Image classification using CNN (CIFAR10 dataset) | Deep Learning Tutorial 24 (Tensorflow & Python)

Поділитися
Вставка
  • Опубліковано 20 гру 2024

КОМЕНТАРІ • 339

  • @codebasics
    @codebasics  2 роки тому +9

    Check our Deep Learning Course (in PyTorch) with Latest, Industry Relevant Content: tinyurl.com/4p9vmmds
    Check out our premium machine learning course with 2 Industry projects: codebasics.io/courses/machine-learning-for-data-science-beginners-to-advanced

    • @nagababuyerramsetti8715
      @nagababuyerramsetti8715 9 місяців тому

      sir plese plese reply i am doing a project on pcb defect detection using cnn model please help me out i am not getting it please help me

  • @lucianoval903
    @lucianoval903 4 роки тому +67

    From Brazil, you are the best ML teacher!!! Thank you.

    • @codebasics
      @codebasics  4 роки тому +6

      Thanks Luciano for your kind words

  • @nilanjanap
    @nilanjanap 3 роки тому +31

    Excellent tutorials much better than many highly paid course floating online..Thanks a lot sir ..your videos helped me lot ...

  • @mrawesome-o7p
    @mrawesome-o7p 3 роки тому +19

    From South Korea, Learning Much Faster, Accurate than Univ. Thanks

  • @rb4754
    @rb4754 Рік тому +7

    Your tutorials are truly outstanding, surpassing many paid online courses. I want to express my deep appreciation for the invaluable support they've offered. Your detailed explanations of each code line have been incredibly helpful, particularly when I'm teaching machine learning to my students. Your videos provide a level of comprehension and utility that distinguishes them from other machine learning resources. Your efforts are greatly appreciated... Cheers!!!!!!!!!!!!!!!!💥💫💢

  • @albertoramos9586
    @albertoramos9586 2 роки тому +30

    You are so much better than my university tutors :-D Thanks a lot for your help!

  • @ChessLynx
    @ChessLynx 2 роки тому +8

    I am a young Ai and machine learning engineer from a IIIT and your videos are like food for me if i don't eat then I can't live .Great explanation ...
    finally I commented after watching tons of your videos daily . Salute to your spirit sir you will reach 10 M subs soon cause AI and ML is growing exponentially and your videos in this direction in serving as no. 1 you tube channel for simple explanations on Practical AI,ML coding and more people will join with you soon and soon...

    • @codebasics
      @codebasics  2 роки тому +2

      Ha ha .. thanks for your kind words of appreciation my friend :)

  • @sabrinazahir01
    @sabrinazahir01 4 роки тому +20

    I started to learn ml after getting inspirations from your videos. Thank you !

  • @bhaskargg6018
    @bhaskargg6018 2 роки тому +2

    the important CNN concept is explained in superb and simple to understand , Thanks a lot

  • @tesfitgi7579
    @tesfitgi7579 11 місяців тому

    Indeed you are an excellent tutor. Your efforts are greatly appreciated .I am fun of you. I AM an AI and machine learning outreach ,you pave me the way .Thanks a lot for you support

  • @Manojrohtela
    @Manojrohtela 3 роки тому +1

    as you teach all concepts even a primary student can understand it easily. Seriously big fan of your teaching style

  • @jogadornumerozero3257
    @jogadornumerozero3257 2 роки тому +1

    someone give this man a life elixir, he must give this knowledge for all the future generations

  • @sukumarroychowdhury4122
    @sukumarroychowdhury4122 4 роки тому

    Mr. Modi (Mr. Patel) is one side and rest Opposition (Data Science UA-camr) is on the other side.
    I really envy you (ONIDA TV) and you command that envy with your highest excellence.
    I am a retired Sr. Citizen and love data science (not because I understand it) but because of the amazing things that Amazon and Tesla and Google are doing..
    Please keep going..and may God give you a very long life..

