C4W2L07 Inception Network

แชร์
ฝัง
  • เผยแพร่เมื่อ 8 พ.ย. 2024

ความคิดเห็น • 47

  • @navid2368
    @navid2368 5 ปีที่แล้ว +44

    Andrew teaching me about memes, epic!
    thanks again for the amazing lecture

  • @Небудьбараном-к1м
    @Небудьбараном-к1м 5 ปีที่แล้ว +47

    Didn't know one could cite memes in science papers 😂 gonna do it in mine

  • @Небудьбараном-к1м
    @Небудьбараном-к1м 5 ปีที่แล้ว +7

    I'm so excited about this channel that I'm actually a little paranoid that it will shut down before I can finish watching all of the videos

    • @ericklestrange6255
      @ericklestrange6255 4 ปีที่แล้ว +1

      its a very new topic so no much material on it but as time progresses even if this video might be removed more and better videos probably would arise on the matter

  • @sebbecht
    @sebbecht 5 ปีที่แล้ว +22

    Yep I am totally going to find a way to cite a meme in one of my papers!

  • @ureunz
    @ureunz 4 ปีที่แล้ว +1

    really thanks Andrew. 🙏 Through your video, I totally understood what Inception network!! (including CNN)
    다른 한국 영상들에서는 보기 어려운 체계적이고 + 쉬운 설명입니다 영상 강력추천합니다. 👍

  • @sandipansarkar9211
    @sandipansarkar9211 3 ปีที่แล้ว

    very good explamnation.need to watch again

  • @piankk
    @piankk 3 ปีที่แล้ว +3

    Great lecture! Thank you.
    I have a question.
    2:18
    Can I move the 1x1 conv layer to before max-pooling layer to reduce channels, like the one before 3x3 and 5x5 conv?
    What’s the difference?

    • @Matttsight
      @Matttsight ปีที่แล้ว

      That's the same question i do have , do you got any clarity on that ?

  • @shwethasubbu3385
    @shwethasubbu3385 5 ปีที่แล้ว +5

    How do you know how small the bottleneck layer should be? And why would one want to shrink the number of channels as done in 8:46, what is the benefit of doing this?
    Also, instead of using a 1x1 as a bottleneck layer and then using 5x5 or 3x3 filters to reduce computational complexity, why can't we just use 1x1 filters throughout to get the required output dimensions?

    • @kishorekumarsingam
      @kishorekumarsingam 5 ปีที่แล้ว +1

      please let me know if anyone fimds the answer

    • @OneAndOnlyBigMax
      @OneAndOnlyBigMax 5 ปีที่แล้ว +2

      From what I've understood from this video the idea is to just reduce the amount of computations needed.
      Think of it as densely packing and combining all the features from the previous layer and proceeding to work with this "dense/tight" features - this is just computationaly cheaper.
      You can't just throw away 3x3, 5x5 filters because they are useful for finding "patterns" in images, like lines, curves, etc. A 1x1 convolution only looks at 1 pixel at a time - and such a network would just be a MLP with extra steps.
      This is just my intuition - feel free to add/correct something.

    • @pushyashah1377
      @pushyashah1377 5 ปีที่แล้ว +1

      3x3, 5x5 and like those filters used to learn edge detection and many more details whereas 1x1 are a really useful tool for transforming the number of channels without changing the spatial dimensions.

  • @beagle989
    @beagle989 3 ปีที่แล้ว

    I love you and your videos.

  • @jiangyuanhang1934
    @jiangyuanhang1934 2 หลายเดือนก่อน

    after the maxpool step, the output shoud be 26*26 *192(assume that we use 192 filters) , in the video it says 28*28*192? Why is that?

    • @jiangyuanhang1934
      @jiangyuanhang1934 2 หลายเดือนก่อน

      or it is assumed that there are paddings ?

  • @sinaro93
    @sinaro93 ปีที่แล้ว

    Thanks a lot for sharing this.

  • @conorsmyth12358
    @conorsmyth12358 3 ปีที่แล้ว

    This movie The Inception sounds great.

  • @shaelanderchauhan1963
    @shaelanderchauhan1963 3 ปีที่แล้ว

    What is the purpose of using Maxpooling if we are not reducing the height and width of the dimension? I guess in previous lectures Andrew Ng said that max pool reduces the dimension such as 28*28*8 to 14*14*8 what is the purpose of applying it here is it to only keep the most important information by maxing it?

