andreas

Did you find a satisfying solution? What did you try so far?

Where do the NaNs occur in the network? As the network architecture is bijective, even the untrained network should be invertible. Try to predict the latent vectors (z) for an...

You could try following: - Decode the z-LR pair with z of standard deviation [0, 0.1, 0.2, ... 1.0, 1.1]. - Add a small number to the division to protect...

**Did you try those experiments from the previous answer?** - Decode the z-LR pair with z of standard deviation [0, 0.1, 0.2, ... 1.0, 1.1] and compare them visually. -...

Sorry for the late reply. We have good news! We were allowed to publish the model codes. Does this help you? Any thoughts on improving it?

Great, feel free to reach out anytime!

Thanks, great question! ### What are the architectural differences of VAE and NF? For autoencoders, the encoder and decoder are two separate networks and usually not invertible. A Normalizing Flow...

Hi viki-li, this error usually occurs in the back propagation step of the 1x1 convolution, when the learning rate is too high. Does it help to reduce the learning rate?


The final loss of SRFlow is negative and steadily decreasing: We did not track those two components separately. Please try to run our code and log the loss (NLL is...