ResNet Explained Step by Step( Residual Networks)

Поделиться
HTML-код
  • Опубликовано: 9 ноя 2024

Комментарии • 218

  • @tejasbankar3136
    @tejasbankar3136 2 года назад +1

    thank you mam for this. I saw almost 4-5 videos on youtube, but didn't get ResNet. You make it very simple. Thanks!

  • @saravananbaburao3041
    @saravananbaburao3041 4 года назад +4

    Easily one of the best video in Resnet . Crisp and clear explanation. Good job

  • @muhtadirshihab
    @muhtadirshihab 4 года назад +10

    Thanks, Ma'am for your easy explanation. I spent almost entirety day to catch some things. It's all clear for me now. Keep updating such materials related to CNN. I am also interested in learning Data Science related to mathematics from you.

    • @CodeWithAarohi
      @CodeWithAarohi  4 года назад +5

      Glad this video is helpful. And i have a playlist named “statistics for data science” there you can learn maths . I have few videos in it , rest will update soon

    • @muhtadirshihab
      @muhtadirshihab 4 года назад

      @@CodeWithAarohi Thanks so much for kind information. I will obviously check cause I need to learn maths.

    • @_sonu_
      @_sonu_ 10 месяцев назад +1

      you can't believe I minimise the video for giving 👍 likes, but I found I already had liked@@CodeWithAarohi

  • @eliashossain4327
    @eliashossain4327 2 года назад +5

    What an explanation! This is a masterpiece tutorial, and thank you, Ma'm, for making such mesmerizing video.

  • @hulkbaiyo8512
    @hulkbaiyo8512 Год назад +1

    back to this old video, and get back and review, just realize how beautiful Resnet it is. how those ppl come up with those cool ideas

  • @LucyRockprincess
    @LucyRockprincess 2 года назад

    i've watched 10 videos explaining this and yours was the best

  • @codebite3951
    @codebite3951 3 года назад +6

    This is an excellent description of resnet50 architecture. You earned a subscriber. 👍

  • @RanjitSingh-rq1qx
    @RanjitSingh-rq1qx 2 года назад +1

    Mam, you are to good. Really trust keep going on your way. Your content is really very helpful. I didn't see such a content on RUclips.

  • @ThamizhanDaa1
    @ThamizhanDaa1 3 года назад +3

    This is the best video on this topic!! Thank you so much, Aarohiji.. Your help is greatly appreciated for my research.

  • @yaqubshuaib5060
    @yaqubshuaib5060 3 года назад

    this is the greatest explanation i have ever seen upon this topic. thank you

    • @CodeWithAarohi
      @CodeWithAarohi  3 года назад

      Glad it was helpful!

    • @yaqubshuaib5060
      @yaqubshuaib5060 3 года назад

      @@CodeWithAarohi
      Mem i want a certificate course on AI, ML,DL .If u make any course on this topic i wanna enroll under u .

  • @RanjitSingh-rq1qx
    @RanjitSingh-rq1qx 2 года назад

    Mam, i am following your playlist. Really it is very helpful content. But mam your playlist is short.please make more videos. Because now I don't want follow the playlist from any youtuber except you mam. 🥰🥰🥰

    • @CodeWithAarohi
      @CodeWithAarohi  2 года назад +1

      Sure, I will update the playlist and also try to add more videos soon 😊

  • @QingyuanYang
    @QingyuanYang 6 месяцев назад

    I appreciate the patience and very useful repeat in the presentation!

  • @durgarani9573
    @durgarani9573 2 года назад

    Thank you very much mam for your good explanation about ResNet.

  • @patiladiti2116
    @patiladiti2116 3 месяца назад

    Thank you so much for this lecture! Clear and to the point!

  • @DevanshShukla11
    @DevanshShukla11 8 месяцев назад

    Mam I understood in detail about the Resnet 50 architecture, but there is one question, like I am right now making a project on LDW system it has to detect the lanes, so how do use this model? What should be my approach?

