PyTorch for Deep Learning - Full Course / Tutorial

Поделиться
HTML-код
  • Опубликовано: 15 дек 2024

Комментарии • 375

  • @ClarHD
    @ClarHD 3 года назад +68

    This is the best course on Neural Networks and PyTorch I have ever watched in my life, and I'm barely done with it. I could cry. Everything is explained in detail, amazing. I am completely new to Neural Networks and I feel somewhat comfortable already. Thank you!

  • @maoryatskan6346
    @maoryatskan6346 4 года назад +149

    Amazing, freecode should reserve a prize for their efforts.

  • @pfever
    @pfever 2 года назад +5

    I'm impressed by the quality of this course, he knows the topic very well and explains it clearly!

  • @boreycheng9260
    @boreycheng9260 3 года назад +10

    This tutorial is complete and materials are available across multiple platforms. Thank you!

  • @sekandooon
    @sekandooon 4 года назад +39

    Perfect course for someone who wants start learning PyTorch. Amazing work, thanks a ton!

  • @ravidhar79
    @ravidhar79 4 года назад +21

    I really liked the second last part of the training program where the instructor has brought in a game changer that accelerates a data science model performance from 50% to over 95% using various techniques. ..Well what this means is that Data Science Models can now train faster and predict more accurate insights.
    Great job instructor, some more user cases in the medical field would be appreciated in your next video. Thank you so much, great work!!

    • @Raj-gc2rc
      @Raj-gc2rc 2 года назад

      What is the use of building intuition by trying out different hyper parameters, when we have Gaussian process optimization that can learn a function of hyperparameters and estimated loss and accuracy?
      can you please explain the disadvantages of this method?
      This way trial and error approach is replaced by a mathematical model ?

  • @hemaswaroop7970
    @hemaswaroop7970 4 года назад +41

    This video was uploaded 3 hours ago having a duration of 9hrs. Folks have already commented praising the video. I'm wondering if they have really seen it fully and commented or just posting randomly.

    • @pixel7038
      @pixel7038 4 года назад +2

      Millennial's like attention

    • @karthik-ex4dm
      @karthik-ex4dm 4 года назад +8

      @@alangobryan5022 But the only thing is it wouldn't take 9 hrs to tell if a girl is beautiful or ugly

    • @BreakItGaming
      @BreakItGaming 4 года назад

      may be they developed 3x and used it to watch this video.
      kidding bro

  • @atraps7882
    @atraps7882 4 года назад

    i usually hate ads on youtube video but when it comes to ads on FCC, i gladly watch them cause I know its gonna help them provide us with more free quality content like this. Like seriously, I tried to learn some pytorch from a book and I wasn't making much progress but then this video really propelled me forward.

    • @maanasverma7659
      @maanasverma7659 4 года назад

      If you don't click on the advertisement directed to its website there is no earning for this channel ;)

    • @atraps7882
      @atraps7882 4 года назад

      @@maanasverma7659 oh I see...thanks for letting me know

  • @caleb_sample
    @caleb_sample 4 года назад +5

    I love it every time he says "r"

  • @covid-19ultrapromax25
    @covid-19ultrapromax25 4 года назад +16

    Summary : Coding = Food + Digestion = $hit
    Artificial Intelligence = Food + $hit = digestion.

  • @shalerr5513
    @shalerr5513 4 года назад +119

    It is perfect with indian accent

    • @1play919
      @1play919 4 года назад

      ㅋㅋㅋ

    • @ayushshukla1438
      @ayushshukla1438 4 года назад +6

      @bronskie1974 it easy being racist ain't it ?

    • @AakashNS
      @AakashNS 4 года назад +22

      @bronskie1974 you're welcome! (I'm the tutor)

    • @sangramjitchakraborty7845
      @sangramjitchakraborty7845 4 года назад +7

      @@AakashNS Thanks a lot for making this tutorial man. Very comprehensive. I love it.

    • @ankitkumarojha8360
      @ankitkumarojha8360 4 года назад +3

      @@AakashNS You are a hero. Thanks for the tutorial!

  • @indranilchakraborty6372
    @indranilchakraborty6372 4 года назад +21

    Wow first time I heared Indian Voice in this channel.

    • @ProdDanny03
      @ProdDanny03 3 месяца назад

      You'd be surprised how amazingly Indians can teach, nothing better than a RUclips tutorial made by an indian

  • @AlessandroPepe
    @AlessandroPepe 3 года назад +6

    Fantastic content, thank you so much for sharing this course for free.
    One small suggestion : I understand it's additional work but it would be great to update the video to match the latest notebook content. For instance, notebook 3 is now at version 32 which is substantially different from the video content and in order to get the matching version you've to revert the notebook back to version 6. Note this is not a complaint, just a constrictive suggestion of improvement. Thank you again for sharing this.

    • @fxtech-art8242
      @fxtech-art8242 3 года назад

      cool found someone who might be trying ML stuff houdini

    • @chandanhariharan4491
      @chandanhariharan4491 2 года назад

      Hi.
      Do u know how to change to the previous version of the notebook. For example how to change to version 6 of notebook 3 as u mentioned in the comment.
      Thank You

  • @sricharan2136
    @sricharan2136 4 года назад +11

    i just started to learn pytorch this evening , phew, just got some good material to learn, thanks :)

  • @pranayp1950
    @pranayp1950 4 года назад +1

    I would recommend the viewers to check out these notebooks in the description. It's pretty good.

  • @DrPrabathJayatissa
    @DrPrabathJayatissa 3 года назад +1

    Perfect course for someone who wants to start learning PyTorch.

  • @mohamedkeita8209
    @mohamedkeita8209 4 года назад +8

    wow ive been waiting for this im 13 learning ai ive already learned the basic of python . but this is my first time watching such a thorough tutorial.

  • @Aditya.K14079
    @Aditya.K14079 Год назад

    One of best vedio for students getting started with Pytorch

  • @manhhai7427
    @manhhai7427 4 года назад +17

    pls generate the eng-sub so that we can learn even more easier! anyway, this course is amazing!

    • @mwont
      @mwont 2 года назад

      Why? His English is perfect.

  • @pratiksaria5830
    @pratiksaria5830 4 года назад +3

    This is the first time i am learning deep learning and it is explained so beautifully by Aakash Sir.Thank You Sir.

  • @rutvikbaxi8420
    @rutvikbaxi8420 4 года назад +5

    Why is this channel so good! Loved the Jovian notebooks!:)

  • @chowadagod
    @chowadagod 4 года назад +12

    Been looking forward to this forever..thanks ..saved

  • @marytajz1814
    @marytajz1814 3 года назад

    WOW! I would say this is the best and most comprehensive tutorial I have ever seen! Thanks

  • @huseyneliyev8415
    @huseyneliyev8415 4 года назад +12

    It is perfect within quarantine time

  • @alayetmanel6986
    @alayetmanel6986 2 года назад

    This is what i need to pass my semester Thank you deeply

  • @rigeleisenheim8860
    @rigeleisenheim8860 4 года назад +4

    I'm confused a blit. Are you calling "test set" as a "validation set"? Because we're not updating hyperparameters according to validation loss. And the figure in 6:48:55 is a train-test error figure.

  • @EmiliaKaida
    @EmiliaKaida 2 года назад +1

    One video to watch before bedtime!

  • @user-sv4zm5jc2g
    @user-sv4zm5jc2g 4 года назад +5

    Timestamps little bit wrong
    1:33:04 - Image Classification with Logistic Regression

  • @ericdoolaar4007
    @ericdoolaar4007 4 года назад +9

    Really well done, Aakash explains the concepts very well, and the code is easy to follow. Unfortunately, the Residual Network (Part6) file from Jovian doesn't match the video - seems the Jovian version doesn't use the FastAI modules. But the explanation of RN's was well done. Highly recommended!

