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
0
votes
0answers
9 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
1answer
35 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
0answers
74 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
0answers
17 views

GAN that generates locally accurate results

I'm wondering if there are any resources for problems of the following nature: Instead of training a GAN on a bunch of different faces, train a GAN on a very small number of faces (even 1), and ...
0
votes
1answer
15 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 ...
0
votes
0answers
22 views

Question on hinge loss for GANs

I'm currently experiencing some difficulty with the hinge loss optimizer for GANs. In the equation below, the discriminator is looking to minimize $L_D$ and the ...
0
votes
0answers
18 views

How to swap the clothes of person with some clothes using GAN? [duplicate]

I have one source image of person , the persons clothes should swap with destination image (contain the picture of any clothes) .I want to use GAN , like use StyleGan for it . I am trying to find out ...
3
votes
2answers
83 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 ...
0
votes
0answers
22 views

StarGAN How to test discriminator

I'm running the following code: https://github.com/taki0112/StarGAN-Tensorflow I have my model pretrained. After the training I want to run the discriminator function to check its accuracy. Assume ...
0
votes
0answers
63 views

How to train a GAN to generate categorical variable

I am trying to train a simple GAN to generate a categorical variable size, which takes discrete values between 1-100. I am looking for some tips or directions on ...
0
votes
0answers
16 views

When training a cGAN on a X (B/W image) to Y (RGB image) "paired" dataset, how much will slight differences in the images matter in terms of results?

Right now I am working on a colorization project with GANs, and had originally settled on using a CycleGAN because I considered structuring my dataset in an unpaired manner. I've since been able to ...
0
votes
0answers
30 views

GAN model with different optimization functions

Building GAN model contains the following steps: Build generator model, and choose ...
1
vote
0answers
16 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) ...
1
vote
1answer
24 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 ...
0
votes
0answers
35 views

How to use mean IoU for RGB mask (keras implementation)?

I am training pix2pix GAN for converting SAR satellite images to segmentation mask. But I am not aware about how to use the mean IoU to evaluate my model. My output is of ...
1
vote
0answers
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: ...
1
vote
1answer
221 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, ...
0
votes
1answer
39 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 ...
0
votes
0answers
26 views

DCGAN: why does my generator has less loss then my discriminator?

I have constructed a DCGAN (deep convolutional generative adversarial network) inspired by this github repository. It is written in a more low level Tensorflow code that I tried transforming into ...
1
vote
0answers
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 (...
1
vote
0answers
22 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-...
0
votes
0answers
15 views

DCGAN: how do we construct the proposed CNN of the original DCGAN paper?

I am reading the original paper on the Deep Convolutional GAN (link: DCGAN paper) and on the fourth page the authors make a proposition on how to model the generator and discriminator as CNNs. However ...
0
votes
0answers
12 views

Weigthing discrimnator and generator loss in GAN networks?

Training of good generator model in vanilla GAN (Generative adversarial networks) https://papers.nips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf is achieved via minimax game, where <...
2
votes
1answer
57 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
0answers
32 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
1answer
55 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. ...
0
votes
1answer
2k views

How to Connect Convolutional layer to Fully Connected layer in Pytorch while Implementing SRGAN

I was implementing the SRGAN in PyTorch but while implementing the discriminator I was confused about how to add a fully connected layer of 1024 units after the final convolutional layer My input ...
0
votes
1answer
333 views

Improving the pix2pix Architecture for Sketch to Image Translation on a Dataset of Sketches of People to Photos of People

For a university project, I need to create a neural network that translates sketches of people into images. In order to implement such a neural network, I decided to implement a pix2pix GAN ...
1
vote
0answers
120 views

pix2pix GAN with Rectangular Image Dataset

I am currently working on a project (for university) which translates sketches of faces to images of this person. For implementing this, I decided to use a pix2pix GAN architecture. However, I have ...
0
votes
0answers
9 views

Regress to the mean problem

I was reading Video-to-Video Synthesis (link) paper, in related works for future video prediction it is mentioned that existing methods fail because of regress-to-the-mean problem. What exactly is the ...
1
vote
1answer
51 views

Using GANs to generate synthetic tabular data to improve supervised learning

One topic I see some people trying is using GANs to generate synthetic tabular data for supervised learning. Also as a way to oversample the minority class in a binary classification. For me creating ...
0
votes
1answer
29 views

How are pictures pre processed before being used as ML data

So I was watching this YouTube video So basically the professor used ML to generate random faces in order to create data for a Kaggle challenge. When I looked into the data file, I was expecting to ...
0
votes
2answers
61 views

When to use GAN over conventional sampling methods?

