Transfer Learning | Deep Learning Tutorial 27 (Tensorflow, Keras & Python)

Поділитися
Вставка
  • Опубліковано 1 гру 2024

КОМЕНТАРІ • 168

  • @codebasics
    @codebasics  2 роки тому +6

    Check out our premium machine learning course with 2 Industry projects: codebasics.io/courses/machine-learning-for-data-science-beginners-to-advanced

  • @sherifbadawy8188
    @sherifbadawy8188 2 роки тому +12

    Man your courses taught me to lose my ego, and to live out for the people. Thank you so much for this. This has to be a blessed deed that you did this.

  • @mhdkfl
    @mhdkfl 4 роки тому +40

    By watching your deep learning whole series i have cleared my bunch of doubts .
    Your way of putting any topic so simple is really amazing.
    Hatts off to your teaching methodology.
    A heartiest request to you to
    Please upload NLP series (including LSTM and Encoders/Decoders) with a good project.
    I am eagrely waiting.

    • @codebasics
      @codebasics  4 роки тому +8

      Yes nlp series is in my plans

    • @zkhan2023
      @zkhan2023 3 роки тому

      @@codebasics sir, when will you starting that series?

    • @bagheerathan8975
      @bagheerathan8975 Рік тому

      here how can we test the model after train the model plz tell me

    • @bagheerathan8975
      @bagheerathan8975 Рік тому

      @@codebasics here how can we test the model after train the model plz tell me

  • @GautamKumarBEE
    @GautamKumarBEE 3 роки тому +16

    A very humble request, please add atleast 5-6 more videos in this series.

  • @sandiproy330
    @sandiproy330 Рік тому +1

    With a clear example you explained transfer learning so beautifully. LOved to see your tutorial. Thank you so much sir.

  • @PriyankaDarshanam
    @PriyankaDarshanam 2 місяці тому +4

    For those who are getting this error
    Only instances of keras.Layer can be added to a Sequential model. Received: (of type )
    try this,
    import tf_keras
    and replace every 'tf.keras' with 'tf_keras'

  • @AlonAvramson
    @AlonAvramson 3 роки тому +3

    Your way of explaining complex issues in such an easy and simple way is truly amazing. Thank you!

  • @yaswanthyalamuri8799
    @yaswanthyalamuri8799 Місяць тому +2

    Wow, such a great techique to train models. Thank you sir for making it easy for us

  • @anoshpa-6531
    @anoshpa-6531 3 роки тому +3

    I don`t have words to thank you for this deep learning series, you have explained every single topic in simple language.
    Thanks a ton :) :) Keep Uploading such series :)

    • @codebasics
      @codebasics  3 роки тому +2

      👍☺️

    • @bagheerathan8975
      @bagheerathan8975 Рік тому

      here how can we test the model after train the model plz tell me

    • @prajjowldahal8959
      @prajjowldahal8959 6 місяців тому

      @@codebasics sir in github code are not there it shows error it is moved from github????

  • @mums2109
    @mums2109 Рік тому +2

    Even though this of two years old it is still very well taught. Thank you!

  • @izharkhankhattak
    @izharkhankhattak 3 роки тому +3

    Really great lecture. Keep helping the people like that. Thank you so much.

    • @codebasics
      @codebasics  3 роки тому

      My pleasure

    • @bagheerathan8975
      @bagheerathan8975 Рік тому

      @@codebasics here how can we test the model after train the model plz tell me

  • @zaidalmahmoud4272
    @zaidalmahmoud4272 2 роки тому

    Wow! What a simple and clear illustration of Transfer Learning. Thank you!

  • @mangaldasgaonkar568
    @mangaldasgaonkar568 4 місяці тому +9

    import tf_keras
    IMAGE_SHAPE = (224, 224)
    classifier = tf_keras.Sequential([
    hub.KerasLayer(model_link, input_shape=IMAGE_SHAPE+(3,))
    ])
    First install tf_keras by pip install tf_keras then,
    import it by import tf_keras
    And use it
    classifier = tf_keras.Sequential([...])
    For me it is working
    Replace tf.keras to tf_keras everywhere

  • @bhaskargg6018
    @bhaskargg6018 2 роки тому +1

    no words to praise, the session is superb , thanks a lot for sharing your knowledge

  • @shreyasb.s3819
    @shreyasb.s3819 3 роки тому +2

    Omg..u have cleared my lot of doubts here...superbbb explained...thank you much sir. Please contribute more towards RNN also like this.

  • @sumit121285
    @sumit121285 3 роки тому

    really helpful....you are the best teacher for deep learning....also for machine learning.....thankyou so much...... i m a big fan of yours.....