  • @harinath_mishra
    @harinath_mishra 4 года назад +2

    Thanks for providing video on pytorch akash sir

  • @Karthik-yy8ny
    @Karthik-yy8ny 4 года назад +14

    we should support this channel more!

  • @ndiayemodou3474
    @ndiayemodou3474 3 года назад

    I wish I could like this Course 1000000 times it is very helpful
    Thanks a lot

  • @annawilson3824
    @annawilson3824 4 года назад

    About tricky generator loss function 9:04:21

  • @hadjseddikyousfi00
    @hadjseddikyousfi00 4 года назад +3

    Thank you so much. This helped me to transition from TensorFlow. SO well explained!

    • @sairaparla7938
      @sairaparla7938 3 года назад

      Wdym, helped transition from TensorFlow?

  • @AndyChamberlainMusic
    @AndyChamberlainMusic 4 года назад +1

    Whats with the discrepancies between notebook 04 on jovian and what Aakash has in the video? The MnistModel class has a bunch of extra methods on jovian, and it doesn't have a loss_batch function anywhere
    Edit: I needed to look at a previous version. Specifically version 10 it seems

  • @viktormartinovic9446
    @viktormartinovic9446 3 года назад

    Danke!

  • @bigsandip
    @bigsandip 4 года назад +12

    saving for future...

  • @imagenigraphics
    @imagenigraphics 4 года назад

    I just paid $10 dollars for an online python machine learning not knowing there's a deep learning tutorial free on youtube and without ADS! SUBSCRIBED!

  • @prashantgaigavale5973
    @prashantgaigavale5973 4 года назад +1

    Hi Akash, Thanks for the video. I am still watching. One doubt/clarification. at around 01:20:00, regarding SGD. I think in SGD we process one example/observation at a time and then take gradients of that observation. When we process in batches it is called mini/Batch Gradient descent.

    • @ayushjangid
      @ayushjangid 3 года назад

      i was also thinking the same

  • @hidetominitta4149
    @hidetominitta4149 7 месяцев назад

    I highly recommend for people to check the newer, 24 hr course on PyTorch over this one. You need to do your due diligence when it comes to learning deep learning. This course skips over a thorough explanation of concepts such as convolutions, backpropagation, and gradient descent to name a few. I started learning PyTorch with this course but I felt lost because he skipped over the WHY and was just focusing on the HOW.

    • @777priyanshu
      @777priyanshu 7 месяцев назад

      that 24 hours by jason is it better than this one ? can we skip this entirely or should we go through both

  • @sarthakshukla5251
    @sarthakshukla5251 3 года назад +1

    When I try doing from fastai.basic_data import DataBunch on kaggle, it throws the error that the module fastai.basic_data does'nt exist. What should I do?

  • @MatTheBene
    @MatTheBene 4 года назад +2

    What's the difference between this course and the ongoing live pytorch course on Saturdays?

  • @ayuumi7926
    @ayuumi7926 4 года назад +10

    This is an amazing series. Looking forward to another new series on NLP with tensorflow/pytorch that covers RNNs, transformers and more. Thousands of thanks

    • @rajatvarma5256
      @rajatvarma5256 4 года назад

      Yeessss

    • @Raj-gc2rc
      @Raj-gc2rc 2 года назад

      What is the use of building intuition by trying out different hyper parameters, when we have Gaussian process optimization that can learn a function of hyperparameters and estimated loss and accuracy?
      can you please explain the disadvantages of this method?
      This way trial and error approach is replaced by a mathematical model ?

