TensorFlow 2.0 Crash Course

Learn how to use TensorFlow 2.0 in this crash course for beginners. This course will demonstrate how to create neural networks with Python and TensorFlow 2.0.
If you want a more comprehensive TensorFlow 2.0 course, check out this 7 hour course: • TensorFlow 2.0 Complet...
🎥 Course created by Tech with Tim. Check out his KZbin channel: / @techwithtim
⭐️ Course Contents ⭐️
⌨️ (0:00:00) What is a Neural Network?
⌨️ (0:26:34) How to load & look at data
⌨️ (0:39:38) How to create a model
⌨️ (0:56:48) How to use the model to make predictions
⌨️ (1:07:11) Text Classification (part 1)
⌨️ (1:28:37) What is an Embedding Layer? Text Classification (part 2)
⌨️ (1:42:30) How to train the model - Text Classification (part 3)
⌨️ (1:52:35) How to saving & loading models - Text Classification (part 4)
⌨️ (2:07:09) How to install TensorFlow GPU on Linux
--
Learn to code for free and get a developer job: www.freecodecamp.org
Read hundreds of articles on programming: www.freecodecamp.org/news

[@freecodecamp]

If you want to learn even more about TensorFlow, check out this 7-hour course: kzbin.info/www/bejne/qoG8m2ace696oM0

[@stronggun2014]

Which one is better? Should I watch this first or the other one?

[@saurabhs4743]

@@stronggun2014 longer one has machine learning, deep learning, and reinforcement learning video parts.. however this one is only deep learning with videos on image classification and text classification

[@pythonprogrammer8989]

am i the only one getting an error?

[@pythonprogrammer8989]

is anyone getting this error? Failed to load the native TensorFlow runtime.

[@ibrahimrefai1]

does the course demonstrate how to use gpus?

[@TechWithTim]

Hope you guys liked it! If you want more machine learning and AI tutorials check out my channel 🔥

[@TheAnswerworld-et6ze]

Thank you for this presentation Tim. God bless you.

[@kamalpandey7177]

Already subscribed. Could you please reply to my question. I am beginner in this.

[@xerowon3490]

Big fan of your videos and I was so excited to see you doing this course

[@toluwaniamos7681]

Thank you Tim!!!

[@DJBremen]

Thank you for this Tim!

[@benhudelson]

Hey Tim, great content so far. I would recommend in future videos to reduce the point size on your pen so that your handwriting is a little clearer. Thanks for putting this together. Very well constructed explanations.

[@colinrey4589]

Best beginner tutorial on entire KZbin!! Thank you so much! Very good explained.

[@neelanjanmanna6292]

Great tutorial so far, just a quick correction that the sigmoid activation function ranges between 0 and 1. What you had drawn was actually the tanh activation function, that ranges between -1 and 1. Cheers!

[@nixlq]

Correct, I just came to write that

[@hemanthkotagiri8865]

Oh man, Thank you so much, Tim! I also follow your channel!

[@jamiecybersecurity]

(0:00:00) What is a Neural Network? (0:26:34) How to load & look at data (0:39:38) How to create a model (0:56:48) How to use the model to make predictions (1:07:11) Text Classification (part 1) (1:28:37) What is an Embedding Layer? Text Classification (part 2) (1:42:30) How to train the model - Text Classification (part 3) (1:52:35) How to saving & loading models - Text Classification (part 4) (2:07:09) How to install TensorFlow GPU on Linux

[@jordanmoore4104]

I'm excited to learn this with Tim! He taught me Java thoroughly!

[@azizulhakim1534]

He became my favorite by saying he doesn't know what Verbose is.

[@cplusplusgoddess3359]

that comment gave me less confidence in him

[@johnkeating7170]

I spent 3days to watch and figure out the basic theory behind this tutorial, thank you very much~!

