Transfer Learning Using CNN(VGG 16)| Keras Tutorial|

Поділитися
Вставка
  • Опубліковано 1 гру 2024

КОМЕНТАРІ • 78

  • @simonegasparella1228
    @simonegasparella1228 3 роки тому +6

    Hi, How can we see the accuracy chart of the validation test set? How can we see the incorrect pictures in the test set? Thanks a lot

  • @dishachakraborty9769
    @dishachakraborty9769 2 місяці тому

    I need help. I don't have separate train, test and validation data for my dataset on Kaggle.
    The dataset only has 3 folders - Normal, Benign and Malginant which contain images but no subfolders for train and test.

  • @mohammedzia1015
    @mohammedzia1015 3 роки тому +1

    I have one question, the VGG16 model would have been trained for this type of Dataset ? I mean for the classes Benign and Malignant ?

  • @alexomelak4200
    @alexomelak4200 9 місяців тому

    Sir ,help me please? I was doing gray scale image classification using VGG16. their is an error when I update the code from
    vgg = VGG16(input_shape=IMAGE_SIZE + [3], weights='imagenet', include_top=False) to
    vgg = VGG16(input_shape=IMAGE_SIZE + [1], weights='imagenet', include_top=False). help me please

  • @sayansaha5348
    @sayansaha5348 2 роки тому

    Thanks bhaiya can you please make a separate video for the prediction part only

  • @reemalmijmaj3215
    @reemalmijmaj3215 2 роки тому

    This video save my life :)) Thanks a lot !!

  • @TitoWPurnomo
    @TitoWPurnomo 2 роки тому

    I've run code with jupyter-lab but during training process always appears statement "the kernel appears to have died. it will restart automatically" . do you know the solution?

  • @sherin7444
    @sherin7444 Рік тому

    1 question.Lets say in my train file couple of images are not of 224*224 .How can we convert them to standard size

  • @vanshajgoel8783
    @vanshajgoel8783 2 роки тому +1

    InvalidArgumentError: Graph execution error: -->Any idea why this error is coming ??

    • @NachiketaHebbar
      @NachiketaHebbar  2 роки тому

      Normally you get this error when there is a mismatch in the number of data classes that you defined in model and the one which you are actually giving it. Double check the input shape, target size , number of dataset folders and the number of output layers

  • @syedzoofa8711
    @syedzoofa8711 3 роки тому

    Ur videos have helped me a lot.. Thank u

  • @komaldaoud3445
    @komaldaoud3445 3 роки тому +1

    how can we use grid search cv with model.fit??

  • @ashikroy4618
    @ashikroy4618 2 роки тому +2

    Hi Nachiketa,
    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 your transfer learned model?
    Thanks

    • @swatimishra1555
      @swatimishra1555 Рік тому

      I am also not getting validation accuracy and loss because they n
      have not to use a train test split. I really don't know how he is getting validation accuracy and loss for the model. Plz, include this in the code.

    • @swatimishra1555
      @swatimishra1555 Рік тому

      Hi Nachiketa,
      plz clear this doubt

    • @leo7662
      @leo7662 Рік тому

      ​@@swatimishra1555when u r writing u just need to write validation split =0.2 that will automatically take 20% of our data as validation set randomly so u will get both validation loss and accuracy

  • @pavantripathi1890
    @pavantripathi1890 2 роки тому

    Can you please show how to predict on a new image.

  • @rohit_mondal__
    @rohit_mondal__ 3 роки тому

    Sir if you could explain the vgg.input thing we are putting in the inputs section of the model !

  • @umanggupta1003
    @umanggupta1003 2 роки тому

    Can you show end to end code with model.Predict() to verify the results?

  • @rakeshsahoo3711
    @rakeshsahoo3711 2 роки тому

    Can u apply k-fold cross-validation for this

  • @bhavukthakur9501
    @bhavukthakur9501 2 роки тому

    sir, when you do ImageDataGenerator step how many images we get?
    Like, if we have 10 image in train dataset and we apply rotation_range, width_shift_range, height_shift_range=0.2 so we get 30 images or just 10 images?

  • @girimadhavchowdhury1281
    @girimadhavchowdhury1281 Рік тому

    I could not able to resize my input into 224*224*3... Can any one help me on this

  • @plabmadeeasy
    @plabmadeeasy 3 роки тому

    You've got a subscriber!

  • @minakshisonawane5929
    @minakshisonawane5929 2 роки тому

    sir can u help me when i create folder but i have error .

