Lecture 7: Convolutional Networks

แชร์
ฝัง
  • เผยแพร่เมื่อ 9 ก.พ. 2025

ความคิดเห็น • 31

  • @jh97jjjj
    @jh97jjjj ปีที่แล้ว +9

    Great lecture for free. Thank you Michigan University and professor Justin.

  • @alokoraon1475
    @alokoraon1475 ปีที่แล้ว +1

    I have this great package for my university course.❤

  • @faranakkarimpour3794
    @faranakkarimpour3794 2 ปีที่แล้ว +3

    Thank you for the great course.

  • @temurochilov
    @temurochilov 2 ปีที่แล้ว +3

    Thank you I found answers to the questions that I have been looking for long time

  • @hasan0770816268
    @hasan0770816268 3 ปีที่แล้ว +3

    33:10 stride
    53:00 batch normalization

  • @fa7234
    @fa7234 12 วันที่ผ่านมา

    37:00 the size of the filter should be 32 x 64 x 1 x 1. another typo. Also the input tensor shape is disproportion. depth (64) should be longer than height and width (56)

  • @tatianabellagio3107
    @tatianabellagio3107 3 ปีที่แล้ว +10

    Amazing!
    Pd: Although I am sorry for the guy with the coughing attack...........

    • @kobic8
      @kobic8 ปีที่แล้ว +2

      yeah, kinda disturbed me to concentrate. 2019 it was right before covid striked the world hahah
      😷

  • @rajivb9493
    @rajivb9493 3 ปีที่แล้ว +1

    at 35:09, the expression for output in case of stride convolution is (W - K + 2P)/S +1...for W=7, K=3, P = (K-1)/2 = 1 & S=2 we get output as (7 - 3 + 2*1)/2 + 1 = 3 +1 = 4 ...however, the slide shows the output as 3x3 instead of 4x4 at the right hand corner... is it correct..?

    • @DED_Search
      @DED_Search 3 ปีที่แล้ว

      I have the same question.

    • @krishnatibrewal5546
      @krishnatibrewal5546 3 ปีที่แล้ว +1

      both are different situations, the calculation is done without padding whereas the formula is written considering padding

    • @rajivb9493
      @rajivb9493 3 ปีที่แล้ว

      @@krishnatibrewal5546 ... thanks a lot, yes you're right..

    • @DED_Search
      @DED_Search 3 ปีที่แล้ว

      @@krishnatibrewal5546 thanks.

  • @eurekad2070
    @eurekad2070 3 ปีที่แล้ว +1

    Thank you for exellent video! But I have a question here, at 1:05:42, after layer normalization, every sample in x has shape 1xD, while μ has shape Nx1. How do you perform the subtraction x-μ?

    • @useForwardMax
      @useForwardMax 3 ปีที่แล้ว +1

      I wonder if gamma and beta with 1 x D is a typo? If it should be N x 1? If it is not a typo, doing the subtraction is just using the broadcasting mechanism like in numpy.

    • @eurekad2070
      @eurekad2070 3 ปีที่แล้ว +1

      @@useForwardMax Broadcasting mechanism makes sense. Thank you.

    • @vaibhavdixit4377
      @vaibhavdixit4377 6 หลายเดือนก่อน

      Just finished watching the lecture, as per my understanding, X (1 X C X H X W) is the shape of the input vector consumed at once in the algo, and for the calculated means and standard deviations they have mentioned the shape of the output vectors of these parameters in terms of batch size (N X 1 X 1 X 1) as each value uniquely represents each input (1 X C X H X W).
      It is a late reply but I am replying if someone else would scroll through with similar question to yours!

  • @DED_Search
    @DED_Search 3 ปีที่แล้ว

    1:01:30 what did he mean by “fusing BN with FC layer or Conv layer”?

    • @krishnatibrewal5546
      @krishnatibrewal5546 3 ปีที่แล้ว +1

      You can have conv-pool-batchnorm-relu or fc- bn- relu , batch norm can be induced between any layer of the network

    • @DED_Search
      @DED_Search 3 ปีที่แล้ว

      @@krishnatibrewal5546 thanks a lot!

    • @yahavx
      @yahavx ปีที่แล้ว

      Because both are linear operators, then you can simply concat them after training (think of them as matrices A and B, in test time you multiply C=A*B and you put that instead of both)

  • @jijie133
    @jijie133 4 ปีที่แล้ว +1

    Great.

  • @intoeleven
    @intoeleven 3 ปีที่แล้ว

    why they don't use batch norm + layer norm together?

  • @puranjitsingh1782
    @puranjitsingh1782 3 ปีที่แล้ว

    Thanks for an excellent video Justin!! I had a quick question on how does the conv. filters change the 3d input into a 2d output

    • @sharath_9246
      @sharath_9246 3 ปีที่แล้ว +1

      When you dot product 3d image example(3*32*32) with filter(3*5*5) gives a 2d feature map (28*28) just bcoz of the dot product operation between image and filter

  • @rajivb9493
    @rajivb9493 3 ปีที่แล้ว

    In Batch Normalization during Test time at 59:52, what are the averaging equations used to average Mean & Std deviation, sigma ..during the lecture some mention is made of exponential mean of Mean vectors & Sigma vectors...please suggest.

  • @ibrexg
    @ibrexg ปีที่แล้ว

    Well don! here is more explanation to normalization: th-cam.com/video/sxEqtjLC0aM/w-d-xo.html&ab_channel=NormalizedNerd

  • @magic4266
    @magic4266 ปีที่แล้ว +1

    sounds like someone was building duplo the entire lecture

    • @brendawilliams8062
      @brendawilliams8062 ปีที่แล้ว

      Thomas the tank engine?

    • @park5605
      @park5605 9 หลายเดือนก่อน

      ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem ahem .
      ahem ahem.
      ahe ahe he he HUUUJUMMMMMMMMMMMM

  • @japanboy31415
    @japanboy31415 9 วันที่ผ่านมา

    im fucked for this quiz 2 lol