  • @sajjadrahman-m1r
    @sajjadrahman-m1r Год назад

    Very friendly explanation . I clear my problem by help of your presentation. Love u mammmammmaaa❤❤❤❤❤❤❤❤❤❤

  • @geekieyyy
    @geekieyyy Год назад

    much much thanks mam , very very much far better from my college professors

    • @CodeWithAarohi
      @CodeWithAarohi  Год назад

      Glad my video is helpful! Keep watching and learning 😊

  • @duen-shianwang378
    @duen-shianwang378 4 года назад +2

    Thank you so much for your excellent explanation of Resnet!!!

  • @ananyabhattacharjee4217
    @ananyabhattacharjee4217 3 года назад

    The best resnet video explained in so much detail. Thank you Aarohi.

  • @coolandhot2006
    @coolandhot2006 4 года назад +4

    Great explanation! Thank you so much, I know what ResNet now. ^^

  • @emirhanbilgic2475
    @emirhanbilgic2475 3 года назад

    Thanks alot ♥ Greetings from Istanbul Technical University

  • @divyanshubse
    @divyanshubse 8 месяцев назад +1

    Nice explanation mam

  • @poojakabra1479
    @poojakabra1479 3 года назад +1

    4:50 you say we avoid vanishing gradient by skipping layers, back propagation however does not travel through the skip connections. Can you explain how the vanishing gradient is exactly solved?

    • @ni_nou-u5r
      @ni_nou-u5r 3 года назад

      from my understanding, back propagation does travel through the skipped layers but stack them as a single one. So a set of stacked layers have one common weight that the gradient travels throught. simply put you have a direct weighted connection lets say between layer 1 and 10 for example. in the end the gradient goes through less connections and thus remains stable

  • @ajaysivasaitangella1717
    @ajaysivasaitangella1717 Год назад

    This video is very helpful! ,one of the best video in Resnet, thankyou mam, it would be helpful if share the slides

  • @bhargavram860
    @bhargavram860 3 года назад +3

    Thank you Aarohi 👍🏻. I have doubt - So does the residual networks play their part only while updating weights?

  • @munnaram8527
    @munnaram8527 2 года назад

    Thanks ma'am for such nice explanation.,🙏🙏

  • @salmanahmedkhan3979
    @salmanahmedkhan3979 2 года назад

    Great explanation Ma'am Aarohi. You made all the concepts very easy and clear. Lots of love from Pakistan.

  • @ecemiren6600
    @ecemiren6600 Год назад

    Dear I couldn't understand the logic of usage of identity block in the first convolutional block. Because input is 75x75x64. But in the last convolutional layer as 1x1x256, the output should have dimension of 256. Therefore we can not add input and output, could you please clear this with an example ? Thank you very much for the video.

  • @abbas19852000
    @abbas19852000 2 года назад

    Thank you Ma'am for your great and amazing explanation

  • @jaivalani4609
    @jaivalani4609 3 года назад

    We track FX such that it gets as min as possible and hence Y becomes as close as possible to Input. FX is acting like a Regularisation function also

  • @ariouathanane
    @ariouathanane 2 года назад

    Thank you for this video. Excellent work

  • @shidharthrouth
    @shidharthrouth 3 года назад

    Ok so what I understood about the identity and convolution block is that their result is added to the output of a normal block of convolution and pooling in a network to generate a residual block and then the result of the residual block is fed to the next residual block in line... I.e., we are changing the value of activations of a block explicitly
    Please correct me if I am wrong

  • @Saritty-j5w
    @Saritty-j5w Год назад

    Good Explanation. But 301/2 can never be 150. So how do we correct it?

  • @ashishmohite803
    @ashishmohite803 2 года назад

    thanks mam....great explaination
    1 doubt:
    in lung disease detection our image of xrays will be in grayscale format so,
    while giving size [224.224] +[3] what will be in place of 3 as 3 is used for colored image?

  • @niluthonte45
    @niluthonte45 Год назад

    thank you mam ,please explain implementation like this

  • @afnersirait
    @afnersirait 3 года назад

    Thankyou so much. This explanation is really helpful

  • @csabarikannan
    @csabarikannan 3 года назад

    Really Worth of my time to watch the video. Great explanation Madam.

  • @yashsonar9400
    @yashsonar9400 Год назад

    Great great Explanation. Thank you so much mam

  • @supritodeysarkar4094
    @supritodeysarkar4094 Год назад

    You make deep learning easy!

