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

In this video we will do small image classification using CIFAR10 dataset in tensorflow. We will use convolutional neural network for this image classification problem. First we will train a model using simple artificial neural network and then check how the performance looks like and then we will train a CNN and see how the model accuracy improves. This tutorial will help you understand why CNN is preferred over ANN for image classification.
Code: github.com/codebasics/deep-le...
Exercise: Scroll to the very end of above notebook. You will find exercise description and solution link
Do you want to learn technology from me? Check codebasics.io/?... for my affordable video courses.
Deep learning playlist: • Deep Learning With Ten...
Machine learning playlist : kzbin.info?list...
#cnn #cnnimageclassification #imageclassificationpython #cnnmodel #deeplearning #tensorflowimageclassification #pythonimageclassification
🌎 My Website For Video Courses: codebasics.io/?...
Need help building software or data analytics and AI solutions? My company www.atliq.com/ can help. Click on the Contact button on that website.
#️⃣ Social Media #️⃣
🔗 Discord: / discord
📸 Dhaval's Personal Instagram: / dhavalsays
📸 Codebasics Instagram: / codebasicshub
🔊 Facebook: / codebasicshub
📱 Twitter: / codebasicshub
📝 Linkedin (Personal): / dhavalsays
📝 Linkedin (Codebasics): / codebasics
🔗 Patreon: www.patreon.com/codebasics?fa...
DISCLAIMER: All opinions expressed in this video are of my own and not that of my employers'.

[@codebasics]

Do you want to learn technology from me? Check codebasics.io/ for my affordable video courses.

[@nagababuyerramsetti8715]

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]

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

[@codebasics]

Thanks Luciano for your kind words

[@nilanjanap]

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

[@albertoramos9586]

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

[@rb4754]

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!!!!!!!!!!!!!!!!💥💫💢

[@Manojrohtela]

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

[@ChessLynx]

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]

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

[@bumjunoh6233]

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

[@codebasics]

🤗🤗🙏

[@SoulFrmTitanic]

We Asians are for us ❤

[@tesfitgi7579]

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

[@mayankpatil7303]

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

[@bhaskargg6018]

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

[@rishavbhattacharjee7182]

Exciting Times!! May this series long continue😁

[@codebasics]

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

[@michelletan4249]

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

[@Lina-cy9ln]

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

[@codebasics]

Zeenat, thanks for you kind words

[@sabrinazahir01]

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

[@codebasics]

Happy to hear that sabrina!

[@anishachakravorty1395]

@@codebasics lol lo

[@anishachakravorty1395]

Plpp

[@anishachakravorty1395]

Pl

[@anishachakravorty1395]

@@codebasics pl

[@santoshkumarmishra441]

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

[@sandiproy330]

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

[@archenemy49]

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

[@codebasics]

Glad it was helpful!

[@prachidoshi9082]

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

[@pa5119]

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

[@codebasics]

Glad to hear that

[@techguyz839]

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

[@RadhakrishnanBL]

Excellent demo, saved my time.

[@ivoroupa2925]

Excellent content! Thank you very much.

[@saadmuhammad4890]

Thank you so much! Your tutorials are very helpful

[@codebasics]

Glad you like them!

[@yoverale]

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

[@user-ry5ks3hg6y]

Thank you a lot! You helped me with my project!

[@codebasics]

Glad it was helpful!

[@BhautikaPatel-gg3ij]

All the way superb!!!! All videos.

[@lindadelalifiasam5878]

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]

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]

@@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.

[@zainulabideen_1]

I love your way of teaching

[@mohammadhosseinjafari5621]

really good explanations. thanks for your great help

[@jogadornumerozero3257]

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

[@8shounak]

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

[@codebasics]

😊😊👍

[@sankistudio1771]

Thank you sir, excellent explanation

[@priyanshujadon3442]

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...👌😊

[@codebasics]

Glad you like them!

[@khanwali9672]

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]

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

[@khanwali9672]

@@codebasics bless you.

[@elma2577]

Excellent explanation. 👏

[@gauravshah8554]

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

[@JapiSandhu]

Awesome really like the face to face introduction

[@codebasics]

Glad you like it

[@rishanVJrathne]

Thank you, It is a great tutorial😍 on CNN

[@snehasneha9290]

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

[@codebasics]

You're most welcome sathiya

[@maxgriffiths6968]

Excellent video. Thank you

[@codebasics]

I am happy this was helpful to you.

