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.

Filter by
Sorted by
Tagged with
1 vote
1 answer
24 views

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 ...
  • 9
0 votes
0 answers
9 views

What is the difference between a perfect image-GAN and duplicating the photo a billion times and having auto-photo-shop?

What is the difference between a perfect image-GAN and duplicating the photo a billion times and having automatic Adobe photoshop to do style-transfer/deep-dream? I can't tell you what the advantage ...
0 votes
0 answers
20 views

Interpreting GAN loss

I'm using the standard implementations of the DCGAN paper in PyTorch with one variation. I'm introducing multiple Discriminators and I have trouble understanding the plotted loss and what is going ...
  • 1
0 votes
2 answers
28 views

Why is my DCGAN not converging?

I'm training a tf DCGAN on the MVTec hazelnut dataset and I found some difficulties. The problem is that after a lot of epochs the generate does not produce some quality images. My model is the ...
  • 1
1 vote
0 answers
28 views

Minor error in Ian Goodfellow's GAN optimality proof

I've been thinking of a part of the proof of the optimality of GANs from the original paper, and I can't manage to solve what seems to be an error. The paper states that the maximum of the function $y ...
1 vote
0 answers
18 views

Why is my GAN diverging?

I am trying to train a GAN related to this project. At ~100k steps, the discriminator's fake loss suddenly went to 0, and real loss increased very high. (Can look at the plots below). What could be ...
0 votes
0 answers
9 views

Is GAN better than DBNs?

I understand that they are different models and work differently, but they are both generative models and can both be used to do feature learning and classification. Is GAN most of the time better ...
  • 1
0 votes
0 answers
18 views

Do we know why GAN-based data augmentation works?

Although I've seen many examples of GAN-generated synthetic data greatly improving the performance of models, I struggle to understand how this is possible. Say we are training a classifier $h$ to ...
0 votes
0 answers
67 views

GAN - discriminator loss remains at a constant value while the generator loss decreases?

I am building my first GAN network, and I noticed that sometimes the discriminator loss remains at a constant value while the generator loss decreases. I couldn't find an explanation - if the ...
0 votes
0 answers
6 views

Why is FID so popular for evaluating GANs and other generative models?

The FID seems to be the most popular evaluation metric for GANs and other generative models. Why is it so popular? It seems to have some obvious issues, such as the assumption of Gaussian ...
1 vote
0 answers
7 views

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 ...
  • 113
0 votes
0 answers
10 views

WGAN-GP: how to understand whether my networks are working as they are supposed to?

I am training a WGAN-GP. Is there any way to verify whether my networks are working as they are supposed to during training? I have no feeling about the outputs of my networks. I do not want to wait ...
  • 1
1 vote
0 answers
11 views

In which way GAN generator transforms the data(for transforming a noise to the data)?

I have the problem: I understood how GAN works in general, but I need information how it work detailed. The part I don't understand is how the random noise at input is transformed to data on the ...
  • 11
0 votes
0 answers
30 views

Predicting a signal based on other signals

I want to predict a signal based on other related signals, how would I go about doing this? My current approach is to do some feature extraction (in the time and frequency domain) on both the ground ...
1 vote
0 answers
20 views

Is it right to argue that a testing dataset is not needed when evaluating the performance of a GAN?

For my degree final project I have been working on a GAN to solve a certain image enhancement task. The problem I’m currently working on has an extremely limited number of datasets due to the physical ...
0 votes
0 answers
12 views

How do GANs learn category distributions

I'm currently getting more into the topic of GANs and Generating Models. I've understood how the Generator and Discriminator work together in optimization to generate synthetic samples. Now I'm ...
  • 1
0 votes
0 answers
53 views

CycleGAN: Both losses from discriminator and generator drop fast, after 100 epochs outputs blurred original image

I'm trying to train a 3D Cycle-GAN on medical image synthesis, more specifically CT to MR. Currently I'm using a 3-Layer Discriminator and a 6 layer UNetGenerator borrowed from the official CycleGAN ...
0 votes
0 answers
8 views

proper solution to synthesize nailart on hand picture

I'm trying to synthesize nailart on hand picture. Next 3 steps are what I'm trying to do. take hand pictures select options like color, cubic .. etc synthesize And the way I thought to solve this is ...
  • 1
1 vote
0 answers
35 views

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 ...
0 votes
0 answers
32 views

Keras Backpropagation when Later Layers are Frozen

I am working on a project with facial image translation and GANs and still have some conceptual misunderstandings. In my definition of my model, I extract a deep embedding of my generated image and ...
0 votes
0 answers
17 views

Can I use Variational Autoencoder/GAN for image manipulation?

I have a CT image with the tumor and the corresponding Radiotherapy image. I want to predict the CT-Image with the corresponding change. For my training, I do have input CT image, Radiation therapy ...
0 votes
0 answers
21 views

Is there any papers on adaptive discriminator augmentation in 3D?

I am really impressed with the results of ADA in action. Currently I work with 2D data (normal png images) but I would like to train StyleGAN2 + ADA in 3D space. Is there any papers/implementations ...
0 votes
0 answers
29 views

WGAN with simplest data

I want to train WGAN (pyTorch) to generate this simple data. Here below my generator and critic architechtures: ...
0 votes
0 answers
17 views

Generation of similar images with a neural network

Are there some known neural networks that, given an input image, can generate a similar image, with the same topic? Example: input = a photo of a cat on a green tablecloth, output = a generated photo ...
0 votes
0 answers
55 views

Affine transformation in Style gan

I'm reading Style GAN paper and in style gan, we are passing the vector "W" through "A". I didn't understand what exactly the "A" is doing. In paper, it's mentioned ...
  • 1
0 votes
0 answers
74 views

Predict sequence using seqGAN

I am trying to create a GAN model in which I am using this seq2seq as Generator and the following architecture as Discriminator: ...
  • 53
0 votes
0 answers
158 views

Image normalization and reverse normalization: colors lost on image generation (GAN)

I'm working on a Gan. Based on different papers, I use a Tanh activation function on the last layer of the generator. Which produces [-1,1] outputs. To make this coherent, I use image normalization ...
  • 3
2 votes
1 answer
74 views

RCNN to predict sequence of images (video frames)?

