New answers tagged variational-autoencoder
1
vote
Accepted
Is the discriminator of a GAN network embedded in VAE?
To train a GAN you need only 2 networks, the generator and discriminator, none of which require to be an encoder. You also don't require synthetic data, those are generated by the generator network, ...
0
votes
Datasets input at model.fit produce unexpected results of training loss vs validation loss
Solved it. It was a bug in my code after all.
preprocess_dataset function divide the data by 255 and I used the same for both the training dataset which was coming from a directory (0-255 range) and ...
0
votes
VAE giving near zero output when latent space dimension is large
Old question but hopefully OP is still active.
I also agree with recessive that perhaps it is struggling to create a continuous representation of your data in the latent space. Have you looked at your ...
Top 50 recent answers are included
Related Tags
variational-autoencoder × 93autoencoders × 23
deep-learning × 17
generative-model × 15
neural-networks × 12
generative-adversarial-networks × 11
evidence-lower-bound × 10
machine-learning × 8
kl-divergence × 8
papers × 7
image-generation × 7
latent-variable × 7
variational-inference × 7
convolutional-neural-networks × 5
comparison × 5
objective-functions × 5
pytorch × 5
probability-distribution × 5
notation × 5
terminology × 4
tensorflow × 4
math × 4
implementation × 4
computer-vision × 3
hyper-parameters × 3