  • @aliksmshaik-x8t
    @aliksmshaik-x8t 2 місяці тому

    Amazing explanation, very easy to understand

  • @work-dw2hl
    @work-dw2hl 3 роки тому

    Your teaching style is outstanding

  • @homeOfTrivia
    @homeOfTrivia 2 роки тому

    Excellent course. This is my "Go To" resource for Machine Learning and Deep Learning.
    Please think of creating a series of projects that can make one grow their skills. Keep the price affordable.

  • @inhibited44
    @inhibited44 Рік тому +1

    That example with the flower identified as an umbrella got me thinking. I applied your model to my data. I have pictures of an object with rust and blemishes on them. The model identified a few pictures as a snake of some sort or a hyena. If I do a case study of a bunch of pictures in my data and feed them to the model, I should be able to program into it the actual appropriate identity once the model has ascertained it's a snake, hyena or whatever.

  • @kunalll24
    @kunalll24 8 місяців тому +6

    Having error while using the pretrained model,
    error : ValueError: Only instances of `keras.Layer` can be added to a Sequential model. Received: (of type )
    please help.

  • @nineteen5899
    @nineteen5899 3 роки тому +1

    Thanks mate... it helped.. Love from London..

  • @harshalbhoir8986
    @harshalbhoir8986 Рік тому

    This is something new I learned!!!

  • @pratyushsinha5201
    @pratyushsinha5201 3 роки тому +1

    Thank you so much sir. This was extremely helpful!

  • @pvtgcn8752
    @pvtgcn8752 Рік тому

    Very Lucid Explanation

  • @tomdapchai
    @tomdapchai Рік тому

    thanks, very easy to follow

  • @kollurisharada5102
    @kollurisharada5102 3 роки тому

    VERY GOOD EXPLANATION

  • @ucm269
    @ucm269 Рік тому +1

    In the last layer of the trained model, though softmax layer is being used , how we are getting some of our prediction values to be greater than 1??

  • @SachinGupta-dn7wt
    @SachinGupta-dn7wt 3 роки тому +2

    You predicted using a classifier that was pre-trained(in which you got inaccurate results), but I wanted to see how we can give one input image and check the output by using the new classifier.

  • @srishtikumari6664
    @srishtikumari6664 3 роки тому

    Wonderful explanation!!

  • @zzzmd11
    @zzzmd11 Місяць тому

    Hi Thanks for the great explanation as always. Just wanted to know about model ensembling or stacking across different datasets. As in developing a one single model which is trained from 2 separate datasets which have their own separate set of features (which are not overlapping with each other). Is it possible and are there any examples which are already done? Can you please shed a light on this..Thank you so much in advance...

  • @ansariarbaz3374
    @ansariarbaz3374 3 роки тому

    nice video sir just wanna add u must use softmax activation function in last layer directly.... please

  • @nguyennhi8524
    @nguyennhi8524 Рік тому

    Thank you so much!!! 👏

  • @advertisemedia1509
    @advertisemedia1509 Рік тому

    can you show how prediction is done after transfer learning is done .... i mean after retraining the model with flower images plz show how to check results... thanks a lot... i tried but couldn't do ....thanks a lot

  • @sagarmahobia5159
    @sagarmahobia5159 3 роки тому +2

    Wouldn't it affect the ability to recognize images other than these flowers because now the last layer has been trained with a smaller dataset? Like recognizing a chair or. bike

  • @juangutierrez3309
    @juangutierrez3309 2 роки тому +2

    YOU ARE A LEGEND! Thanks for helping me understand how transfer learning worksQ
    Just had one question... I understood everything but this piece of code:
    model.compile(
    optimizer="adam",
    loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    metrics=['acc'])
    Where did you get this? Do I use this with any model I use for transfer learning?

    • @codebasics
      @codebasics  2 роки тому +1

      This has nothing to do with transfer learning. Whenever you train a model in deep learning you need to use this line

    • @bagheerathan8975
      @bagheerathan8975 Рік тому

      here how can we test the model after train the model plz tell me

    • @bagheerathan8975
      @bagheerathan8975 Рік тому

      @@codebasics here how can we test the model after train the model plz tell me

    • @PavanKumar-rp2xz
      @PavanKumar-rp2xz 3 місяці тому

      ​@@bagheerathan8975
      Model.evaluate(X_test,y_test)

  • @akshayvasav2497
    @akshayvasav2497 Рік тому

    @codebasics this is greatest video of transfer learning i have ever seen, usually people load dataset from tensorflow directly instead of local disk. You load it from local disk which is great thing.
    I just have one question what you appended in "y" , class name or class Id ?

