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
11 views

How to generate several elements on image with input parameters

For example, i need to generate circles. I have dataset of images with non-intersecting circles and can generate random circles with DCGAN, but each circle has a different diameter. So I need to ...
0
votes
0answers
6 views

WGAN-GP slow critic training time

I am implementing WGAN-GP using Tensorflow 2.0, but each training iteration of the critic is very slow (about 4 secs on my CPU, and somehow 9 secs on Colab GPU). Is WGAN-GP usually this slow or ...
0
votes
0answers
5 views

How to grasp the full entropy of the distribution we want to model in GAN

In pix2pix GAN paper( https://arxiv.org/abs/1611.07004), authors found that the noise vector and the dropout are not efficient in grasping the full entropy of the data distribution we want to model. ...
0
votes
0answers
8 views

InfoGAN Learning Latent Categorical Code

While reading the InfoGAN paper and implement it taking help from a previous implementation, I'm having some difficulty understanding how it learns the discrete categorical code. The implementation ...
1
vote
1answer
18 views

Different optimizers for generator and discriminator in GAN

I've seen an advice about GAN implementation, that there should be different optimizers for generator (G) and discriminator (D). As I understand, it depends on how fast each model (G and D) ...
0
votes
0answers
7 views

Validation of Images generated using DCGAN

I have trained a Deep Convolutional Generative Adversarial Network(DCGAN) model and generated some images. Now, I need to validate these images if generated images ...
1
vote
0answers
14 views

GAN for illumination removal

i'm reading a paper using GAN to process illumination in image: https://ieeexplore.ieee.org/document/8545434. In the paper, the author mentioned using the SSIM loss for quality evaluation of the ...
0
votes
1answer
45 views

DC GAN with Batch Normalization not working

I'm trying to implement DC GAN as they have described in the paper. Specifically, they mention the below points Use strided convolutions instead of pooling or upsampling layers. Use only one fully ...
1
vote
2answers
43 views

Which service could I use to train my networks?

My laptop's Intel i7 3630QM 2.4GHZ, 8Gb RAM and GXForce 670M are clearly not sufficient... By reading some papers, I've written an SRGAN with Python Keras. At runtime there is no error but training ...
0
votes
1answer
11 views

SRGAN Generator Architecture: Why is it possible to do this elementwise sum?

Consider the first residual block. Its first convolution layer takes in inputs: THe PRELU's output 64 filters(64 outputs) each one being 3*3 with a stride of (1 ; 1) So I think that the output of ...
3
votes
1answer
32 views

How and Why to rescale image range between [0,1] and [-1,1]

I am trying to implement model described in Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network in which author says in section 3.2 that We scaled the range of the ...
0
votes
0answers
94 views

How to compute Frechet Inception Score for MNIST GAN?

I'm starting out with GANs and I am training a DC-GAN on MNIST dataset. The two metrics that are used to evaluate GANs are Inception Score (IS) and Frechet Inception Distance (FID). Since Inception ...
0
votes
2answers
13 views

Why does discriminiator accuracy falls to 0%, and is there a fix around this?

I am training a Vanilla-GAN(or original GAN 2016) on a pokemon dataset https://www.kaggle.com/kvpratama/pokemon-images-dataset, for few epochs the discriminator has 100% accuracy over the real ...
1
vote
0answers
15 views

How can one be assured that generative models are not memorizing dataset, and that they will generate an unique image outside of dataset?

If all GAN can do is capture the probability distribution of the dataset, then shouldn't they be similar to handing out images from the dataset? How can we verify that the images that they generate ...
0
votes
1answer
24 views

What does this symbol means, what operator is it?

I am confused about the $E_{x\sim P_{data}(x)}$, what does $E$ means here. I cannot find an appropriate answer on the internet, and hence I am trying data science stack exchange. Please help.
1
vote
1answer
51 views

Are mainstream pre-trained models useful as discriminators?

