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
1 vote
1 answer
47 views

How to select relevant columns from a dataset with many features

I have a dataset with a large number of potential features (>100) and I am interested in finding a relatively small subset of these (maybe on the order of 5, or 20) features which is best suited to ...
user avatar
  • 35
0 votes
0 answers
8 views

KL divergence loss first decreases and then increases in VAE training

I am training a VAE on CelebA HQ (resized to 256x256). The training is going well, the reconstruction loss is decreasing and reconstructions are also meaningful. But, the problem is with KL divergence ...
user avatar
1 vote
0 answers
17 views

ML techniques for mathematical inverse approximations

I have some inputs and outputs of a set of functions, and I want to be able to find/approximate any given input vector from its corresponding output vector (In other words learn the inverses of these ...
user avatar
  • 35
0 votes
0 answers
6 views

Why is FID so popular for evaluating GANs and other generative models?

The FID seems to be the most popular evaluation metric for GANs and other generative models. Why is it so popular? It seems to have some obvious issues, such as the assumption of Gaussian ...
user avatar
0 votes
0 answers
7 views

Generate examples with high targets

Suppose you have trained a Feedforward Neural Network with labeled examples ($x$,$y$) in a regression task to learn a function $\hat{f}$ to predict $y$ from $x$ with some error $\epsilon$ as $\hat{f}...
user avatar
  • 89
1 vote
0 answers
10 views

In which way GAN generator transforms the data(for transforming a noise to the data)?

I have the problem: I understood how GAN works in general, but I need information how it work detailed. The part I don't understand is how the random noise at input is transformed to data on the ...
user avatar
  • 11
0 votes
1 answer
17 views

Are genetic algorithms considered to be generative models?

My understanding is that these sorts of algorithms can evolve/mutate data to hone in on specific desirable areas in large/difficult to search parameter spaces. Assuming one does this successfully, how ...
user avatar
  • 35
0 votes
0 answers
9 views

How do GANs learn category distributions

I'm currently getting more into the topic of GANs and Generating Models. I've understood how the Generator and Discriminator work together in optimization to generate synthetic samples. Now I'm ...
user avatar
  • 1
0 votes
0 answers
14 views

How to improve L2 loss for generative autoencoder

I am working with a modified generative autoencoder and having issues getting the L2 sufficiently low. I think problem is that because my data is over a very large range and is standardized to values ...
user avatar
  • 35
0 votes
0 answers
9 views

Generate profile face from front face image

How can I generate profile face image, based on an input of a front face image? specifically, I'm more interested in doing it for illustrated characters. For example, given the input of the front face ...
user avatar
  • 101
1 vote
0 answers
11 views

P-value using Gaussian Discriminate Analysis

I was wondering , in Gaussian Discriminate Analysis (GDA) model, say we have two classes to classify y=0 and y=1 So after fitting the Gaussian over y=0 and y=1 dataset, when we try to predict class ...
user avatar
0 votes
0 answers
29 views

Function for KDE-style distribution generation for sampling

I have some points in pytorch and I would like to sample from a distribution that resembles these points. I noticed that the seaborn kde plots seem to draw out/define a distribution graphically and I ...
user avatar
  • 35
0 votes
0 answers
12 views

Reverse scaling Synthetic KDE data

For Python 3.9, sklearn version: 0.24.2 and numpy version: 1.20.3, I am using a Kernel Density Estimation (KDE) generative model. The goal is to generate new data using a given input data. The steps ...
user avatar
  • 121
0 votes
0 answers
28 views

Neural network architecture to automatically crop a photo of a paper sheet

With an RGB image of a paper sheet with text, I want to obtain an output image which is cropped and deskewed. Example of input: I have tried non-AI tools (such as ...
user avatar
0 votes
0 answers
10 views

Random number generator and JL lemma

Suppose we are given access to a random number generator U, which generates independent random real variables distributed uniformly in the range [0,1). Show that this can be used to produce an ...
user avatar
2 votes
1 answer
41 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 ...
user avatar
0 votes
1 answer
15 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 ...
user avatar
  • 3
2 votes
1 answer
53 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 ...
user avatar
  • 123
1 vote
1 answer
209 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, ...
user avatar
1 vote
0 answers
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 ...
user avatar
1 vote
0 answers
13 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 ...
user avatar
2 votes
1 answer
181 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 ...
user avatar
  • 240
0 votes
0 answers
12 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 ...
user avatar
  • 1
0 votes
1 answer
18 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 ...
user avatar
  • 143
1 vote
0 answers
36 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 ...
user avatar
1 vote
0 answers
19 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 ...
user avatar
  • 11
0 votes
0 answers
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 ...
user avatar
1 vote
0 answers
200 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 ...
user avatar
1 vote
0 answers
28 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 ...
user avatar
  • 11
0 votes
0 answers
10 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 ...
user avatar
  • 197
2 votes
1 answer
42 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?
user avatar
0 votes
0 answers
31 views

GAN model with different optimization functions

Building GAN model contains the following steps: Build generator model, and choose ...
user avatar
0 votes
1 answer
57 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 ...
user avatar
  • 1
1 vote
0 answers
18 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 ...
user avatar
  • 11
0 votes
1 answer
33 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 ...
user avatar
0 votes
1 answer
20 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. ...
user avatar
  • 101
1 vote
0 answers
7 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 ...
user avatar
  • 11
1 vote
0 answers
15 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 ...
user avatar
  • 131
1 vote
1 answer
72 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 ...
user avatar
2 votes
1 answer
42 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?
user avatar
2 votes
1 answer
130 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 ...
user avatar
  • 257
1 vote
1 answer
152 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 ...
user avatar
  • 21
2 votes
1 answer
363 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 ...
user avatar
1 vote
1 answer
147 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 ...
user avatar
0 votes
1 answer
22 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). ...
user avatar
0 votes
0 answers
23 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 ...
user avatar
  • 11
3 votes
1 answer
190 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 ...
user avatar
  • 169
1 vote
0 answers
46 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 ...
user avatar
  • 722
1 vote
0 answers
35 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 ...
user avatar
1 vote
0 answers
91 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 ...
user avatar