  • @MonishNS22BCE333
    @MonishNS22BCE333 5 місяців тому

    This was my first to machine/deep learning as i had to do an assignment. Still i understood it vey well and now I'm able to do CNN on my own. Thanks to the tutor :)

  • @nikhildaram3354
    @nikhildaram3354 11 місяців тому +2

    how to split the image data into training and testing in folders

  • @michelletan4249
    @michelletan4249 Рік тому +1

    Excellent tutorials much better than my professor! You are the best! thank you so much! your videos helped me a lot....

  • @prachidoshi9082
    @prachidoshi9082 3 роки тому +2

    how come you tube did not recommend me this way before. Your videos are just perfect for people who want to learn Deep Learning and want to overcome the fear of AI

  • @rishavbhattacharjee7182
    @rishavbhattacharjee7182 4 роки тому +3

    Exciting Times!! May this series long continue😁

    • @codebasics
      @codebasics  4 роки тому +7

      yes it will. My goal is to cove all the topics and make this your one stop place for deep learning

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

    For digits: ann gives 90%, cnn gives 99+% on train dataset and 99% on test data, thanks sir

  • @mayankpatil7303
    @mayankpatil7303 2 роки тому +2

    Thank you sir! Teaching is also a skill and you nailed it!

  • @rafiahmed4247
    @rafiahmed4247 Місяць тому

    From Bangladesh...very helpful ❤

  • @Dev-D20
    @Dev-D20 2 роки тому +1

    sir when i running all this code in google colab my accuracy is 0.1 and not increasing in cnn case also.

  • @sergiochavezlazo5362
    @sergiochavezlazo5362 Рік тому +4

    I found something very important. When you reshape your y into 1 dimension, save it in a different variable and use the original one (2d) in the training and test process. Otherwise, the results change a lot

  • @zainulabideen_1
    @zainulabideen_1 Рік тому

    I love your way of teaching

  • @kennyhnsom
    @kennyhnsom 10 місяців тому +1

    The ann model refuse to run. It saying keras has no attribute sequential

  • @pa5119
    @pa5119 4 роки тому +3

    Such a Good Content.
    I am really exciting for upcoming videos.

  • @lindadelalifiasam5878
    @lindadelalifiasam5878 3 роки тому +2

    thank you soo much. from the knowledge i gained from this video, i decided to also increase the number of epochs in the first network(ann) from 5 to 10 and that led to a slight increase in the training accuracy(0.49 to 0.54). and for the cnn i intentionally decided first use the SDG optimizer and later the adam which also gave two different but better results than the ann. i also adjusted the epochs in each case. this has given me some more ideas to play around with, with regards to this model. once again thank you for bn such a great teacher

    • @ahmedhelal920
      @ahmedhelal920 2 роки тому

      me too i searched for my issue accuracy was 10 % and no increase however i increased hidden layers epochs , but what help me is changing the softmax to sigmoid and the number of hidden units it was 4 on my project here i found it 3000 , it increase my accuracy too , but based on what he choosed 3000 and 1000 hidden units ?

    • @dheerajvasudevaraovelaga6006
      @dheerajvasudevaraovelaga6006 Рік тому

      @@ahmedhelal920 More hidden units will recognize more patterns and more features, which will help if your images have many patterns and objects. It is always recommended to use more hidden units on layers and decrease it after every layer to reach a better solution.

  • @Lina-cy9ln
    @Lina-cy9ln 3 роки тому

    You are the best teacher of mine. I'm grateful to you always. Thanks a lot, sir.

    • @codebasics
      @codebasics  3 роки тому

      Zeenat, thanks for you kind words

  • @zaindurani8168
    @zaindurani8168 4 роки тому +1

    No one in universe can teach like this

    • @codebasics
      @codebasics  4 роки тому

      Thanks zain for your kind words

  • @techguyz839
    @techguyz839 7 місяців тому

    REALLY A GOOD VIDEO , i finally understood implementing CNN using CIFAR10

  • @gauravshah8554
    @gauravshah8554 3 роки тому +1

    You are superb in teaching. Please make video on how to deploy such trained models to production.

