This is my first variational autoencoder. Background info: I am using the MNIST digits dataset. The model is created and trained in PyTorch. The model is able to get a reasonably low loss, but the images that it generates are just random noise. Here are my script and the images that were generated by the model: https://github.com/jweir136/PyTorch-Variational-Autoencoder-Latent-Space-Visualization.

Any advice or answers on how to solve this problem are greatly appreciated.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.