  • @tewodrosgebre204
    @tewodrosgebre204 3 роки тому

    Thank you. Helpful.

  • @dileeppanigrahi4453
    @dileeppanigrahi4453 3 роки тому +2

    Hi sir, How can i remove the last layer , without using feature_vector model. what i mean is how to remove the last layer from the classification model(mobilenet_v2) and freeze the trained layers .

  • @studentmitra5372
    @studentmitra5372 8 місяців тому +1

    Can you please analyse HAM10000 dataset. Because this dataset is highly imbalanced and it also contain meta data in csv file. So I am bit confused.

  • @reinishasarojini6908
    @reinishasarojini6908 Рік тому

    I need more videos on transfer learning sir

  • @wcottee
    @wcottee 4 місяці тому

    So let me see if I understand...we froze all the weights/biases/filters for all the layers except the final one. So when we say we are "training" the model with our flower data set, we are only optimizing the weights and biases of the final layer (i.e. the input to the softmax function)?????

    • @CertifiedAuthur
      @CertifiedAuthur 3 місяці тому

      How do you get past the hub and keras.layer zone. I have been getting value error

  • @naa12333
    @naa12333 Рік тому

    thank you sir for the wonderful tutorials...
    I am following all the steps in this video as well in previous episode (26), I get an error when I train the model, since I am new I could not figure out how to fix this error.
    error:
    ValueError: Data cardinality is ambiguous:
    x sizes: 2752
    y sizes: 918
    Make sure all arrays contain the same number of samples.

  • @RanjitSingh-rq1qx
    @RanjitSingh-rq1qx 2 роки тому

    Sir please make more videos on transferring learning.i think this is not sufficient to use transferring learning in more easy way 🙏

  • @saltanatkhalyk3397
    @saltanatkhalyk3397 3 роки тому

    Thank you very much.

  • @dilipkumar2k6
    @dilipkumar2k6 2 роки тому

    You need a standing ovation :-)

  • @lalitsingh5150
    @lalitsingh5150 4 роки тому +1

    Thank you sir

  • @nastaran1010
    @nastaran1010 9 місяців тому

    the model perfomance with useing 'feature vector' is increased. but when i tried to predict ([X[0],X[1], X[2]]), it perfomes so bad. why?

  • @HIMANSHU-lm5tg
    @HIMANSHU-lm5tg Рік тому

    sir, u have taught so much of free that i have not learnt in any of the paid courses.
    i am trying to use ML and AI in financial instruments for trading and investing. but due to non familiarity with ML and AI world I m not able to figure out from where to start and what is relevant for me. plz guide me.

  • @arcanepersona1676
    @arcanepersona1676 2 роки тому

    Thanks a lot , I appreciate your way of explaining deep learning 😊
    I would like to ask about image classification using transfer learning .. if I have a dataset of images with the size 100x100 .. and the image size in the pre trained model is 300x300 .. a bigger size .. how do I make my smaller sized original images fit in that pre trained model ?

  • @aninditasaha0307
    @aninditasaha0307 4 роки тому

    Sir... Can you please show CNN in UCIHAR dataset... Will be really helpful

  • @adityahpatel
    @adityahpatel 3 роки тому

    Hello, why are there so many MobileNet model variants on Tensorflow hub? Like mobilenet_v2_50_192, mobilenetv2_035_96, mobilenetv3_large_100_224 and so many other variants? What is the different between these?

  • @siddharthkshirsagar2545
    @siddharthkshirsagar2545 3 роки тому

    amazing🙃

  • @Janamejaya.Channegowda
    @Janamejaya.Channegowda 4 роки тому +2

    Thank you, can transfer learning be done for time series data?.

    • @chymoney1
      @chymoney1 3 роки тому

      Yes, but I’d imagine it does not have advantages over LSTM or transformer

  • @yassmingourya9975
    @yassmingourya9975 3 роки тому +2

    Hey, I really liked your videos you are explaining everything in a quiet simple way, but can we use transfer learning on non_image data set? , like I have a dataset composed of srtings I transformed it to arrays and I want to make predictions using arrays, does transfer learning help in this case?
    Thanks a lot

    • @codebasics
      @codebasics  3 роки тому +1

      yes transfer learning is not restricted to only images. you can use it for other problems too

    • @yassmingourya9975
      @yassmingourya9975 3 роки тому

      @@codebasics ah great, thanks for your reply. please can you help with some documentations or instructions on how to do i'll be so grateful

    • @sanarabhi4906
      @sanarabhi4906 Рік тому

      @@yassmingourya9975 please did you found documentations for using transfer learning on non_image data set , i need to do it but can't find anything useful. thank you

  • @HotshotArafath
    @HotshotArafath 3 роки тому

    Sir can we use this method for the leaf disease project also as a extension?

