Automatic Neural Network Hyperparameter Tuning for TensorFlow Models using Keras Tuner in Python

แชร์
ฝัง
  • เผยแพร่เมื่อ 1 ก.พ. 2025

ความคิดเห็น • 55

  • @GregHogg
    @GregHogg  ปีที่แล้ว

    Take my courses at mlnow.ai/!

  • @lukasshipley9251
    @lukasshipley9251 หลายเดือนก่อน

    I like how you explain what each portion of the code means and where it comes from as you write it. It makes understanding what everything is doing so much better!

  • @proterotype
    @proterotype 2 ปีที่แล้ว +4

    I’m using this for a CNN. Thanks for the clear presentation and walk through. You’re the man

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      Sounds great. No problem! Thanks!

    • @temmmbebkd2922
      @temmmbebkd2922 8 หลายเดือนก่อน

      Did you get good results

  • @shrutihegde763
    @shrutihegde763 7 หลายเดือนก่อน +1

    thank you for this extremely useful video!! it cleared up all my confusions regarding hyperparameter tuning!!

  • @drjabirrahman
    @drjabirrahman 2 ปีที่แล้ว +2

    Thank you Greg. That's very helpful.

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      Great to hear!

  • @ithaca2076
    @ithaca2076 2 ปีที่แล้ว +1

    actually incredibly useful thank you so much

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      Oh I'm really glad to hear that! :)

  • @Xnshau
    @Xnshau 2 ปีที่แล้ว

    Brilliant thanks Greg👍

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      You're very welcome!

  • @hawaiisunkissselftanner4890
    @hawaiisunkissselftanner4890 ปีที่แล้ว

    Amazing Viedo! Thank you so much! Saved my ass of my assignment 😂

    • @GregHogg
      @GregHogg  ปีที่แล้ว

      So glad to hear it :)

  • @hardikmakwana4266
    @hardikmakwana4266 5 หลายเดือนก่อน

    Great session

  • @shantanukulkarni2413
    @shantanukulkarni2413 2 ปีที่แล้ว +1

    Excellent topic

  • @eranfeit
    @eranfeit 2 ปีที่แล้ว +3

    Very nice.
    How can I extract the best parameters , for each layer. For example : how many filters in each cnn layer. What is chosen activation function , what is the size of the filters ? Etc.
    Basicly get the structure of the model.
    Thanks
    Eran

    • @mohammeddanishreza4902
      @mohammeddanishreza4902 2 ปีที่แล้ว +1

      Hello. Did you get the answer ? If yes, please share the answer. Thanks :)

    • @eranfeit
      @eranfeit 2 ปีที่แล้ว

      @@mohammeddanishreza4902 No. I did not. However , I figured it out by myself. I uploaded some videos about it.

    • @mohammeddanishreza4902
      @mohammeddanishreza4902 2 ปีที่แล้ว +1

      @@eranfeit Please share the link of the video. It would be helpful. Thank you : )

    • @eranfeit
      @eranfeit 2 ปีที่แล้ว

      @@mohammeddanishreza4902 please this playlist :
      th-cam.com/play/PLdkryDe59y4ZO3WjBjcEUP1drjPcVvRBA.html
      The third video is dealing with this subject.

  • @sergiochavezlazo5362
    @sergiochavezlazo5362 ปีที่แล้ว

    Great video! Thank u!

    • @GregHogg
      @GregHogg  ปีที่แล้ว

      You're very welcome :)

  • @commonsense1019
    @commonsense1019 2 ปีที่แล้ว

    your coding tutorial are way better than that review content

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      Thanks for the feedback!

  • @ponsaravanan
    @ponsaravanan 6 หลายเดือนก่อน

    Great video

  • @omario.tntech
    @omario.tntech 2 ปีที่แล้ว

    this is 🔥

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      Great to hear!

  • @LukasSkywalker_
    @LukasSkywalker_ ปีที่แล้ว

    Thanks a lot!

    • @GregHogg
      @GregHogg  ปีที่แล้ว

      You're welcome!

  • @AbuZaynab1
    @AbuZaynab1 ปีที่แล้ว

    This was a fantastic tutorial. I am curious to know if I could do the same with signal data using a 1D CNN Model? If so, how would the input shape differ in that scenario since I am not working with photo data?

