View source: R/approach_vaeac_torch_modules.R
gauss_cat_loss | R Documentation |
torch::nn_module()
Representing a gauss_cat_loss
The gauss_cat_loss module
layer computes the log probability of the groundtruth
for each object
given the mask and the distribution parameters. That is, the log-likelihoods of the true/full training observations
based on the generative distributions parameters distr_params
inferred by the masked versions of the observations.
gauss_cat_loss(one_hot_max_sizes, min_sigma = 1e-04, min_prob = 1e-04)
one_hot_max_sizes |
A torch tensor of dimension |
min_sigma |
For stability it might be desirable that the minimal sigma is not too close to zero. |
min_prob |
For stability it might be desirable that the minimal probability is not too close to zero. |
Note that the module works with mixed data represented as 2-dimensional inputs and it
works correctly with missing values in groundtruth
as long as they are represented by NaNs.
Lars Henry Berge Olsen
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.