  • @raajproduction9462
    @raajproduction9462 3 года назад

    Love you mam,,,,,I really love your explaination....Thank you very much for making such a video

  • @马豆豆-t4j
    @马豆豆-t4j 2 года назад

    thank you much , so helpful video

  • @jesmithathoras2572
    @jesmithathoras2572 2 года назад

    Thank you for the good explanation.. I have one doubt. What will the filter matrix will contain I mean values??

    • @CodeWithAarohi
      @CodeWithAarohi  2 года назад

      Those will be some pixel values from image

  • @meklitmesfin5968
    @meklitmesfin5968 2 года назад +6

    great explanation thanks a lot. but I have a question. after 2 convolution layers our input dimension changed in to 75*75*64. this will be the input after the next three convolution layers. to add this with the output of these three convolution layers their dimensions must be the same but the third convolution has 256 filter size which makes the output x dimension*y dimension*256 which can't be added to the 75*75*64 dimension and we used identity blocks even though their dimension is different. can you please explain to me this? thanks once again😊

  • @rahulchaubey8988
    @rahulchaubey8988 3 года назад +1

    Very detailed explanation. 👌👌👌👌

  • @omkarsargar5375
    @omkarsargar5375 4 года назад +1

    Can you PLEASE make a Attention model in deep learning video just like this one step by step and detailed explanation it will be a great help.

  • @VEDANSHUDHAWANI
    @VEDANSHUDHAWANI 9 месяцев назад

    Best Explanation ever...Can i get this ppt ?

  • @chandrasenpandey5108
    @chandrasenpandey5108 4 года назад +2

    Well explained maam thank you so much for explaining this 🙏

  • @prasadk-u1o
    @prasadk-u1o Год назад +1

    nice explanation @Aarohi can you please explain that convolutional block how the output size(28*28*128) matches the input size (56*56*64) once again there is a little confusion for me

  • @kanikagupta2806
    @kanikagupta2806 2 года назад

    amazing and detailed explaination

  • @balagurugupta5193
    @balagurugupta5193 Год назад

    thanks a lot for the neat explanation

  • @ernestbeckham2921
    @ernestbeckham2921 Год назад

    superb explanation. if you explain nlp series (transformers), it will be also superb

  • @gaganmalhi1229
    @gaganmalhi1229 4 года назад +1

    How to manage a big topic in short video....👍🏻👍🏻

  • @VinothKumar-hw7ud
    @VinothKumar-hw7ud 4 года назад +1

    Hi.. great video... have a small doubt regarding identity block..let consider 1st skip connection where identity block works. X=75*75*64 to add this o/p of 1x1 conv, 256. But the size of X (input) is not matching with o/p of 1x1 conv, 256. Then how identity works???? pls comment..

    • @CodeWithAarohi
      @CodeWithAarohi  4 года назад

      Hi.. thanks for appreciation... Please provide me the output size also. Because we apply identity block when input size and output size is similar. And as per your comment, x=75*75*64 and you are applying 1*1 conv,256 in the shortcut path. But what is the size of output image then only we can compare whether 1*1 conv,256 is giving us correct size or not.

    • @poojakabra1479
      @poojakabra1479 3 года назад

      @@CodeWithAarohi The 75*75*64 has depth=64 and after the 1*1 conv,256 layer, depth = 256. How can you add them?

    • @dhivyaakumar
      @dhivyaakumar Год назад

      @@poojakabra1479 Correct.. you cant add 75*75*64 with the output of the first convolution block (1*1*256). If you see the resnet architecture code, we use a 1*1 con with stride =1 in the first skip connection and the filter 64 is multipled by 4 = 256; so the shortcut size would be 75*75*256 which can then be added with the output from the 1*1*256 conv layer which is also 75*75*256.

  • @sorymillimono5931
    @sorymillimono5931 3 года назад

    thank you very good job and explanation.

  • @blacknwhite5875
    @blacknwhite5875 3 года назад +1

    great explanation on architecture and I am not able to understand channel change from layer to layer

    • @CodeWithAarohi
      @CodeWithAarohi  3 года назад

      Channels are changing layer to layer because all these channels are already fixed as per the paper of Resnet. See Resnet is an algorithm and all the parameters like how neurons in a layer, padding, pooling size and channels are pre defined. So we are using those parameters. If you want you can change the number of channels and play around.

