10. AlexNet - CNN Explained and Implemented.

Поделиться
HTML-код
  • Опубликовано: 27 ноя 2024

Комментарии • 69

  • @lakshmisreekanth9256
    @lakshmisreekanth9256 17 часов назад

    Best way you explained the concept .

  • @setupyouryoutub
    @setupyouryoutub 4 года назад +1

    Very simple way of explaining deep learning. Awesome playlist

    • @ShriramVasudevan
      @ShriramVasudevan  4 года назад

      Thanks and glad u liked. Your comments keep me moving

  • @subashsi9420
    @subashsi9420 Год назад +1

    Your, voice is similar to Ravi Ashwin. Great explanation

  • @dawit_haile
    @dawit_haile 4 года назад +1

    it is a good explanation in a simple way. Thank you.

  • @technologyhunter2460
    @technologyhunter2460 4 года назад +3

    Nice effort, Appreciated!

  • @nastaranmarzban1419
    @nastaranmarzban1419 3 года назад +2

    Hi, thanks for your really nice explanation, would you please explain a bit more why do we have 96 filters ?

  • @sp3519
    @sp3519 4 года назад

    You have made it very easy to understand

  • @menakaraman3374
    @menakaraman3374 4 года назад

    Thanks for the explanation in a simple way

  • @anitanbhatt
    @anitanbhatt 2 года назад

    Nicely explain and very easy to understand

  • @keerthanaag8561
    @keerthanaag8561 7 месяцев назад

    does the table value change?? does the stride and image size from the alexnet architecture table in the video remain the same irrespective of the input image??

  • @suyogborkar6644
    @suyogborkar6644 Год назад

    Great explanation sir!!

  • @nevillechristopherraja3470
    @nevillechristopherraja3470 3 года назад +2

    hello Shriram, you have explained very well.. I have a question, the conv layer 2 has a padding of 2 as per the architecture but I see you have mentioned the padding as 'valid' for this layer, could you kindly clarify this? am I missing something here?

  • @djjohny19
    @djjohny19 2 года назад

    Sir, thank you very much!

  • @afiatasnim8848
    @afiatasnim8848 8 месяцев назад

    u can train this AlexNet in tensorflow. but tensorflow won't provide pretrained weights for AlexNet. only pytorch will provide that.

  • @ninadkulkarni9426
    @ninadkulkarni9426 4 года назад +3

    Hello sir, it is very informative. I want to ask you is it possible for you to make a video for training Alexnet architecture with pre trained cifar 10 dataset with explaining on how to rescale the datasets from 32*32 to 227*227? This will be very much helpful

  • @profdurgahere9007
    @profdurgahere9007 4 года назад

    This is one of the best.

  • @muslumyildiz5694
    @muslumyildiz5694 Год назад +1

    thanks

  • @sstech6695
    @sstech6695 4 года назад

    Very nicely done

  • @aritraroy4275
    @aritraroy4275 Год назад

    You didn't use batchNormalization or according to paper Local response Normalization

  • @unggulprabowo1045
    @unggulprabowo1045 3 года назад +1

    Nice tutorial and demo sir, I want to ask about layer output. In this video and architecture output layer using 1000 classes, If our have classes 4, do we have anything ouput layer change 4 classes ?.

    • @esraahamada4784
      @esraahamada4784 9 месяцев назад

      did you know the answer because I have the same question ?

  • @thepresistence5935
    @thepresistence5935 2 года назад

    Hey Bro, you told transfer learning, where is the weights for this. I think we are using only architecture of the AlexNet, how to apply weights

  • @sstech6695
    @sstech6695 4 года назад

    Very well done..

  • @hasinamoideen584
    @hasinamoideen584 4 года назад +1

    clearly explained !

  • @munazzapedia
    @munazzapedia Год назад

    can we change parameters like input size , layer , feature map , size , kernel size , stride , activation ? any of them changing any of them will change alexnet architecture ? is it necessary to use same parameters which described in video to use this architecture namesd as alexnet ? If i change parameters it will be also called as alexnet ?

    • @keerthanaag8561
      @keerthanaag8561 7 месяцев назад

      lemme know if you have found the answer

  • @KARTHIK-mm5uz
    @KARTHIK-mm5uz 2 года назад

    Sir, it is very informative. thank you very much.
    Sir at the second convolution layer it is said that the size is 27x27x256. But it will be 23x23x256 right. in the program output, it is correctly calculated but in all the slides available it is 27x27x256. There are corresponding changes in the following layers (ie. in the next layer it is 11x11 then 9x9 then 7x7 etc.

  • @nsridevi8569
    @nsridevi8569 4 года назад

    Very informative and useful sir.... very used for my research.... can you explain the drawbacks of these pretrained models.... like googlenet, inception, resnet

  • @rohitborra2507
    @rohitborra2507 4 года назад

    this is the best I have found on internet but you would have implemented with some example

    • @ShriramVasudevan
      @ShriramVasudevan  4 года назад

      I have done that. Video follows shortly brother.

    • @rajanrana4887
      @rajanrana4887 4 года назад

      @@ShriramVasudevan Please upload it bro we are waiting...

  • @sinzsma8841
    @sinzsma8841 4 года назад

    Very nice sir...

  • @JuneLetsPlays
    @JuneLetsPlays 3 года назад

    You talked about augmentation? I cant find this in the code...

  • @amankushwaha8927
    @amankushwaha8927 3 года назад

    Is it possible to build the entire model without using the library?

  • @FahadKhan1
    @FahadKhan1 Год назад

    Can you please provide example code?

  • @ihebdhouibi5132
    @ihebdhouibi5132 4 года назад +2

    can you please share the code of AlexNet, it would help alot

    • @ShriramVasudevan
      @ShriramVasudevan  4 года назад +1

      I will upload in GIT tomorrow..username shriramkv

    • @ihebdhouibi5132
      @ihebdhouibi5132 4 года назад

      @@ShriramVasudevan add the link to it in description please

  • @parthdedhia4182
    @parthdedhia4182 4 года назад

    Hey, thanks for the explanation.
    Regarding the input dimension of the AlexNet network, I tried implementing it in TensorFlow and only works if the size is 227 x 227. But Many of the literatures following them have made use of different dimensions. Like SPPNet paper says its 224 x 224 x 3, and R-CNN paper uses 227 x 227. Please can you explain me as to what should be believed.

    • @ShriramVasudevan
      @ShriramVasudevan  4 года назад +1

      To my knowledge... it should work with any dimension. There is no hard rule about the dimensions bro.

    • @saikrishnadas666
      @saikrishnadas666 3 года назад +1

      The larger the image dimension, the more time it's gonna take for training and inference!

  • @muhammadfaizan8839
    @muhammadfaizan8839 4 года назад

    sir very nice explanation and as well slides. thanks sir. kindly can you share the slides?

  • @babj32
    @babj32 3 года назад

    Thanks too much

  • @amrutsanjawadmath47
    @amrutsanjawadmath47 4 года назад

    nice

  • @zouhairinfo7497
    @zouhairinfo7497 3 года назад

    can you please share the code

  • @saritagautam9328
    @saritagautam9328 3 года назад

    please provide the code sir

  • @syedaneeshamuskan4712
    @syedaneeshamuskan4712 Год назад

    hello i need code

  • @fathimaa3617
    @fathimaa3617 4 года назад

    👍

  • @samsondawit
    @samsondawit Год назад

    why 227x227? The paper itself says 224x224? could you please explain

  • @امنهطه-ع7ق
    @امنهطه-ع7ق 2 года назад

    Please sir can you send me code