Let's say I have a dataset from a diabetes hospital which has 30000 Type 2 diabetes and 300 Type 1 diabetes patients. So this dataset has millions and millions of other data points like lab ...
-1
votes
1answer
27 views

How much GPUs are needed for Image ehancement? [closed]

I'm looking for a GPU to train my model. Most of the papers that I have followed used 2 or more gtx 1050ti card or higher. (MIRNet, EnlightenGAN) I need to that how much GPU power will it take to ...
0
votes
1answer
35 views

Image regression problem

I've tried a number of experiments with machine learning. From trying to use GANs to upscale images to playing with auto-encoders. There is one problem that haunts me and always ends up ruining my ...
1
vote
0answers
161 views

Understanding image size changes in DCGAN

I have been studying and trying to implement Generative Adversarial Networks using PyTorch. More precisely I tried to replicate the DCGAN PyTorch Tutorial tutorial using some custom dataset. My code ...
2
votes
1answer
20 views

Why a GAN trained on same data and same parameters may produce different results?

I am trying to train a Generative Adversarial Network and ran the training a few times with same dataset and same parameters but it seems tp produce different results. Why this may happen?
1
vote
0answers
60 views

Is it possible to use Inception Model in GANs (DCGAN) using PyTorch(or any other library)?

MAIN ISSUE: Is it possible to use Inception Model (e.g. v3) for DCGAN using PyTorch(any other library)? I've tried to find info how it could be implemented but nothing has been found. It was explained ...
1
vote
1answer
2k views

Should Discriminator Loss increase or decrease?

This question is purely based on the theoretical aspect of GANs. So, when training a GAN how should the discriminator loss look like? Should the loss of discriminator increase (as the generator is ...
2
votes
1answer
3k views

Tensorflow gradient returns nan or Inf [closed]

I am trying to implement a WGAN-GP model using Tensorflow and Keras (for credit card fraud data from kaggle). I mostly followed the sample code that is provided in Keras website and several other ...
3
votes
2answers
112 views

How is the Gaussian noise given to this BLSTM based GAN?

In a conditional GAN, we give a random noise along with a label to the generator as input. In this paper, I don't understand why in one section of the paper, they say they are giving the random noise ...
1
vote
1answer
103 views

what is meant by minimizing and maximizing in GANs?

It is a subtle change that involves the generator maximizing the log of the discriminator probabilities for generated images instead of minimizing the log of the inverted discriminator probabilities ...
0
votes
1answer
19 views

Generate series of values using Keras GAN architecture

I'm trying to generate something like that: Which is a random sample from my real data function (that i'm trying to mimic). ...
3
votes
1answer
111 views

Help interpreting GAN output, and how to fix it?

After a few tries, I had trained a GAN to produce semi-sensible output. In this model, it almost instantly found a solution and got stuck there. The loss for both the discriminator and generator were ...
1
vote
0answers
27 views

Checkerboard artefacts vs distinct objects in GANs

I found a very good solution for getting rid of checkerboard artefacts in GANs: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/190 Instead of using Transposed Convolution, use bilinear ...
1
vote
0answers
75 views

Fine tuning Conditional GANs for low data scenarios

I was wondering what the process was for fine tuning a conditional GAN. For example, say I wanted to generate pictures of an object X given a certain condition such as a sentence describing it, which ...
3
votes
1answer
34 views

Generative Adversarial Text to Image Synthesis

Can anyone explain the meaning of this line: "Deep networks have been shown to learn representations in which interpolations between embedding pairs tend to be near the data manifold". ...
2
votes
2answers
262 views

Using a part of a trained model in a custom loss function -Tensorflow

I want to write a custom loss function that uses the intermediate result of a trained discriminator. the loss function compares images. the loss function is for recovering the latent vector of an ...
1
vote
2answers
23 views

How discriminator loss generated?

The images generated by generator has no labels, then how do Discriminator loss is generated on the basis of classification of generator generated images.
0
votes
0answers
11 views

How would one modify CycleGAN in order to map a distribution to itself?

CycleGAN can map between two different distributions $X$ and $Y$ with cycle consistency. This is done with generator functions $F: X \mapsto Y$ and $G: Y \mapsto X$, such that $||G(F(x)) - x||_1 \...