial Networks" paper. One thing that I noticed is that the ...
0
votes
0answers
16 views

Architecture used by author in StackGAN

I was going through this paper stackedGAN I somehow understood how it is working. But I wanted to know it's architecture so that I can implement it myself. I went through the implementation code of ...
0
votes
1answer
34 views

Why does the DCGAN output degrade with an increase in the kernel size?

Thank you for the explanation on the kernel size. I have been experimenting with the sample Generative Adversarial Network (GAN) code from the book on Deep learning with Python by François Chollet, ...
5
votes
2answers
58 views

Why are Generative Adversarial Networks classed as unsupervised

The title of the question is basically all I'm asking, but I should explain why GANs don't seem to be unsupervised to me! Here's my understanding of unsupervised learning: Unsupervised learning is ...
1
vote
0answers
22 views

What method to use for conditional density querying

I have a dataset of 3d poses each represented by 40 points (all relative to the central point). So my data has dimensionality 120. What is needed is to learn how build realistic pose, when positions ...
0
votes
0answers
122 views

DCGAN generator accuracy doesnt improve for high-res images

I trained a DCGAN on MNIST and CelebA dataset with 28x28 image size. Both the models were able to train successfully. I used many tips from https://github.com/soumith/ganhacks to make both the G and D'...
0
votes
0answers
15 views

How do GANs stay in sync?

What further research has been done since the introduction of GANs on the problem of keeping the generator and discriminator in sync, i.e. so one does not overpower the other?
4
votes
1answer
45 views

Convergence to gradient in limit of variance

I came across this equation in the original GAN paper (pg 2 https://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf): $$\lim_{\sigma \rightarrow 0} \nabla_{\bf x} \mathbb{E}_{\epsilon \sim \...
1
vote
0answers
27 views

Image generation based on sketch

Are there any instances of image generation models, where an image (a very rough sketch) has been used as an input and was then augmented. For example: This could be a rough sketch, which is then ...
0
votes
1answer
40 views

Generative model to generate hidden activations coming from a previously trained hidden layer

I need to train a generative model to generate vectors which resemble the activations of a particular hidden layer of a neural network which has been previously trained. In particular, the hidden ...
0
votes
0answers
12 views

What are the constituents of “distributions” in GANs?

We have a distribution for the Generator and the Discriminator, and we minimize their divergence, but how do the inputs (say, images) constitute a probability distribution? Or is the distribution ...
0
votes
0answers
199 views

Which GAN is the best for data augmentation?

I have around 200000 images and I want to augment the data by generating more of them. Images do not have classes, because they are the same object and are used for the task of object detection. Can I ...
2
votes
1answer
63 views

Prerequisites for Wasserstein GAN/Autoencoder

Can someone who read WGAN/WAE papers and understood Wasserstein part, could you share how you prepared necessary Optimal Transport background? The mentioned papers seem little tough if you don't have ...
1
vote
1answer
90 views

Why are GANs so innovative?

I've been reading about the importance of Generative Adversarial Networks (GANs), and I would like to double check that I understood correctly why they are so relevant. Before GANs, what people did ...
1
vote
1answer
124 views

What is the difference between Generative Adversarial Networks (GAN) and Generative Antagonistic System (GAS)?

What is the difference between Generative Adversarial Networks (GAN) and Generative Antagonistic System (GAS) in the neural network?
1
vote
0answers
90 views

Categorical data & Gaussian latent variables

I am learning about imposing structure on the latent variables in autoencoders. In that context I have looked at variational autoencoders (VAEs) and adversarial autoencoders (AAEs). This paper ...
0
votes
0answers
72 views

GAN generated images all similar per epoch

I'm working on a GAN using cifar-10 images. After each epoch I create 10 new random z noise vectors, and use them to create 10 images using the generator. All of the 10 images look very similar, but ...
-1
votes
1answer
52 views

Machine learning books covering neural networks / cnn / GAN [duplicate]

I'm not an expert in machine learning. Is there any textbook (with a decent amount of mathematical rigor) that cover the subjects neural network / convolutional neural network / GAN network? I've the ...
0
votes
0answers
138 views

Generative Adversial Networks (GAN) - Dimension of the Latent Space

I am trying to synthesis medical images with GAN. The problem is that my generator loss is very bad behaved: I read that if latent space dimension is not enough for representation of the true ...
0
votes
1answer
44 views

volume generation with GAN

I'm not a GAN expert, but I have a problem and I would like to understand if GAN could help me in some way. Essentially my problem is to convert a 3D grayscaled volume in another 3D grayscaled volume, ...
0
votes
0answers
33 views

Data Synthesis based on Deep Learning

Is there any open source tool available to synthetically generate a new dataset with the same statistics than the original one? The objective is to create a new tabular dataset that is private but ...
1
vote
0answers
201 views

GAN and NN for sparse data

I have a set of images which represent some correlated sparse data $x_1,\ldots ,x_n$. there are a number of specific pixels in the images which might hold value or not (with some probability), while ...
2
votes
0answers
83 views

GANs for image translation

I am training a generative adversarial network to perform style transfer from two different image domains (source S and target T)...
1
vote
1answer
68 views

Where's wrong in my reasoning behind upper bound for reconstruction error?

In the paper Mutual Information Neural Estimation, the authors derive the reconstruction error in BiGAN as $$ \mathcal R=E_{x\sim q(x)}E_{z\sim q(z|x)}\left[-\log p(x|z)\right] $$ where $q(z|x)$ is ...
3
votes
1answer
97 views

In Ian Goodfellow et al's paper “Generative Adversarial Networks”, why do they specify that they do not need a Markov chain or inference network?

In Ian Goodfellow et al's paper Generative Adversarial Networks, they state, "There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of ...
1
vote
1answer
480 views

When should I stop a training of WGAN model?

The loss function of the WGAN is a continuous one. It doesn't have a convergence point. I don't really understand when we should stop the training.
2
votes
0answers
31 views

Any Asynchronous Training Methods for GAN?

GAN sometimes get really unstable with the high dimensional data. Can we train GAN is Asynchronous manner? It's like we have one master Generator and Discriminator. But we actually update it ...