  • @karatugba
    @karatugba 3 місяці тому

    What if I want to classify 1005 classes with freezing, what do I need to do?

  • @tirthadatta7368
    @tirthadatta7368 3 роки тому

    Sir, the tutorial is well made. But can u please tell us how to add batch size and other preprocessing steps in this code??

  • @bensalah90
    @bensalah90 3 роки тому

    nice video keep going ;so what would you suggest as model from TL HUB to train signal or spectogram

  • @fvviz409
    @fvviz409 4 роки тому

    Hey can you teach us how to do real time neural network prediction using open-cv? It is very useful in computer vision

  • @Raj-sz9pg
    @Raj-sz9pg 2 роки тому +1

    from where did you downloaded those classes list
    ?

  • @andrewzolensky9807
    @andrewzolensky9807 2 роки тому

    Hi, great tutorial! Quick question, when training the single dense layer around minute 24:00, why is there no activation function (e.g. softmax) applied to the final, trainable dense layer?

    • @andrewzolensky9807
      @andrewzolensky9807 2 роки тому

      Edit: minute 23:30

    • @gauravtripathi562
      @gauravtripathi562 2 роки тому

      It's taking by default value for that and its relu i think or you can check....but keeping it empty means it's taking default value for that

  • @abduladhilpk8223
    @abduladhilpk8223 4 роки тому +1

    why yolo algorithm takes hours to train to perform object detection using transfer learning

  • @suleyman.p
    @suleyman.p 2 роки тому

    why we didn't use an activation function in last dense layer ?

  • @sabarimahesh
    @sabarimahesh 2 роки тому

    Is it possible to do transfer learning for ANN ? Any reference available ?
    I could see more examples for CNN. Is there any reason behind.

  • @balajim2107
    @balajim2107 3 роки тому

    It shows flowers as umbrella and so on..Then using mobilenet is good?or bad?

  • @saarakauser7008
    @saarakauser7008 2 роки тому

    very informative sir. can you explain how to combine 2 or more pretrained models..

    • @aintthatharsh
      @aintthatharsh 2 роки тому

      How and why would someone do that?

  • @suhaalam2127
    @suhaalam2127 3 роки тому

    Do you have any tutorial where u have shown any regression problem solving using deep learning?

  • @Suriyabegum22PHD053
    @Suriyabegum22PHD053 9 місяців тому

    sir, how to search TensorFlow hub training models give me the same as you have used.

  • @navneetkumar5517
    @navneetkumar5517 8 місяців тому

    thank you so much bhaiya

    • @CertifiedAuthur
      @CertifiedAuthur 3 місяці тому

      I'm having a value error when trying to wrap the hub and keras.layer, how were you able to get past there?

  • @321-youvrajsinghgaur3
    @321-youvrajsinghgaur3 Рік тому

    Please Tell How can we save this model after transfer learning !

  • @UsmanKhan-hu8hw
    @UsmanKhan-hu8hw Рік тому

    can we apply the same way for transforming of text sentiment model?

  • @zaindurani8168
    @zaindurani8168 4 роки тому

    Thanks a lot sir

  • @Frostbyte-Game-Studio
    @Frostbyte-Game-Studio 2 роки тому

    holy fuck that might save me a lot of fucking trouble thank you so much for this video and for this code

  • @rasanjalirathnayake8873
    @rasanjalirathnayake8873 2 роки тому

    when we use pupil detection, i mean wha t I need is to localize the pupil center, are we using classification? just like left eye and right eye ? or something else?
    please reply.

    • @codebasics
      @codebasics  2 роки тому

      Are you doing object detection? Have you tried yolo etc?

  • @saltanatkhalyk3397
    @saltanatkhalyk3397 3 роки тому

    your code works ^_^

  • @quattrandang4312
    @quattrandang4312 Рік тому

    Hello guy ! I need help . Specifically, I followed your code but when I bring that model to deploy in my project, using load_model does not work. Ok i understand it doesn't save the complete model but i want it to save only the part i changed (output layer) so when i use it i need to have it (custom_objects={'KerasLayer':hub.KerasLayer }) . But the problem here is that when I use the above command, my model will not work after a period of time (according to my understanding, when I load the model in the above way, it will download a temporary folder containing the information. the model number and structure ( which contains some .pb and pbtxt files ) - this folder will be partially deleted by something after about a week , so it causes an unusable error , If you want to use it again, you need to delete the folder and let it download the new one). I don't want my program to crash every once in a while. Do you have any way ?
    In addition, I have found a way to fix it, but it is not a good way. I use :" from tensorflow.keras.applications import " to load sample models and add classes directly to this model. It works like a self-built model so you don't have to reload the keras layer every time you use it (which caused my error). However, this way it is quite resource-intensive. Do you have a better alternative?
    Thanks for reading .
    Looking forward to hearing from you soon.

