Skip to main content
OverflowAI is here! AI power for your Stack Overflow for Teams knowledge community. Learn more

Questions tagged [generative-adversarial-networks]

For questions related to generative adversarial networks (GANs), introduced in the paper Generative Adversarial Nets (2014) by J. Goodfellow et al. A GAN is composed of a discriminative model (D) and a generative model (G). The discriminator D needs to distinguish between data generated by the generator G and data in the training set, while the generator G needs to generate data such that the discriminator D is not able to accomplish its task.

Filter by
Sorted by
Tagged with
0 votes
1 answer
40 views

How to interpret this training

I'm still learning ml/ai and I'm running a training where the curves look like this. I was told that this looks good by some and that it doesn't look good by others... But none told me exactly why, I ...
user17952421's user avatar
0 votes
0 answers
14 views

How to learn pattern of lower pixels rate in Pix2Pix GAN AND not background [closed]

I am working on a project to generate a forged image ( Almost a copy of it but not a copy completely!) from some source images. After some epochs, the generator model generates some white images. I ...
Ali AminiBagh's user avatar
0 votes
1 answer
20 views

Question about the redundance in DCGAN training

I don't understand the necessity of the redundance in the training of DCGAN. So a classical DSGAN training procedure is like this: My questions: Can I remove step (7)-(8) and and reuse the fake ...
lovetl2002's user avatar
1 vote
0 answers
17 views

re-use D(fake) for optimizing both, G and D when training GANs

When training GANs, I can do this: pseudo code opt_g = Optimizer(G.params) opt_d = Optimizer(D.params) ...
Klops's user avatar
  • 111
1 vote
1 answer
42 views

Why do you sample twice from the generator during a GAN training step?

Most basic GAN algorithm definitions I found go like this: Generate Train discriminator Generate Train generator Like this one: GAN pseudocode If I'm not misunderstanding, we sample twice from the ...
John Smith's user avatar
2 votes
1 answer
214 views

Why are the generator and discriminator designed differently in this example?

Why are the generator and discriminator designed differently in the example My First GAN of the coursera course: Build Basic Generative Adversarial Networks (GANs)? Why didn't we use the same set of ...
SJa's user avatar
  • 393
0 votes
0 answers
63 views

What are the differences between Inception Score and Fréchet Inception Distance?

From the articles I've read about image generation using GANs, the Inception Score measures two things simultaneously: the variety of images (diversity) and the distinct quality of each image. Does ...
user avatar
0 votes
0 answers
34 views

StyleGAN 2 multiplies loss components with zero, why?

I found a rather odd piece of code in a 3.8k star repo of the well known StyleGAN 2 paper. In the loss function they use the following expression: ...
Klops's user avatar
  • 111
0 votes
1 answer
264 views

Why does the latent space in Stable Diffusion have a shape of 64x64x3?

Since the encoding is performed by a Variational Autoencoder, the VAE encoder must output some mean and log variance that we can ...
Renat Abdrakhmanov's user avatar
5 votes
1 answer
665 views

How can the discriminator determine the sample is fake or real?

Based on the articles I've read, the discriminator can identify whether a sample is fake or real. However, the articles don't clarify the conditions used to determine if a sample is fake or real. I ...
user avatar
2 votes
1 answer
75 views

What are meaning of parameters $\theta$ in this context?

I'm reading the article about generative model from Open AI, here is the section where they explain them: Our network is a function with parameters $\theta$, and tweaking these parameters will tweak ...
user avatar
1 vote
1 answer
114 views

Do I understand the technology of AI upscaling of films and cartoons correctly?

With the help of artificial intelligence, it is possible to increase the resolution of images that are initially low resolution, bringing it to ultra-high resolution. Also, initially static images are ...
dtn's user avatar
  • 239
2 votes
0 answers
133 views

cGAN: Discriminator loss going to zero while Generator's going always up but the result is very good

I have a Conditional Generative Adversarial Network for Quantum State Tomography. The metrics I am monitoring during the training process are the losses and the Fidelity (the degree of similarity ...
Dimitri's user avatar
  • 23
1 vote
1 answer
80 views

Do GANs have constant running time?

After the model is trained, you just need to input random noise and the generator will output an image, does this mean GANs have constant running time ? I'm asking about both naïve GAN and variants of ...
user avatar
1 vote
0 answers
159 views

Question about the Conditioning Augmentation technique?

In the paper StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks, the goal is to convert text descriptions into images. The text encoder encodes the ...
user avatar
1 vote
2 answers
213 views

The training process of a conditional GAN

For example, consider a dataset like MNIST. I give the conditional vector to produce only the number $7$ for both the generator and discriminator. In the following scenarios, what will the ...
user avatar
0 votes
1 answer
254 views

In the conditional GAN (cGAN) architecture, why does the discriminator need conditional variable?