  • @fitnessismypassion
    @fitnessismypassion 10 місяців тому

    Hi, thanks for the clear explanation. I was wondering why you did not use softmax activation function in the last layer instead of sigmoid? As far as I know, softmax is preferred in multiclass problems (like in this case) and sigmoid is used for binary classification problems. Let me know and I appreciate your answer in advance.

  • @betsynwankwo1094
    @betsynwankwo1094 3 місяці тому

    Thank you...this course has been inspiring

  • @yoverale
    @yoverale 6 місяців тому

    Amazing tutorial, thanks a lot for sharing! Saludos desde Argentina! 🇦🇷

  • @sandiproy330
    @sandiproy330 Рік тому

    Very good explanation with a clear easily understandable video. Thank you for your tutorial. Loved it.

  • @ahmedzahid8354
    @ahmedzahid8354 Місяць тому

    thank you from Finland

  • @daggerdudes9211
    @daggerdudes9211 4 роки тому +5

    Your classes are really beginner friendly and I have a doubt will adding more layers improves the accuracy

    • @codebasics
      @codebasics  4 роки тому +3

      yes it might. you can try adding them. sometimes too many layers will overfit a model and while accuracy improves on training set, on test set it might perform poorly. You can use regularization techniques such as adding dropout layer to tackle these issues partially

  • @notavailable3331
    @notavailable3331 4 роки тому

    thanks a lot sir for your explanation. i got accuracy of 98.97% using cnn model

  • @inhibited44
    @inhibited44 6 місяців тому

    haven't watch the entire video yet. Is there a way to type in a command which looks for statistical outliers in the data that don't match anything well , so they can be eliminated to improve the model?

  • @mrkrupeshpatel
    @mrkrupeshpatel 8 місяців тому

    Very nice explanation on CNN....
    how you can simplify such complex topics ? You must be having rich experience in this field...😊

  • @uddalakmitra1084
    @uddalakmitra1084 2 роки тому +1

    Dear Sir, I have a data-frame with shape: 6500 rows and 146 cols. It is not a 3D data. How can I apply input_shape parameter to use CNN model?

  • @keshavgoyal3106
    @keshavgoyal3106 4 роки тому +8

    sir how i convert the prediction into csv file with column names (filname and label)

    • @sanskartewatia4320
      @sanskartewatia4320 3 роки тому +2

      convert to pandas dataframe and just execute - df.to_csv('df.csv')

  • @sankistudio1771
    @sankistudio1771 6 місяців тому

    Thank you sir, excellent explanation

  • @debojyotisinha5031
    @debojyotisinha5031 4 роки тому +1

    Your approach is very well. You can explain the topics so well and easy to understand the complex topic.

    • @codebasics
      @codebasics  3 роки тому

      Glad to hear that, I am happy this was helpful to you.

  • @IQTIDAR8
    @IQTIDAR8 2 місяці тому

    the VIdeo is really help full, but you should have also to show where you data set is store, because I am accessing but unable to access my data set from my computer

  • @khanwali9672
    @khanwali9672 4 роки тому +1

    Hi Thank you for all your tremendous work you make fall in love with Machine learning. don't you dare to stop;) Thank you so so so much.

    • @codebasics
      @codebasics  4 роки тому +3

      Thanks for your kind words khan ☺️ and yes now after reading your comment I am not going to stop 😉

    • @khanwali9672
      @khanwali9672 4 роки тому +1

      @@codebasics bless you.

  • @vishalgarg7207
    @vishalgarg7207 2 роки тому

    IT's not the case Dhaval, that ANN is performing badly, if you change the y_train/y_test to categorical and use loss='categorical_crossentropy' it's giving 91% accuracy. I feel CNN will perform certainly better but we may need much higher dataset.