  • @rahulrangu6506
    @rahulrangu6506 2 роки тому

    hi sir can we get the ppt also in deep learning tutorials and Machine Learning tutorials that you have used to explain the concepts

  • @dr.md.atiqurrahman2748
    @dr.md.atiqurrahman2748 3 роки тому

    Wow!!!!!!! If I had an option, I would subscribed (1000000000000000000000000000....................I don't know how many zeros I would add) times.

    • @codebasics
      @codebasics  3 роки тому

      Thanks for your kind words of appreciation Atiqur.

  • @Maryashahere
    @Maryashahere Рік тому

    Sir how can we apply transfer learning for numerical data?

  • @praneedhaweerakoon8570
    @praneedhaweerakoon8570 4 роки тому

    What are the methods available to improve the accuracy of custom models??except trial and error.

  • @Raj-sz9pg
    @Raj-sz9pg 2 роки тому

    how to know if its working? in the end after we run 5 epoch

  • @riadelectro1
    @riadelectro1 2 роки тому

    Please teacher; could you give me a master topic proposal about clustering images?

  • @nastaran1010
    @nastaran1010 9 місяців тому

    what is the version od tensorflow, hub?

  • @MJEEVA-r5f
    @MJEEVA-r5f Рік тому

    how to increase running speed of epoch in jupyter notebook for flower dataset classification

  • @jrajpal5
    @jrajpal5 2 роки тому

    Hi sir, i watch your videos every day
    But with the same dataset, i am getting losses of 1.6 and accuracy close to 0.21 with transfer learning as well as with cnn
    So please tell how can i improve them

  • @chealsytchasso3871
    @chealsytchasso3871 2 роки тому

    HI is it possible tu convert an image of 3D dimensions in to an image of 4D dimensions?

  • @baburamchaudhary159
    @baburamchaudhary159 Рік тому

    since, we have 1000 classes, why do we get (1, 1001), when executing result.shape

  • @Makingrobloxvids
    @Makingrobloxvids 2 роки тому

    hello how can I use Transfer learning on 1 dimension data

  • @arpitjain6451
    @arpitjain6451 2 роки тому

    model.fit(X_train_scaled, y_train, epochs=5)
    ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type list).
    error occur at this line

    • @anshXR
      @anshXR 2 роки тому

      model.fit only accept numpy arrays. So try running this :-
      X_train_scaled = np.array(X_train_scaled)
      y_train = np.array(y_train)

  • @gokkulkumarvd9125
    @gokkulkumarvd9125 4 роки тому

    sir, how many more videos will be there?

  • @yashu1089
    @yashu1089 3 роки тому

    which classifier are you using

  • @tickokok1410
    @tickokok1410 2 роки тому

    while i am running classifier.preduction it's showing your kernal is dead

    • @tickokok1410
      @tickokok1410 2 роки тому

      please let me know the solution

  • @Piyush-yp2po
    @Piyush-yp2po 4 місяці тому

    Tensorflow hib is not compatible with latest tf versions

  • @charantejchetty149
    @charantejchetty149 3 роки тому

    Hey , how can I download Mobile net V2 dataset?

  • @rahaf1418128
    @rahaf1418128 3 роки тому

    is this could consider as convolutional neural network?

  • @krutikagouda2696
    @krutikagouda2696 Рік тому

    Can you please suggest trained model for ai based picture translation project

  • @nareshagarwal8243
    @nareshagarwal8243 3 роки тому

    can you please also add a video on NLP?

    • @codebasics
      @codebasics  3 роки тому +1

      Yes the RNN tutorials are coming up from tomorrow. First one will be uploaded tomorrow (Tuesday) 7 pm IST

  • @amudalagopikrishna5745
    @amudalagopikrishna5745 Рік тому

    what is that third value in the input shape

    • @huskymotivations
      @huskymotivations Рік тому

      it mean the images are color images, like (RGB), and if we have black and white images we use 1 instead of 3. I'm also a beginner but i guess most probably that's the reason

  • @Abhishek-jd9qk
    @Abhishek-jd9qk 3 роки тому

    What was the need of adding 1 and 3 to the dimensions ?

    • @lakshsinghania
      @lakshsinghania 5 місяців тому

      same doubt, maybe the index/number