-
Hi @bogedy
Thanks for sharing your code.
I train the code on a custom dataset. The result is getting better after every epoch, however, the loss is increasing. Looks like you maximize instead of mi…
-
Hi,
i am attempting to build a equivariant Variational Encoder-Decoder framework.
For this I am using R2Conv() and R3(Conv) layers in the encoder with trivial-representation input & output and …
-
The screenshot below was taken from [the demo site for this package](https://mkdocs-jupyter.danielfrg.com/variational-inference-nb/). As you can see, the math is not rendered correctly. However, somet…
-
When using the pre-made conda environment for PyEMMA, the numpy version used is new enough to have removed numpy.bool. However, the pyemma code still uses this deprecated and, now, removed attribute …
-
To add a loss and metrics to a model, I can add them to `model.compile(loss=..., metrics=...)`, provided that they have the signature `fn(y_true, y_pred)`, see the [docs](https://keras.io/api/models/m…
-
Dear Hugh,
Firstly i would like to thank you for your paper "Doubly Stochastic Variational Inference for DGP" and sharing its implementation online.
I started working with your implementation recent…
-
We define
- the subspace/submodule of symmetric matrices
- the cone of positive-semidefinite matrices (with `ambient` = the full matrix space; `affine_hull` = the above subspace), implementing the A…
-
In the paper, the author said, the number of topics can be determined with cross validation or held-out likelihood.
But I run the code, and just set default T and K. The number of topics is always eq…
-
# Code Review
## Handling of Alpha Channel
I'm having some troubles running the code. I figured out that I needed to convert images to .pxa format with the supplied Python scripts, but there are…
-
reasons:
- poor performance
- complex code to support
- highly unlikely that this backend is used
cc @cpcloud