  • @kmedia5759
    @kmedia5759 3 роки тому

    Thank you
    model.evaluate:10000/10000 [==================] - 1s 57us/sample - loss: 0.0275 - accuracy: 0.9910

  • @BhautikaPatel-gg3ij
    @BhautikaPatel-gg3ij 8 місяців тому

    All the way superb!!!! All videos.

  • @biswajitpatra5411
    @biswajitpatra5411 2 роки тому

    @codebasics why flattening again in model when reshape() is used to do it ??

  • @mach9libra
    @mach9libra 3 роки тому +2

    Hello, can you please guide for the K-NN, MLP, CNN, Decision Tree, K-Mean Clustering, regression to solve this CIFAR-10 dataset problem. And compare the accuracies for each of the methodologies used.

  • @aryanjain7819
    @aryanjain7819 7 місяців тому

    how can you get more accuracy? I have messed around with the hyper parameters a lot but I can't seem to find something that gets me a good accuracy (above 80-85)

  • @elma2577
    @elma2577 2 роки тому

    Excellent explanation. 👏

  • @bencyshaji7557
    @bencyshaji7557 2 роки тому

    We should use softmax for multiclass classification right?. But here we used sigmoid? How is it executing?

  • @8shounak
    @8shounak 4 роки тому

    very nicely explained brother. Loved the teaching style and followed the explanation

  • @vishnucruz4529
    @vishnucruz4529 Рік тому

    Could you explain in detail about the reshaping process, on why its necessary ?

  • @suprovodas504
    @suprovodas504 2 роки тому

    Sir I have a problem...when I have to do same code of you in my computer it takes more time in computing .....can you help me please!?

  • @RadhakrishnanBL
    @RadhakrishnanBL 2 роки тому

    Excellent demo, saved my time.

  • @mohammadhosseinjafari5621
    @mohammadhosseinjafari5621 2 роки тому

    really good explanations. thanks for your great help

  • @nastaran1010
    @nastaran1010 10 місяців тому

    please explain that, why you reshape x_train in exercise, and also change input_shape in conv2D

  • @居陳
    @居陳 3 роки тому

    I’m from Taiwan. It’s really helpful

  • @alexandrosiii5676
    @alexandrosiii5676 3 роки тому +1

    I want to use the weights in the hardware upper model in the model. So how do I print out that weight (I'm a beginner)

  • @vallabhahere1564
    @vallabhahere1564 Рік тому

    Sir ,why images are blur can we use our own dataset in same way?

  • @sandhyabansal5264
    @sandhyabansal5264 2 роки тому

    Very lucid explanation

  • @rishanVJrathne
    @rishanVJrathne Рік тому

    Thank you, It is a great tutorial😍 on CNN

  • @EliEpic-gh5qs
    @EliEpic-gh5qs Рік тому

    How can I train my own custom data sets? How do I load in my own data when i want to do multiple classification in different folders.

  • @jeffallenmbaagborebob5869
    @jeffallenmbaagborebob5869 3 роки тому

    You are the best by far

    • @codebasics
      @codebasics  3 роки тому

      I am happy this was helpful to you.

  • @mousumibhaumik1735
    @mousumibhaumik1735 5 місяців тому

    Where is the jupyter notebook code link? Plz share

  • @ajaykundu6446
    @ajaykundu6446 4 роки тому +1

    Sometimes i have thoughts in my mind that is this really happening or is this valuable( i am not judging or not even assuming) as this type of course are paid and with huge amount of money with high demand but how you can give this for freeee ???????
    How sir how ???
    Hats off👍👍👍👍👍and big thanks 👌👌👌
    🙏🙏🙏🙏
    I think this learning won't be stopped ever from you.