In the following work the authors apply a convolutional recurrent neural network (RNN) to predict the spatiotemporal evolution of microstructure represented by 2D image sequences. In particular, they ...
0 votes
1 answer
22 views

Gan paper: sampling the distribution

In the Gan paper it is said page 3 Figure 1: "The lower horizontal line is the domain from which z is sampled, in this case uniformly. The horizontal line above is part of the domain of x. The ...
  • 3
0 votes
0 answers
6 views

Symmetry when using the Kantorovich-Rubinstein duality

In the WGAN-paper, an equivalent formulation of the Wasserstein distance is used. From my understanding, the Wasserstein distance is symmetric, but the version in paragraph 3 doesn't seem like it is. ...
0 votes
0 answers
14 views

Latent Space/Vector of StyleGANv1

I was going through the paper titled "A Style-Based Generator Architecture for Generative Adversarial Networks". You can find this paper here. I have the following two doubts: The generator ...
1 vote
1 answer
333 views

In my GAN model, the discriminator loss quickly descends to magnitudes of $10^{-4}$ while generator loss is at levels of 5+?

I am creating a Generative Adversarial Network (GAN) for generating artificial trading cards, but I am a complete novice in the field. The problem I'm consistently having is that my discriminator, ...
0 votes
0 answers
11 views

Synthetic Tabular Datta

I have found many examples of GANs on github for generating synthetic tabular data. I am trying to emulate this google collab notebook for synthea data. https://colab.research.google.com/drive/...
0 votes
1 answer
45 views

Connection between GANs and adversarial learning

Is there a connection between: "Adversarial Learning" (AL) and "Generative Adversarial Networks" (GANs)? Is it valid to say that GANs employ AL?
  • 1
0 votes
0 answers
14 views

Is it possible to have ACWGAN

We have ACGAN model where the vanilla or basic GAN architecture. But in the same way can we have ACWGAN and ACWGAN-GP architectures for specific class image generation?
1 vote
1 answer
63 views

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 ...
3 votes
0 answers
89 views

VQ-GAN understanding

I tried to understand how VQ-GAN works, but unfortunately I have not understood it. I tried to read some articles about it and watch a video. I believe a good and simple article will help me. You ...
0 votes
1 answer
50 views

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 ...
2 votes
2 answers
144 views

How to replace the clothes of person using GAN?

I have one source video, let us say if the person is standing or walking in the video, the person's clothes should swap with the destination image (contain the picture of any clothes). I would like to ...
  • 219
0 votes
0 answers
34 views

GAN model with different optimization functions

Building GAN model contains the following steps: Build generator model, and choose ...
1 vote
0 answers
64 views

DCGAN - advise on why the training is not working

Objective Seeking for suggestions and advice why the DCGAN training is not working. Task Train DCGAN to learn to generate CIFAR10-like images. Each CIFAR10 image has the shape (32,32,3) where (32x32) ...
  • 513
1 vote
1 answer
34 views

Understanding math notation in infoGAN paper

I'm reading this paper about mutual information in infoGAN infoGAN_paper_link and already have the code to run it. I pretty much found code for it which is fine and dandy except for the fact that I ...
  • 309
1 vote
0 answers
19 views

SAGAN - what is the correct architecture?

Hi, in the original paper the following scheme of the self-attention appears: https://arxiv.org/pdf/1805.08318.pdf In a later overview: https://arxiv.org/pdf/1906.01529.pdf this scheme appears: ...
  • 157
3 votes
1 answer
2k views

Is a multi-layer perceptron exactly the same as a simple fully connected neural network?

I've been learning a little about StyleGans lately and somebody told me that a Multi-Layer Perceptron, MLP, is used in parts of the architecture for transforming noise. When I saw this person's code, ...
  • 309
0 votes
1 answer
52 views

Question About Discriminator of CycleGan

The Discriminator of CycleGan outputs not just a single value to say that the image is real or fake.... But It outputs a grid of numbers (like 8X8 or 7x7), where each number says whether one patch of ...
1 vote
0 answers
27 views

How does the GAN based prediction in K. Zhang et al. (2018) improve performance?

In Stock Market Prediction Based on Generative Adversarial Network by K. Zhang et. al, the authors feed financial data (X0...Xt) into an LSTM to predict Xt+1. Then, they evaluate whether the series (...
  • 584
1 vote
0 answers
26 views

Generative adversarial network error in training process

I'm trying to make GAN which will generate art from random noise. I rely on this article https://towardsdatascience.com/generating-modern-arts-using-generative-adversarial-network-gan-on-spell-...
2 votes
1 answer
168 views

Channels in CNN/GAN

I found this article about art generation which uses GAN architecture to generate art. Let's move to part where we define our generator model. ...
1 vote
0 answers
42 views

Using StyleGAN for generative design of aircraft

I haven't worked on a machine learning project in a year and now that I am in university I am trying again :) Anyway, the end goal is to create a GAN that can design aircraft. I was inspired by the ...
0 votes
1 answer
115 views

Get data from intermediate layers in a Pytorch model

I was trying to implement SRGAN in PyTorch and I have to write a Content loss function that required me to fetch activations from intermediate layers for both the Generated Image & Original Image. ...

1
2 3 4 5