Classifying Handwritten Digits with TF.Learn - Machine Learning Recipes #7

  Рет қаралды 312,528

Google for Developers

Google for Developers

Күн бұрын

Пікірлер: 170
@WhirlpoolBrewer
@WhirlpoolBrewer 8 жыл бұрын
I love this series, please make more! I'm learning quite a bit, I can't wait to learn more! The books on this topic are often quite expensive and dig deep into math (which is fine, but often slow) and other youtubers don't really explain whats going on. You're nailing that sweet spot of teaching about whats going on, without digging too deep. I know enough to speak to whats going on, without requiring brushing up on my Calculus. Love. It.
@rezayahya3539
@rezayahya3539 8 жыл бұрын
Ryan Johnson
@robind999
@robind999 6 жыл бұрын
You really take us to a brand new TF world, thank you very much.
@girishbkool
@girishbkool 8 жыл бұрын
This is the most well defined video of the Digit classifier. Awesome Job.
@gouthamk139
@gouthamk139 8 жыл бұрын
When will the next video releases .
@XF3DeX
@XF3DeX 8 жыл бұрын
This series is great! Keep it coming
@typingcat
@typingcat 7 жыл бұрын
Use your machine learning to predict when the next episode will come out.
@akl6111
@akl6111 7 жыл бұрын
Josh, You made it look so simple..atleast to get the basics. You are awesome.
@ShawnHice
@ShawnHice 8 жыл бұрын
I'm excited for the deep learning segment! Very nice tutorials I am loving it so far
@niccolomarcon
@niccolomarcon 8 жыл бұрын
Awesome video! Happy to see that the thesis for my high school diploma uses the same concept :) Can't wait for the next video!
@dmytrozelinskyi4824
@dmytrozelinskyi4824 8 жыл бұрын
Hey. Don`t u think it`s time to make new cool video about ML ? Thx for last 7n.
@juanok2775
@juanok2775 7 жыл бұрын
These are the best videos, we need more!!
@JacquesvanWyk
@JacquesvanWyk 8 жыл бұрын
Wow a whole new world opened.This is great stuff cant wait to learn more.
@AmCanTech
@AmCanTech 7 жыл бұрын
I am loving this series. was working with caffe for a bit, but need to start myself with TF
@yurielzhang5884
@yurielzhang5884 8 жыл бұрын
I can't wait to see the next episode, it's awesome, thank you very much
@shmigelsky
@shmigelsky 8 жыл бұрын
Awesome, looking forward to the deep learning episode. Would be interesting to see learning times for different approaches and hardware. G
@RobertShaverOfAustin
@RobertShaverOfAustin 8 жыл бұрын
Some people put a slash through the zero and the seven character when they write it. How would you incorporate those alternative forms into this digit recognizer? Does the training set contain data about what each character is actually (a designator)? If that is true it seems like you could include the alternative digit forms with the correct designator. Then both forms would contribute to the weights for those two other characters, zero and seven, right?
@afederdk
@afederdk 8 жыл бұрын
You simply would provide a training data set containing a sufficient number of examples of those alternative forms. The classifier is as good as the data it is trained on.
@parampalsingh3339
@parampalsingh3339 7 жыл бұрын
Continue the series pleaseeeee....I'm lovin it
@maplicant232
@maplicant232 8 жыл бұрын
Thanks for doing this! I have a question though. Would the classifier get better results if you had 10 extra weights: biases on the outputs? It seems like it would, but I don't know how much of a difference it would make.
@shahroozgovahi674
@shahroozgovahi674 7 жыл бұрын
Thank you for your effort in creating quality material in ML. The method you use for explaining is amazing. Is there any more videos beside these 7?
@SaaranshMehta
@SaaranshMehta 8 жыл бұрын
I'm a fan of your videos, thanks for the lucid explanation
@_akuma06
@_akuma06 7 жыл бұрын
I want MOAR ! Thanks for the series, it was really helpful :)
@dc5
@dc5 8 жыл бұрын
Time to go DEEP :) Great videos... Thanks for sharing Josh!
@yousufazad6914
@yousufazad6914 7 жыл бұрын
please continue making these awesome videos!
@sallerc
@sallerc 8 жыл бұрын
Great series, hope you do more episodes.
@yosaikan
@yosaikan 8 жыл бұрын
Thank you Joch for this very clear presenation :)
@chiranjib-konwar
@chiranjib-konwar 7 жыл бұрын
why just 7 videos only. please make more videos. you are just awesome. thanks a lot.
@Tzvetkov
@Tzvetkov 7 жыл бұрын
So weights are like pixel intensities of the digits learned by the model?
@kamikaz1k
@kamikaz1k 7 жыл бұрын
Anyone having problems with running the classifier.predict method? The evaluation method works (it gives me an accuracy score) but the predict method always throws an InvalidArgumentError saying that "shape in shape_and_slice spec [1,10] does not match the shape stored in checkpoint: [784,10]"
@chinamatt
@chinamatt 6 жыл бұрын
I get the same error...
@chinamatt
@chinamatt 6 жыл бұрын
I found this works too: pred = clf.predict(np.array([test_data[0]]), as_iterable=False) print("Predicted %d, Label: %d" % (pred, test_labels[0]))
@robertlam88
@robertlam88 6 жыл бұрын
Thanks I ran into the same error and the above works.
@thinkcreativewithsakshi259
@thinkcreativewithsakshi259 5 жыл бұрын
I am getting the same error dude. Please respond how you solved it! Thank you.
@adambrown234
@adambrown234 8 жыл бұрын
This was a really nice video, it helped me a lot. Thanks! When is the next episode coming up? I'd love to see it.
@juansantiagocuadra3672
@juansantiagocuadra3672 6 жыл бұрын
What tools are you using to create the animations? great videos, Thank You.
@Taha-jj1kr
@Taha-jj1kr 6 жыл бұрын
Beautiful ...just beautiful explanation !!
@Xenotropic
@Xenotropic 5 жыл бұрын
If you get an error using a newer version of TensorFlow when trying to predict from the test data try the following: replace - print ("Predicted %d, Label: %d" % (classifier.predict(test_data[0]), test_labels[0])) with - print ("Predicted %d, Label: %d" % (classifier.predict(np.array([test_data[0]], dtype=float), as_iterable=False))
@nguyenthanhdong
@nguyenthanhdong 4 жыл бұрын
Thank you
@mpik97
@mpik97 8 жыл бұрын
Looking forward to the next video!
@jonathanmv
@jonathanmv 7 жыл бұрын
Im getting an error when trying to visualize the weights *weights = classifier.weights_* throws an _AttributeError: 'LinearClassifier' object has no attribute 'weights_' error. Does anyone have a clue about what's happening or how to the the weights for the classifier?
@yording54cala
@yording54cala 7 жыл бұрын
hi, i have the same error, Could you solve it?
@adeeb12321
@adeeb12321 7 жыл бұрын
me too
@isco2252
@isco2252 7 жыл бұрын
Me too. I've checked the library. No attribute weights_ in it.
@jonasschmeiss5487
@jonasschmeiss5487 7 жыл бұрын
short: replace "weights = classifier.weights_" with for var in classifier.get_variable_names(): print("var:", var, "=", classifier.get_variable_value(var)) weights = classifier.get_variable_value("linear//weight/d/linear//weight/part_0/Ftrl_1")
@danielrichards3159
@danielrichards3159 7 жыл бұрын
I found the answer, just DELETE THE LINE (seriously, it works)
@bantuthomas
@bantuthomas 5 жыл бұрын
Hi!! My Anaconda installation does not have the tensorflow module. Neither could I install it through conda. Similar problem with IDLE and PyCharm. I get the error message: Could not find a version that satisfies the requirement tensorflow (from versions: ) No matching distribution found for tensorflow I am stuck without being able to install tensorflow. Is there any IDE the comes with tensorflow?
@splashgi
@splashgi 7 жыл бұрын
Love the series. When will next video be released?
@matheoland
@matheoland 8 жыл бұрын
Good episode. Thanks !
@nguyenthanhdong
@nguyenthanhdong 4 жыл бұрын
How do I predict for a single image in my computer?
@user-jk3dq2fp7n
@user-jk3dq2fp7n 7 жыл бұрын
I can't seem to find the Docker quickstart terminal on my Mac. I am using Version 17.03.0-ce-mac1.
@NathboGames
@NathboGames 6 жыл бұрын
Hi once classifier works well what is the next step to build a program to use the results to return something to user? Ie I would want to read digits and maybe a + - = so I would classify the image as 1+2= and my program should return the result of the math operation, so 3. What are the ways to do that?
@Realxar
@Realxar 8 жыл бұрын
The error was: SyntaxError: Unexpected token < in JSON at position 4
@eddalexander6030
@eddalexander6030 8 жыл бұрын
Yes getting same errorr too if anyone knows how to resolve
@DanielMarrable
@DanielMarrable 8 жыл бұрын
The "Visualizating MNIST" link is missing a space between the link and "(this blog is outstanding)" and as such the link gets garbled and 404s. Great video as always!!
@eliesaad
@eliesaad 7 жыл бұрын
What happened? why did the series stop? when's the next video?
@nikitatank6672
@nikitatank6672 7 жыл бұрын
Is docker installation necessary for this tutorial ?? If no. I am getting "AttributeError: 'LinearClassifier' object has no attribute 'weights' " error. Not able to print predicted and actual label. May i have the solution please
@RAJATTHEPAGAL
@RAJATTHEPAGAL 7 жыл бұрын
We need more videos . :-D ... Josh Gordon awesome introduction from you sir.
@Johnny5490
@Johnny5490 8 жыл бұрын
What if the numbers are not centered, isn't that an easy way to beat this? Like if the one was left of the center pixel
@jiteshmohite1069
@jiteshmohite1069 8 жыл бұрын
Great videos on machine learning. also it would be nice if you guys come up with some more videos with much deeper knowledge.
@thinkcreativewithsakshi259
@thinkcreativewithsakshi259 5 жыл бұрын
Helli Sir, I ran the above source code. Well, it is giving me an error at the "Classify few examples" point where we are meant to predict the actual number. Can you please help. Thank you.
@bmusician08
@bmusician08 5 жыл бұрын
Now that TF2 is out all these Episodes are obsolete. Does any know where to find updates to them?
@tjhannover3069
@tjhannover3069 7 жыл бұрын
is their a diffrence between skit learn and tensflow?
@abishekkumar316
@abishekkumar316 5 жыл бұрын
Unable to start the quick start terminal for docker
@miguelpereira9613
@miguelpereira9613 7 жыл бұрын
"I’d like to spend a lot more time on this next episode, if there’s interest?" When? :D Love your videos and your links btw!
@yuval9064
@yuval9064 7 жыл бұрын
when i run this code i get an error with classifier.predict help?
@SirajRaval
@SirajRaval 8 жыл бұрын
Hell yeah! If you guys like machine learning check out my new ML series on my channel.
@patyarakawa
@patyarakawa 7 жыл бұрын
I have a doubt. In the examples you use python. Have you tried some functional language, such as elixir, for example? I am interested in deepening machine learning but I still do not know which language is the best. Thanks for the videos, by the way!
@JoeWong81
@JoeWong81 6 жыл бұрын
Thank you for these videos buddy!!!
@conradosanchez7332
@conradosanchez7332 6 жыл бұрын
Anyone know if this is with multilayer perceptron or convolutional neural networks?
@actechforlife
@actechforlife 7 жыл бұрын
when is the episode on deep learning going to start.... kindly post link if already.. thanks..
@narendranathp
@narendranathp 8 жыл бұрын
Are more episodes coming in?
@OussamaHaff
@OussamaHaff 7 жыл бұрын
Can I use Tensorflow to do OCR on Android ?
@mitrathakker
@mitrathakker 7 жыл бұрын
Hey Josh It was a great series so far and expecting more such videos But there was this one thing that constantly pricked me during the whole playlist and that's the order of the videos It is reverse chronological and for someone like me who started watching the playlist once it already had 7 videos, it got really cumbersome (and sometimes confusing) to actually go to the previous video after each video I saw Is it possible to get this (and most others, too) playlist ordered in a chronological fashion (or maybe get a "Reverse Playlist" functionality on KZbin as that'd work too :P) Cheers
@Skandawin78
@Skandawin78 7 жыл бұрын
is this the last video in this series ? :(
@IagobaApellaniz
@IagobaApellaniz 8 жыл бұрын
the order of the playlists is reversed
@wessidemd
@wessidemd 8 жыл бұрын
This should be the top comment. The reverse order makes it difficult to watch them sequentially.
@priyankamaurya8175
@priyankamaurya8175 5 жыл бұрын
if i want to input an image then how it recognize that image
@sheresh
@sheresh 6 жыл бұрын
what are weights in ML ?
@sudharsanamtk
@sudharsanamtk 6 жыл бұрын
I am planning to develop a chat bot in non english language? where to start ? is TF an option or anything ? please suggest
@lakshmichandubathini6354
@lakshmichandubathini6354 5 жыл бұрын
do docker doesn't work in windows 8.1?
@huynguyen-cy8ig
@huynguyen-cy8ig 7 жыл бұрын
When the next video come out, I've been waiting for too long!
@AlexanderCastroRomero
@AlexanderCastroRomero 8 жыл бұрын
I am a teacher and this video is so userfull :)
@madhuvamsimachavarapu5267
@madhuvamsimachavarapu5267 7 жыл бұрын
is this the last episode?
@yixunnnn
@yixunnnn 7 жыл бұрын
Hi guys! Does anyone knows what version to use as of this moment? Thanks!
@yixunnnn
@yixunnnn 7 жыл бұрын
Is it 1.4.0-rc0-py3?
@joostavontuur2144
@joostavontuur2144 6 жыл бұрын
i just installed it all
@chrispeng5269
@chrispeng5269 8 жыл бұрын
why the episode is not updated?