  • @manikhossain5697
    @manikhossain5697 2 года назад

    Thank you so much.

  • @ayay9423
    @ayay9423 3 года назад +1

    This video is very helpful! Thank you so much for explaining this :)

  • @vinaymurthy4388
    @vinaymurthy4388 3 года назад

    Very well explained. Thanks

  • @harishdasari5545
    @harishdasari5545 11 месяцев назад

    can you please explain
    How this res-net 50 applied to speech

  • @mahadrashid2794
    @mahadrashid2794 3 года назад

    Amazing step by step by explanation!

  • @jibinjohn1530
    @jibinjohn1530 4 года назад +1

    Explained very well. Good work

  • @siddharthmodi2740
    @siddharthmodi2740 2 года назад

    Best explanation on internet , Thanks Aarohi 🧡

  • @widdalightsout
    @widdalightsout 3 года назад +1

    Thankyou so much, this was really helpful.

  • @manojexpert
    @manojexpert 2 года назад

    Thanks... very helpful...

  • @pusuluriaditya1369
    @pusuluriaditya1369 3 года назад

    Does the skip layers get trained during forward propogation?

    • @CodeWithAarohi
      @CodeWithAarohi  3 года назад

      skip layers are skipped from training. This is the logic of resnet

  • @arjunbansal674
    @arjunbansal674 3 года назад +1

    M'am i have used resnet50 for a project but my guide asked me to do changes in the algorithm,so mam what changes i can do in the algorithm without disturbing accuracy to large amount.

    • @CodeWithAarohi
      @CodeWithAarohi  3 года назад +3

      You can remove 1 or 2 layers from the algorithm or you can change the filter size in any of the layer or you can change the pool size . You can change the stride in 1 or 2 layers of the algorithm. When you will do changes in 1 or 2 layer that will not impact the accuracy much.

  • @deepsingh274
    @deepsingh274 3 года назад

    thanks for explaining

  • @ajilisaaliyar3156
    @ajilisaaliyar3156 3 года назад

    Hello Maam...Very Good Explanation, Can you explain attention gate mechanism in a video?

  • @raj4126yt
    @raj4126yt Год назад

    Great tutorial

  • @MATHEMATICSGURU21
    @MATHEMATICSGURU21 Год назад

    Super explanation

  • @rabailrana9916
    @rabailrana9916 2 года назад

    Thank you

  • @lukmanahromi8295
    @lukmanahromi8295 3 года назад

    Great explaination thanks!!

  • @anuragshrivastava7855
    @anuragshrivastava7855 2 года назад

    You have so much of knowledge about AI then why you not working in big brand, MNC

    • @CodeWithAarohi
      @CodeWithAarohi  2 года назад

      I like to work the way I am working now 😊

  • @aswathycomm4852
    @aswathycomm4852 2 месяца назад

    Thank u so much mam

  • @deepikasingh3122
    @deepikasingh3122 8 месяцев назад

    How would we get f(x) if we won't pass through the layers

  • @arulgnanaprakasama.samjosh733
    @arulgnanaprakasama.samjosh733 2 года назад

    super akka 👏

  • @tarasaber4525
    @tarasaber4525 2 года назад

    hello dear if we want to change the input of pretrained network Resnet50 224 * 224 to some higher value what should we do ?

    • @CodeWithAarohi
      @CodeWithAarohi  2 года назад

      You can write your own resnet model and change the input size. Check this link: github.com/AarohiSingla/ResNet50/blob/master/3-resnet50_rooms_dataset.ipynb Here I am using the input size 64. and you can replace that 64 with your customized image size.

  • @ed21b006
    @ed21b006 Год назад

    Thank u so much dii

  • @santiagogomez8354
    @santiagogomez8354 3 года назад +2

    You can put subtitles in English, I appreciate it.

  • @Fatima-kj9ws
    @Fatima-kj9ws 3 года назад

    You are the best

  • @wahyupriyowicaksono4900
    @wahyupriyowicaksono4900 2 года назад

    is the number of layers in ResNet50 the same as those in ResNet50V2?

