How To Train Deep Learning Models In Google Colab- Must For Everyone

Поделиться
HTML-код
  • Опубликовано: 24 янв 2025

Комментарии • 360

  • @maryzakiandourrugrats4671
    @maryzakiandourrugrats4671 Год назад +6

    This is an amazing video, as a beginner you answered so many questions that popped up as I was following along, as if you were reading my mind, excellent brother

  • @sandhyasharmil
    @sandhyasharmil Месяц назад +3

    I had struggled too much with loading data from MyDrive to Collab. Your video helped. Thank you so much. And God Bless you. :)

  • @JordanMetroidManiac
    @JordanMetroidManiac 3 года назад +9

    Google Colab is such a helpful resource. Thank you for explaining this!

  • @zulfiqarali-zq1rg
    @zulfiqarali-zq1rg 4 года назад +4

    Exellent sir. you are one of my mentor in Deep learning CV.Thanku sir

  • @CreatingUtopia
    @CreatingUtopia 4 года назад +25

    Tech websites: Let's compare gpu on benchmark scores
    Krish: Let's compare prices

  • @ashutoshdixit2806
    @ashutoshdixit2806 3 года назад +1

    great work ....
    this is my first time on your channel

  • @tasveerahmad5002
    @tasveerahmad5002 4 года назад +2

    Thanks dear, A very nice and helpful video. I learned a lot and enjoyed. Stay Blessed!

  • @apunbhagwan4473
    @apunbhagwan4473 3 года назад +3

    He did gave UPSC in 2019 and now he is a youtuber, Sandeep bhaiya

  • @rkag5811
    @rkag5811 3 года назад +1

    I got a clear idea. Good explanation sir👏

  • @akansha_bhatt28
    @akansha_bhatt28 4 года назад +12

    Sir,
    After training model on Google Colab, please make video on how to test on real time

    • @jayhingrajiya3703
      @jayhingrajiya3703 4 года назад +1

      To test on real time.. just click the picture of the leaf of tomato and use the model to predict whether the leaf is healthy or not.... google it

    • @Thearvindkumar
      @Thearvindkumar 4 года назад

      Great question .

    • @dhakshajey7032
      @dhakshajey7032 4 года назад +1

      @@jayhingrajiya3703 Can you please explain sir. what should be done after training the model.

    • @aisyahrobi3623
      @aisyahrobi3623 3 года назад

      @@jayhingrajiya3703 hello...can you explain more how to test in real-time..thank you so much..

  • @sheikhobama3759
    @sheikhobama3759 Год назад +1

    OMG I absolutely loved your video Sir, I Have just watched it halfway and I felt I had to comment. The way you explain things are just perfect. I wish if only we students had teachers like you. I've already subscribed to your channel and can't wait to watch more of your content. Your knowledge is invaluable, and I appreciate you taking the time to share it with us.
    Thanks again for creating such an awesome content! 🥰
    These videos really do help us beginners in a great way!!

  • @ALLFITdudes
    @ALLFITdudes 2 года назад +3

    Thank you so much sir for this wonderfull video..❤❤

  • @kalpanab9869
    @kalpanab9869 4 года назад +7

    Error in model fit
    InvalidArgumentError Traceback (most recent call last)
    in ()
    7 epochs=10,
    8 steps_per_epoch=len(training_set),
    ----> 9 validation_steps=len(test_set)
    10 )
    InvalidArgumentError: Reduction axis -1 is empty in shape [16,0]
    Any idea what can be the error. I have followed the same steps

  • @chinmayshinde6478
    @chinmayshinde6478 4 года назад +9

    Good video. Can u show the following:
    1) importing tensorflow/pytorch/scikitlearn
    2) import specific version of tensorflow/ pytorch/ detectron
    3) advise about loading personalised dataset - whether it should be zip upload or extracted image files.

    • @vineethv3050
      @vineethv3050 3 года назад +1

      %tensorflow_version
      % tensorflow_version 2.x
      import tensorflow as tf
      print(tf.__version__)

  • @mrbroker3777
    @mrbroker3777 4 года назад +9

    Can we convert our image classification code in colab into tensorflow lite inorder to run it in android studio

  • @dikshabhati1441
    @dikshabhati1441 4 года назад +2

    really amazing video sir....i have learnt a lot of things thorugh watching your videos....you are just amazing.....sir please one video on how to deploy model by writing code on google colab

  • @anirbansarkar6306
    @anirbansarkar6306 3 года назад +3

    Thanks for this wonderful tutorial Krish.
    Also please do come up with the architecture video they will be really helpful

  • @Abdnimit00
    @Abdnimit00 3 года назад +9

    After completing the epoch how can i call an image and test it? what is the code can anyone help?

