Self-Supervised Learning of Image Features with SwAV (with author Mathilde Caron)

Поділитися
Вставка
  • Опубліковано 17 лис 2024

КОМЕНТАРІ • 12

  • @intisarchy7059
    @intisarchy7059 2 роки тому +3

    Mathilda Caron thanks a lot for such clear and concise explanation. I enjoyed your talk in the ML street talk too. Looking forward to more great works from you.

  • @OscarRangelMX
    @OscarRangelMX 3 роки тому +7

    great topic, but can understand her... I was looking for subtitles, but there are not enabled.... it will be a good idea to enable them. thanks.

  • @datajedi4393
    @datajedi4393 4 роки тому +3

    Awesome! Great work Mathilde!

  • @mohammadmotiurrahman
    @mohammadmotiurrahman 3 роки тому +8

    A proper sound quality would have been much appreciated.

    • @PyTorchLightning
      @PyTorchLightning  3 роки тому +2

      Agreed, thanks! We have been working on ensuring better sound quality in our videos

    • @yoadtew
      @yoadtew 3 роки тому +2

      @@PyTorchLightning Is there a possibility to add subtitles to the video? It will help with the videos that already have bad audio quality

  • @guruswaroop
    @guruswaroop 3 роки тому

    When using multi-crops, the size of the crops is not fixed. For example, the author uses 2 crops of 160x160 and 4 crops of 96x96. How can the network architecture remain the same when the input dimensions are not fixed?

    • @jjxed
      @jjxed 3 роки тому +1

      It uses this function pytorch.org/vision/0.8/_modules/torchvision/transforms/transforms.html#RandomResizedCrop which crops first but then resizes the crops, so the output size of all the crops are the same

    • @LukosPC
      @LukosPC 3 роки тому +2

      @@jjxed I don't think this is correct. If you look at the code, the model really processes (3, 224, 224) and (3, 96, 96) images. It's the AdaptiveAvgPool2d layer which pools the final representation in a size-specific way so the output size stays the same

  • @astudent8885
    @astudent8885 8 місяців тому

    French accent is classy but also unfortunately hard to understand

  • @444haluk
    @444haluk 3 роки тому +1

    PhD student looks like 17.