Skip to content

More informative error messages for "mixture" efficiency mode #49

@logan-blaine

Description

@logan-blaine

Report

If using the mixture model, we should check to ensure that each cell only has one guide instead of throwing this sort of cryptic error during training:

ValueError: Expected parameter probs (Tensor of shape (512, 19212)) of distribution Bernoulli(probs: torch.Size([512, 19212])) to satisfy the constraint Interval(lower_bound=0.0, upper_bound=1.0), but found invalid values:

Version information

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type
    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