  • @Nissearne12
    @Nissearne12 4 года назад +4

    You are a grate teacher. I got the eureka moment when you show the Linear Regression implementation, when you show the 3D visual graph with one axis output prediction and 2 axis input, with the hyperplane and with the Linear algebra Matrix all thing's fall in to place in my head. Best explained example of training a Linear regression task, Thank's. Best Regards Olle Welin

  • @AK-Star007
    @AK-Star007 4 года назад +6

    8 hrs ago 9:41 hrs long video uploaded, how ppl can praise in this such short time?? this is beyond machine learning.

  • @anant115
    @anant115 2 года назад +1

    Im starting right now. Anyone else with me? to track our progress

  • @dh5159
    @dh5159 4 года назад +24

    Could you also share the assignment solutions? Appreciate!

    • @sandro5535
      @sandro5535 4 года назад +5

      We are supposed to figure it out ourselves but must say I enjoy to get stuck ... Brain just fries.

  • @musamohammed9294
    @musamohammed9294 3 года назад

    Hi Jovian, i followed the same tutorial and got 95% accuracy.

  • @tanvirmahtab5931
    @tanvirmahtab5931 4 года назад +7

    For a first timer like me, things got really complicated from the later half of the Logistic Regression part. :(

  • @muhammadroshan7315
    @muhammadroshan7315 4 года назад +5

    I fell in love with the instructor

  • @heandma
    @heandma 4 года назад +1

    the third notebook is not reflecting the one in the video at some point

  • @AndyChamberlainMusic
    @AndyChamberlainMusic 3 года назад +1

    why does SGD work so poorly on the CNN from part 5a? or is that just me? using Atom I get similar results but with SGD it pretty much just bounces around whatever accuracy it's already at.

  • @kaushu42
    @kaushu42 4 года назад

    In the linear regression example, a graph is shown of loss vs a weight.
    If the loss is quadratic with respect to any weight, then why is the graph not a parabola but such a curve?

  • @ketchupparty9997
    @ketchupparty9997 4 года назад +5

    Can you please do a Complete systematic step by step video on Android Development too.... Please
    And thanks for all the video guys

  • @joekanaan2548
    @joekanaan2548 2 года назад

    At 28:00-29:00 he talked about how tensors are better for the GPU and that both numpy and tensors have the same functionalities. So why should we use numpy if tensors are better?

  • @bhagatsingh5019
    @bhagatsingh5019 2 года назад +1

    Thank you for helping us to learn, sir

  • @PremanshuMitra
    @PremanshuMitra 4 года назад +1

    Fcc keeps going better.n.better and better..

  • @hadirahmanpanah5860
    @hadirahmanpanah5860 2 года назад

    great course, comprehensible and fluent

  • @swayanpravasahoo8735
    @swayanpravasahoo8735 4 года назад +1

    Very excited to see this...Thank you

  • @parastimilsina7645
    @parastimilsina7645 4 года назад +4

    Can you please do an full MEAN stack course?

  • @chandanhariharan4491
    @chandanhariharan4491 2 года назад +1

    The code used in the vid is different from the notebook shared in the comment section.
    Can we get the notebooks of the code used in the vid..
    Thanks

  • @bhanutejanellore8393
    @bhanutejanellore8393 3 года назад +106

    Small suggestion. Instead of following 10 hour video, its more convenient for me to follow a playlist broken up based on small topics.

    • @Praveenstein
      @Praveenstein 3 года назад +18

      some people like to binge watch tech videos.....so it's better this way....and if it's split up...we have to search for each and every bit...

    • @ferp.2078
      @ferp.2078 3 года назад +3

      Follow Akash channel. He does have them split up per lesson.

    • @shivamkhamble
      @shivamkhamble 3 года назад +4

      You can find the playlist here
      ruclips.net/p/PLWKjhJtqVAbm3T2Eq1_KgloC7ogdXxdRa

    • @bhanutejanellore8393
      @bhanutejanellore8393 3 года назад +1

      @@shivamkhamble thank you!

