LSTM Model not training

[KXBuzz]

Not a solution, but I have the not training problem with autoencoders… Weird enough, I think it’s the office example Still waiting for reply…

PyTorch VAE (Variational Autoencoder) example not training (no meaningful model returned)

I tried to implement this VAE example using PyTorch: https://github.com/pytorch/examples/blob/master/vae/main.py All the parameters were left as default. But the “learned” autoencoder is not meaningful. It produces a blurred image looks like the mean of the MNIST training set regardless of the input. Please help me figure out what went wrong during training. Thank you! [Screenshot from 2017-09-29 17-18-23]