[@joseortiz_io]

Oooo awesome man! I literally just saw a video from your main channel I'm assuming! Awesome content my friend. Im trying to familiarize myself with the AI community on KZbin. Have a good one!😃👍

[@saikumarreddyatluri3332]

Thanks for this series we need more series of videos on tensorflow 2.0

[@just-another-life]

1:47:14 - The verbose parameter is a simple debugging tool which prints the status of epochs while the model is being trained. In the case, verbose=1 displays the epoch number with a little decoration. Please feel free to correct if any and add more info.

[@dassad9777]

your're right. You can use verbose to track model's progress, if you dont want to see it's learning process you can switch it off. verbose = 0 - you see absolute no progress, just when training is finished program will go on, verbose = 2 - you'll see which epoch is already trained, verbose = 1 you'll see number of epoch (for example Epoch 11/100), progress bar in %, and some parameters (loss function, and accuracy).

[@jermaineken7772]

Was using google collab to implement this tutorial. Thank you for the great content.

[@2rfg949]

Thanks for your video. I really appreciate the simplicity of your explanations and your humility is refreshing! Will watch more.

[@ilegallive999]

1:19:30 He prints the codes from the train_data[0], but presents the string results from test_data[0]. So there's a mismatch. Hopefully, it's helpful.

[@17Koche]

This tutorial is well put together. I was looking to learn more about neural nets and TensorFlow. this is perfect for a beginner in the field.

[@gaddafim7959]

⭐ course contents ⭐ (0:00:00) what is a Neural Network? (0:26:34) Loading & Looking at Data (0:39:38) creating a model (0:56:48) using the model to make predictions (1:07:11) Text Classification p1 (1:28:37) what is an Embedding Layer? Text Classification P2 (1:42:30) Training the model - Text classification P3 (1:52:35) saving & Loading Models - Text Classification 4 (2:07:09) How to install Tensorflow GPU on Linux -- Learn to code for free and get a developer job:

[@aZaamBie135]

Thank you!!

[@maoryatskan6346]

That's helpful tnx

[@PesTech1]

@@feridakifzade9070mmmmm. : Hmmmm

[@calibr0636]

as if it wasn't already in the description

[@azchen6511]

Well, ppl can click on the timestamps here, so I think it is kind of useful.

[@piccamix9345]

thanks so much dawg, helped me out with my AI assignment, you da man!

[@SkyFly19853]

Thank you sooooo much for this tutorial!!!!!

[@toluwaniamos7681]

Thank you so much Tim! As a beginner into tensorflow and machine learning, you were so excellent and helped me grasp the basic tips! Thank you again!! 😀

[@erniea5843]

Very well done tutorial. Nice intro to TF and Neural Networks with some quick and easy to follow examples. So much to learn!

[@cam41527]

Somebody has probably already answered this but "verbose" means descriptive. If your were to enable the verbose property on an object it would normally give a lot more details about something, whether that is debug information or just printing output. Also Great Video Tim! I am a big fan of the tutorials on cutting edge technology as they are difficult to find elsewhere :) Keep up the great work

[@raiden140188]

By far (!) the best video i have found for beginners in neural networks. And i viewed a lot. Love it! What killed me is the writing of numbers from the bottom to the top. Never seen writing numbers that way.

[@jamesh4129]

Awesome video. Thank you. Now I feel ready to dive in with a book I picked up

[@jamesparsons9068]

Great explanation of the activation function.

[@merlinmystique]

thank you very much man, I'm a philosophy student who's trying to find a way in understing AI, that's hard but videos like this are a HUGE help, thank you very much, keep it up

[@BenjaSerra]

for those who are having problem with the predict method, replace it with predict_classes: model.predict_classes([test_review])

[@ruvikperera8813]

Bro you saved me....thanks

[@surajthallapalli4227]

Hey Tim, I enjoyed this tutorial. I have a doubt. In the text classification why wasn't nltk used to remove the stopwords and the words that doesn't make sense like 'the'. That might still improve the accuarcy. Could you please correct me if i am wrong ?