    • @tonis864
      @tonis864 3 года назад +6

      Guys be thankful that there are people like this who share their knowledge

  • @zhengdahe
    @zhengdahe 4 года назад

    Third stamp - 2:34:47

  • @adsk2050
    @adsk2050 2 года назад

    Good course! Thank you for putting on youtube!

  • @achleshwarluthra4608
    @achleshwarluthra4608 4 года назад +1

    I couldn't find the records tab in jovian. Is anyone else facing the same problem?

  • @user-or7ji5hv8y
    @user-or7ji5hv8y 4 года назад +1

    but not only did you move tensors to GPU but also previously saved models with their weights and bias? Do the parameters need to be moved to GPU as well, when making evaluation, as you did in the video?

  • @xindizheng400
    @xindizheng400 4 года назад +10

    For the section image classification, the code shown in the video is quite different from the one posted on jovian. Did you update it? Which one should I follow? Thank you. Btw great video!

  • @rigeleisenheim8860
    @rigeleisenheim8860 4 года назад

    5:24:00 why don't we sum the channels in the beginning?

  • @ahmadabousetta
    @ahmadabousetta 3 года назад

    Thank you.
    After three hours, this video has already taught me alot.

  • @shankargupta5254
    @shankargupta5254 4 года назад +1

    Thank you so much for this tutorial. Excellent tutor.

  • @apurvchimralwar
    @apurvchimralwar 4 года назад +3

    Course Prerequisites??

    • @AakashNS
      @AakashNS 4 года назад

      - Basic Python programming
      - Basic linear algebra (matrix multiplication)
      - Basic knowledge of calculus (differentiation)

  • @hariprasad1168
    @hariprasad1168 3 года назад

    Such a wonderful explanation of basics of ML. Thanks a lot

    • @Raj-gc2rc
      @Raj-gc2rc 2 года назад

      What is the use of building intuition by trying out different hyper parameters, when we have Gaussian process optimization that can learn a function of hyperparameters and estimated loss and accuracy?
      can you please explain the disadvantages of this method?
      This way trial and error approach is replaced by a mathematical model ?

  • @suneetham1394
    @suneetham1394 4 года назад +1

    in description box codes are not opening. Can you please look in to that

  • @chanhtructran8375
    @chanhtructran8375 2 года назад

    This course is very useful, thank you so much for sharing.

  • @thatguyadarsh
    @thatguyadarsh 4 года назад +1

    You guyz are just awesome

  • @CelestialEnlight
    @CelestialEnlight 4 года назад +2

    What are the prerequisites??

  • @vnrbhat
    @vnrbhat 3 года назад

    Great content!! sincere thank you.
    Edit: The explanation on training steps are repetitive. For each section he explains about almost similar training steps. Instead the presenter could've spent more time on model architectures.

  • @pouriakalantari6537
    @pouriakalantari6537 4 года назад +10

    Freecode must give peace nobel prize
    Support from IRAN

    • @XMoresh
      @XMoresh 4 года назад

      خیلی دمشون گرمه . رایگان بی محدودیت

    • @saul200
      @saul200 4 года назад +1

      How's your nuclear weapons project going? do you have enough food to last?

    • @saul200
      @saul200 4 года назад +1

      @Mhammad Umair Racist against who? I just wish Iranians have enough food to last, since the economy is collapsing, the regime is shooting protesters on the streets, and wastes all of their money on a failed nuclear weapons program.

  • @fernandogaribaldi7349
    @fernandogaribaldi7349 4 года назад

    Aakash is a godsend!

  • @பி.அம்ரித
    @பி.அம்ரித 4 года назад

    Wow fantastic. You really a great person.. You thought almost 99% of pytorch.. for free.... I have share this many of my collegues... Thanks a lot

  • @baohoangle3901
    @baohoangle3901 4 года назад +13

    Can you do more in JAVA, thank you!

