Skip to content

Code 11.56 and 11.57 issue with negative log probabilities from softmax #239

Description

@DamonCharlesRoberts

For the code in 11.56 and 11.57, I had been trying to replicate the results using the pm.math.softmax method, however, I was getting errors during sampling due to it producing negative values.

Adjusting p_ = at.nnet.softmax(s) to be p = pm.math.softmax(s, axis=1) resolved the problem.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions