No video :(

Neural Network For Handwritten Digits Classification | Deep Learning Tutorial 7 (Tensorflow2.0)

Подписаться 1,1 млн

Просмотров 410 тыс.

50% 1

In this video we will build our first neural network in tensorflow and python for handwritten digits classification. We will first build a very simple neural network with only input and output layer. After that we will add a hidden layer and check how the performance of our model changes.
🔖 Hashtags 🔖
#handwrittendigitrecognition #tensorflowtutorial #handwritingrecognition #mnisttensorflowtutorial
Do you want to learn technology from me? Check codebasics.io/... for my affordable video courses.
Github link for code in this tutorial: github.com/cod...
Next video: • Activation Functions |...
Previous video: • Pytorch vs Tensorflow ...
Deep learning playlist: • Deep Learning With Ten...
Prerequisites for this series:
1: Python tutorials (first 16 videos): www.youtube.co...
2: Pandas tutorials(first 8 videos): • Pandas Tutorial (Data ...
3: Machine learning playlist (first 16 videos): www.youtube.co...
🌎 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.co...

Опубликовано:

21 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 489

@codebasics 2 года назад

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

@brad8122 Год назад

Hello, why do we have 1875 steps in each epoch in 20:40 ? Where is this 1875 number coming from? It is not the 60000 training data size or nothing else we saw above that line? Thank you so much by the way..,

@Rafian1924 Год назад

Sir.. you deserve to teach the entire world machine learning.. you are an exceptional talent.

@rohithgangarapu4648 5 дней назад

@@brad8122 good question bro same doubt?a brief information about epoch sir?

@skojjalar 2 года назад

Using 1 hidden layer (1000) & relu (remaining parameters untouched), I reached 0.9908 accuracy. Thanks a lot for this course.

@RajaKumar-hg9wl 2 года назад

Is it a evaluation score or training score?

@shijilvr120 2 месяца назад

Training

@phaniauce 4 года назад

Excellent Video.. I always follow the philosophy: First have something working with as much little theory as possible...and then play with parameters that increase curiosity and then dissect the theory..Makes life easy.. than the other way around..

@codebasics 4 года назад

Phani, exactly. I am following exactly same principal. There are many things in this tutorial such as loss, optimizer etc which remains mystery but I wanted to use that first and than unveil the mystery step by step :)

@niveditadas5532 Год назад

Sir, you are a born teacher. The way you represent complex topics in simpler way is truly amazing. I really admire your hard work for designing such wonderful courses. Thank you sir.

@iva1389 3 года назад

This is the most elegant solution of Hand-Written digits MNIST problem in the whole Internet! Thank you. I've learned so much! You have my sub and much respect!

@codebasics 3 года назад

Glad it was helpful!

@AlonAvramson 3 года назад

from the Optimizers ['SGD','RMSprop','Adam','Adadelta','Adagrad','Adamax','Nadam','Ftrl'] with 5 Ephocs, Adamax got the highest score on Test samples. Ftrl got the lowest score.

@amineamaach4450 2 года назад

Just love the way you're making things pretty simple. A big shout-out to you.

@drmanishmadhavatripathi6798 4 года назад

I become fan of you as your style of explaining the things. You explained the complex topics in such a lucid manner that audience could not be distracted for a single while.

@codebasics 4 года назад

Thanks Dr Manish 😊👍

@Sazia_Cooking_Creativity 3 года назад

have you understood clearly?

@aditiparetkar2862 2 года назад

Thank you so much for the great explanation! By using relu in the hidden layer and softmax in the output layer , was able to achieve an accuracy of 99%

@eclairs0909 2 года назад

can you explain a little more how to use it?? or refer me some videos

@amaningoma4831 Год назад

Your course is more than explicit. Thank you so much for giving such efforts to share knowledge

@shoaibsaifi9806 3 года назад

This is the only lecture where I got a really great idea about neural network. I have seen many lectures no one explain each thing like you did. They just make the neural network

@nikhilkashyap1771 2 года назад

Best Deep Learning Course I found On RU-vid, I mean you the gave the content that I was looking for.

@rkag5811 4 года назад

Well lectured..Have to listen twice to understand this session accordingto my perception..

