-
This issue tracks Pyro components that should be moved to upstream dependencies.
## Move to PyTorch
- [x] `constraints.IndependentConstraint`
- usage in `MultivariateNormal`
- usage in `dist…
-
I thought it'd be good to get a discussion going on how we represent distributions in pymdp.
Currently we have the categorical and dirichlet classes, which I believe we are trying to move away from…
-
I have been trying to install `tensorflow` and `edward` on my macos laptop and I failed following all the recipes in the web. This is how I installed edward and tensorflow
```
conda create -n tf_env…
-
### Issue with current documentation:
After seeing that some methods, like `dist`, accept both `shape` and `size` I looked for information about the difference between the two but could not find anyt…
lciti updated
8 months ago
-
I have Tensorflow installed. When I check the version, it is 2.12.
tensorflow::tf_config()
2023-02-27 15:55:21.780906: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binar…
-
> The PR made me wonder whether it would be possible to improve performance of `with_logabsdet_jacobian` for `SimplexBijector` by not performing `transform` and `logabsdetjac` separately when both are…
-
### Description
For evaluating and understanding a LDA topic model, phi and theta are essential. The documentation really should
provide information on how these can be aquired.
### Link to Do…
-
Hello, I’m a student majoring in biology in Japan.
I usually use Python so I'm very new to Julia...
I am trying to fit my experimental data(~400,000 angles, -pi ~ +pi bimodal) with mixture of von…
-
Trying to compute gradients of the `rand` function wrt to parameters for certain distributions will produce incorrect results, because some of these functions use branching or iterated algorithms and …
-
## Description of your problem
I have a model that compiles correctly when the priors are represented as numpy arrays, but that gets a shape error when those numpy arrays are wrapped in `pm.Data`, …