How to Generate Music - Intro to Deep Learning #9

Поделиться
HTML-код
  • Опубликовано: 12 янв 2025

Комментарии • 142

  • @jackglendenning8509
    @jackglendenning8509 7 лет назад +11

    Siraj you're videos are getting better and you're starting to explain concepts so that a wider audience can understand! Just started second year of comp-sci degree but been doing ML on the side for 6months, your videos always inspire! I appreciate your work.

    • @SirajRaval
      @SirajRaval  7 лет назад +2

      Thanks Jack! Keep it up!

  • @KapilYadav-90
    @KapilYadav-90 7 лет назад +22

    As i can infer from your videos you are multi talented.
    you sings, you dance, you learn, you read and write, you make youtube and watch all the movies at the same time.
    My question to you is: DO YOU EVEN SLEEP, IF YES HOW MUCH?

    • @SirajRaval
      @SirajRaval  7 лет назад +16

      Thanks Kapil! Lol i do sleep. about 6 hours a night. I JUST LOVE MAKING MACHINE LEARNING VIDEOS I WILL KEEP CRANKING THEM OUT :)

  • @kapilsharma1704
    @kapilsharma1704 6 лет назад

    I don't know ,what all you have learned.but the way you presents is terrific and can beats anyone out there

  • @michaelbowie8315
    @michaelbowie8315 7 лет назад

    Loved the LSTM explanation..
    From 4:38 to 6:38, you could totally make this a separate video... "LSTM 100% Explained in 2 Minutes"... I have been reading a bunch of papers, articles, etc on LSTM, and this is by far the most intuitive explanation (for me at least).
    I wish I had seen this earlier, but it was hidden inside of this video.

  • @chrisoffersen
    @chrisoffersen 7 лет назад +1

    I don't know how you do it Siraj. You make this stuff very accessible. Many thanks, once again.

    • @SirajRaval
      @SirajRaval  7 лет назад +1

      lots of sacrifice np thx

  • @WilliamDye-willdye
    @WilliamDye-willdye 7 лет назад +35

    It doesn't matter much, but I've always heard "MIDI" pronounced as "middy".

    • @SirajRaval
      @SirajRaval  7 лет назад +3

      you're right thanks Will

  • @renanlopes9144
    @renanlopes9144 7 лет назад +34

    Am I the only one who thinks those explanations are way too fast to understand? I know the video is intended to be short, but how about 15-20 min? Good job nevertheless.

    • @timschafer2536
      @timschafer2536 5 лет назад

      Renan Lopes agree

    • @yellowbeard1
      @yellowbeard1 5 лет назад

      He has other videos where he dives into the topic at more length. I agree that if you only look at this video it is inadequate for learning a topic like this but think of this as an introduction and overview, his in depth how to do this video is about an hour long.

  • @llumino1455
    @llumino1455 7 лет назад +6

    SIRAJ CAN YOU PLEASE PUT THE CODE IN THE DESCRIPTION OR ON GITHUB

  • @the_infantraj
    @the_infantraj 7 лет назад

    Siraj your intro was well edited. Keep up the good work!

  • @MichaelRicksAherne
    @MichaelRicksAherne 7 лет назад +46

    "Middy" not "Mid-eye"
    Otherwise flawless. :)

  • @BrianFaure1
    @BrianFaure1 7 лет назад +7

    dude you're channel is like the Rosetta Stone of machine learning

  • @wobanda5986
    @wobanda5986 7 лет назад +12

    I never understood his any video till date😇 (I watched his all video), but some day this will make sense to me that I am sure🙂

  • @phuccoiinkorea3341
    @phuccoiinkorea3341 7 лет назад +3

    love this channel so much

  • @easter.bunny.6
    @easter.bunny.6 7 лет назад

    Siraj YOU ROCK!! nice work!!

    • @SirajRaval
      @SirajRaval  7 лет назад

      thanks Kevin

    • @easter.bunny.6
      @easter.bunny.6 7 лет назад

      but plz maybe do a tut about polyphonic music? or even how to transform your modling in mind to mathmatical modeling?

  • @tastelesstouch
    @tastelesstouch 7 лет назад

    The memes in your episodes are the best!

  • @FastestPodcastClips
    @FastestPodcastClips 6 лет назад +5

    Where do you get data_fn from ???
    NameError: name 'data_fn' is not defined

  • @MatthewHallberg
    @MatthewHallberg 7 лет назад +29

    vishal batchu, wins everytime.

    • @jboss7820
      @jboss7820 7 лет назад

      MatthewHallberg lol

    • @ayushkarnawat6817
      @ayushkarnawat6817 7 лет назад +3

      its because he is probably already a data scientist at some big company and has a lot of experience

    • @chandrashekard.7543
      @chandrashekard.7543 7 лет назад +23

      MatthewHallberg plot twist: Vishal was Siraj all this time. fight club style.