In the context of GANs I see many papers designing new discriminator networks. I'm curious about the usefulness of designing discriminators as modified versions of mainstream models like Inception, ...
0
votes
0answers
15 views

Thresholding in intermediate layer using Gumbel Softmax

In a neural network, for an intermediate layer, I need to threshold the output. The output of each neuron in the layer is a real value, but I need to binarize it (to 0 or 1). But with hard ...
0
votes
0answers
18 views

Problem regarding designing the generator function

I am implementing the paper Perceptual GAN for small object detection. The design is described by the picture given below. I have used Transfer Learning concept and used a pretrained model inside the ...
1
vote
0answers
16 views

Examples of using GANs to sort numbers?

Does anyone know of any publicly available GAN implementations to sort numbers with? As in, the input to the generator is an unordered sequence of numbers, and the goal of the generator is to output ...
1
vote
2answers
76 views

How discriminator knows if the image is real or fake at the initial phase?

If the discriminator and generator in GAN learn together, How the discriminator knows whether the image is real or fake in the initial phase of training? Does the discriminator need to get trained ...
0
votes
1answer
54 views

Comparsion between DCGAN and WGAN

What is the main architectural difference between DCGAN and WGAN? For which problems each models can be more useful than the other one?
0
votes
1answer
37 views

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?
0
votes
0answers
21 views

Training neural network to generate realistic terrain

I've recently had an idea to create a tool that makes it easier for environment artists to generate highly realistic terrain for video games. I've seen approaches using GANs and I'm familiar with the ...
0
votes
0answers
11 views

issues related to implementation of the paper 'Perceptual GAN for small object detection'

I am trying to implement the perceptual gan network using keras as backend. I am new in the field of GAN, can anyone provide me the model for perceptual GAN in keras backend
0
votes
1answer
19 views

Issues related to the code for ROI pooling from the feature map

I am trying to do ROI pooling on the feature map obtained from the VGG layers but I don't know how to code this layers. Can anybody help me out? Here is my VGG layers: ...
0
votes
0answers
12 views

Convert theano model to Caffe

Is there a way to convert a Theano model into a Caffe model? I've found several scripts that converts Caffe -> Theano but not the other way around.
2
votes
1answer
41 views

Implementation of the paper 'Perceptual Generative Adversarial Nets for small object detection'

I studied the research paper on Perceptual Generative Adversarial Nets for small object detection. There they have detailed the structure of Generator network as given in the picture below: I am new ...
0
votes
0answers
10 views

What is ideal loss scenario for Generative adversarial networks

I am trying to code and learn Auxiliary Classifier Generative Adversarial Networks (AC-GANs for short) from here. In this post ...
1
vote
0answers
22 views

Visualizing general adversarial network

I am working on a DC GAN model using my own data set. How can I visualize (see output) of the GAN generator to see how my network is working (replicating the training data)? Here is my code: ...
2
votes
1answer
35 views

Is conditional GAN supervised learning?

I am trying to understand this paper about conditional GAN, it says that extra information y (class labels) is given to the network. However, I cannot understand its usage during training or its ...
1
vote
1answer
33 views

Generating Synthetic Image to improve the performance of classifier

I need some suggestion from experts. For my project work, I have been learning about Generative Adversarial Network. I am trying to make a ...
0
votes
0answers
13 views

Using multi-channel input for a CNN, can one channel benefit from the other (in terms of resolution, texture etc.)?

I have one low resolution image (A) and a high resolution image (B) from another modality. A and B have statistical correlations at some arbitrary scale space. I would like to use the information from ...
1
vote
0answers
21 views

When is bias set to False?