    • @richarashmi72
      @richarashmi72 3 года назад

      Same here. I too want to do that. I have trained my model, now how to call the trained model while testing my data.

    • @rayane4975
      @rayane4975 3 года назад +2

      model.evaluate(test_images, test_labels, batch_size=batch_size, verbose=2)

  • @kMuhammadUzair
    @kMuhammadUzair Месяц назад +1

    krish ? there is no test data folder what path did you give in the data_generator for the test_data

  • @ashikroy4618
    @ashikroy4618 2 года назад +8

    Hi Krish,
    Thank you for your tutorials.
    I am a beginner, and I am wandering why didn't you use validation and test, both of the datasets to evaluate the model?
    thanks

  • @suryav3959
    @suryav3959 4 года назад +5

    Please make a video on the architectures of cnn transfer learning models.

  • @princeprajwal
    @princeprajwal 3 года назад +1

    u been always helpful krish thank you so much

  • @ajayraju999
    @ajayraju999 4 года назад +12

    Sir can you please can you make a video on image segmentation..🙏

  • @kenyosh8957
    @kenyosh8957 Год назад +1

    Thank you SOOO much for making this video

  • @rshndb99
    @rshndb99 4 года назад +5

    This video is not for everyone it is for expert
    New learners can't understand

    • @eduxlearntodayapplytomorro6616
      @eduxlearntodayapplytomorro6616 2 месяца назад

      man it's enough for a free video, if you don't know much then learn. Krish can't just explain every single step

  • @priyeshgautam668
    @priyeshgautam668 4 года назад +2

    can we fine tune the last dense layers using grid search cv or keras tuner

  • @CogniCraftedMinds
    @CogniCraftedMinds 2 года назад +1

    Thank you, I've learned from your tutorials.

  • @nriezedichisom1676
    @nriezedichisom1676 Год назад

    Perfect as usual. Thank you

  • @hemanthmohan4334
    @hemanthmohan4334 2 года назад +1

    Dude, on the galaxy watch 4 is there a way to turn off the indicators like the airplane icon and the phone icon on the main screen? cause its annoying on analog watch faces that these icons overlay it....can't find any toggle in settings? reply plz..anyone

  • @bhaumiks.6543
    @bhaumiks.6543 Год назад

    Amazing videos sir. Thanks for videos.

  • @sunidhiashtekar9175
    @sunidhiashtekar9175 4 года назад +2

    sir can you please tell me your video in which you have explained all this code

  • @amanuelhirkooyoutubepage7743
    @amanuelhirkooyoutubepage7743 3 года назад +2

    THANKS ALOT! let u teach as well on text classification specially on multi label problem using CNN

  • @akashdebnath3631
    @akashdebnath3631 4 года назад +4

    sir, please tell me how did you know how many hidden layer and neuron will give best result in MLP-ANN?

    • @jungleking9
      @jungleking9 4 года назад

      Neuron will be average of your dependent variables and independent variables.. its the best practice.. and for hidden layers you can take any amount.. increase them until your accuracy increases

  • @muskaanfathima8183
    @muskaanfathima8183 Год назад +1

    Thank you so much sir u saved my final year project

    • @Kaifrockstar-od1nj
      @Kaifrockstar-od1nj 3 дня назад

      Hello,can you help me out im giving the code because currently iam doing my final yr project

    • @muskaanfathima8183
      @muskaanfathima8183 23 часа назад

      @@Kaifrockstar-od1nj its long back i dont remember now

  • @SGandhi
    @SGandhi 3 года назад +1

    Showing epoch 1/10 but then utbis showing failed to get convolution algorithm , because of cuDNN failed so try looking to see if a warning log message is printed above this error is coming how to solve sir

  • @poshamchandrika1340
    @poshamchandrika1340 4 года назад +2

    during to fit the model i am getting value error
    ValueError: You are passing a target array of shape (16, 1) while using as loss `categorical_crossentropy`. `categorical_crossentropy` expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via:
    ```
    from keras.utils import to_categorical
    y_binary = to_categorical(y_int)
    ```
    Alternatively, you can use the loss function `sparse_categorical_crossentropy` instead, which does expect integer targets.