  • @byDes
    @byDes 3 роки тому

    Hello, this helped me a lot! I hope you could also make a tutorial for medical images using mobilenetv2

  • @shivambaldha3914
    @shivambaldha3914 2 роки тому

    Very very useful for me , thank you :)

  • @darshitavijayakumar2021
    @darshitavijayakumar2021 3 роки тому

    I'm getting that the object is not callable . Please help me

  • @kaouthergacem8135
    @kaouthergacem8135 6 місяців тому

    your video helped me a lot thank you

  • @sagnikroy6405
    @sagnikroy6405 3 роки тому

    Thanks @Nachiketa . Really helped. One question , what does the .h5 extension is for?? Storing trained NNs??

    • @NachiketaHebbar
      @NachiketaHebbar  3 роки тому +2

      Yeah, it stores the model architecture and weights

  • @anchalsharma6163
    @anchalsharma6163 7 місяців тому

    Hloo sir can you help ke for plot graph

  • @byDes
    @byDes 3 роки тому +1

    Hi! How did you split the train, val, and test dataset?

    • @sololife9403
      @sololife9403 2 роки тому

      if you download the dataset from kaggle, you will find out that the train and test sets were already split for us. but i did not find val , though

  • @aninditasaha0307
    @aninditasaha0307 Рік тому

    Hi... Can anyone send me the confusion matrix code for this prob?

  • @hamzanaeem4838
    @hamzanaeem4838 3 роки тому

    What if we don't use steps per epoch and validation steps ? Can we use model.fit only if we don't apply augmentation.

    • @sagnikroy6405
      @sagnikroy6405 3 роки тому

      I guess YES, as the fit_generator is deprecated in the newest version of tensorflow or keras.

  • @nikolaostziokas6847
    @nikolaostziokas6847 3 роки тому +1

    Great video. I have only one question. What are the dimensions of your training and test images? Do they have to be 224*224 before you import them into the algorithm?

  • @OpeLeke
    @OpeLeke 2 роки тому

    Great Video, it's skin lesion dataset not skin cancer.

  • @madhukanadeeshani6982
    @madhukanadeeshani6982 3 роки тому

    Hi it's great .can you please share the code and link of the dataser

  • @vanillasky1842
    @vanillasky1842 3 роки тому

    So if I'm using grayscale images,where should I make the changes?

    • @NachiketaHebbar
      @NachiketaHebbar  3 роки тому

      in the input shape. Instead of 3 as the depth of image, use 1.

  • @jaideeppanwar2730
    @jaideeppanwar2730 3 роки тому

    hey.....can we make a gradio app on this ......i mean it will the same process ....that u showed in the earlier video ?

    • @NachiketaHebbar
      @NachiketaHebbar  3 роки тому +1

      Yes, you can. I had shown an inception model in that video, you can just replace that by this vgg model. It will work

  • @rasanjalirathnayake8873
    @rasanjalirathnayake8873 2 роки тому

    Instead of classification do something related to deep learning with regression analysis please.

  • @Megh93
    @Megh93 2 роки тому

    getting error in model.fit_generator

  • @adarshrkr9355
    @adarshrkr9355 3 роки тому

    Bro when im doing prediction im only getting class 0 for all my test data
    Any idea?

    • @NachiketaHebbar
      @NachiketaHebbar  3 роки тому

      If your test accuracy is good, then most probably the mistake you are making is in pre processing the input. For example, if while training you are rescaling the input or something else, then you have to do the same on an image before making predictions also.

    • @adarshrkr9355
      @adarshrkr9355 3 роки тому

      @@NachiketaHebbar ok bro thankyou will try that out

    • @simonegasparella1228
      @simonegasparella1228 3 роки тому

      Hi Sir, after training how can we make a prediction in one specific picture? Can you share the code ? Thanks

    • @simonegasparella1228
      @simonegasparella1228 3 роки тому

      @@NachiketaHebbar Can you provide the code for making a prediction on a single image? THANKS

    • @pranshusharma2030
      @pranshusharma2030 3 роки тому

      Sir Using transfer learning in various dataset we ar getting same value for all the datsets, how to process our inputs for predicting can you please do it sir, It will be of great help

  • @shivamkashyap6207
    @shivamkashyap6207 3 роки тому

    can you make a video on covid 19 detetection using chest xray using transfer learning

  • @bihanbanerjee
    @bihanbanerjee 2 роки тому

    thank you

  • @saisingireddy2359
    @saisingireddy2359 6 місяців тому

    💎🛐

  • @Ticitacapepguordiola
    @Ticitacapepguordiola 2 роки тому

    Where can i find the fucking dataset

  • @gunnu61
    @gunnu61 3 роки тому

    x = Flatten()(vgg.output)
    prediction = Dense(6, activation='softmax')(x)
    model = Model(inputs=vgg.input, outputs=prediction)
    model.summary()
    getting this error:
    Attempt to convert a value (None) with an unsupported type () to a Tensor

  • @leenaselvamani9065
    @leenaselvamani9065 2 роки тому

    Can you help me if I try to fit my model it says kernel is dead what shld I do for this prblm