I have been working with DC-GAN to generate pairs of images based on WGAN paper. For which I referred fastai notebook on WGAN where the bias in the network has been set to False. Jeremy Howard in his ...
0
votes
0answers
37 views

Map predictions to real text

I have read the paper "Learning to Read by Spelling" by Gutpa et al. They present a method for visual text recognition without using any paired supervisory data. In chapter 4 they describe how to ...
0
votes
1answer
25 views

Generative network understanding

I was going through GAN's notebook by fchallot on Generative Adversarial Networks where, in the Generator Network, he creates a Dense layer with $16*16 * 128$ (...
0
votes
0answers
43 views

Get label from CGAN or InfoGAN

So i'm trying to build a CGAN. I know you can have several labels and tell the GAN to generate an image from one. But what if i want to feed it an image and have it tell me if it's real or fake? Let'...
1
vote
0answers
30 views

CGAN - Shape must be rank 2 error

I'm trying to create a conditional GAN with the following code: learning_rate = 0.0002 batch_size = 128 epochs = 10000 ...
0
votes
1answer
30 views

Error on CGAN / InfoGan [closed]

So i'm trying to execute the code provided here: https://github.com/eriklindernoren/Keras-GAN/blob/master/infogan/infogan.py Both for InfoGAN and CGAN i get the same error: ...
2
votes
1answer
32 views

How to optimize the lambdas of a hybrid loss in a deep learning model

I am using a generative adversarial deep learning model (GAN) with a hybrid loss represented by a linear combination of four losses with three $\lambda$'s, something like: $total\_loss = loss_1 + \...
0
votes
0answers
55 views

Transposed convolution as umpsampling in DCGAN

I read several papers and articles where it is suggested that transposed convolution with 2 strides is better than upsampling then convolution. However implementing such model with the transposed ...
1
vote
2answers
648 views

GAN - am I seeing mode collapse? Common fixes not working

I have a 2 part question. Context I am learning about GANs and writing my own starting from the very simplest example of adversarial learning (1-parameter node), then implementing a very simple 1-...
0
votes
0answers
57 views

Label embedding in Auxiliary Classifier GANs

In Auxiliary Classifier GAN the generator takes two inputs, 1. one hot encoding of the labels, and 2. noise vector. But in the implementation of the GAN (e.g.:) some embedding is used, I think it is ...
2
votes
1answer
118 views

Where can I find out about the “Helvetica scenario”?

From the paper introducing GANs: It makes sense that collapsing too many $\vec{z}$-values to a single $\vec{x}$-value will cause problems. However, I was a bit confused as to how training $G$ for a ...
1
vote
0answers
35 views

Something is disastrously wrong with my neural network and what it's produced

I just got a neural network to run and although it doesn't raise any exceptions, I'm left with a horrible mess after 80 to 100 epochs: After 100 epochs with the adapted code: After 100 epochs with ...
1
vote
1answer
47 views

Understanding notation of Goodfellow's GAN objective function

What is the meaning of $V(D,G)$? How do we get these expectation parts? I was trying to understand it following this article: Understanding Generative Adversarial Networks (D.Seita), but, after many ...
1
vote
0answers
53 views

GAN optimizer settings in Keras

I am working on a Generative Adversarial Network, implementing in Keras. I have my generator model, G, and discriminator D, both are being created by two functions, and then the GAN model is created ...
0
votes
0answers
41 views

Dimension of feature vectors for classification task in the DCGAN paper

I am trying to implement one of the section in the DCGAN paper (https://arxiv.org/pdf/1511.06434.pdf) i.e. Using the Discriminator network trained on ImageNet-1k as a feature extractor to classify ...
2
votes
0answers
93 views

How to design the generator in generative adversarial network (GAN)?

I am new to GAN. And recently read a paper about how to implement GAN in recommender system here I have a question in the paper. The Eq (20) in the paper should ...
0
votes
1answer
29 views

In CycleGAN are there two different generators and two different discriminators?

I am trying to assimilate the contents of this paper. I have a confusion about how many different networks are there in the architecture of CycleGAN. To my understanding, the concept of cycle means ...
2
votes
0answers
90 views

Knowing when a GAN is overfitting (sequence classification study)

I have sequences of long, sparse 1_D vectors (3000 digits, made of of 0s and 1s) that I am trying to classify. I have previously implemented a simple CNN to classify them with relative success (with ...