-
Hey @alejandroschuler! Is it possible to create an MDN with ngboost? That is combine multiple distributions (in the most general case, from different families) to predict the output of interest?
-
See also http://edwardlib.org/tutorials/mixture-density-network.
-
I wanted to run the Edward notebook on mixture density networks.
But the notebook won't run completely. After executing code-cell 5
The Following error appears:
`ValueError: Incompatible shape …
-
## Description
The MDN i.e. Gaussian Mixture Density network, is a density estimator which gets a lot of "special" treatment.
- SNPE_A requires it, and implements a special "corrected" `SNPE_A_MDN…
-
The following assertion error occurs when tested on h36m dataset:
Run command: python predict_3dpose_mdm.py --test True --load 4679232 --load_dir ../Models/mdm_5/
error callback:
AssertionError…
-
There are various ways this could be done:
* purely from samples. pros: model agnostic, cons: high variance, need to use a kernel method
* using mixture of gaussians: pros: lower variance, cons: ver…
-
https://github.com/OptiMaL-PSE-Lab/DeepDock/blob/ab1e45044c5e0a69105b48d09ea984c6a5ebc26c/deepdock/models.py#L218
Hi,
first of all thanks for sharing the code.
Just a simple question: what is t…
-
### 🚀 The feature, motivation and pitch
Currently, the `MultivariateNormal` distribution is parameterised based on the Cholesky factor of the covariance matrix, referred to in the code as `scale_tril…
-
-
Check if the data output is uni or multi modal. If distributions are skewed, logarithmise respective features. Inspect either visually, or run one of the https://en.wikipedia.org/wiki/Normality_test. …