Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [generative-models]

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

Models designed for generating new data, or equivalently, generating samples from a probability distribution.

Examples are Generative Adversarial Nets (GANs), some applications of Recurrent Neural Nets (RNNs), Markov chain Monte Carlo (MCMC) to name a few.

163 questions
15
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?
Muhammad Hanif Sarwari
  • 315
  • 1
  • 3
  • 8
15
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…
snowparrot
  • 305
  • 1
  • 3
  • 9
12
votes
2 answers

When to use Stateful LSTM?

I'm trying to use LSTM on time-series data in order to generate future sequences that looks like the original sequences in term of values and progression direction. My approach is: train RNN to predict a value based on 25 past values then use the…
Hastu
  • 408
  • 1
  • 5
  • 11
11
votes
2 answers

Find optimal P(X|Y) given I have a model that has good performance when trained on P(Y|X)

Input Data: $X$ -> features of t shirt (colour,logo,etc) $Y$ -> profit margin I have trained a random forest on the above $X$ and $Y$ and have achieved reasonable accuracy on a test data. So, I have $P(Y|X)$. Now, I would like to find $P(X|Y)$ i.e…
claudius
  • 153
  • 8
8
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…
Przemysław Czechowski
  • 181
  • 4
8
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…
Peter
  • 181
  • 1
  • 3
7
votes
5 answers

Could GANs be used to augment data?

I want to use GAN for data augmentation but I am confuse what are the pros. and cons. of data augmentation using GAN or why we use data augmentation using GAN compared to other data augmentation technique like standard data augmentation? Your answer…
Nawaf Khan
  • 83
  • 2
7
votes
1 answer

Can a GAN-like architecture be used for maximizing the value of a regression predictor?

I can't seem to convince myself why a GAN model similar to regGAN couldn't be modified to maximize a regression predictor (see the image below). By changing the loss function to the difference between the current predicted value and the maximum…
Ryan Gross
  • 73
  • 4
6
votes
3 answers

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, y is unbalanced...etc. Let's also say this data…
Lucas Morin
  • 2,513
  • 5
  • 19
  • 39
6
votes
2 answers

Latent loss in variational autoencoder drowns generative loss

I'm trying to run a variational auto-encoder on the CIFAR-10 dataset, for which I've put together a simple network in TensorFlow with 4 layers in the encoder and decoder each, an encoded vector size of 256. For calculating the latent loss, I'm…
Ali250
  • 213
  • 2
  • 5
6
votes
3 answers

Best way to generate artificial handwritten text?

I would like to train a generative model that generates artificial handwritten text as output. which architectures would you recommend to use? Training input could be either images of handwritten letters, not words, or maybe sequences of points for…
GrozaiL
  • 374
  • 3
  • 6
5
votes
1 answer

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 uses the Inception network to extract features from…
Giang Nguyen
  • 235
  • 2
  • 8
5
votes
1 answer

Real world example of Generative model & Discriminative model

After going over the math/stats behind the Generative model & Discriminative model, I still have no intuition about it. Does any one have a good real-world example or use case for Generative model and Discriminative model ? Thanks!
Edamame
  • 2,705
  • 5
  • 23
  • 32
4
votes
1 answer

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 yet predicted), so it can be used…
David Rein
  • 53
  • 6
4
votes
1 answer

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 0.68 (I have used a BCE loss), and the accuracies…
Andrew
  • 179
  • 3
1
2 3
…
10 11