    • @Erilyth
      @Erilyth 7 лет назад +10

      Haha :'D, I'm just a student learning how to use DL :)

    • @MatthewHallberg
      @MatthewHallberg 7 лет назад +1

      hahaha that was too good.

  • @NightmareTV666
    @NightmareTV666 7 лет назад +1

    Are the results dramatically better than RBM with a GIBBS sampler? And is the CNN parametric approach the best, but potentially intractable in higher dimensions?

  • @ConTejasMusic
    @ConTejasMusic 7 лет назад

    that LSTM beat was magical!

  • @rafaellazo1725
    @rafaellazo1725 5 лет назад

    love your videos Siraj

  • @Towzeur
    @Towzeur 7 лет назад

    i have trouble to install preprocess library
    Traceback (most recent call last):
    File "setup.py", line 28, in
    import preprocess
    File "lib\preprocess.py", line 264
    except Exception, ex:
    ^
    SyntaxError: invalid syntax

  • @HelloThere-xs8ss
    @HelloThere-xs8ss 7 лет назад +1

    Hey, I'm from the future. We need more veggie gardens. amazing how you do it

  • @RonoTron01
    @RonoTron01 4 года назад

    If I want to feed like a series of midi files into this neural network, how to do that? I have maybe a few hundred midi files of the style that I like, is this possible to use as a source?

  • @ConTejasMusic
    @ConTejasMusic 7 лет назад

    Anyone notice the background music at the start is Moonlight Sonata 1st movement, but a hip hop version?

  • @abhiksingla7274
    @abhiksingla7274 7 лет назад +2

    Siraj, you are doing a great work! Can you do a video on Image Captioning using Deep Learning?

    • @SirajRaval
      @SirajRaval  7 лет назад +1

      Thanks Abhik! I have one called build an AI writer, more soon

  • @md.shahidulislam3178
    @md.shahidulislam3178 7 лет назад +1

    Hey Man why i love your video so much ;) !!
    >>> Nice Explanation Every time

  • @samuelvarghese6881
    @samuelvarghese6881 7 лет назад +1

    +Siraj Ravel Nicely explained about lstm man keep it up. Btw you know when you say batch size is 128 in this instance, how do you do that with your own data from like a excel sheet.

  • @owena7434
    @owena7434 7 лет назад

    Great vid! VERY new to this stuff. so just to clarify, hope this isn't horribly wrong, the reason we need to put in an LSTM is to keep the program learning from the jazz, and not accidentally learning its own randomness?

    • @SirajRaval
      @SirajRaval  7 лет назад +1

      Thanks Owen, LSTM helps it remember ALL the jazz it trained on, not just the most recent jazz (long short term memory)

    • @owena7434
      @owena7434 7 лет назад

      Thanks Siraj! Cool stuff! I think it would be cool to explore how a machine might navigate a more complicated classical work with key changes with LSTM so the machine-generated piece has overall structure. Or even reverse engineer different composer's harmonic structures. But I'm still on the basics lol!

  • @roguenoir
    @roguenoir 7 лет назад

    I'm curious if it would be legal to use music you generate this way as your own.. especially if you train the deep learning net on a commercial artist's music then use that to generate new music which you use for, say, a movie or game you make.

  • @modelworkzseo
    @modelworkzseo 7 лет назад +1

    Lol, it's pronounced "middy". Great video man, keep em coming!

  • @sukumarhonkote9936
    @sukumarhonkote9936 7 лет назад

    can you provide the link for the preprocess library code? I am getting an import error

  • @HikikomoriDev
    @HikikomoriDev 7 лет назад

    How long did it take for the computer to finalize the final music piece ?

  • @klaudialustig3259
    @klaudialustig3259 7 лет назад +1

    I used to think that Markov chains are complicated stuff. I learned that it's basically just a state machine.

  • @larryteslaspacexboringlawr739
    @larryteslaspacexboringlawr739 7 лет назад

    thank you for music deep learning video

  • @rgrimoldi
    @rgrimoldi 7 лет назад

    We should have gone for Hendrix instead! I definitely have to build that.

  • @tylerangert9121
    @tylerangert9121 7 лет назад

    do you have scripts for all of your videos or are you just explaining off the top of your head? I think a big thing you can do to help make our learning experiences better is providing us with the transcripts of the videos. for me at least, having text to reference and look back to is much easier than just going back and listening to audio again (this is why i usually watch TV shows with closed captioning).

