Mastodon Skip to content
  • Home
  • Aktuell
  • Tags
  • Über dieses Forum
Einklappen
Grafik mit zwei überlappenden Sprechblasen, eine grün und eine lila.
Abspeckgeflüster – Forum für Menschen mit Gewicht(ung)

Kostenlos. Werbefrei. Menschlich. Dein Abnehmforum.

  1. Home
  2. Uncategorized
  3. Hats off to whoever took time to create this (and the beautiful whippet!).

Hats off to whoever took time to create this (and the beautiful whippet!).

Geplant Angeheftet Gesperrt Verschoben Uncategorized
38 Beiträge 31 Kommentatoren 0 Aufrufe
  • Älteste zuerst
  • Neuste zuerst
  • Meiste Stimmen
Antworten
  • In einem neuen Thema antworten
Anmelden zum Antworten
Dieses Thema wurde gelöscht. Nur Nutzer mit entsprechenden Rechten können es sehen.
  • natasha_jay@tech.lgbtN natasha_jay@tech.lgbt

    Hats off to whoever took time to create this (and the beautiful whippet!).

    tomulne@framapiaf.orgT This user is from outside of this forum
    tomulne@framapiaf.orgT This user is from outside of this forum
    tomulne@framapiaf.org
    schrieb zuletzt editiert von
    #29

    @Natasha_Jay
    For me it's like :

    1 Antwort Letzte Antwort
    0
    • agowa338@chaos.socialA agowa338@chaos.social

      @Natasha_Jay

      Oh so Gemini has issues differentiating dogs and bicycle seats? Good to know.

      alice@lgbtqia.spaceA This user is from outside of this forum
      alice@lgbtqia.spaceA This user is from outside of this forum
      alice@lgbtqia.space
      schrieb zuletzt editiert von
      #30

      @agowa338 these used to be used as adversarial training sets for computer vision algorithms (not this one, probably, but Chihuahua or blueberry muffin, Sharpei or towel, Labradoodle or fried chicken, etc). There are whole image sets of them.

      @Natasha_Jay

      agowa338@chaos.socialA 1 Antwort Letzte Antwort
      0
      • natasha_jay@tech.lgbtN natasha_jay@tech.lgbt

        Hats off to whoever took time to create this (and the beautiful whippet!).

        alice@lgbtqia.spaceA This user is from outside of this forum
        alice@lgbtqia.spaceA This user is from outside of this forum
        alice@lgbtqia.space
        schrieb zuletzt editiert von
        #31

        @Natasha_Jay I love these adversarial image sets 😂

        @darkphoenix

        stephaniepixie@fandom.gardenS 1 Antwort Letzte Antwort
        0
        • alice@lgbtqia.spaceA alice@lgbtqia.space

          @agowa338 these used to be used as adversarial training sets for computer vision algorithms (not this one, probably, but Chihuahua or blueberry muffin, Sharpei or towel, Labradoodle or fried chicken, etc). There are whole image sets of them.

          @Natasha_Jay

          agowa338@chaos.socialA This user is from outside of this forum
          agowa338@chaos.socialA This user is from outside of this forum
          agowa338@chaos.social
          schrieb zuletzt editiert von
          #32

          @alice @Natasha_Jay

          And captures are often used to label such datasets.

          E.g. You know the result to 80% of the shown images and let the user click all of them. The user doesn't know which ones you expect them to click. Then for the few unlabeled ones you record if they did/didn't click them and then you serve the same unknown ones to multiple people and bam you've a very good way to enlarge your datasets.

          That's how google originally started with recaptures and what they're doing now...

          alice@lgbtqia.spaceA 1 Antwort Letzte Antwort
          0
          • agowa338@chaos.socialA agowa338@chaos.social

            @alice @Natasha_Jay

            And captures are often used to label such datasets.

            E.g. You know the result to 80% of the shown images and let the user click all of them. The user doesn't know which ones you expect them to click. Then for the few unlabeled ones you record if they did/didn't click them and then you serve the same unknown ones to multiple people and bam you've a very good way to enlarge your datasets.