[@ProgrammingwithPeter]

Pretty neat, tensor flow grow so much

[@nhimong1799]

Was using google collab to implement this tutorial. Thank you for the great content. I'm excited to learn this with Tim! He taught me Java thoroughly!

[@kidsfree6615]

Who is botting?

[@samraeburn9341]

Best tensorflow tutorial ive ever seen, thanks for this one!

[@ayushyadav4412]

have yopu completed the course ?? How was it?

[@shawnliu8563]

Newbie in almost every aspects in what is said in this video. Took me a whole day to get to 35:10. Had issues (1). downloading python. The correct version is python3.6.1 for tensorflow 2.0.0, to avoid "from google.protobuf.pyext import _message ImportError: DLL load failed: The specified procedure could not be found." errors, (2). Tensorflow 2.0.0, not 2.0.0alpha0, to avoid many many many "future warnings" (3). "Cache entry deserialization failed, entry ignored", solved by opening command prompt as administrator! (4). many typo error from my own fault. Almost given up. Using windows10 pro, CPU, intel64. I know the problem relates to my special settings, but might happen to other new users. This is a great video for beginners, thou.

[@ehsansaraee5473]

Love every minute of this video!great tutorial!thank you so much!

[@chase8264]

This was super helpful, thanks!

[@AB-cp1yy]

Great job! Is there like a Part 2 video for new example modeling? Or is this the only video?

[@heritagehomes6397]

Thanks for taking time and explaining this concepts with example. it helps many beginners. I teach advanced statistics and this details will help many people to understand fundamentals. nice job.

[@ai.201]

Best tutorial I've ever seen, learned so much about neural networks.

[@amitkehri]

Hats off to you dude. Crystal clear everything .

[@tet_2947]

Thanks for that Review as å tutorial and the preps and effort in Ur workspace. It took me just å little to catch the nearby and parental prints in tensor, which came from cran-R as spss clone. Now as New Tool for the unforseeanable..... Thx and Rock on 🤘

[@kamalpandey7177]

Thanks for the video. How to calculate error in the text classification one. How can we split the dataset in test train validation one. Do all of those contains the label? and how to test the model on new different datasets. I am new to this subject.

[@ANILKHANDEI]

Very nice explanation of neural netwiorks and using the same to predict the fashion mnist. This makes a lot of sense to me, thanks for this.

[@ali.swatian]

love you man. really a good teacher.

[@nikhilkumarjha]

Thanks for sharing this informative tutorial. Big like (y)

[@hohodsj]

Thank you for the great video!! I have a quick question. 1:40:46 from the GlobalAveragePooling1D to the next Dense layer, should it be fully connected?

[@user-fk1wo2ys3b]

Super clear, easy to follow explanations, THANKS!

[@tak68tak]

Great tutorial. Thanks. You might want to use Jupyter with Visual Studio Code, so you don't need to run from the beginning every time.

[@vinaypatil7293]

At 1:05:25 you mentioned if we need to make predictions on a single image from the dataset we just need to put [test_images[7]] instead of test_images. correction: prediction = model.predict(np.array([test_images[7]])) we need to pass a NumPy array to the model else one would run into this error: ValueError: Input 0 of layer dense is incompatible with the layer: expected axis -1 of input shape to have value 784 but received input with shape [None, 28]

[@theegyptiancamel]

When you divide your data by the max value, you are essentially "normalizing" it. "Shrinking it" or more appropriately quantizing the data is a different process involving reducing the number of significant bits and the quantization step.

[@whliao98]

excited about your tutorial！！！！

[@ChrisField13]

This is incredible. I'm an hour in, and I feel like I've learned more practical application in this video than I have in all of the other ML research I've done combined.

