python (65.1k questions)

javascript (44.2k questions)

reactjs (22.7k questions)

java (20.8k questions)

c# (17.4k questions)

html (16.3k questions)

r (13.7k questions)

android (12.9k questions)

Questions - autoencoder

Why does my variational autoencoder only produce positive values?

I copied this example to build a variational autoencoder (VAE). The example uses images, but I use it for a signal that contains negative values. After training, the autoencoder only reconstructs the ...
test-img

jfn

pytorch

autoencoder

Votes: 0

Answers: 1

Latest Answer

If you used the exact code as the one shown in the example you put the link in, then at the end of the decoder you have x = torch.sigmoid(self.decConv2(x)) which take the real number line and outputs ...
test-img

Tomer Geva

Why does my autoencoder generate the Anomalous image instead of the anomaly-free image?

I really need help with this, I am working on an anomaly detector project using Autoencoder, the first part of the project is to build an autoencoder trained only on non anomalous images so when it is...
test-img

Asky

deep-learning

encoding

decoding

autoencoder

anomaly-detection

Votes: 0

Answers: 0

VAE reconstruction loss (MSE) not decreasing, but KL Divergence is

I've been trying to create an LSTM VAE to reconstruct multivariate time-series data on Tensorflow. To start off I attempted to adapt (changed to Functional API, changed layers) the approach taken here...
test-img

Lucas Correia

tensorflow

autoencoder

Votes: 0

Answers: 1

Latest Answer

Could it be that you are using an Autoencoder and in the loss there is a KL Divergence term? In a (Beta-) VAE the loss is Loss = MSE + beta * KL . Since beta = 1 would be a normal VAE you could try t...
test-img

Error404

How to convert nested array to grayscale images?

I want to take the WM-811k dataset (https://www.kaggle.com/code/ashishpatel26/wm-811k-wafermap/notebook) and autoencode the normal wafers to test how an autoencoder could pick out anomalous wafers. I'...
test-img

Mark McGown

python

autoencoder

Votes: 0

Answers: 1

Latest Answer

The problem you are encountering is with the PIL call .fromarray(img). This call makes assumptions about the bit depth of the image you are trying to make. See the optional parameter 'mode' in the off...
test-img

blarg

Posts

Questions

Blogs

Jobs