Skip to content

An option to minimize/omit Normalization and Activation layers #114

@caiuspetronius

Description

@caiuspetronius

Is your feature request related to a problem? Please describe.
Large networks appear about 3x times larger than they should because of the omnipresent normalization and activation layers. One doesn't really need to see normalizations and activations represented by the same size blocks as more important layers, e.g. convolutions.

Describe the solution you'd like
Ideally, an option to fold them into a line of a given color for normalization and another color for activation juxtaposed to the bottom of the block that they follow.

Describe alternatives you've considered
An option of omitting them altogether would be another solution.

Screenshots / Text
When showing piece of code/error, please always prefer text format (over screenshot of the code/error) unless screenshot is absolutely necessary.
If you provide text format (that is executable), it is easier to copy and paste.

Additional context
Add any other context or screenshots about the feature request here.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions