Skip to content

Increase specificity for initializers #13

Description

@MartinuzziFrancesco

Currently the weights are initialized through specific initializers specified by *_kernel_init. However, in case of multiple gates or more matrices, all the matrices share the same init, ie all the recurrent matrices will be initialized by recurrent_kernel_init: Callable = nn.init.normal_, etcetc. Providing as way to increase control over which matrix get initialized by which init would increase customization

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions