In SVI latent random variables sampled from the guide completely mask those sampled in the model during inference. However, nothing prevents us from specifying different shapes for such a sample site in model and guide respectively. This makes it easy to introduce confusing bugs when code in the model expects a certain shape that is different than what guide provides. This can easily happen if the
Currently, all the VED/VAE models work only with a single channel data (e.g. grayscale images but not color images). The extension to multiple channels should be pretty straightforward if there is a use case.
Proof-of-principle application of Gaussian process modeling to gamma-ray analyses. Code repository associated with the paper https://arxiv.org/abs/2010.10450.
In SVI latent random variables sampled from the guide completely mask those sampled in the model during inference. However, nothing prevents us from specifying different shapes for such a sample site in model and guide respectively. This makes it easy to introduce confusing bugs when code in the model expects a certain shape that is different than what guide provides. This can easily happen if the