Questions tagged [generative-models]

For questions about models designed for generating new data (or generating samples from a probability distribution).

Filter by
Sorted by
Tagged with
2
votes
1answer
27 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
1answer
7 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 ...
2
votes
1answer
39 views

Why does SVM considered as discriminative model?

I read in several places that SVM is a discriminative model, but SVM has no statistical aspects per se, by that I mean that is does not estimate any probablity, specifically the postirior distribution ...
1
vote
1answer
18 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, ...
1
vote
0answers
27 views

Train a parametrized model to sample from a known target distribution

I wonder if there is a way to train a parametrized model to sample from a known distribution such as Gaussian. We usually don't need a model to sample from a known distribution (if we know the CDF for ...
1
vote
0answers
12 views

What kind of machine learning model beautiful.ai and others use for slide generation?

Hope this question belongs here. Constantly I see advertising from some sites and services that they generate content with AI (machine learning). I was wondering how beautiful.ai, slidebean, even ...
2
votes
1answer
172 views

Which type of models generalize better, generative or discriminative models?

In NLP, which type of models (generative or discriminative) is more sensitive to the amount of data to generalize better? references? This is related to the way those two types capture the data ...
0
votes
0answers
6 views

Understanding forward process in diffusion models

I was reading a blog on diffusion models where I came across this expression. I didn't understand why it is \begin{align} \sqrt[]{1-\beta \small{t}}*\large{x}\small{t-1} \end{align} and what exactly ...
0
votes
1answer
13 views

Assess the goodness of a ML generative model (text)

Take a RNN network fed with Shakespeare and generating Shakespeare-like text. Once a model seems mathematically fine, as can be assessed by observing its loss and accuracy over training epochs, how ...
1
vote
0answers
31 views

Monte Carlo Markov Chain

I was trying to figure out what is a Monte Carlo Markov Chain. From what I understand it is a way of computing an approximation of a probability distribution, which cannot compute exactly. So we ...
0
votes
0answers
12 views

Does there exist a "content transfer" like a neural style transfer?

Normally, a neural style operation works by taking a content image and a style image. A third image is optimized to have the same content as the content image and the same style as the style image by ...
0
votes
0answers
18 views

Generating unique points with an auto-encoder

I have been working on some research using a type of auto-encoder to generate new points with specific desirable properties. I trained my network and successfully generated some points, but when I ...
1
vote
0answers
73 views

Best way to find nearest neighbor distance for large datasets

I am a grad student doing research using generative machine learning with pytorch, and I have generated a set of points. I would like to check how similar these new points are to the points I used in ...
1
vote
0answers
18 views

Text generation with deep neural network?

For my master's project, I have to build a deep learning model for text generation: the model learns on a set of sentences, then it generates new sentences based on those from which it learned. I ...
0
votes
0answers
8 views

Latent space optimization for sketch to image translation

I've been given a task to try and use [http://www.vision.huji.ac.il/lord/][1] architecture for the task of translating sketches to images (take for example the edge2shoes dataset) Now this ...
2
votes
1answer
36 views

What are the math Prerequisite for understanding 'First Order Motion Model for Image Animation' Paper?

This is the 'First Order Motion Model for Image Animation' Paper. But I don't understand most of the mathematical things in the paper. What are the math Prerequisite for understanding this paper?
0
votes
0answers
19 views

Scene Graph Generation. How to choose a loss function

I am implementing a paper Graph R-CNN for Scene Graph Generation They say: For P (E|V:I), we use another binary cross-entropy loss on the relation proposals. This ...
0
votes
0answers
30 views

GAN model with different optimization functions

Building GAN model contains the following steps: Build generator model, and choose ...
0
votes
1answer
49 views

How can I generate handwritten notes given any handwriting sample and text file?

I am new to ML/DL and looking for a good way to generate a handwritten (simulated) file given 2 inputs: A set of sample handwritten notes (for training). All notes will be from the same person. A ...
1
vote
0answers
15 views

How do I initialize a Hidden Markov Model when using MFCC features for speech recognition?