    • @codebasics
      @codebasics  4 роки тому +3

      ha ha... that's a nice way of appreciating my work Ajay. Thank you. Well this course is not free, the fee you need to pay is share this with as many as you can (via linkedin, watsapp, facebook groups, quora etc) :)

    • @ajaykundu6446
      @ajaykundu6446 4 роки тому

      @@codebasics will do it definitely
      ✌✌Long live developers👍👍👍

  • @apoorvashekhawat7771
    @apoorvashekhawat7771 3 роки тому

    how does the machine decide the filter and the weights in it to detect a feature??

  • @JapiSandhu
    @JapiSandhu 3 роки тому

    Awesome really like the face to face introduction

  • @ivoroupa2925
    @ivoroupa2925 Рік тому

    Excellent content! Thank you very much.

  • @aashishchaubeyschannel2676
    @aashishchaubeyschannel2676 3 роки тому

    Here 9:13 I believe since this is a multiclass classification, we should be using Softmax instead of sigmoid as the activation function in the last layer. Do you think it should be corrected?

    • @aashishchaubeyschannel2676
      @aashishchaubeyschannel2676 3 роки тому

      Also the way we input the number of neurons in the hidden layer has to be systematically picked. There has to be some organized approach. I know about this klearn library which I found while just looking it up on google. Anyone with more insights please comment. It will be useful! Thanks!

    • @codebasics
      @codebasics  3 роки тому

      Aashish, for multilabel classification sigmoid is preferred whereas for multiclass classification softmax is a popular choice. So you are right that I should have used softmax here. I will update the notebook when I get a chance but if you have time can you give me a pull request?

    • @aashishchaubeyschannel2676
      @aashishchaubeyschannel2676 3 роки тому

      @@codebasics sure, let me do that!

    • @codebasics
      @codebasics  3 роки тому

      @@aashishchaubeyschannel2676 hey Aashish don't worry I just updated the notebook and uploaded it on github. We are all set and thanks for your feedback

  • @jyotiprakashnayak2117
    @jyotiprakashnayak2117 3 роки тому

    Realy sir I like your teaching way

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

    Really nice video...its helped me lot...
    I want you to start Audio, Video processing tutorial also because I like it your teaching skills.

  • @saimaasghar6109
    @saimaasghar6109 Рік тому

    I hope you are doing...I had an assignment of image classification and we were suppose to make a confusion matrix I searched on your channel ...and couldn't find any related to confusion matrix. Please make one on that

  • @samruddhianikhindi7341
    @samruddhianikhindi7341 2 роки тому

    can i use a similar cnn for object recognition? I want to give multiple labels for each image and in the output i would need the bounding boxes and the corresponding predicted label. How to prepare the dataset accordingly if i were to implement a cnn implemented in the video?Or are there any other deep learning models i could build for this application?

  • @snehasneha9290
    @snehasneha9290 4 роки тому +1

    Tq so munch sir for continuing this series amazing content supreb nice explantion

    • @codebasics
      @codebasics  4 роки тому

      You're most welcome sathiya

  • @pawanagrawal7653
    @pawanagrawal7653 3 роки тому

    sir I am really appreciated, the way you teach all the concepts related to CNN, and how to build it,
    sir how can get more accuracy using Keras tuner, please make a video on that.

  • @rnjn291
    @rnjn291 2 роки тому

    Sir, i don't know what wrong happen i follow your video's and write same code on my jupyter notebook it is taking too much time on processing i am using dell, i5, 11 gen laptop, still taking too much time for processing
    Is that cifar10 huge dataset ? What i do, any suggestion ??

