Skip to content

question #2

Description

@zhengshuaikang

Hi, I'm interested in figuring out the logic of the code, could you please describe what the dimensions n_views, (N, L, S, d) = len(enc_output), enc_output[0].shape represent in haav/models/transformer/decoders.py, especially N, L , S, d. Thank you.

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