    • @aidynabirov7728
      @aidynabirov7728 2 ปีที่แล้ว

      Well, the purpose is not the actual reducing the height and width, it's more of taking Features(max values) from the activations, and leaving the unnecessary features. So, that's why, I guess, they are applying MaxPooling, in order to reduce some features, and applying padding at the same time not to reduce the dimension. It's just the assumption, please tell me know, if I am wrong :)))

  • @marcocaceres4867
    @marcocaceres4867 ปีที่แล้ว

    How small the number of filters have to be in the 1 x 1 convolution? Why 192 -> 16 -> 32 instead of 192 -> 1 -> 32?

  • @TheSalto66
    @TheSalto66 4 ปีที่แล้ว

    The film Inception means put inside other people/mind a external thought (virus) , and from that thought start a new way to see world

  • @strongsyedaa7378
    @strongsyedaa7378 2 ปีที่แล้ว

    I haven't understood 😕
    Why we are using different filters?

  • @amineabid7220
    @amineabid7220 4 ปีที่แล้ว +1

    How do we manage to train the intermediate forks (to do predictions from hidden layers)? do we stop the back propagation at the fork?

    • @amineabid7220
      @amineabid7220 4 ปีที่แล้ว +1

      Besides, how to define a labeled sample? 1. Is it the same training sample (x,y), in which case what would be the impact of running two back propagation process on the same layers: all layers before the fork?
      2. or is it (x',y) where x' is the activation of the layer just before the fork? And here, I see a problem concerning the fork itself: for the very first training samples, the activation just before the fork deeply depends on the weights of all the previous layers, which are not well trained yet (still a random guess). This means that this activation is not, to some extent, a good representation of the input data in the first place. Using this "bad/distorted" data as an input to the forked network would make us train it on discriminating something that is completely different from our real input data!

    • @mashmesh
      @mashmesh 4 ปีที่แล้ว

      I am also curious about this. I do not understand how the outputs from the forks are put together in end.

  • @scchouhansanjay
    @scchouhansanjay 3 ปีที่แล้ว +1

    I was thinking of the movie as well but I was also thinking that I am stupid to think that such a important paper will have anything to do with a movie.

  • @DrN007
    @DrN007 4 ปีที่แล้ว +3

    Better naming would've been: Deep Modular Network

  • @dcastudios7185
    @dcastudios7185 5 ปีที่แล้ว +9

    And I came here from - Inception movie explained 💤

  • @EranM
    @EranM 5 ปีที่แล้ว +6

    Know your meme!

  • @iammakimadog
    @iammakimadog 3 ปีที่แล้ว

    2:52 What's the purpose of "maxpool -> 1x1 conv"? Seems like applying 1x1 conv directly is strictly better than that, coz some information will be lost in maxpool...

    • @akashkewar
      @akashkewar 3 ปีที่แล้ว

      information is always lost in pooling, we use the max pool to keep important information (it has got "max" in it, and hence we use pixel which has maximum information). We use 1x1 conv to change the depth (channel) of the output by max-pooling so that we could perform concatenation (require the same dimension). Additionally, not every piece of information is important, using too much information could result in overfitting and you have compensated for it either by using the max pool (could be treated as weak regularize, theoretically ), kernel regularizer, dropout and so on.

  • @andrewwilliam2209
    @andrewwilliam2209 4 ปีที่แล้ว

    what are the max pools for if they don't reduce the size? (SAME max pooling)

  • @ericklestrange6255
    @ericklestrange6255 4 ปีที่แล้ว

    thanks, very useful

  • @DevilErnest
    @DevilErnest 4 ปีที่แล้ว

    Padding is applied, isn’t it?

  • @alex_316
    @alex_316 2 ปีที่แล้ว

    This looks like an autoML but for the Conv NN

  • @aione7448
    @aione7448 5 ปีที่แล้ว +1

    I dint get the Inception , How can we stack convolved image after passing through different filter without pasdding since according to different filter dimension of convolved image too change

  • @vytasmatas
    @vytasmatas 5 ปีที่แล้ว

    thank you very usefull

  • @thovinh5386
    @thovinh5386 4 ปีที่แล้ว +1

    From now on, I'll expect meme while reading papers

    • @ericklestrange6255
      @ericklestrange6255 4 ปีที่แล้ว +1

      millenial contributing in their (our) language

  • @itohamza
    @itohamza 4 ปีที่แล้ว

    how to concatenate 4 different data sizes?

  • @trexmidnite
    @trexmidnite 3 ปีที่แล้ว

    VampireNet also good

  • @anjithaanju2584
    @anjithaanju2584 4 ปีที่แล้ว

    Can you make a video about Inception v4?