[@maclacrosse1]

you explain this better then most college professors do and it doesn't cost me my future in student loans

[@lachlanoflynn3235]

🥺 I'm excited to learn this with Tim! He taught me Java thoroughly!

[@shangyunlv]

When shifting the word index by 3 and add the special token into the dictionary for "" and "" and so on, the whole system will have a mismatch of words, because such shift is not made to the data accordingly.

[@TheDeadSource]

A lot of people are asking what versions of python and windows can be used to run TensorFlow 2.0. I've dug into this for you all. A lot of info is from the official site, some is from github issues and published articles regarding TF 2.0, so at the time of writing this should be accurate information. First, operating systems. TF 2.0 was tested and is officially supported on the following *64-bit* systems: * Windows 7 or later. * Ubuntu 16.04 or later. * macOS 10.12.6 (Sierra) or later - note that these versions do not offer GPU support. * Raspbian 9.0 or later. Python versions that are currently supported are: * Python 3.6 (but NOT Python 3.7, despite its recent release.) * Python 2.7.

[@mli8847]

i am 13 years old and don't speak and understand very much englisch, but i am now watching the video at 25 min and i have understand how neural networks work and every thing else expect the activation function, thanks

[@thomaspgeorge4339]

Thank you so much for this!! :D

[@bryancc2012]

is it possible to build an autoencoder on a RNN/attention with an embedding layer?

[@anynamecanbeuse]

56:27 Training acc marginally larger than the val acc indicates that a high variance problem, and extends the training epochs doesn't sound like a good idea. Tricks as regularizations, dropout or just reduce the number of parameters should be work.

[@davincy09]

i have high school math and i understook what an activation function is so is very well explained!

[@achmed20]

thx a ton, i finaly understood the basics :)

[@starship9874]

for the length of the reviews i used for i in range(len(test_data)): sum = sum+len(test_data[i]) print(sum/len(test_data)) to simply calculate the average length, the average review is 230 words long i think thats a good limit

[@RecursiveTriforce]

Shorter and more pythonic: s = sum(len(i) for i in test_data) print(s/len(test_data))

[@RecursiveTriforce]

Whenever you write something like... for index in range(len(something)): print(something[i]) ...just use... for element in something: print(element)

[@kiranmacherla1815]

Hi, when I try to run the imshow() stuff you are teaching at around 39 mins, I am facing this error: name '_warn_for_nonsequence' is not defined can you please tell me what to do for its rectification? Thank You

[@sajjaddehghani8735]

Great explanation, thanks

[@heisenberg4703]

Took me hours to figure this out: If training the model takes really long, this might be the fix: Don't use IDLE to run the Code. Just use CMD/Terminal.

[@ivanmorn]

Hi Tim thanks a lot for the tutorial. I'm trying to save the model via typing exactly the same as you did here. However, after executing the code, I just can't find the model.h5 file anywhere in my laptop. (I'm using a mac here, and there's no error message after executing the code). Is this something you can help?

[@rajeshsomasundaram7299]

It was a great first half session (I watched till that point). How do we tell our neural network output neurons (output1 to output9) to predict the specific labels. For ex: output 1 neuron should predict the output of Trouser. Where do we really mention that?

[@gauravsharma-ow8st]

y labels represent the actual output.

[@rohithdsouza8]

39:30 - Isn't decimal representation of numbers harder to work with over integer representation of number for a computer? (32 bit floating point vs 8 bit integer)

[@osxs333__7]

scaling the features is common practice when creating models for machine learning, you can kind of think of it as having the data sit close together for the model to make more accurate decisions. In some cases you can work with models that take in a variety of features that all operate on different scales, so you will use Standardization to create more effective models.

[@darcos7535]

On the gpu (cuda) there is no penalty for single precision vs int. Fp16s are also available

[@mosyright4799]

Excellent! Thank you

[@chavoyao]

When you are working with a single neuron, like at the beginning of your video, you have only one bias term. It makes no sense to have one per connection. Your excitation function should have been \sum_{i=1}^4 { w_i \cdot v_i } + b. This neuron requires five parameters instead of eight.