[@sukumarroychowdhury4122]

Mr. Modi (Mr. Patel) is one side and rest Opposition (Data Science KZbinr) 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..

[@AdityPai]

Thank you for the efforts you put in all these vedios, it is giving us a clear image of what is happening in each part. Thanks alot

[@sohailali5741]

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

[@shuaibalghazali3405]

Thank you very much sir for this 😊

[@sanooosai]

great sir thank you

[@payamtorna2]

very nice videos thank you so much bro :)

[@samirkouiderbouabdallah9392]

thank you very much sir

[@sandhyabansal5264]

Very lucid explanation

[@mainuddinali9561]

GREAT SIR

[@mekdesmekonnen2242]

Brilliant!

[@pawanagrawal7653]

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.

[@RanjitSingh-rq1qx]

Tq u 💯 much sir, this video is very helpful.😍❤️🌹👍🥰🇮🇳

[@jeffallenmbaagborebob5869]

You are the best by far

[@codebasics]

I am happy this was helpful to you.

[@talesbyreza]

awesome

[@jyotiprakashnayak2117]

Realy sir I like your teaching way

[@codebasics]

Thanks and welcome

[@notavailable3331]

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

[@codebasics]

Great job

[@rizabekkorabay108]

Can you share with your code?

[@user-xy5sd8my2e]

I’m from Taiwan. It’s really helpful

[@codebasics]

Glad it was helpful!

[@amazighkab9904]

amazing

[@shreyasb.s3819]

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

[@codebasics]

Glad it was helpful!

[@AHMADKELIX]

permission to learn sir. thanks you

[@bassemessam3002]

Thank you so much for this great tutorial. It is really helpful. I have a question, you used 'sparse crossentropy' in prediction and it's supposed to return the class number but the output of y_pred is an array of the probability of each class, and to get the predicted class we used argmax function to get the index of maximum value?

[@vaishalibalaji886]

Hello Bassem, "Sparse categorical cross entropy" is the loss function to be used when the actual output Y in the dataset is not in the one hot encoded format. And, sir has used "softmax" as the final activation function in the code showed in the video. It is because of this function that the final output, y_pred is an array of the probability of each class. Hence, finally in order to get the index position of the maximum probability value, which is typically the output class predicted by the CNN model, sir has used the np.argmax function.

[@khalilturki8187]

Great Work! keep it up!

[@codebasics]

Thanks a lot!

[@aloksheth7477]

Thanks for nice explanation. Easy to understand the concepts. Can you make video for region CNN and faster R CNN?

[@moinafatima7990]

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%

[@mehdisoleymani6012]

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?

[@rulaalsamarie3607]

Thank you 🙏

[@codebasics]

Glad it was helpful!

[@debojyotisinha5031]

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

[@codebasics]

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

[@daggerdudes9211]

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

[@codebasics]

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

[@a57_nikeshsinghajaysinghba89]

Can you suggest some good final year project ideas related to image classification. I'll be grateful

[@tomcat9761]

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

[@sergiochavezlazo5362]

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

[@umer_c0des330]

Why results change alot?

[@mrkrupeshpatel]

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

[@mach9libra]

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.

[@zaindurani8168]

No one in universe can teach like this

[@codebasics]

Thanks zain for your kind words

[@alexandrosiii5676]

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)

[@shaantanukulkarni5668]

nice!!!

[@codebasics]

Thank you! Cheers!

[@nikhildaram3354]

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

[@fitnessismypassion]

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.

[@samruddhianikhindi7341]

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?

[@kmedia5759]

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

[@tonyennis1787]

Great video. I was hoping you'd visualize the CNN kernels so we could see what they looked like. You specified 32 of them. Does this mean that all 32 are used in every image, and thus are meaningful in every case? that is, you won't have one what has a koala's eyes because the input images also include, say, rocks, buildings, and GPU cards?