@cooleo2350 Год назад

This is phenomenal, thank you so much! Truly a brilliant teacher. Been looking for a while, and this video summed up so much. You sir earned yourself a subscriber, and perhaps many more as I share your channel. Thank you for taking the time to do this.

@user-pb6pt4rw1l 7 месяцев назад

What an amazing tutorial! Did a machine learning for the first time with so much clarity! Thank you so much sir

@mithlesh0singh 3 года назад

love the have you figure out the issue of accuracy, That makes a huge difference.

@arnavg7789 2 года назад

THANK YOU ,LOVE FROM INDIA .... GAYATRI , GAURAV (LOOSERS)

@sand9282 Год назад

Even though you have mentioned 3Blue1brown over here you have explained Neural Network with much concrete example here. Your examples are very easy to visualise and understand for beginners and in some cases it's even better than the great AndrewNG himself. Being from the field of education I see all the qualities of a great teacher in you, keep up the good work and thank you for such a good tutorial for free.

@codebasics Год назад

🙏🙏🙏 thanks and yes I am continuing it and even left my 9 to 6 job to do this full time

@parthshah6463 3 года назад

You're god for the Beginner !!! The way you explain is way different than anyone else... SUPER AMAZING... HIGHLY RECOMMENDED

@codebasics 3 года назад

👍😊

@anirbanc88 Год назад

exhilarating to see the inner workings of deep learning! thank you sir

@rubaitrahman4449 2 года назад

this is the easiest and a must watch video to learn deep learning basics. I will be always grateful to you sir

@theodoregiannilias5140 2 года назад

God damn man you're amazing, every doubt that I had during my education degree you solved it. Keep up the good work man :D

@PRABALBAISHYA-xi1fd Месяц назад

Awesome tutorial ! I just increased the iterations to 10 and the accuracy turned out to be 99.55% !

@amitagrawal9308 3 года назад

Hi, For prediction of single image, you need to reshape to (1,784) i.e. X_test_flattened[0].reshape(1, 784).

@Essentialenglishwords-ii7ek Год назад

i always get the score 0 could you explain that please

@manishgautam134 4 года назад

accuracy = 99.25% with code below, model = keras.Sequential([ keras.layers.Flatten(input_shape=(28, 28)), keras.layers.Dense(100,activation='relu'), keras.layers.Dense(10,activation='sigmoid') ]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(x_train,y_train,epochs=10)

@adamalasaibalajireddy4688 2 года назад

Sir can you please send me source codes files if available

@pasangsherpa6594 2 года назад

accuracy= 99.92% with code below model = keras.Sequential([ keras.layers.Flatten(input_shape=(28, 28)), keras.layers.Dense(100,activation='relu'), keras.layers.Dense(50,activation='sigmoid'), keras.layers.Dense(10,activation='sigmoid') ]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(X_train,y_train,epochs=70)

@abeerzidan4349 Год назад

Dear Sir... thanks a lot for your clever and robust teaching ... please can i get presentation of this course ...

@abhishekkhare6175 3 года назад

Thank's a lot for making this wonderful playlist for Deep Learning.

@sjatin1842 4 года назад

This video is awesome. I got 99.3 % accuracy when I changed epochs to 10 and out of curiosity I tried it for 20, accuracy is 99.8 now, finally for epochs = 30 accuracy is 99.94. I will try changing other parameters too.

@codebasics 3 года назад

Good job Jatin, that’s a pretty good score. Thanks for working on the exercise

@saideekshith3295 2 года назад

are u trying some sort of prameter tuning ?

@dutta.alankar 4 года назад

Great introductory video! Thanks a lot.

@jaganinfo 4 года назад

student : What is tensor? codebasics: in the general case, an array of numbers arranged on a regular grid with a variable number of axes is know as a tensor

@akshaypatil8155 Год назад

You explain all of us like we are 5 yr old. This is very hard recipe to master. Thank you for everything. Please do not delete this videos from youtube ever. Stay healthy and stay happy. Thoda weight badao yaar. And please make a video with your manager which can guide us about inter company tarnsfers. Their are many who do not have finances to study in the US but we want to experience working their. This is my humble request. Thank u for ur videos

@SingingWithAdi Год назад

I have been following you from the ML Playlist , amazing content !! Thank you so much sir !

@pratik19901 3 года назад

Hi dhaval, You have explained the concept in very simple manner. Could you please share all ppts of deep learning series? It will be a great help for all learners.

@zeeshansadiq6150 2 года назад

it needs time to develop, so wait for the time

@nkanyisosigwaza 6 месяцев назад

You are an absolutely amazing teacher! Thank you for the great content

@jainamshroff4998 2 года назад

Since we have categorical predictions to be made, shouldn't we use softmax as an activation function in the output layer to get best possible performance?

@ousmanealamakaba3135 2 года назад

i think it depends on your choice based on activation function

@mdmonzurmorshed3557 2 года назад

Its a great presentation !!! I appreciate your teaching method.

@rajkalashtiwari 2 года назад

This is awesome I got accuracy of 99.52%

@RajaKumar-hg9wl 2 года назад

Is it a evaluation score or training score?

@sayedikramulhaqbanuree6923 5 месяцев назад

Amazing, I am completely new in the field but you explain in such a good manner. 10+ out of 10 stars. I have done exercise with a small dataset all the samples are about 1797: from sklearn.datasets import load_digits from sklearn.model_selection import train_test_split digits = load_digits() X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target, test_size=0.2, random_state=42) and then: model = keras.Sequential([ keras.layers.Dense(100, activation='relu'), keras.layers.Dense(10, activation='sigmoid') ]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(X_train, y_train, epochs=20) i have just increased number of epochs which given me a very good result of accuracy once again thank you from #Afghanistan

@dantedt3931 5 месяцев назад

One of the best tutorials.

@zerocoding6420 3 года назад

thank you for wonderfull gift. i'm a NOOB programmer just starting to pythoning again. to predict single data training input shape must be (,784) you can either .reshape(-1,784) it or X_test_flattern[[0]]

@nirajasanghai9707 Год назад

your videos are very helpful. It clears all doubts about machine learning and deep learning. can you please make a video on Deep learning using PyTorch?

@mithunpathak9558 3 года назад

you are the best teacher in data science

@user-vc5kp1tl8r 2 года назад

you are SUPER , please continue ,also if you can explain deep reinforcement learning , i will be so grateful !!

@phaniauce 4 года назад

result of playing with various optimizers: 0.9912 : adam 0.9886 : rmsprop 0.9488: SGD 0.7354: adadelta 0.9208 : adagrad 0.9757: adamax 0.9921: nadam 0.7387 :Ftrl I would begin the play with losses tomorrow. Looks like atleast CategoricalCrossentropy expects y in one hot representation. After using dummies, got accuracy of 0.9309 for 10 epochs. Poisson's class gave 0.9181. binary_crossentropy gave 0.9212

@rupaksinghchauhan7235 Месяц назад

Very insightful and clearly explained, thanks.

@nazlerdemir8142 11 месяцев назад

I wish I started to learn neural network with your tutorials. thank you

@navyasri5077 3 года назад

I saw many courses on neural networks even MIT lecture but nothing seemed understandable. Thank you so much you helped me in gaining a idea. And proved Indian teachers are always best and in case of studies India deserves best in the world.

@codebasics 3 года назад

You are most welcome, I am happy this was helpful to you.

@navyasri5077 3 года назад

@@codebasics 🤩🤗

@navyasri5077 3 года назад

@@codebasics sir we want more projects on AI. Pls consider sir

@hstrinzel 2 месяца назад

Great teaching video! WELL EXPLAINED! Best one I have found so far.

@ChanceMinus 8 месяцев назад

Brilliant! This was great. Thank you.

@070_rahulbhataniya7 2 года назад

you are the best tutor for Deep Learning

@ECX0x100h 3 года назад

Awesome and clearly explained! Love it!

@nikitasharma2757 3 года назад

Amazingly explained!! Appreciate your work sir. Big fan!!

@wrenchfusion 3 года назад

My suggestion to grasp this video concept is first to watch the whole video with patience then the second time watch again and apply the mentioned concepts line by line. Believe me, you are not going to forget what you have just learned.

@codebasics 3 года назад

That's a good tip Shamir

@vivekpatil681 4 года назад

Again waiting for next ❤️ I love your way of explains something.

@adityashining Год назад

Dhaval, does the trained model expect that after deploying it to real life situation, I should provide the images of handwritten text (say by myself) in a specific size of file, format of file , color of handwritten text etc ? Or can it be different from mnist database ?

@udayashangar 4 года назад

Hey Dhaval, you made DataScience easy for me by all these wonderful playlist!! Thank you so much for all your efforts. Got accuracy: 0.1059 for loss = 'mean_squared_error'.

@slayer_dan 3 года назад

MSE is used for Regression problems not for Classification

@TheFadime123 3 года назад

@@slayer_dan don't be that guy

@slayer_dan 3 года назад

@@TheFadime123 sorry, i didn't get u

@raghuram6382 2 года назад

Hello sir, thanks for beautiful explanation and I just got one doubt, why haven't you used standard scaler or Minmax kind instead of scaling it down by dividing 255?

@argha-qi5hf 2 года назад

He used min max scaling only. Notice that x_min = 0 and x_max = 255. Just omit the 0s. scaled_x = (x - 0)/(255 - 0) = x/255

@bapaimallik5173 3 года назад

Crisp, Clear, Uncluttered. I have a couple of online certificates (AI from Stanford and IBM data scientist professional). I have been looking for stuff on neural networks coding using Tensorflow. I tried a few lectures on youtube and left less than halfway through. This looks promising. Thanks Dhaval . I hope to complete the series and be able to do DNN stuff on my own the way I have been able to tackle other machine learning algorithms. Cheers

@codebasics 3 года назад

Bapai, thanks for the comment and I wish you all the best 😌👍

@raufodilov2203 3 года назад

greatest teaching style. every detail comes in right position with actual meaning

@codebasics 3 года назад

Rauf I am glad you liked it

@aryanjaswal8370 Год назад

My model accuracy is 0.9888 thanku so much sir . i am very happy 😃😃😃

@Microraptorofmillinea 2 года назад

really i have tried so many tutorials from today morning but this is like butter smooth thank you dhaval for such a great lectures and with all this knowledge you have a good hair with very little of this i lost 40%... JK really awsome thank you very much.

@tobewanad Год назад

I would legit buy a "CTRL+C CTRL+V is your friend" t-shirt after hearing it throughout your videos lol

@surarun 3 года назад

very clear explanation.Your way of making complex things look simple and elucid serves as role model for each of us to be. Thank you so much sir

@codebasics 3 года назад

Glad it was helpful!

@ganpatibappamorya9612 Год назад

Explain in very efficient manner. Very Impressive

@sohaibshah1771 11 месяцев назад

Sir in this video your practical example is different then our use case insurance. Appreciate you r effort

@mayanktripathi4u 4 года назад

Hi Sir, your videos are so insightful and well managed. Thanks for sharing this.

@codebasics 4 года назад

Glad you liked it Mayank

@tejendrasaraswat6766 4 года назад

Sir Keep it up,eagerly waiting for next video. Thank You...😊.

@saurabhtalele1537 3 года назад

Best teacher is here!!!!!

@codebasics 3 года назад

Thanks saurabh

@ahsanfarooq210 3 года назад

i got the accuracy of 98.37 on training data and 97.32 on the test data and on the graph of truth vs predicted (tha we made using sea born library) the highest value other than diagonals was 19

@shivav7379 2 года назад

Hello Sir, this is amazing code walk through with very very good explanation.

@stepanlebedev8790 Год назад

acuraccy 99.51% - epochs: 8, optimizer: Adam, loss: spacse-categorical_crossentropy, hidden layer neurons number: 300

@anmolkhurana490 2 месяца назад

I got best scores (0.98) from Optimizers- rmsprop, ndam, adam Metrics- sparse categorical accuracy, accuracy

@rabiafyz9952 2 года назад

Thank you so much for making such a simple explanation. I cleared all my doubts that I had during my Education degree.

@codebasics 2 года назад

Glad it was helpful!

@wongsimon2387 Месяц назад

Awesome！Thank you so much.

@poongothai23 Год назад

Great explanation...

@aureliussimon1012 Год назад

Your videos are fantastic, I really appreciate the time you have taken to explain complex concepts so simply. Thank you very much 🙏🏼

@sumit121285 3 года назад

you are simply superb sir.... thankyou so much for this series.....