I'm reading about conditional GAN (cGAN) architecture, what I know is that the generator creates images combining both noise vector and conditional variable, the noise vector brings in random elements ...
user avatar
0 votes
1 answer
222 views

Generator loss not decreasing while training GAN

I’ve been attempting to create a basic GAN to generate images using this database of flowers (https://www.robots.ox.ac.uk/~vgg/data/flowers/102/). I’ve spent a few days on this, and largely based my ...
Hozaifa Bhutta's user avatar
0 votes
0 answers
20 views

Is synthetic data just a placebo for immature models?

I apologize for the provocative question, but let me elaborate. I am trying to wrap my head around the logic of synthetic data. When you train a model what you are trying to do is to teach the ground ...
Pigna's user avatar
  • 295
0 votes
1 answer
39 views

Do WGAN gradients require multi-variable calculus?

The generator tries to maximise this function D(G(z)). That much I understand. But how can the critic maximise D(x) - D(G(z)). ...
zacoons's user avatar
  • 13
0 votes
1 answer
62 views

How to deal with sparse 1D data with WGAN-gp

I want to modify WGAN-gp so that it will work on very sparse 1D data (FFT of Gauss signal). Can you suggest any methods or papers that will be helpful? I have a working WGAN-gp, but it is not ...
chrzanowski's user avatar
1 vote
1 answer
98 views

How the generator loss works in a GAN

I've been reading about GANs so I can implement a simple image generator. It seems that the loss for the generator is given by the following equation: ...
zacoons's user avatar
  • 13
0 votes
0 answers
27 views

FastGAN implementation has redundant SpectralNorm followed by BatchNorm?

I am implementing a version of FastGAN, and it seems like (see the official repo) they use a Spectral norm directly followed by a Batch norm. Doesn't the spectral norm get fully cancelled by the ...
Ronald's user avatar
  • 21
0 votes
0 answers
58 views

How to generate quality synthetic images of human subjects to be used for training stable diffusion

I'm trying to generate some synthetic images of humans, that are "good enough" to be used to fine-tune a stable diffusion model, but i'm not sure if this is possible. I have experimented ...
interesting's user avatar
0 votes
0 answers
35 views

Method of encoding vector graphic data for a GAN

I am working with vector data that I want to train a GAN on. The vector data is a combination of the following forms of vector primitives: Lines - format: ...
JS4137's user avatar
  • 143
1 vote
1 answer
193 views

Math behind Diffusion models explanation?

I am recently reading this wonderful article https://lilianweng.github.io/posts/2021-07-11-diffusion-models/#what-are-diffusion-models about the math behind the diffusion models , As i dont have a ...
mat's user avatar
  • 13
2 votes
1 answer
120 views

how the GAN architecture maintain similar images close in the latent space?

I am learning about generative models, and I don't quite understand how the GAN architecture can maintain similar generated images close in the latent space. For example, an autoencoder and a ...
Cesar Ruiz's user avatar
3 votes
2 answers
715 views

Implementing a GAN with control over the output class

I am trying to accomplish the reverse of the typical MNIST in machine learning using a GAN - instead of predicting a number from an image of a digit, I want to reconstruct an image of a digit from a ...
JS4137's user avatar
  • 143
0 votes
2 answers
65 views

Are popular songs considered outliers to AI

I was thinking about making an adversarial network to generate popular music, so one AI which generates and then two others which detect whether the song is AI generated and the expected view count of ...
Alex Breeze's user avatar
0 votes
1 answer
51 views

StyleGAN runtime phenomenom

I was playing around with MobileStyleGAN pretrained model and multithreading and came along with an interesting phenomenom. After a while application is running MobileStyleGAN starts to produce video ...
harism's user avatar
  • 125
1 vote
1 answer
81 views

Comparison of the two alternative forms for the KL divergence [closed]

On page 468 of 'Pattern Recognition and Machine Learning', what does 'the same variables given by the product of two independent univariate Gaussian distributions' mean? The PDF says, The green ...
diffusion stable's user avatar
0 votes
0 answers
20 views

Quantization Parameters when converting Quantized Transposed Convolution to Conv2D

A simple way to compute TransposedConv2d is to convert it to a regular Conv2d by padding the input value with zeros, as is described in A guide to convolution arithmetic for deep learning. Does this ...
Necrotos's user avatar
0 votes
1 answer
208 views

Why does the critic of WGAN-GP run more steps than the generator?

As noted in the paper introducing WGAN-GP (see the pseudo-code), for each minibatch of data, the generator's weights are updated only once, and the critic (or discriminator) is updated multiple times. ...
Value_Investor's user avatar
0 votes
0 answers
94 views

Unstable Progressive GAN Training with Exploding Gradients when Fading in New Layers

I'm trying to implement and train a Progressive GAN for TensorFlow (to generate faces like the CelebA dataset), following along with the original paper (https://arxiv.org/pdf/1710.10196.pdf), as well ...
alexdea's user avatar
1 vote
1 answer
223 views

What are alternatives to Inception Score? Can it be used for non-photographic image types?