    • @SirajRaval
      @SirajRaval  7 лет назад

      scripts. youtube has automatic captioning

  • @aidangomez4726
    @aidangomez4726 7 лет назад

    yo man your channel is blowing up

  • @bomb3r422
    @bomb3r422 7 лет назад +1

    i started programming in python 5 months ago . i have a good idea of oop and algorithms . should i start with machine learning now or is it too early?

    • @y.z.6517
      @y.z.6517 6 лет назад

      Don't touch ML at the moment, or you will hate it. Find a project that solves your problem, and work on it. Something involves parsing texts and doing maths you can understand. Then make codes reuseable and easy to maintain. At that moment, you will have experience in researching, debugging, and maintaining long and complicated codes along with someone else's libraries.

  • @lesmizzle
    @lesmizzle 6 лет назад

    What was the training data used? I missed it.

  • @prateekthakur4060
    @prateekthakur4060 6 лет назад

    I don't see the code Siraj explained in the GitHub link. Can somebody help here:;)

  • @Frankthegravelrider
    @Frankthegravelrider 7 лет назад +1

    Siraj, your T-Shirt is pretty good - your videos are alright too ;)

    • @SirajRaval
      @SirajRaval  7 лет назад

      Fr Ya! Good to see you. Thanks!

  • @debarokz
    @debarokz 7 лет назад

    Nice video.. I am planning to buy a rig for stuffs related to deep learning ..what's your system config that you use for deep learning??? will MacBook pro suffice??

    • @SirajRaval
      @SirajRaval  7 лет назад +1

      Macbook pro works also I prefer the cloud to a dedicated rig (AWS)

    • @debarokz
      @debarokz 7 лет назад

      Siraj Raval thanks bud

  • @rhezabudiono2385
    @rhezabudiono2385 7 лет назад

    Hey Siraj, as an undergrad should I prepare differently to be a machine learning researcher vs ML engineer?
    I was thinking that to be to be a researcher I should take more stats, math, physics whereas to be an engineer I should take more programming-heavy CS classes

  • @shivanasr8127
    @shivanasr8127 5 лет назад

    i want extract pichbend from midi file can you help me?

  • @NoName-iz8td
    @NoName-iz8td 5 лет назад

    can you explain please the input data, cuz for me it is difficult to transform from midi file to vector numbers :p

  • @timehrensberger6479
    @timehrensberger6479 7 лет назад

    I can't figure out how to generate based on other midi files than the standard metheny piece

  • @RicardoMV95
    @RicardoMV95 6 лет назад

    Pat Metheny is a guitarist not a pianist. I’m not sure if you chose to make piano pieces based on his music or if you didn’t realize that he is a guitarist. Regardless, cool video!

  • @eumieumi8766
    @eumieumi8766 7 лет назад +1

    hmm the output kinda sucks when i train it on own midis ..sure would be nice if it would train multiple times

  • @Mosfet510
    @Mosfet510 7 лет назад +1

    I didn't do it! It was my algorithmic counterpart, I swear!! lol Great video.

  • @dmitrykarpovich7579
    @dmitrykarpovich7579 6 лет назад +1

    mid E! Love your videos man!

  • @calvin5371
    @calvin5371 5 лет назад

    Honestly, I had to watch the video twice ... cause the first time I was just focussing on the t-shirt

  • @yousof_e
    @yousof_e 7 лет назад +1

    Nice shirt :)
    can you also provide a video on speech recognition?

    • @SirajRaval
      @SirajRaval  7 лет назад +1

      thanks! i have one 5 videos back

    • @yousof_e
      @yousof_e 7 лет назад

      Do you mean "How to Do Sentiment Analysis" ?
      What I meant is that the input of the Algorithm is the sound and the output is the pronounced words.

  • @sir_aken9706
    @sir_aken9706 7 лет назад

    I have Pycharm and I'm not sure I can replicate what you did in it.

  • @WilsonMar1
    @WilsonMar1 7 лет назад

    [2:32] Coding begins

  • @travisgoodwin6802
    @travisgoodwin6802 6 лет назад

    Ok, let's hear it already, the music that is. Something inspired, not sounding derivative.

  • @diegoantoniorosariopalomin4977
    @diegoantoniorosariopalomin4977 7 лет назад

    sinesthesia as an artificial nn (natural sinestesia is also on neural networks ) , in other works real life theme music

    • @SirajRaval
      @SirajRaval  7 лет назад

      good insight! i have sinesthesia

    • @diegoantoniorosariopalomin4977
      @diegoantoniorosariopalomin4977 7 лет назад

      Siraj Raval you do ?! .... oh that explains why you break your videos with musical numbers that explain the topic

  • @aseemKurhekar
    @aseemKurhekar 6 лет назад

    In one of his videos siraj talked about how neural networks can make music from images. If some one could point me to its source it would be great 😊

  • @EduardoRenz
    @EduardoRenz 7 лет назад

    Cool
    Can you make a ML that learns to make music from a real music audio? Analysing a whole album of a band?

