Questions tagged [vae]
The vae tag has no usage guidance.
35
questions
0
votes
1
answer
21
views
Generate new distribution from auto-encoder /variational autoencoder
I know that autoencoders can be used to generate new data.
From what I could understand..
The autoencoder uses the original distribution X to learn a random gaussian distribution described by mean and ...
0
votes
0
answers
73
views
Reference code for LSTM Variational Autoencoder for dimensionality reduction
I have time series data, with many features.
I would like to reduce the dimentionality by using LSTM VAE.
Does anybody know an example code or a reference to guide me to impolement it?
Both Pytorch ...
0
votes
0
answers
58
views
Variational autoencoder for time series denoising and dimentionality reduction
I have a dataset X of multiple series say 100 (size=100).
I would like to use VAE to both denoise the data and reduce the dimensions to a smaller latent space Z (size Z << size X), because I ...
0
votes
0
answers
18
views
Expectation of ELBO in Variational Autoencoder
I am working with VAEs. My input is x, which is a product of two variables $x_1$ and $x_2$.
The objective (ELBO) of VAE in terms of x is:
$E_{z\sim Q}[\log P(x|z)] - \mathcal{D}[Q(z|x)||P(z)]$.
I want ...
1
vote
0
answers
28
views
How should I think when I want to compare mu and sigma for different images in VAE?
I'm searching for a way to compare mu and sigma values of the encoder network's output of variational autoencoders.
In detail, imagine I trained my VAE on the MNIST digits dataset using the official ...
1
vote
0
answers
39
views
What does it means (concretly) that a VAE encode inputs as distribution?
From this post we can read that VAEs encode inputs as distributions instead of simple points ?
What does it mean concretely ? If the encoder consists of the weights between the input image and the ...
0
votes
0
answers
59
views
converting a KL divergence from torch to pytorch
The following code is the KL divergence between a Gaussian posterior and mixture of Gaussian priors and it is part of the model described in this paper. The published code is written in torch language
...
0
votes
0
answers
37
views
Tensorflow Probability Implementation of Automatic Differentiation Variational Inference with Mixtures
In this paper, the authors suggest using the following loss instead of the traditional ELBO in order to train what basically is a Variational Autoencoder with a Gaussian Mixture Model instead of a ...
0
votes
0
answers
9
views
save reconstructed data points from variational autoencoder as original MNIST
I have a VAE implementation that generates images from the latent distribution. I want to save those "images" as we have in the original dataset. For example, my VAE generates a data point, ...
0
votes
0
answers
38
views
VAE generating same results during test time
I have trained a VAE to generate a style transferred sentence, from a negative sentence to a positive sentence. The underlying concept of VAE tells us that the sampling is done randomly, to which Mean ...
0
votes
0
answers
38
views
Which is better KL- Divergence or Bhattacharya(Hellinger) Distance
I'm beginner in probability and statistics. I came across the concept of comparing two probability distributions. KL-Divergence and Bhattacharya(Hellinger) Distance are used to compare two probability ...
0
votes
0
answers
53
views
How do I prevent infinite variances/standard deviations in my variational autoencoder?
I am working on a project with a variational autoencoder (VAE).
The problem I have is that the encoder part of VAE is producing large log variances, which leads to even larger standard deviations, ...
1
vote
1
answer
62
views
Latent variable graph in Variational Autoencoder
I followed this Keras documentation guide about Auto Encoders.
At the end of the documentation there is the graph of the latent variable z:
But I can not understand and how to interpret the plot, ...
0
votes
0
answers
15
views
VAE will always results in somewhat different latent vectors for same input?
Hey I was wondering if my intuition is correct that for the same input in a VAE we will get a slightly different vector every time we feed it through the network, due to the random sampling operation?
0
votes
1
answer
277
views
Controlling the sampling from Variational AutoEncoder (VAE)
Suppose a Variational Autoencoder (VAE) is trained with mnist data. To sample, one draws from normal distribution. My question is: suppose I am interested in generating only 1s and no other digits. ...
0
votes
1
answer
92
views
Help needed in interpreting the loss, val_loss vs epoch plots for an autoencoder training?
I am training a variational autoencoder and I am getting a loss-plot as follows:
Rigt after epoch 224, val-loss overtakes train-loss and sort of getting bigger but at an extremely slow pace as you ...
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 ...