            That's how google originally started with recaptures and what they're doing now...

            alice@lgbtqia.spaceA This user is from outside of this forum
            alice@lgbtqia.spaceA This user is from outside of this forum
            alice@lgbtqia.space
            schrieb zuletzt editiert von
            #33

            @agowa338 yup, crowd-sourced ML training.

            @Natasha_Jay

            1 Antwort Letzte Antwort
            0
            • alice@lgbtqia.spaceA alice@lgbtqia.space

              @Natasha_Jay I love these adversarial image sets 😂

              @darkphoenix

              stephaniepixie@fandom.gardenS This user is from outside of this forum
              stephaniepixie@fandom.gardenS This user is from outside of this forum
              stephaniepixie@fandom.garden
              schrieb zuletzt editiert von
              #34

              @alice Sloth au chocolat 😋

              1 Antwort Letzte Antwort
              0
              • cainmark@mstdn.socialC cainmark@mstdn.social

                @phil_stevens @Natasha_Jay

                Glad you posted this before I had to. Well done.

                isaacfreeman@cloudisland.nzI This user is from outside of this forum
                isaacfreeman@cloudisland.nzI This user is from outside of this forum
                isaacfreeman@cloudisland.nz
                schrieb zuletzt editiert von
                #35

                @cainmark Yeah, we all came here to post this. Whippet indeed good. Good whippet.
                @phil_stevens @Natasha_Jay

                1 Antwort Letzte Antwort
                0
                • natasha_jay@tech.lgbtN natasha_jay@tech.lgbt

                  Hats off to whoever took time to create this (and the beautiful whippet!).

                  bot_anix@nrw.socialB This user is from outside of this forum
                  bot_anix@nrw.socialB This user is from outside of this forum
                  bot_anix@nrw.social
                  schrieb zuletzt editiert von
                  #36

                  @Natasha_Jay gut kombiniert ‼️

                  1 Antwort Letzte Antwort
                  0
                  • pork_soda@friendsofdesoto.socialP pork_soda@friendsofdesoto.social

                    @srtcd424 @Natasha_Jay@tech.lent wait a minute, where are people getting pain au chocolate with THREE pieces of chocolate in it???

                    bot_anix@nrw.socialB This user is from outside of this forum
                    bot_anix@nrw.socialB This user is from outside of this forum
                    bot_anix@nrw.social
                    schrieb zuletzt editiert von
                    #37

                    @pork_soda @srtcd424 me, sometimes

                    1 Antwort Letzte Antwort
                    0
                    • phil_stevens@mastodon.nzP phil_stevens@mastodon.nz

                      @Natasha_Jay Whippet good.

                      stuartl@mastodon.longlandclan.id.auS This user is from outside of this forum
                      stuartl@mastodon.longlandclan.id.auS This user is from outside of this forum
                      stuartl@mastodon.longlandclan.id.au
                      schrieb zuletzt editiert von
                      #38

                      @phil_stevens @Natasha_Jay Yep, now I'm thinking of a DEVO parody playing on "Whippet" vs "whip it".

                      1 Antwort Letzte Antwort
                      0
                      • alsternerd@akkoma.alster.spaceA alsternerd@akkoma.alster.space shared this topic
                      Antworten
                      • In einem neuen Thema antworten
                      Anmelden zum Antworten
                      • Älteste zuerst
                      • Neuste zuerst
                      • Meiste Stimmen



                      Copyright (c) 2025 abSpecktrum (@abspecklog@fedimonster.de)

                      Erstellt mit Schlaflosigkeit, Kaffee, Brokkoli & ♥

                      Impressum | Datenschutzerklärung | Nutzungsbedingungen

                      • Anmelden

                      • Du hast noch kein Konto? Registrieren

                      • Anmelden oder registrieren, um zu suchen
                      • Erster Beitrag
                        Letzter Beitrag
                      0
                      • Home
                      • Aktuell
                      • Tags
                      • Über dieses Forum