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.

GAN refers to Generative Adversarial Networks.

Such networks is made of two networks that compete against each other:

The first network generates new samples, based on random input samples to create variability
The second network discriminates between generated samples and true samples. It usually entails running the first network to generate a new sample and the discriminator network must tag it as artificial. At the same time, a true sample is passed in the discriminator to and this one must be tagged as non artificial.

By optimizing the first network in alternance with the second one, more and more realistic samples will be created by the generative network which can then be used without the discriminator once trained.

235 questions

votes

3 answers

GANs (generative adversarial networks) possible for text as well?

Are GANs (generative adversarial networks) good just for images or can they be used for text as well? Like training a network to generate meaningful text from a summary. UPD - quotes from the GAN inventor Ian Goodfellow. GANs have not been applied…

gan

asked Nov 18 '17 at 08:31

Open Food Broker

votes

1 answer

what is the main difference between GAN and autoencoder?

what is the main difference between GAN and other older generative models? what were the characteristics of GAN that made it more successful than other generative models?

gan generative-models

asked Jul 04 '19 at 19:11

Muhammad Hanif Sarwari

votes

1 answer

What is the difference between ImageNet and ImageNet1k? How to download it?

Some papers mention just ImageNet and some papers mention ImageNet 1k database? What is the difference between these 2? Are they same or is the latter one subset of the former one? I'm working on Generative Adversarial Nets. I wanted to train it on…

gan databases

asked Mar 17 '19 at 07:58

Nagabhushan S N

votes

4 answers

How to calculate the output shape of conv2d_transpose?

Currently I code a GAN to generate MNIST numbers but the generator doesnt want to work. First I choose z with shape 100 per Batch, put into a layer to get into the shape (7,7, 256). Then conv2d_transpose layer to into 28, 28, 1. (which is basically…

neural-network tensorflow convolutional-neural-network gan generative-models

asked Jan 09 '18 at 19:14

snowparrot

votes

4 answers

Can we generate huge dataset with Generative Adversarial Networks

I'm dealing with a problem where I couldn't find enough dataset(images) to feed into my deep neural network for training. I was so inspired by the paper Generative Adversarial Text to Image Synthesis published by Scott Reed et al. on Generative…

deep-learning gan

asked Apr 04 '17 at 11:26

Alwyn Mathew

votes

3 answers

How to use GAN for unsupervised feature extraction from images?

I have understood how GAN works while two networks (generative and discriminative) compete with each other. I have built a DCGAN (GAN with convolutional discriminator and de-convolutional generator) which now successfully generates handwritten…

feature-extraction unsupervised-learning gan

asked Mar 09 '17 at 13:17

exAres

votes

2 answers

Automatically generating images for an art show with deep learning software

My pursuit is to generate something like a grottesque(a kind of painting producing human-animals and plants hybrids). I need to do something like this painting in order to create an art exhibition. I don't need that produced images are ordinate or…

neural-network deep-learning algorithms gan

asked Apr 16 '18 at 08:07

Nico Ghira

votes

1 answer

What are "VGG54" and "VGG22" derived from the VGG19 CNN?

In the paper Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network by Christian Ledig et al., the distance between images (used in the loss function) is calculated from feature maps extracted from the VGG19 network.…

deep-learning cnn gan

asked Dec 31 '17 at 14:46

Lafayette

votes

1 answer

Why Gaussian latent variable (noise) for GAN?

When I was reading about GAN, the thing I don't understand is why people often choose the input to a GAN (z) to be samples from a Gaussian? - and then are there also potential problems associated with this?

deep-learning gan gaussian

asked Mar 16 '19 at 22:27

asahi kibou

votes

1 answer

Train a GAN on "before and after" images of dental surgeries

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:…

tensorflow computer-vision gan vae

asked Mar 21 '20 at 05:21

Lakshay Dulani

votes

1 answer

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 discriminator much of the time. Could I then use the…

neural-network classification gan

asked Jan 09 '20 at 20:34

rgov

votes

3 answers

Why do I get an OOM error although my model is not that large?

I am a newbie in GPU based training and deep learning models. I am running cDCGAN (Conditional DCGAN) in TensorFlow on my 2 Nvidia GTX 1080 GPUs. My data set consists of around 320,000 images with size 64*64 and 2,350 class labels. If I set my batch…

tensorflow gan gpu

asked Mar 14 '19 at 01:51

Ammar Ul Hassan

votes

3 answers

Are there any actual, commercial uses of GANs already?

Doing research on the internet, I found many scientific papers, ideas, and experiments concerning GANs. But I was unable to find a single example of it being already used commercially. Q1 can you give examples of companies already using GANs in…

machine-learning deep-learning neural-network gan generative-models

asked Feb 01 '19 at 12:15

Przemysław Czechowski

votes

1 answer

GAN vs DCGAN difference

I am trying to understand the key difference between GAN and DCGAN. I know that DCGAN uses a convolutional network. But: What data is better to push into GAN and what data fits better to DCGAN? Does DCGAN work better with small data dimensions?

deep-learning convolution gan

asked Jun 05 '18 at 12:51

CezarySzulc

votes

2 answers

Strange patterns from GAN

I'm doing experiments with GAN. I've successfully trained GAN on 28x28px MNIST dataset (samples scaled to (-1,1) interval) My next experiment is to train GAN on bigger images. My dataset consists of grayscale 128x128px images. I've added one more…

deep-learning keras convolution gan generative-models

asked Sep 25 '17 at 14:23

Peter

2 3

…

15 16 Next