[@ajaykundu6446]

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]

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]

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

[@vishnucruz4529]

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

[@mukthaaa3506]

Sir, can you please show us how to plot the accuracy curve for the cnn model

[@biswajitpatra5411]

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

[@mrCetus]

Sir thanks for an amazing video. I am having a little trouble visualising the numpy array and how the pixel values are stored to eventually form the image, any video link you'd suggest for that please?

[@sethlawson2389]

Hi, an image is represented by a numpy vector of shape 3 x Height x Width. The 3 is because color is represented by red, green, and blue intensity values. So each position in an array represents the intensity of one of three colors at a specified height and width location in the image. Here is a visual representation of a vectorized image being convolved over. i.stack.imgur.com/2ezvr.gif Fun to note that this is the same information that human brains work with. Cone cells in the eye are optimized to one of three regions in the electromagnetic spectrum corresponding to RGB, which activate impulses based on the intensity of that wavelength of light. Though the human brain also has to do some transformations on the data, namely flipping and reflecting it, since the human eye works like a pinhole camera.

[@keshavgoyal3106]

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

[@sanskartewatia4320]

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

[@XChinaX00]

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]

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

[@XChinaX00]

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

[@dariovicenzo8139]

Hi beautiful video! I have some special image in Black and white to be classified. I have two questions: 1. Do you think it is better to colorize them in order to improve the predicion? 2. If yes at the first question, what is a suitable technique to add colors? Thanks a lot.

[@prvs2004]

Not necessary as long as your test or prediction is also B&W

[@deepaliaggarwal6429]

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?

[@ahmedhelal920]

Hi sir , based on what we can choose 3000 hidden units and 1000 hidden units on our project ?

[@mahammadaliyev8345]

I love your lectures Sir ! Thank you for your efforts and works. I have question , how did you Get accuracy ~90% with 10 epochs while i get hardly 10% with 25+ epochs?

[@kunalrastogi6530]

facing same problem

[@a57_nikeshsinghajaysinghba89]

Hey your content is great!! I just wanted to make a request that datasets of image classification are generally folder based like for example when we download a dataset from kaggle, so I request you to please share a video or any good resource to read the images from folders and use it like we have used it in this video for image classification. Thank you!

[@codebasics]

yes I have covered that in my sports celebrity classification project. Check it out. it is an entire playlist but the thing that you mentioned is covered in one of the videos.

[@a57_nikeshsinghajaysinghba89]

@@codebasics Thank you very much!!

[@pradyumsingh2638]

okay i got the procedure thanks, but what to do if we want to provide our own datasets

[@kirankumarb2190]

Sir, one small doubt.. you said that we can use categorical_crossentropy when there is one hot encoded output pattern.. but in this example we used sparse_categorical_crossentropy , but still we used 10 output neurons and output was considered as max of that...which is like one hot encoding only right..

[@siddharthsingh2369]

The 10 output neurons gives the probability of each true possibility and its value will be ranging in 0 - 1 and in order to get the index position of the maximum probability value, which is typically the output class predicted by the CNN model, we used the np.argmax function. i got an answer from stackExchange - If your Yi's are one-hot encoded, use categorical_crossentropy. Examples (for a 3-class classification): [1,0,0] , [0,1,0], [0,0,1] But if your Yi's are integers, use sparse_categorical_crossentropy. Examples for above 3-class classification problem: [1] , [2], [3]. For complete explanation check this - stats.stackexchange.com/questions/326065/cross-entropy-vs-sparse-cross-entropy-when-to-use-one-over-the-other

[@siddharthchaudhary2320]

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)

[@ravitrivedi4208]

if anyone is getting "ssl certificate verification failed" error then add following lines before it import ssl ssl._create_default_https_context = ssl._create_unverified_context

[@wiekiangh.2542]

great tutorial and I enjoyed it! However, what if I want to classify new images which not in CIFAR dataset, for an instance, I want to classify a butterfly breed. Any suggestion?

[@codebasics]

For that you need to add images of butter fly breed in this dataset and train the model again.

[@wiekiangh.2542]

@@codebasics Thanks for your reply. Can you give me some clue or code on how to add the new images into the existing dataset to re-train the model with CNN? Do I need to annotate those images if those are not in the cifar, imagenet, coco and google open images? I see that in your last video mentioned about these data source, however, I didn't see any info how to add and train custom dataset.

[@bencyshaji7557]

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