    • @umanggoel5385
      @umanggoel5385 11 месяцев назад +1

      you havent setup the number of classes, it should be greater than or equal to 2

  • @Anilpawar_11
    @Anilpawar_11 4 месяца назад +1

    Please anyone explain to me how to get Testing and Training accuracy in Colab 🙏🙏(and is in data set already training and testing folders included or do we have to create)

  • @Pran254
    @Pran254 3 года назад +3

    After training the model in google colab , how to run or execute the project???

  • @carijay2400
    @carijay2400 4 года назад +2

    thank you very much sir for this tutorial. seems im getting the right direction for ML lecture for clinical dx. im a newbie who want a career shift.

  • @qchirac
    @qchirac 3 года назад

    Another questions, should we save the training data in google drive and mount or copy them to colab? google drive is a cloud drive away from colab I guess. If save in google drive, the training would be slower or same same?

  • @NilBorun
    @NilBorun 4 года назад +1

    Do you have video on Inception3 or will you make it?

  • @Abdnimit00
    @Abdnimit00 3 года назад +2

    Can anyone provide me code for PREDICTING IMAGE of these diseases in google colab please! 🙏 🙏 🙏

  • @fabricesimo6163
    @fabricesimo6163 3 года назад +7

    Hi Sir! Following your steps, I bumped into this error
    UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
    [[node model/conv2d_94/Conv2D (defined at :7) ]] [Op:__inference_train_function_17502]
    Function call stack:
    train_function
    Could you please help me to solve it?

    • @aditi1666
      @aditi1666 2 года назад

      Hello Sir, Did u get the solution?

  • @uswamubeen9522
    @uswamubeen9522 4 года назад +1

    Assalam o Alaikum sir i want to know which one is the latest architecure for multi class image classification ????

  • @stitou2010
    @stitou2010 9 месяцев назад

    Usefull video. Thank you Sir.

  • @melusimj3800
    @melusimj3800 Год назад +1

    @Krish Naik, and everyone.. Can someone please assist me, I have a problem when it comes to fitting my model during training... How can I fix the "Invalid-Argument-Error? I have followed all the steps from this video, but I still get the same error. Any suggestion, on how to solve the error?

  • @anupurbadas8609
    @anupurbadas8609 3 года назад +1

    i got multiple errors after #fit the model portion. it says r is not defined than it says Model is n ot defined

  • @MAhmadian
    @MAhmadian Год назад

    Thank you for your great work, I see the input image size in the Kaggle is 256x256 but you specified 224x224 is it a typo or you have done some scaling. My second question is in the training dataset you have 10 classes but your model's output has 15 classes which is not right, please elaborate.Thanks again for your awesome work.

  • @spiritualjourney5566
    @spiritualjourney5566 2 года назад

    How to predict a test image other than that from dataset?

  • @SurajKumar-bw9oi
    @SurajKumar-bw9oi 4 года назад +1

    The video was a lot of fun. Explaining and searching about GPUs and saying P4 instead T4 :)

  • @knowledgehub9106
    @knowledgehub9106 3 года назад

    Sir can you helpp.me i have image dataset in csv file and i have an image in this dataset so how can i fetch the image in loaded dataset??

  • @Sazia_Cooking_Creativity
    @Sazia_Cooking_Creativity 3 года назад +2

    Can you upload a video on the Facial recognition project?

  • @ginawhalevg
    @ginawhalevg Год назад

    your video is really helpful thanks a lot! but i can't find the colab notebook address of the examlpe you use in this video. can you please upload again?

  • @sameerdubey1990
    @sameerdubey1990 2 года назад

    Hi krishna,
    i have droplet videos/images at 5 viscosity ratio each at 8 speeds of fluid .can we train deep network to find the speed of fluid for any droplet image.I need not categorize the images but it must be able to tell speeds other than given 8 speeds.plz guide

  • @jagyansenipanda12panda37
    @jagyansenipanda12panda37 2 года назад

    Sir can you show a small example of the CNN model for image interpolation using Google Colab?