Most online sources recommend using versions of the Inception score to evaluate the synthetic images generated by a GAN. These scores are pre-trained on the InceptionV3 model. Does this mean that ...
ThreeOrangeOneRed's user avatar
1 vote
1 answer
59 views

Which face filter algorithms can work on CPU or integrated GPU?

I see many realtime face swap filters and appearance enhancement filters on smartphone apps. Even apps that can make you look like a granny or show you having a frown, no matter what your actual ...
Julia's user avatar
  • 113
0 votes
1 answer
41 views

Query regarding the minimax value function of GANs

In the book Generative AI with Python and TensorFlow 2 from Babcock and Bali (page 172), it is stated that the value function of a GAN is the following: where D(x) is the output of the discriminator ...
Claudia P's user avatar
0 votes
1 answer
84 views

References for synthetic images generation from small datasets (~10-50 images)

I'm looking a references (papers / works) for synthetic image generation from small datasets. By small dataset, I mean 10-50 images. I assume, that the best approaches should be based GAN (cGAN ?) or ...
Michael D's user avatar
  • 101
-2 votes
1 answer
55 views

I'd like some suggestions on how to effectively master machine learning. I'm new to this and I'm kinda lost [closed]

Thing is, I got a lot of resources to learn from and I have no idea which ones will be the most effective, and where to start. I've come across 2 kinds of books, the ones which talk about the ...
Meerkat's user avatar
0 votes
1 answer
137 views

Keypoint generation in 3D point clouds with Deep Learning

I have a huge dataset of 3D point clouds (each point consists of X,Y,Z coordinates) and another dataset with keypoints (also X,Y,Z) which lie on quite recognizable structures in the point cloud. As a ...
nmb's user avatar
  • 1
0 votes
1 answer
492 views

How to prevent vanishing/exploding gradients in a GAN with large mini-batch size?

I am training several different GAN architectures, and I noticed that larger batch sizes may lead to vanishing or exploding gradients. In the interest of accelerating training, however, larger batch ...
postnubilaphoebus's user avatar
1 vote
2 answers
1k views

Converting RGB images to Thermal Images

I am working on a project where I am planning to convert RGB images to thermal images. I can convert to either near infrared spectrum images or far infrared spectrum image. I am planing on using ...
programmer_04_03's user avatar
1 vote
0 answers
244 views

How can I solve the blurring problem in GAN generated images?

In my project I work in dresses dataset. I can solve the problem of black pixels but blurring still existed. I tried many computer vision filters like median filter, Biliteral filter, Sharpen methods ...
Abeer Elmorshdy's user avatar
3 votes
0 answers
384 views

GAN : Why does a perfect discriminator mean no gradient for the generator?

In the training of a Generative Adversarial Networks (GAN) system, a perfect discriminator (D) is one which outputs 1 ("true image") for all images of the training dataset and 0 ("false ...
Soltius's user avatar
  • 271
-1 votes
1 answer
140 views

Combination of VAE with GAN

I am going to implement a lecture which it aims to generate new images. It uses a variational autoencoder to produce latent vector and then feed it to a gan network as input. My question is, in ...
Pedram Yazdipoor's user avatar
1 vote
0 answers
159 views

Is it possible to combine DDPM with GAN?

From what I understand in GAN, the main idea is that you have a generator and a discriminator network that are "competing" with each other. The generator trying to make images that the ...
Nikita Belooussov's user avatar
0 votes
1 answer
392 views

Using GANs to generate data augmentations for YOLOv5

I was building a YOLOv5 object detection model, and was looking into researching synthetic methods like GANs to increase the size of my training set in an unsupervised manner. I know that few-shot ...
Nebula's user avatar
  • 3
0 votes
1 answer
37 views

Can any GAN's utilize labels in their datasets while they are training?

It seems to me that the Generative Adversarial Networks have a practical issue when trying to reproduce some of their output images For example, as you can see https://www.youtube.com/watch?v=...
user1833028's user avatar
0 votes
1 answer
66 views

Best way to generate a human face over a face generated by FaceFormer framework?

FaceFormer framework generates a talking face from audio, focusing on the lip and face movement when a person talks. Now from that what would be the best way to generate a human face on top of that? I ...
Sadaf Shafi's user avatar
1 vote
2 answers
858 views

GAN with multiple discriminators

I am looking for literature recommendations regarding GANs with multiple discriminators. In particular, I am looking for examples where each discriminator has a slightly different learning objective, ...
postnubilaphoebus's user avatar

1
2 3 4 5 6