    • @GregHogg
      @GregHogg  ปีที่แล้ว

      Yes you could use something like this for 1d CNN's

  • @gamuchiraindawana2827
    @gamuchiraindawana2827 ปีที่แล้ว

    Hey Greg, I'm applying your techniques to model time series data and I'd like to ask when we call tuner.search() and pass it the training data and validation data, does it randomly shuffle the data? You probably already understand why I'm asking thank you.
    And if it does, how can we preserve the time series ordering?

  • @juanete69
    @juanete69 ปีที่แล้ว

    Hello.
    What if I want to optimize the batch size, the number of epochs or use callbacks such as ReduceLROnPlateau or EarlyStopping? Can I use keras tuner for that? Or is it already included in the search procedure?

  • @bencekato4053
    @bencekato4053 ปีที่แล้ว

    If I want to add k-fold cross validation during hyperparameter tuning, do I add the tuner.search() (i.e. simply replacing model.fit() command with this) inside my loop for k-fold ?
    Thanks for the great vid!

  • @Smeoneonyt
    @Smeoneonyt 10 หลายเดือนก่อน

    Thank you!!

  • @royranggarofiulazmi9708
    @royranggarofiulazmi9708 ปีที่แล้ว

    Hi Greg!
    thanks for create this tutorial, it help me so much.
    but I'm currious about the possibility of implementing the keras-tuner, after i augmenting the number of image samples, by ImageDataGenerator. is it possible??

    • @GregHogg
      @GregHogg  ปีที่แล้ว

      It should be I think?

  • @thefruitsofzei924
    @thefruitsofzei924 4 หลายเดือนก่อน

    Hi I am having Problems with the Epochs and Number of test run. For e.g. when i want to have it adjust the dropout from 0 to 0.5 steps 0.1 it runs the search for each options with 2 epochs and then stops. So basically nothing is really tested it and it stops prematurely.
    max_epochs could be set to 100 or even 1000000000 it does nothing. Settings the epoch in search does literally nothing i could even set it to -1 or even a string of gibberish.
    But when i run a search where i configured a lot in Hyperband(including cnn stride, filter sz, kernel, etc.) it works fine and does what is should.
    The more i try the more im confused.....

  • @adaravivianagomezcruz8380
    @adaravivianagomezcruz8380 ปีที่แล้ว

    Hi Greg!
    I hope you are doing well, wanted to ask you if there is a way to use keras tunner with an stacked model, which comes from two models.
    And if there is which is the best way to do it

  • @asgardro4434
    @asgardro4434 2 ปีที่แล้ว

    Hey Greg, do you prefer more tensorflow or pytorch and why? Sorry for bothering you

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      I haven't learned pytorch.

  • @leiladarabi6438
    @leiladarabi6438 2 ปีที่แล้ว

    Hi, I want to know how can I get the name of AF and other info of the best model. for example for the best mode, which AF used

  • @alberro96
    @alberro96 2 ปีที่แล้ว

    How could I implement this with CNN? I'm working with my own dataset adn it seems like the keras tuners don't like the tf.data.Datasets yet. They're still expecting (x_train, y_train), (x_test, y_test). Is my thinking correct there? Essentially I'm loading my data using tf.keras.preprocessing.image_dataset_from_directory and would like to feed this into the tune.
    How could I split my own data in (x_train, y_train), (x_test, y_test)?

  • @hassanayaz6242
    @hassanayaz6242 หลายเดือนก่อน

    is it possible i use this menthod lstm and xlstm

  • @robottalks7312
    @robottalks7312 2 ปีที่แล้ว

    Is there a way to get best number of layers also?

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว +1

      Yeah I didn't do it but I'm guessing you could mix the functional API with one of those random integers as the number of iterations of a loop. I don't think this is often done in practice though

  • @astronemir
    @astronemir 2 ปีที่แล้ว

    Would have been nice to see model.summary()

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      You can run the colab code and do that if you'd like :)

  • @juanete69
    @juanete69 11 หลายเดือนก่อน

    max_epochs is 10 but epochs is 50. Isn't it contradictory?

  • @muhammadhafizi5953
    @muhammadhafizi5953 2 ปีที่แล้ว

    Hi may i know how to contact you?

    • @GregHogg
      @GregHogg  2 ปีที่แล้ว

      Check the about section of my TH-cam channel

  • @cagataytekin6372
    @cagataytekin6372 6 หลายเดือนก่อน

    imparator