  • @Pran254
    @Pran254 3 года назад +1

    After training the model what about the next process i.e runing or executing?? Please help or share videos

  • @madhukanadeeshani6982
    @madhukanadeeshani6982 3 года назад

    Thank you very much!!! Tutorial is great

  • @qchirac
    @qchirac 3 года назад

    is there a way to rename 'My Drive' to something like 'my_drive' in google drive? Sometimes, the space cause trouble. I know we could rename sub folders in google drive. However I didn't find the way to rename the root 'My Drive'.

  • @2SourceFort
    @2SourceFort 3 года назад

    Thank you so much 🥰 it's such a wonderful help to me

  • @lydiadarla7543
    @lydiadarla7543 3 года назад

    Thank you so so much sir!

  • @PoojaGupta-ry3oj
    @PoojaGupta-ry3oj 4 года назад +2

    After training now how to predict class for new image?

    • @Alexandre-vn6ii
      @Alexandre-vn6ii 4 года назад

      I want to know that too! Probably he needs to save the trained file on json or h5

  • @MoganaVadhnaSuntraKumar
    @MoganaVadhnaSuntraKumar 2 года назад

    Thank you so much😃😃

  • @mahinqureshi5809
    @mahinqureshi5809 4 года назад

    i m totally new on colab .. i have one question ... what can i use in colab instead of OS module?????? i need some operations like, os.isfile .. bt i donno how . and also how can i access the folders in gDrive.. what module to use ??????

  • @qchirac
    @qchirac 3 года назад

    a third question is how to keep it training backstage. the training might take much time, the mount and even the colab runtime session might disconnected before training is finished. how to resolve this concern..

  • @nayanagrawal8157
    @nayanagrawal8157 2 месяца назад

    Hey sir can you tell me how to run code of ResDiff given in github on Google colab

  • @philip-niron
    @philip-niron 3 года назад

    Nice Video sir. How to change this model to tflite and deploy in android Application? Kindly do a video on that sir

  • @jongameshow
    @jongameshow Год назад

    Any idea how I can create a model with three dimensions? As this is resulting in a 2 dimension model

  • @Thedark.i
    @Thedark.i 4 года назад +1

    Sir please make transfer learning architect videos if its possible.

  • @naeemmuhammad3494
    @naeemmuhammad3494 4 года назад

    after the execution how do we normalize the training and validation curves (overfitting problem)

  • @nazzishrazzaq
    @nazzishrazzaq 3 года назад

    Do i need to have cuda installed in my workstation to run Google Colab and train the model?

  • @avinashnair5064
    @avinashnair5064 4 года назад +1

    Can anyone help me with this :
    The training gets stuck at epoch 1 (completes)its not moving to another epoch.

    • @anuragmaurya3805
      @anuragmaurya3805 4 года назад

      do u resolved this i am getting same error

    • @avinashnair5064
      @avinashnair5064 4 года назад

      @@anuragmaurya3805 Not as of now please let me know if you get any solution

    • @sameersingh5078
      @sameersingh5078 4 года назад +1

      @@avinashnair5064 try to check your steps_per_epoch. maybe this is problem is due to that

    • @avinashnair5064
      @avinashnair5064 4 года назад

      @@sameersingh5078 sure... Ill tell you about that

    • @lesliepaulraphael459
      @lesliepaulraphael459 4 года назад

      @@avinashnair5064 Do you Solve the Problem ?

  • @samarjitnathmazumder4241
    @samarjitnathmazumder4241 4 года назад

    Sir I am doing a project related to defect detection and sizing. I have build a model using ANN to classify defect.
    Can you guide me how can I get the bounding box coordinate of classified image.

  • @lias1
    @lias1 Год назад

    Do you have zoomclasses or tutoring? if yes where can i sign up?

  • @umerkhan4987
    @umerkhan4987 3 года назад

    very nice video, there is one query, can we run the code once and turn off the note book, is there any option with us that we can resume after an hour or some couple of hours to get output values?

    • @stzgaming2430
      @stzgaming2430 3 года назад

      I have the same question on google colab i dont want to run code again and again or train

  • @ethicalsaw8101
    @ethicalsaw8101 3 года назад

    can you please tell me how to use this .h5 model in raspberry pi. any conversion needed in the model or I directly use this model in raspberry pi.

  • @dirobayisa864
    @dirobayisa864 Год назад

    Hi Krish,
    Thank you for your tutorials.
    I am doing on plant species recognition can you share something............