4
votes
1
answer
1k
views
1D CNN Variational Autoencoder Conv1D Size
I am trying to create a 1D variational autoencoder to take in a 931x1 vector as input, but I have been having trouble with two things:
Getting the output size of 931, since maxpooling and upsampling ...
2
votes
1
answer
41
views
What are the Most Dissimilar MNIST Digits?
Using whatever definition of dissimilarity over sets that you'd like, what are the most dissimilar two digits in MNIST? I was thinking that a reasonable approach to answering the question would be to ...
1
vote
0
answers
146
views
pytorch code for VAE for MINST forces mu and logvar to zero
I am new to pytorch and trying to implement a VAE for MNIST data. When I try to train my model, it appears that the model forces mu and logvar to zero (or something very close to zero) independent of ...
1
vote
0
answers
117
views
Is vanishing KL a problem in vision based VAEs as well?
I came across some work on the problem of a vanishing KL contrbution in Variational Auto Encoders Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing. This work particularly is ...
2
votes
1
answer
192
views
Why KL Divergence instead of Cross-entropy in VAE
I understand how KL divergence provides us with a measure of how one probability distribution is different from a second, reference probability distribution. But why are they particularly used (...
0
votes
1
answer
408
views
What makes the posterior intractable?
In the setting of Variational AutoEncoders, i.e. when we want to find the posterior distribution
over the data generating, latent variable z, given some ...
3
votes
1
answer
571
views
VAE generates bad images. due to unbalanced loss functions?
I'm training a variational autoencoder on CelebA dataset using TensorFlow.keras
The problem I'm facing is that the generated images are not diverse enough and look kinda bad.
(new) Example:
What I ...
1
vote
1
answer
391
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 ...
9
votes
1
answer
449
views
Train a GAN on "before and after" images of dental surgeries [closed]
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: https://img.webmd.com/dtmcms/live/...
2
votes
2
answers
50
views
Can VAEs be used to generate multivariate data?
Most of the tutorials online seem to use VAEs to generate images and use CNNs to generate data. I am working on a game with multivariate data consisting of character position and the character ...
1
vote
0
answers
209
views
Variational Autoencoder: Negative log likelihood not optimized
I am using the auto encoding variational Bayes algorithm for one unsupervised object detection task. In the loss function, the reconstruction loss is calculated as the log likelihood of the original ...
1
vote
0
answers
125
views
How to estimate total correlation KL[q(z)||Πjq(zj)] of VAE after training (useful for latents disentanglement evaluation)
FactorVAE and β-TCVAE both use total correlation (TC) batch estimation for their objectives. Where TC is:
$$
KL\bigl( q(z)||\prod\nolimits_{j} q(z_{j})\bigr)
$$
both estimates are applied to $q(z|x)$...
0
votes
2
answers
112
views
What is the meaning of "probability distribution of p(x)" of something uncountable?
I'm studying VAE and new to both of the neural network and the statistic.
After some researches, I could understand the rough concept of VAE.
But what makes me confused is, the meaning of probability ...
3
votes
1
answer
838
views
Intractability in Variational Autoencoders
I'm having difficulty understanding when integrals are intractable in variational inference problems.
In a variational autoencoder with observation $x$ and latent variable $z$ we want to maximize data ...
6
votes
1
answer
4k
views
Why maximize ELBO in the variational autoencoder?
For a variational autoencoder, we have that:
$$\mathcal{L}(x,\theta,\phi) := \mathbb{E}_{z \sim q_\phi(z|x)}[\log p_{\theta}(x|z)] -KL[q_{\phi}(z|x) ||p(z)] $$
This is called the variational lower ...
4
votes
1
answer
4k
views
ValueError: Cannot convert a partially known TensorShape to a Tensor: (?, 256)
I'm working on a sequence to sequence approach using LSTM and a VAE with an attention mechanism.
...
2
votes
1
answer
4k
views
What do we visualize in showing a VAE latent space?
I am trying to wrap my head around VAE's and have trouble understanding what is being visualized when people make scatter plots of the latent space. I think I understand the bottleneck concept; we go ...
16
votes
2
answers
14k
views
What is "posterior collapse" phenomenon?
I was going through this paper on Towards Text Generation with Adversarially Learned
Neural Outlines and it states why the VAEs are hard to train for text generation due to this problem. The paper ...