[@LimitedWard]

Thank you for pointing that out. I was really confused by that math for a bit. So I'm assuming you'd have 1 bias per node in the output layer?

[@chavoyao]

@@LimitedWard You have a bias term per node in the hidden and output layers.

[@azizulhakim1534]

I was looking for this comment

[@mahdiheidarpoor9452]

the best video for start, its better if you can make another video for more advanced nn works with ts2...

[@maoryatskan6346]

at 00:37:00 255 represents white and 0 represents black. Great video! keep it up.

[@user-or5gd6oq7o]

The tanh function belongs to [-1:1]. Sigmoid activation function is [0:1].

[@wiihackerkris35000vr]

hot

[@vikramadityamathur2420]

Great lecture. Thank you !

[@kaisontoro9665]

hey if i wanted to have the model predict new pictures of clothes, (like say i took a picture of a shirt off google or something) how would i go about doing that

[@krunalzadafiya]

Hey Tim, I have only one question. Since you called the dataset "imdb", I really want to know where it is actually stored. So far, I knew I had to download it. But where does it download from and where is it stored in my storage? Doing great work !!!

[@heyrmi]

At 18:30 you explained about sigmoid function but Its hyperbolic tangent function or tanh

[@dreamofmirrors2]

You can avoid downgrading numpy by changing you pickle value to True in the IMDB file located in your keras packages. line 85 in the file change to this with np.load(path, allow_pickle=True) as f:

[@AndrewTateTopG1]

2:07 maybe chatbot? Yes bro pls.. My pathetic try to make it +1 for NN chatbot

[@Cormac_YT]

This line keeps throwing errors fitModel = model.fit(x_train, y_train, epochs=40, batch_size=512, validation_data=(x_val, y_val), verbose=1)

[@aaronad2456]

Amazing tuto :D 1:50:27 - Why do you put "predict[0]" and not "predict"? Why do we have a shape of the predict variable equal to 250?

[@yuliu1105]

I have the same question, can somebody answer?

[@doc2010]

the variable "predict" is a list so predict[0] is the first item in this list. This is what you want to predict the label on.

[@fabiantan8340]

@@doc2010 Here, predict[0] will only predict on the first item of the sentence/list. However, in this example, we are supposed to predict the class for the entire sentence whether it is positive or negative review, and not the individual token

[@fabiantan8340]

it should be this way predict = model.predict(test_data) print(" Prediction: ", predict[0]) print(" Actual: ", test_labels[0])

[@43585273]

@@fabiantan8340 it shouldn't be predict[0] right rather it should be print(predict) since we are finding out whether sentence as a whole is having positive reviews or not . but it prints size of 250 values instead of single value. can u elobrate a bit more ?

[@NishantSingh-px3jm]

Thank You FreeCodeCamp you people know what I want . I was just about to give ₹15000 for learning this this . Thanks I love you❤😄

[@krishna7440]

Hi Thanks for amazing stuff And specifically layers u explained is amazing in part 1 of tutorial specially i am looking for building model and matrix shape But could u please explain it for new test set Actually i was trying for an audio classifier from a tutorial in youtube But for prediction they used same training dataset , but when i m trying with some new dataset It is showing error " Error when checking input : expected conv2d_1_input to have shape (9,12,1) but got array witj shape of (6,12,1) " So could u please explain how to shape new input dataset in our prection part ??

[@arunramachandran6362]

Can you please explain the cmap and the load_data() you used in keras, actually I'm new to machine learning.