  • @ochanabondhu
    @ochanabondhu 2 года назад

    Now this video is nothing but a gem.. Thank you Krish.. Just 1 question... I have seen in many datasets there is another folder called validation.. Why it's so and what's the use? Can you please explain or guide me to any of your video wish such a reference

  • @alaaabdullah2648
    @alaaabdullah2648 2 года назад

    The path of image should be on Google drive? What if i am working with jupyter and i decide the path in my local device its will work?

  • @arfinarif9669
    @arfinarif9669 2 года назад

    any solution? in google collab
    InvalidArgumentError Traceback (most recent call last)
    in ()
    6 epochs=10,
    7 steps_per_epoch=len(training_set),
    ----> 8 validation_steps=len(test_set)

  • @badass_bloke144
    @badass_bloke144 Год назад

    what is the pre-sequence of following up with this video?

  • @TechInventorAman
    @TechInventorAman 3 года назад

    Is it using keras ?

  • @hazkimshazkim1041
    @hazkimshazkim1041 4 года назад

    hallo sir, great video learning. Can i ask if this method is also in Convolutional neural network?

  • @WaiTheng
    @WaiTheng 8 месяцев назад

    Can this training process be done by using YOLOv8?

  • @vishaldedavat6835
    @vishaldedavat6835 3 года назад

    i am getting error .. i have run the same code as yours.. but while running the epoch.. it is showing failed to get convolution algorithm

  • @PrityKumari-rq2gp
    @PrityKumari-rq2gp 3 года назад

    Also please make a videos for an app development from scratch for disease detection and if i want to deploy that whole app concept on arduino then what are the steps.

  • @mansukhprajapati5242
    @mansukhprajapati5242 3 года назад

    can u make a video for training a model with provided image dataset using YOLOV3 architecture.
    OR can u add a code for it on your github account...please..

  • @lakshmihymavathichaturvedu7953

    good evening ,can anyone please resolve the issue...actually at the last step of execution iam getting error as invalid exception and it is showing that argument error.as we are running the same code but with different dataset.i dont know y the error is occuring.

  • @radhikapatil8003
    @radhikapatil8003 3 года назад

    Please make a video on Fixefficientnet image classification

  • @angie7706
    @angie7706 3 года назад

    I have photos in different resolutions. How can I resize every images in to same resolution?

  • @abhishekpatil2811
    @abhishekpatil2811 10 месяцев назад

    Can you please make a video on Efficientnet V2 model

  • @rehippie
    @rehippie 2 года назад

    Hi Krish, I didi it all and it worked! Now, how do I save my trained model to use it in onther scripts?

  • @sanatbek819
    @sanatbek819 3 года назад

    Thank you. Very nice bro. I am having a hard time understanding the functions you explained. Please, share a successful path to learn.

  • @afzalrahaman6306
    @afzalrahaman6306 3 года назад

    Dear krish, your theory explanation on deep learning helped me a lot. My pc is low configured, it dual core windows 7 64 bit. I know it's impossible to work with tensorflow with this configuration. Let me know is it possible to practice in cloud

  • @sagihaviv5675
    @sagihaviv5675 3 года назад

    sir how can I train for ocr recognition for SPECIFIC word or sentences using OCR and print in pdf

  • @2SourceFort
    @2SourceFort 3 года назад

    14.34 not working I cannot read my folder

  • @navneetgupta2474
    @navneetgupta2474 4 года назад +1

    Sir explain XGBoost algorithm, how it differs from Gradient boost. Also I can't find easy explanation of Bayesian search in hyperparameter tuning so make one on it's theory part. Thank you

  • @touhidulislamsovon6927
    @touhidulislamsovon6927 Год назад

    Thank You sir!!

  • @AJAYKUMAR-sf7mc
    @AJAYKUMAR-sf7mc 4 года назад

    when i train the DL model at google colab , according to this example it throw a msg which is "your session is crashed for unknown reason" , @krish sir plz help over here

  • @platypusnebula7401
    @platypusnebula7401 2 года назад

    Has anyone followed along this video recently with success? I followed along with the video (typed along), and used the picture files from Github, but when I executed the final command to run the cell, I got an "UnimplimentedErrors" at line 8, where the code reads: "validation_steps=len(test_set)". It's a long error message, but at the end is says "DNN Library is not found." Some of the libraries installed earlier in the notebook were of a different version.

  • @kalpanagona7841
    @kalpanagona7841 4 года назад

    Sir please suggest aa good method for paddy leaf disease classification in deep learning please sir