    • @RitobanRoyChowdhury
      @RitobanRoyChowdhury 7 лет назад +1

      You would need it midi format. Analyzing mp3s is a much harder problem (because they store audio data rather than notes)

    • @danieltv123
      @danieltv123 7 лет назад

      there are some people already doing it from real audio, search on youtube

  • @alexhormann8931
    @alexhormann8931 7 лет назад

    What are you doing with your hands?

  • @vigneshsuresh3671
    @vigneshsuresh3671 7 лет назад

    Great series mate! Can you do a video on data points extraction from text with ML .. Regex sucks :(

  • @Wolsacademy
    @Wolsacademy 7 лет назад

    This is Great!

  • @sumantkanala
    @sumantkanala 7 лет назад

    Hmm. this challenge is a tad bit harder to understand than previous ones!

    • @SirajRaval
      @SirajRaval  7 лет назад +1

      indeed but give it a try! You just might win

  • @shaikrasool1316
    @shaikrasool1316 7 лет назад

    Is it better choice to learn machine learning ai,,, in present day

  • @KETANRAMTEKE
    @KETANRAMTEKE 7 лет назад

    Go back to vdo. It's more amazing than comment section :D

  • @MultiSciGeek
    @MultiSciGeek 7 лет назад +1

    This is really confusing. Subscribed

  • @mallikarjun480
    @mallikarjun480 7 лет назад

    What's the best way to start Artificial Intelligence.

  • @easter.bunny.6
    @easter.bunny.6 7 лет назад

    next time maybe polyphonic music?

  • @dominiksabat
    @dominiksabat 6 лет назад

    Briliantly explained, you should work at the university.

  • @aminejadid2702
    @aminejadid2702 7 лет назад

    awesome !

  • @bjyr
    @bjyr 7 лет назад

    it's lit!

  • @raj-cp5nu
    @raj-cp5nu 7 лет назад

    2:20 I press play, so so true haha

  • @sukumarh3646
    @sukumarh3646 7 лет назад +1

    I liked your video but why didn't you cite the original code in the videos or at least in the description? The original code is available here github.com/jisungk/deepjazz

    • @SirajRaval
      @SirajRaval  7 лет назад +1

      just added it thanks

    • @aarondinesh3657
      @aarondinesh3657 7 лет назад

      When I try to run the code this error pops up:
      Traceback (most recent call last):
      File "generator.py", line 21, in
      from music21 import *
      ImportError: No module named music21

  • @sleep4103
    @sleep4103 7 лет назад

    Who else had a Frank Jev Cee association :'D

  • @OrthoGunner
    @OrthoGunner 7 лет назад

    you should go work at OpenAI!

  • @ili626
    @ili626 7 лет назад

    Pat Metheny (ma - thee - nee)

  • @nevokrien95
    @nevokrien95 6 лет назад

    Lstm usualy have atention gates

  • @anthonyparks505
    @anthonyparks505 7 лет назад

    There's a lot of good info in this video, but you move so incredibly quickly that it is impossible to follow. The pacing is frenetic...

  • @432Simthology
    @432Simthology 3 года назад

    CODE SHMODE WHEN ARE YOU NERDS GONNA MAKE A GUI FOR CRYING OUT LOUD?

  • @lxxanderfans267
    @lxxanderfans267 6 лет назад

    this is so interesting lol

  • @berrym8901
    @berrym8901 7 лет назад

    The music generated by RNN is good... Well, anyway, it's better than Kenny G!
    Poor Kenny G~ :p

  • @jiexun9679
    @jiexun9679 7 лет назад

    Hi Siraj, I attempted the challenge but results are not very good for now. Here's my code anyway: github.com/jiexunsee/rudimentary-ai-composer
    Thank you for the video!

    • @SirajRaval
      @SirajRaval  7 лет назад

      great job Jie for going for it

  • @Acc22-mr1qk
    @Acc22-mr1qk Год назад

    I didnt understand anything

  • @kracejiciAlchymista
    @kracejiciAlchymista 5 лет назад

    Noooo, Kenny G`s goood man.

  • @neelpendharkar4793
    @neelpendharkar4793 7 лет назад

    You need help. Thanks tho

  • @gawni1612
    @gawni1612 7 лет назад

    Lost me at mid eye

  • @ukaszOgan01
    @ukaszOgan01 6 лет назад

    Can you speak more slow please? :)

  • @derrik-bosse
    @derrik-bosse 7 лет назад

    Love all your videos but you should talk slower, it gets a little overwhelming for people who aren't so advanced