C4W4L10 Style Cost Function

Поділитися
Вставка
  • Опубліковано 26 гру 2024

КОМЕНТАРІ • 21

  • @gorgolyt
    @gorgolyt 4 роки тому +26

    In case anybody gets confused, there's quite a big editing mistake in this video -- everything from 8:11 to 13:06 is repetition, so just skip to the end of that part.

  • @jerrylin5089
    @jerrylin5089 5 років тому +9

    I think the equation at 15:02 is missing a square exponent

    • @hanifr8380
      @hanifr8380 4 роки тому +2

      tru, there's actually a correction about it on coursera

  • @Scaryder92
    @Scaryder92 5 років тому +3

    Great video as always, thanks! Since the inner product is symmetric, aren't we calculating twice the same thing? (k=1,k'=2 and k=2, k'=1 gives the same result, no?)

    • @ish694
      @ish694 5 років тому

      Yeah..seems like you are right. The gram matrix is computed as the unnormalized covariance matrix (as referred earlier) and a covar matrix is always symmetric. So its transpose should be equal to the actual matrix.

    • @2B_pencil
      @2B_pencil 3 роки тому

      I'm guessing you're still expected to double-sum (k=1,k'=2 and k=2, k'=1). That is why there is a "2" squared in the denominator in the equation at 15:40. Again, just my guess.

  • @lana9459
    @lana9459 5 років тому +2

    wonderful

  • @elgs1980
    @elgs1980 6 років тому +12

    I'm totally lost in this video.

    • @CyborgGaming99
      @CyborgGaming99 5 років тому +1

      Haha it repeats itself from 8:15, but not entirely

    • @gorgolyt
      @gorgolyt 4 роки тому +1

      Watch it twice, I don't think it's too difficult.

  • @KevinKuei
    @KevinKuei 7 років тому +1

    The two equations (@14:17 & @14:39) seems to be different.

    • @CygnusX211
      @CygnusX211 6 років тому +2

      @14:39 there should be a ^2 on the element wise matrix difference

  • @kaitaoyang15
    @kaitaoyang15 7 років тому

    Is there a typo of the Style cost function? Should be the power of the difference between the two style matrices?

  • @PixelPulse168
    @PixelPulse168 2 роки тому

    what parameters does it train?

  • @dfincher6
    @dfincher6 4 роки тому +1

    There're lots of NG takes :)

  • @keshavbansal5148
    @keshavbansal5148 4 роки тому +1

    No idea what went on in this video, seems a bit too complex

  • @atreyamajumdar9836
    @atreyamajumdar9836 5 років тому +1

    Isn't he defining the non-correlation with the definition of anti-correlation?

    • @gorgolyt
      @gorgolyt 4 роки тому +1

      Yes, it would be easy to mistake him there. He means to say that whenever one texture is present, the other texture is no more or less present than usual.

  • @DrN007
    @DrN007 4 роки тому +1

    Style Cost Function is highly subjective, unless we were to find the ground truth for source images of each painting. PERIOD.