  • @siddharthchaudhary2320
    @siddharthchaudhary2320 Рік тому

    Great video thank you for your efforts in creating this , just a small doubt when I replicated the ANN model and ran the code without normalizing the data X_train and test Im getting 100% accuracy in train as well as test where as after normalizing it comes down to 50% and in this video you said then normalization is done to increase the accuracy then how is it happening? (Thank you in for your answer)

  • @khachinboonshup9220
    @khachinboonshup9220 2 роки тому

    How Can I build model by using my own images for multiple calssification , thank you

  • @anirudhsrivastava3530
    @anirudhsrivastava3530 2 роки тому

    Sir Kernel dying at cnn.fit, i cant proceed , please help, the epoch animation doesnt even begin

  • @mehdisoleymani6012
    @mehdisoleymani6012 2 роки тому +1

    Thanks a lot for your great courses, is it possible for you to explain my question? How should we add non-image features to our CNN model (features like cat and dog prices) to our flatten layer? Does the CNN model new added features belong to which input image?

  • @vamsikrishnareddy3146
    @vamsikrishnareddy3146 2 роки тому

    While execution CNN architecture i am getting the kernal appears to have died .it will restart automatically.how can I fix that

  • @XChinaX00
    @XChinaX00 2 роки тому +1

    Thank you for the awesome tutorial. I have one question. Is there a way so I could give a path to one folder and then it would classify images which are in it using this model?

    • @codebasics
      @codebasics  2 роки тому +1

      Yes you can use tensorflow dataset pipeline for that watch TF data pipeline tutorial in this same playlist

    • @XChinaX00
      @XChinaX00 2 роки тому +1

      @@codebasics Thank You, I'll definitely watch it.

  • @priyanshujadon3442
    @priyanshujadon3442 3 роки тому

    Your videos are very good...you explain every line of code...it really helps me a lot to teach ML to my students...your videos are even more useful then other ML videos...👌😊

  • @teamusturbo5071
    @teamusturbo5071 2 роки тому

    i basically need to give an ai images and a numerical values, then i want to predict the numerical value from an image, is this kind of model suitable? what do you suggest?

  • @afiatasnim8848
    @afiatasnim8848 Рік тому

    Sir please pass the output of last Conv2d layer to an LSTM layer.
    Sir how can I add an LSTM layer at last in the model?

  • @sohailali5741
    @sohailali5741 4 роки тому +3

    Thank you so much for detailed tutorial. Can you please make a video on Object detection? Specially Faster RCNN and Yolo models.

  • @santoshkumarmishra441
    @santoshkumarmishra441 4 роки тому

    great job sir.....keep making videos love to watch and learn from your videos

  • @uyghuristan
    @uyghuristan 3 роки тому

    How to choose specific classes in CIFAR-100, if I don't want to use all of the data classes?

  • @abshilo5619
    @abshilo5619 2 місяці тому

    how can we access images from sub directories for example there are images(female(23-24), male(23-24))

  • @moinafatima7990
    @moinafatima7990 3 роки тому +1

    You are doing an amazing work.. I really get intrest in ml after watching your video explanation..
    Sir I'm work on project "image classification using deep neural network" The data set is *CIFAR 10*. Paper on which I'm working it already has 80.2% of accuracy . So by using deep neural network algorithms can I make accuracy beyond 80%

  • @nisharawat1982
    @nisharawat1982 3 роки тому

    Sir, please tell how to input many images other than cifar from pc in jupyter for performing CNN algorithm.

  • @giovannicordova4803
    @giovannicordova4803 2 місяці тому

    So are you executing everything in a GPU?

  • @deepali-e6f
    @deepali-e6f 3 роки тому

    I have one doubt.. like here we are working for colored images , we have 3 channels RGB , so do we need filters also different for all the channels or there will be only 1 filter?

  • @archenemy49
    @archenemy49 3 роки тому

    You are really inspirational and have so much to idolize. Thank you!

  • @pawanagrawal7653
    @pawanagrawal7653 3 роки тому

    sir how to load the dataset if it is not available already in the Keras or TensorFlow library.

  • @tomcat9761
    @tomcat9761 2 роки тому +2

    Nice tutorial sir. Can you create a chatbot using ANN? I would like to know how you will test that. Thanks!