1x1 Convolution

Поделиться
HTML-код
  • Опубликовано: 4 фев 2025

Комментарии • 5

  • @jackrdye
    @jackrdye 2 года назад +3

    This 30 seconds is amazing. Been spending hours trying to actually see an example of how 1x1 conv reduces dimensions to a fixed number of output channels.
    Thank you!!!!

  •  Месяц назад

    But these filters (colored blocks) should have the same depth as the input, so they should be represented as a 1 x 1 x input_depth Matrices.

  • @ariasardari8588
    @ariasardari8588 3 года назад

    Awesome 👍

  • @날개달린_양
    @날개달린_양 Год назад

    wow.

  • @akzsh
    @akzsh 11 месяцев назад

    you ruined it by rotating the axis