senooken JP Social
  • FAQ
  • Login
senooken JP Socialはsenookenの専用分散SNSです。

  • Public

    • Public
    • Network
    • Groups
    • Popular
    • People

Conversation

Notices

  1. Akionux (akionux@status.akionux.net)'s status on Friday, 22-Jan-2021 18:36:44 JST Akionux Akionux
    Why add positional embedding instead of concatenate? · Issue #1591 · tensorflow/tensor2tensor · GitHub - https://github.com/tensorflow/tensor2tensor/issues/1591
    Transformerのpositional embeddingはなぜconcatしないでaddするのかについて
    In conversation Friday, 22-Jan-2021 18:36:44 JST from status.akionux.net permalink

    Attachments

    1. Domain not in remote thumbnail source whitelist: avatars.githubusercontent.com
      Why add positional embedding instead of concatenate? · Issue #1591 · tensorflow/tensor2tensor
      Apart from saving some memory, is there any reason we are adding the positional embeddings instead of concatenating them. It seems more intuitive concatenate useful input features, instead of addin...

    Feeds

    • Activity Streams
    • RSS 2.0
    • Atom
    • Help
    • About
    • FAQ
    • TOS
    • Privacy
    • Source
    • Version
    • Contact

    senooken JP Social is a social network, courtesy of senooken. It runs on GNU social, version 2.0.2-beta0, available under the GNU Affero General Public License.

    Creative Commons Attribution 3.0 All senooken JP Social content and data are available under the Creative Commons Attribution 3.0 license.