  • @naimafarooqi1403
    @naimafarooqi1403 3 года назад

    where did the formula come from? please explain.

  • @niluthonte45
    @niluthonte45 11 месяцев назад

    Can we use this resnet50 model for mri brain tumor image classification having 4 classes in the target feature,?

  • @PoornimaEG25
    @PoornimaEG25 4 месяца назад

    Thank you so mam, can you please language autogenerated hindi to english in this video

  • @vinothsomasundaram9519
    @vinothsomasundaram9519 3 года назад

    I have serious problem with doing resnet model, please let me know

  • @SehanobishDipanjan
    @SehanobishDipanjan Год назад

    good explanation

  • @rickharold7884
    @rickharold7884 3 года назад

    Very nice!

  • @YBMWY
    @YBMWY 3 года назад

    Do you have any code for modulation classification?

  • @mohammademdadulislam5432
    @mohammademdadulislam5432 Год назад

    Excellent mam, keep it up

  • @sajedehtalebi902
    @sajedehtalebi902 Год назад

    useful and simple:)

  • @حسینمهرعلیپورفرد
    @حسینمهرعلیپورفرد 11 месяцев назад

    can anybody write answer of my question
    after of maxpooling layer we have 64 layer that connected to slip connection this input will add to the other input that has 256 layer???
    what is happening in there

  • @Areeva2407
    @Areeva2407 3 года назад +1

    Very Good!!

  • @MuhannadGhazal
    @MuhannadGhazal 3 года назад +1

    if we want to make f(x) equals to zero. then why dont we just remove these layers? if their output is zero, why dont we just remove them? i didnt get this point. anyone please explain what did i miss.

    • @shidharthrouth
      @shidharthrouth 3 года назад +1

      I am pretty new to the whole deep learning thing but what I understood from the explanation was, it is not that we are trying to achieve a fx = 0 but more appropriately we are trying to achieve y = fx + x for each residual block... Now we know that traditionally we try to bring SGD to a local minima and we can only do that if fx is close to the original output but here we are changing the activations explicitly to do so by adding x to fx rather than relying on the network to bring the network to a local minima... Now to answer what u asked according to the paper the identity x is not considered as an extra hyperparameter so it is kinda non existent so during back propagation the network still adjusts the weights of the original layers so we can't remove them...
      Hope this was helpful

  • @amintaleghani2110
    @amintaleghani2110 3 года назад +1

    @Code With Aarohi , thank you for your effort making this informative video. I wonder if we can use ResNet for Time Series data prediction. If so, Could you pls make video on the subject. Thanks again

  • @jayanthikkumari7454
    @jayanthikkumari7454 4 месяца назад

    Hi mam please make videos on SkNet and DieT

    • @CodeWithAarohi
      @CodeWithAarohi  4 месяца назад

      Noted!

    • @jayanthikkumari7454
      @jayanthikkumari7454 4 месяца назад

      @@CodeWithAarohi mam I have phd interview I have some doubts can I contact you mam please if possible to you mam

  • @irfiali199
    @irfiali199 3 года назад

    Well done, very nicely explained. Keep it up

  • @ajanthaalakkshmanan5854
    @ajanthaalakkshmanan5854 3 года назад

    Plz explain red deer optimization mam

  • @shubhamchoudhary3580
    @shubhamchoudhary3580 3 года назад

    Very nice explanation. Mam can u share the ppt..

    • @CodeWithAarohi
      @CodeWithAarohi  3 года назад

      Thanks for liking my work and I am sorry, I dont have this ppt with me. But yes if you want resnet code that I can share.

    • @shubhamchoudhary3580
      @shubhamchoudhary3580 3 года назад

      Okk mam plz share

    • @CodeWithAarohi
      @CodeWithAarohi  3 года назад

      @@shubhamchoudhary3580 github.com/AarohiSingla/ResNet50/blob/master/3-resnet50_rooms_dataset.ipynb

  • @san_dc
    @san_dc 2 года назад

    An interesting video.
    But why so many empty lines in the description?

    • @CodeWithAarohi
      @CodeWithAarohi  2 года назад +1

      Glad you liked my video. And Space is by Mistake. Deleted now

  • @praveenprakash143
    @praveenprakash143 3 года назад

    Fantastic