    • @freecodecamp
      @freecodecamp  4 года назад +6

      Have you seen this Java playlist ruclips.net/p/PLWKjhJtqVAbnRT_hue-3zyiuIYj0OlpyG

    • @w1d3r75
      @w1d3r75 4 года назад +2

      Java definitely need more Spring Boot / Spring MVC :/

  • @hossein_haeri
    @hossein_haeri 2 года назад

    Thanks for the great lecture. Please use a high pass filter for the audio to get rid of annoying puffs.

  • @praveenuggappakodi5344
    @praveenuggappakodi5344 4 года назад

    Thanks for your efforts! This has been a great learning experience!

  • @MirrorNeuron
    @MirrorNeuron 4 года назад

    why w.grad.zero_() is done?

  • @juheehong7445
    @juheehong7445 2 года назад +1

    I tried the second exercise (of the ones shown at 34:41), using the same x, w, b values as originally defined and letting y = torch.tensor([[w, w*x], [w*x+b, b]]). I keep getting "element 0 of tensors does not require grad and does not have a grad_fn" error though; does anyone know how I could fix this?

    • @dereck-2205
      @dereck-2205 2 года назад

      same here

    • @Raj-gc2rc
      @Raj-gc2rc 2 года назад

      What is the use of building intuition by trying out different hyper parameters, when we have Gaussian process optimization that can learn a function of hyperparameters and estimated loss and accuracy?
      can you please explain the disadvantages of this method?
      This way trial and error approach is replaced by a mathematical model ?

  • @driyagon
    @driyagon 4 года назад +2

    I really didn't want to know about all that jovian stuff but eh it's okay if he wants to promote it

  • @San_desh24
    @San_desh24 3 года назад

    why (2,3) matrix transpose? why can't we generate (3,2) matrix earlier for weight?

  • @dikshaadke5209
    @dikshaadke5209 4 года назад

    You are doing an amazing job.

  • @user-or7ji5hv8y
    @user-or7ji5hv8y 4 года назад

    How do we know what needs to go to cuda device? Is it just any matrices that needs cuda for computation?

  • @ffepics7048
    @ffepics7048 3 года назад

    OCEAN OF KNOWLEDGE !! Keep bathing in it

  • @ivanmontes674
    @ivanmontes674 4 года назад +3

    Do you mind if I use your material to translate into Spanish video?

    • @AakashNS
      @AakashNS 4 года назад +6

      Please go ahead Ivan! The knowledge and material is free to use and build upon. I'd really appreciate it if you can link back from your translation to the original notebooks. :)

  • @juheehong7445
    @juheehong7445 2 года назад

    at 34:37 I tried exercise #1 and kept getting "grad can be implicitly created only for scalar outputs" error. Is this supposed to be the case or am I doing something wrong?

  • @Raj-gc2rc
    @Raj-gc2rc 2 года назад

    What is the use of building intuition by trying out different hyper parameters, when we have Gaussian process optimization that can learn a function of hyperparameters and estimated loss and accuracy?
    can you please explain the disadvantages of this method?
    This way trial and error approach is replaced by a mathematical model ?

  • @kennitodevangavani891
    @kennitodevangavani891 4 года назад +4

    Big Shout Out To Haters Who Always Thumb Down (👎) Great RUclips videos they See....
    Great Video by The Way... 👍👌

  • @jamespaz4333
    @jamespaz4333 3 года назад

    What would be the advantage of using pytorch instead of tensorflow or Keras?

  • @mohamadmostafa6696
    @mohamadmostafa6696 3 года назад

    In the logistic regression part the class MnistModel how come we are not calling the forward method and it is enough to put model(images)?

  • @Sam56891
    @Sam56891 4 года назад +1

    can you please make a video on image captioning in PyTorch in Jupiter

  • @jackyhuang6034
    @jackyhuang6034 4 года назад

    Does this cover backpropagation?

  • @beansandpudding
    @beansandpudding 4 года назад +3

    Thank you, this is awesome!!

  • @ykwoozie606
    @ykwoozie606 Год назад

    You're a legend bro!!