@raom2127 2 года назад

Sir your way of explanation is amazing Iam benefited from this your videos are good we appreciate your patience and way of explanation is beautiful.

@shubhamkumar-nw1ui 2 года назад

Sir has subscription of choochoo's story and golgappa girl 😂😂...BTW awesome tutorial sir..many many thanks

@RajaKumar-hg9wl 2 года назад

Thanks for the wonderful video. Exercise: 1000 neurons in hidden layer, 10 epochs & tanh activation; evaluation score is 0.9790999889373779 1000 neurons in hidden layer no other change; evaluation score is 0.9793999791145325

@RajaKumar-hg9wl 2 года назад

Further exercise: 200 neurons in hidden layer & 10 epochs Evaluation score: 0.9807000160217285

@codebasics 2 года назад

Good job raja, that’s a pretty good score. Thanks for working on the exercise

@shrinivaskamath563 2 года назад

Excellent video Great Explanation. very grateful for this

@minTwin 4 года назад

Your videos is a gold mine of knowledge.

@codebasics 4 года назад

😊👍

@hey.its.saunak Год назад

bro i got 99.04% accuracy thanks man😀😀👍

@maryzakiandourrugrats4671 11 месяцев назад

you have an amazing cadence to your speech.

@semiuodunayoadebayo6299 Год назад

Great learning. Can’t thank you enough….great job

@riteshnimje3302 4 года назад

If we use activation function 'softplus' and 'sigmoid' and optimizer is 'nadam' is also giving good result model=keras.Sequential([ keras.layers.Flatten(input_shape=(28,28)), keras.layers.Dense(300,activation='softplus'), keras.layers.Dense(10,activation='sigmoid') ]) model.compile( optimizer='nadam', loss='sparse_categorical_crossentropy', metrics=['accuracy'] ) model.fit(X_train_flattend,y_train,epochs=10)

@codebasics 4 года назад

What accuracy did you get here?

@riteshnimje3302 4 года назад

98.47 percent 😊

@akbarmajidi3934 10 месяцев назад

Amazing!

@iaconst4.0 5 месяцев назад

EN ESPAÑOL: GRACIAS POR EL VALIOSO APORTE!

@meherunnesa4622 2 года назад

You are the best teacher❤️

@shaiksuleman3191 4 года назад

Simply Super B.Teaching should be in the blood.Water has no shape u r teaching have no more questions asked.Your setting the trend how to teach. There are So many videos are there in you tube simply paste the code and explain.Your videos is like everest

@codebasics 4 года назад

Thanks for your great complement Shaik. Comments like this gives me fuel to contribute more :)

@utkarshgoyal6742 4 года назад

Hi, your videos are so insightful. I would like to request if you could include or do a video on kerasclassifier? Thank you so much!

@manishkc3852 4 года назад

Very well planned and simply explained tutorial. But I have a question, I have read that for multi-class classification problem, softmax activation is good, why did you use sigmoid activation here? Thanks.

@preetham4974 4 года назад

Yet another awsome tutorial sir.Waiting for more out of this playlist.And i have a doubt,If i have my own hand written digit on a paper then how can test with this ? should i crop the image and predict it ? thank you

@codebasics 4 года назад

Yes you need the crop the image and then predict

@yannikhauser383 2 года назад

Very very good explanations !! can follow very good...

@ake_bangkok9312 Год назад

very good teacher, you are the man.

@sai.boyina 3 года назад

Nice to see lot of good stuff on youtube. Wondering why can't everyone explain the way you explain. It seems I have finally landed at right place. By the way, how that pic become 7x 7 grid? Same for all image or is there any math behind it?

@YASHOVARDHANMALU Год назад

Firstly, very helpful tutorial. Finally felt relieved after finding this. Now, whenever I run the model cell, my kernel restarts automatically, why does it happen and how do I fix it?

@himanshugarg7113 4 года назад

Hello, I was implementing handwritten digit code in macOS. Every time I ran the model code, I was getting an error 'Kernel has died. It will restart automatically'. However, below snippet resolved my problem import os os.environ['KMP_DUPLICATE_LIB_OK']='True' Can someone please explain this issue?