vae_tutorial

vae_tutorial copied to clipboard

KL loss compare to Keras

1

Thank you the nice tutorial and supporting code. I made a plot (attached) of KL Loss vs iterations of your implementation and that of Keras ([blog](https://blog.keras.io/building-autoencoders-in-keras.html), [code](https://github.com/keras-team/keras/blob/master/examples/variational_autoencoder.py)). Could you please...

samadejacobs

Understanding input to mu and logsd layers

1

Hi thanks for the great tutorial. I have trouble understanding math. What is the reason to pass in `encode3` to `logsd` before the nonlinearity is applied? Why not give `encode3neur`...

nathanin