[@shyamnehru142]

Load_data is used to download the datasets and store as train and test

[@dmsnm]

Hey a small suggestion. When you provide the timeline of topics in the description, plz make them clickable for easier and faster access

[@mattheww9656]

+1 for the ‘plz’, but when you’re requesting an additional feature for your convenience, it doesn’t hurt to show a little gratitude for what has already been provided or a preemptive ‘thank you’ for what you want. Thank you. - the ‘Please & Thank You Police’

[@WalidSadak]

THANK YOU

[@akshiwakoti7851]

Lists and Arrays are very different data structures in the way they work during runtime. Lists are mutable objects, that is, one can add, replace, remove an element in a list whereas Arrays are immutable objects, that is, one cannot change data elements once an array has been created (you can delete the array entirely however). Lists can contain multiple types of data elements in multiple combinations, such as, a list inside a list inside a list, an array inside a nested list, a tuple, a dictionary, a string, an integer, a float, a timestamp, etc., whereas an Array must have all data elements of the same type. There are of course many other differences.

[@amirtaghavy7647]

Thanks for making this insightful video. One quick question, when flattening the data, shouldn't we expect 28 by 28 by 3 values for each image given that each pixel is represented by three RGB values?

[@rottenradish8510]

No because grayscale images are represented as just one value. Theoretically you're right, since the RGB value is (x, x, x), but it is often stored as just x.

[@hiltyMG]

Full Machine Learning For Finance - Quantitative Trading for Beginners (2019) PLEASE!!!

[@AlexCell33]

You don’t need machine learning, just basic regression and statistical models. Oh yeah, and tens of thousands of dollars a month in obscure and alpha generating data feeds. Or co locate a server at a stock exchange and front run the guys running the models.

[@justicegugu9775]

@@AlexCell33 What are the steps to learn machine learning for finance?

[@bryancc2012]

very good tutorial!

[@raj-nq8ke]

Must watch for basics of TensorFlow. Good Tutorial

[@maratimus]

*Thank you so much*

[@josephcohen4077]

How do you pick input layers shape? (the one that gets flattened early on).

[@alvarosanchezp]

19:25 This is not the sigmoid function as you say in the video. This is the hyperbolic tangent. The sigmoid function maps any value between 0 and 1, not between -1 and 1.

[@ianpan0102]

Yup you're correct, the sigmoid function's y coordinate is bounded by 0 and 1.

[@nl1575]

But if you do 1-g(z)^2 it is a value between 0-1

[@nl1575]

These functions are known as non-linear activation functions common ones known are the sigmoid function and hyperbolic tangent but modern ones used are Rectified Linear Unit (ReLU), Leaky LU and Exponential LU

[@nl1575]

We can also use a value between -1 and 1 to represent strongly positive and negative values during testing

[@nl1575]

Just for the people who may have been confused

[@jonasstrabel]

For everyone who as problems installing the pip package, its only for python versions up to 3.8. If you are running python 3.9 or higher install the alpha version of the pip package

[@shippy5952]

Great tutorial! One question about the globalaveragepooling layer. After embedding we are actually taking the average of the embedding features over all the word vectors and not the average of every individual vector? Say we have 2 words in a sentence that we want to predict the sentiment of: "Very nice" -> [1,1,1,1], [2,2,2,2] -> 2 words, 2 word vectors with 4 embedding features (contexts). The correct way is to take the average over these vectors so the lower dimensional output is [1.5, 1.5, 1.5, 1.5], that we then pass to the dense layer. And the incorrect way is to output a 2 dimensional vector averaging the 2 vectors individually -> output: [1, 2]? Just averaging every word vector individually and passing every single one in a new vector doesn't make sense to me and would just throw away the context.

[@joansoleroig518]

I have a question, when I open python 3 it does not say i am in c:/user and so on... and therefore i can not move through folders or anything. What should I do?

[@vasylpavlus]

Can I run TensorFlow 2.0 (or any other version) on Win 7x86 / Python 3.7? Thanks.

[@RecursiveTriforce]

Probably... Please don't use Windows 7!

[@wanabenerd]

amazing video thanks!

[@samwalter3646]

how do you create the recommended direction (8:43)