Skip to content

'epochf' before 'learn' in training algorithm #28

@supersasha

Description

@supersasha

Why 'epochf' is called before 'learn' in train/gd.py algorithms?

Imagine you need only one epoch (for example, in reinforcement learning's step). When you specify 'epochs=1' the algorithms stop before any learning. When you specify 'epochs=2' you get additional unnecessary gradient calculation (so that you double the expensive calculations count).

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