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
4 views

How to train the generator in a Gan

I have trouble training my generator because I don't understand how the discriminator's (1 output) feedback affects the 784 generator's outputs. In my backpropagation function, I need to provide it ...
1
vote
0answers
9 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
19 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". ...
0
votes
0answers
13 views

Training Flags on Keras Layers

I'm pretty new the Tensorflow and Keras and I've started to build a simple GAN to analyze and then synthesize some time-series data. I would like to ask for some feedback to confirm my suspicions ...
0
votes
0answers
17 views

Best way to add border to rectangular images to train on StyleGAN2

TLDR: What is a best way to add borders to rectangular images with widely variable aspect ratios (from 0.5 to 2.0) to later use them as training data in StyleGAN2 with data resolution of 1024x1024 and ...
0
votes
1answer
29 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
12 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
9 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 \...
0
votes
1answer
14 views

Is my loss function right? WGAN

I am new to GANs, but I was able to train a DCGAN decently. I decided to try a WGAN (not the improved one). I seem to get outputs, but my loss doesn't seem to converge for the generator. I am using ...
1
vote
1answer
14 views

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 ...
0
votes
0answers
10 views

Using DCGAN on a (very small) dataset of art

I am developing a DCGAN using the this tutorial in PyCharm. As my usage of this tutorial suggests, I am quite new to DCGANs as I've previously only had a few experiences with machine learning ...
0
votes
0answers
12 views

BatchNormalization for GANs

I am currently implementing a GAN and I tried to find some "best practices" in several tutorials. One of the suggestions was to use BatchNormalization. I am familiar with the concept and know how it ...
0
votes
0answers
18 views

CycleGAN vs. AutoEncoder for transforming sketches into images

I'm playing around with the use of deep learning on images and done quite works : colorizing black and white images for example, or maybe fixing old damaged photos. Today I want to tackle a new ...
0
votes
0answers
19 views

Reward Function for NLP

I would like to design an reward function , I am training two models from the first model that classify set of texts(paragraphs and keywords) and I also got some hidden states. The second model is ...
0
votes
0answers
42 views

What is the purpose of the minus sign in Adversarial Autoencoder

Iam currently implementing an Adversarial Autoencoder. Based on the architecture shown in the original paper I interpret that the input of the Discriminator is either the random sample from the true ...
2
votes
1answer
28 views

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?
1
vote
0answers
26 views

Why -logD trick in GANs training work?

When training the generator, we want to minimize log(1 - D(G(z))) (this has a form of log (1-x)). Using graph calculator we plot and see that the slope of this function is very small at first, thus ...
5
votes
1answer
146 views

How can my Pytorch based GAN output pure B&W with no grayscale?

My goal is to create simple geometric line drawings in pure black and white. I do not need gray tones. Something like this (example of training image): But using that GAN it produces gray tone images....
0
votes
0answers
14 views

Database augmentation using Sobel filter (aka gradient)

I'm working in PyTorch and to improve a ProGAN training I'm augmenting a database by calculating, for each image, the horizontal and vertical gradient via the Sobel operator. Do you have any reading ...
0
votes
0answers
19 views

LOGICS: GAN with image as input instead of a noise vector

i am having an idea for a single-class classifier. I don't know if this is a logical "short circuit", though. The idea is the following: Instead of a noise vector, i use a "noise-image" as input for ...
8
votes
1answer
355 views

Train a GAN on “before and after” images of dental surgeries [closed]

I want a GAN to train on "before and after" images of dental surgeries; so that it can generate "after" pictures for fresh patients. Input images are like these: https://img.webmd.com/dtmcms/live/...
0
votes
0answers
18 views

Is the hyperbolic tangent function a solution to the weight clipping problem of WGAN?

Instead of clipping to the range [-c,c] why not smoothly map into the range [-c,c] by using c*tanh(w) ? This would guarantee the Lipschizt constant is no greater than c. The problem I am talking ...
1
vote
0answers
20 views

How can I know my GAN does converge?

I am training my GAN, and by looking at the loss curves of the generator and discriminator, I think I am going on the right way because from this blog, my curves look reasonable: A stable GAN will ...
0
votes
0answers
7 views

Picking a model to go ahead with for a WGAN

I have been trying to train a model using WGAN loss functions, working different learning rates to choose my hyper parameters based on advice. I was told to try looking into keeping everything simple ...
1
vote
0answers
32 views

GAN training the average of my train data

I have been training a GAN with 1D convolutional layers on sinus functions. However if I start varying my sinus (random amplitude for example), the model generates only the average of the random range....
1
vote
1answer
318 views

Inception Score (IS) and Fréchet Inception Distance (FID), which one is better for GAN evaluation?

IS uses two criteria in measuring the performance of GAN: The quality of the generated images, and their diversity based on the entropy of the distribution of synthetic data. On the other hand, FID ...
0
votes
1answer
40 views

Generator losses in WGAN and potential convergence failure

I have been training a WGAN for a while now, with my generator training once in every five epochs. I have tried several model architectures(no of filters) and also tried varying the relationship with ...
-3
votes
1answer
36 views

Solve an equation using machine learning [closed]

Imagine we have the following equation: y=xz. We have y but not other ones. Note that y is like a matrix and we could as many sample we want. It is the values obtained from sensors. This means it ...
0
votes
0answers
98 views

GAN loss suddenly explodes and model breaks

Almost every time I've tried to train a DCGAN using keras I find that the loss suddenly skyrockets and the model completely stops improving. I find this happens regardless of what combination of loss ...
0
votes
1answer
35 views

What would be a good loss function to penalize big differences and reward small ones, but not in a linear way?

I have an image with the differences between 2 other images. Concentrations of black pixels mean similar regions between the images, whereas, white values highlight differences. Thus I want a ...
1
vote
0answers
26 views

GAN generator producing distinguishable output

I am trying to train a special type of GAN called a Model-Assisted GAN (https://arxiv.org/pdf/1812.00879) using Keras, which takes as an input a vector of 13 input parameters + Gaussian noise, and ...
1
vote
1answer
46 views

GAN: Discriminator converges, generator learns almost nothing

In my GAN, the discriminator loss goes down steadily, while the generator loss oscillates / does not converge. I suspect this is due to the vanishing gradient problem. Theory: as the discriminator ...
1
vote
0answers
44 views

CycleGAN: Generator losses don't decrease, discriminators get perfect

So I´m training a CycleGAN for image-to-image transfer. The problem is: while the discriminator losses decrease, and are very small now, the generator losses don't decrease at all. The generator ...
1
vote
2answers
258 views

Does it make sense to do train test split when trainning GANS?

For normal supervised learning the dataset is split in train and test (let's keep it simple). Generative Adversarial Networks are unsupervised learning but there is a supervised loss function in the ...
0
votes
0answers
15 views

ways to implement multiple discriminators for GAN?

I'm tyring to build TTS system using GAN and was wondering if it's possible to build it using multiple discriminators and if I can, can you also explain how to? I'm building it using Keras.
4
votes
1answer
25 views

Metric to evaluate words generated by Neural Network

I have this task at hand and I would be grateful for some directions. Perfectly not the final solution as I would like to do it myself. Let's say I need to create new fruit names based on existing ...
2
votes
0answers
29 views

Generative Model for learning Periodic solutions 3-body/N-body problems

I am tasked with finding research where a GAN or any other generative model is used to generate new shapes of 3-bodies moving under the influence of each others' gravitational pull, in a periodic ...
6
votes
1answer
97 views

Using a GAN discriminator as a standalone classifier

The goal of the discriminator in a GAN is to distinguish between real inputs and inputs synthesized by the generator. Suppose I train a GAN until the generator is good enough to fool the ...
2
votes
0answers
138 views

One-hot encoding to embedded vector - BigGAN

I am trying to replicate a BigGAN architecture in Tensorflow https://arxiv.org/pdf/1809.11096.pdf but fail to understand exact nature of inputs. BigGAN generator has 2 inputs, noise ...
1
vote
1answer
79 views

GAN loss function [closed]

I am new to deep learning field and I want to synthesize as accurate as it can be, can someone tell me how to construct loss function for such model, any answer will be a great help please do not ...
0
votes
0answers
9 views

Spatial deformation in medical MR images

HI fellows I hope everyone will be good I just want to ask that what is spatial deformation and I want to apply this spatial deformation on medical MR images any answer will be helpful. Thanks and ...
2
votes
1answer
28 views

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 ...
2
votes
3answers
437 views

Is it possible to use Generative Adversarial Networks (GANs) for text classification?

I am working on the classification of fake and real news. I did use a CNN Model for this problem and got satisfactory results. But, I was just wondering if it's at all possible to use any type of GAN ...
1
vote
1answer
374 views

Error: An operation has `None` for gradient with categorical_crossentropy

I am trying to train my discriminator network using Keras with TensorFlow backend. The network is meant to classify the input into one of the 9 output labels. I am passing a 2D input (height, width, ...
0
votes
0answers
17 views

Do I need to train a separate DeepFake model for every input person?

I would like to create a deep fake model of a specific person (we will call him Steve). I would then like to be able to upload a video of any random person and swap their face with Steve's. So far I ...
0
votes
0answers
13 views

Conceptual help generating a text adventure game using a GAN

I have built a playable dungeon crawler game that lets a character progress through a series of randomly generated rooms filled with doors, chests, stairs, etc. Ideally, I would be able to display a ...
1
vote
0answers
66 views

Using a DCGAN to create an intrusion detection system

The TL;DR of my question is how do you write a discriminator and generator of a DCGAN in pytorch to accept a csv file instead of an image? I am attempting to partial recreate an experiment from the ...
1
vote
0answers
19 views

Generative Adversarial Networks - The simplest possible examples

I'm looking for the simplest possible examples of GANs. What would be simple yet illustrative examples with, say, univariate data and in which both the generator and the discriminator are as simple as ...
0
votes
1answer
56 views

What is a latent space vector?

I do not understand this about GANs. Apparently the Generator is supposed to receive a latent space vector as its input. Yet I couldn't find an example of how I can implement it in Pytorch. This is a ...