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.