I have a personal dataset of 10000 audio files, each consisting a single spoken sentence. These files each have the transcribed text labels with them that I can use for supervised HMM training. Now ...
0
votes
1answer
32 views

Forecasting with Neural network and understanding which underlying model is favoured

If I have a very large set of data (~ 1TB). How can I use Neural Network on this data to understand which underlying distribution (eg. let's say a Gaussian or a Poissonian with a certain mean, sd) is ...
0
votes
0answers
25 views

Understanding the ResnetGenerator in the CycleGan Model

In their famous research paper on CycleGans, the authors implement - well, a CycleGan. There are two discriminators and two generators for the CycleGan. Now, they also provide their neural networks ...
0
votes
1answer
18 views

Image parameters for SRGAN

In some implementations of SRGAN I've noticed, that datasets consist of the high-resolution images and the low-resolution images are created later by, e.g. resizing (decreasing the size) hr-images. ...
0
votes
0answers
49 views

How to evaluate pix2pix?

As far as I know, to evaluate synthesized images it is proposed to use: human scoring, "Inception score", where in the second case the quality is rated based on a pre-trained Inception ...
1
vote
0answers
6 views

Training with different datasets for the same better VAE model yields poor results

The VAE model I used here https://github.com/keras-team/keras-io/blob/master/examples/generative/vae.py. It can produce very well results for the minist and fashion minist dataset. But when I use my ...
0
votes
0answers
29 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 ...
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 ...
1
vote
0answers
14 views

What are the motion planning benchmarks?

Suppose I wanted to try and improve on existing motion planning algorithms. What benchmarks should I be trying to beat? Papers with code site has no motion planning benchmarks. I searched online and ...
1
vote
1answer
55 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 ...
2
votes
1answer
22 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?
2
votes
1answer
49 views

How to build Generative Model when we have more than one variable

I have a data-frame which has looks similar to this: A B C 1 2 2 2 4 3 4 8 5 9 16 7 16 32 11 22 43 14 28 55 17 34 67 20 40 79 23 ...
1
vote
1answer
126 views

Training a Variational Autoencoder (VAE) for Random Number Generation

I have a complicated 20-dimensional multi-modal distribution and consider training a VAE to learn an approximation of it using 2000 samples. But particularly, with the aim to subsequently generate ...
2
votes
1answer
238 views

Transformer masking during training or inference?

I'm working through Attention is All you Need, and I have a question about masking in the decoder. It's stated that masking is used to ensure the model doesn't attend to any tokens in the future (not ...
1
vote
1answer
115 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). ...
0
votes
0answers
21 views

accessing individual layers from a saved model

I am in the process of writing a model where I have the layers of the model in the "def _init_( )" section of a class I want to save and load the model in the class' variables where i ahve ...
3
votes
1answer
124 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
31 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
27 views

Magenta MusicVAE/GrooVAE conditioning

I want to try different methods of conditioning the decoding process of the Variational Autoencoder Models of the Google Magenta project for my own research project. As far as I can tell, MusicVAE has ...
1
vote
0answers
79 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 ...
1
vote
0answers
171 views

MNIST GAN generator loss increasing

I'm trying to train a simple vanilla GAN on MNIST with Tensorflow. I used this github page as a reference and in my process to try and get my GAN to work I've made my code more and more similar to ...
1
vote
1answer
351 views

How to make custom callback in keras to generate sample image in VAE training?

I'm training a simple VAE model on 64*64 images and I would like to see the images generated after every epoch or every couple batches to see the progress. when I train the model I wait until the ...
0
votes
1answer
2k views

Is it possible to train stylegan2 with a custom dataset using a graphics card that only has 6GB of VRAM (GeForce GTX 1660)?

I'm attempting to train stylegan2 using a custom dataset, but no matter what settings I use I see the same error: ...
1
vote
0answers
17 views

Limits of generative models

If I was to train a pixel rnn, by concatenating images with noise vectors, I should be able to get new images from that distribution by starting on the prediction with a new noise vector. Would it be ...
1
vote
0answers
214 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 ...
1
vote
0answers
64 views

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

Instead of clipping to the range $[-c,c]$ in WGAN (Wasserstein generative adversarial network), why not smoothly map into the range $[-c,c]$ by using $c\times \mathrm{tanh}(w)$? This would guarantee ...
1
vote
0answers
186 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 ...
2
votes
1answer
3k 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 ...
6
votes
3answers
826 views

Is it possible to use a generative model to "share" private data?

Let's say we have some data set, with lots of instances $X$ and a target $y$. If it is of some importance, you may assume that it is a "real life" data set : medium sized, with important correlations, ...
1
vote
0answers
49 views

Reinforcement learning in bidirectional RNN

I have been self-learning deep generative neural network for a while. I am okay with the basics but I really need some guidance and jump start. I have recently came across this paper “Bidirectional ...