@xingyubian5654
@xingyubian5654 6 жыл бұрын
I am getting Error response from daemon: driver failed programming external connectivity on endpoint objective_volhard
@ashii007
@ashii007 7 жыл бұрын
I ran into env issues with ep7 notebook but I got the gist of it.
@saikatsutradhar1138
@saikatsutradhar1138 7 жыл бұрын
when are you starting classes again? eagerly waiting
@Endlessvoidsutidos
@Endlessvoidsutidos 6 жыл бұрын
how do you download the ipynb file from git hub ?
@ViventhraaRao
@ViventhraaRao 8 жыл бұрын
Anyone got this issue when trying to execute the code? "AttributeError: 'module' object has no attribute 'datasets'"
@AleksandrKrasnovsoprof
@AleksandrKrasnovsoprof 8 жыл бұрын
Probably wrong tensorflow version.
@cjjb
@cjjb 7 жыл бұрын
Really liked these. Pity there's no more :(
@morwar_
@morwar_ 8 жыл бұрын
very good, thanks for the explanation
@russellthurman5509
@russellthurman5509 6 жыл бұрын
Under the "Fit Linear Classifier" sections, I don't get this return: LinearClassifier(). This is what I get: LinearClassifier(params={'head': , 'feature_columns': [_RealValuedColumn(column_name='', dimension=784, default_value=None, dtype=tf.float32, normalizer=None)], 'optimizer': None, 'gradient_clip_norm': None, 'joint_weights': False}). Then the evaluation gives me 0.0988.
@rahulagarwal7303
@rahulagarwal7303 7 жыл бұрын
we need more videos. plz complete the series.
@DilanGamachchige
@DilanGamachchige 8 жыл бұрын
Nice interesting one.. waiting for the next one.. thanks.. :-)
@danielassayag1484
@danielassayag1484 4 жыл бұрын
libraries used arent valid anymore on tensorflow 2. though some of it is deprecated its still on ai.google/education/.. google can"t do better than this?
@yccheng3864
@yccheng3864 4 жыл бұрын
Hi i encountered issue when I run the jupyter notebook: --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 7 get_ipython().run_line_magic('matplotlib', 'inline') 8 import tensorflow as tf ----> 9 learn = tf.contrib.learn 10 tf.logging.set_verbosity(tf.logging.ERROR) AttributeError: module 'tensorflow' has no attribute 'contrib' I just found out this is about 3 years ago, so is that the "contrib" no longer available?
@yccheng3864
@yccheng3864 4 жыл бұрын
oh i solved it, thank you
@RasmusKwerther
@RasmusKwerther 4 жыл бұрын
@@yccheng3864 would you say how? :)
@ahmedalhisaie7698
@ahmedalhisaie7698 6 жыл бұрын
thanks for this great tutorials
@pacozaaskr14
@pacozaaskr14 8 жыл бұрын
Thank you Josh.
@jugadexpert4687
@jugadexpert4687 8 жыл бұрын
sir google finance ke event code kya hai
@user-ny8xt1ui3h
@user-ny8xt1ui3h 4 жыл бұрын
Wonderful Series of ML! Someone recommends me another one? please
@aakashawase1948
@aakashawase1948 7 жыл бұрын
when are you going to release next video
@moinshaikh1333
@moinshaikh1333 6 жыл бұрын
The GitHub link died please send the TF examples proper link
@shikhanshu
@shikhanshu 7 жыл бұрын
where is #8??
@nkf31
@nkf31 8 жыл бұрын
Hope text mining will be covered in one episode!
@gideonamanimarress7441
@gideonamanimarress7441 8 жыл бұрын
awesome video!! THANK YOU
@cashphattichaddi
@cashphattichaddi 8 жыл бұрын
Beautiful !!
@rabanaahoura7593
@rabanaahoura7593 4 жыл бұрын
Great ! Thanks , Can i ask you about WIZARDPKG for other solution ?
@ZIAURREHMAN1991
@ZIAURREHMAN1991 8 жыл бұрын
please comeback soon
@juliozarate5
@juliozarate5 7 жыл бұрын
excellent all videos
@krasin
@krasin 8 жыл бұрын
The link to Docker images leads to the MNIST tutorial.
@akmonra
@akmonra 7 жыл бұрын
The hell? There are none after this?
@tiagoguimaraes5796
@tiagoguimaraes5796 8 жыл бұрын
+1 for docker!
Арыстанның айқасы, Тәуіржанның шайқасы!
25:51
QosLike / ҚосЛайк / Косылайық
Рет қаралды 700 М.
UFC 310 : Рахмонов VS Мачадо Гэрри
05:00
Setanta Sports UFC
Рет қаралды 1,2 МЛН
Machine Learning Zero to Hero (Google I/O'19)
35:33
TensorFlow
Рет қаралды 1,8 МЛН
Intro to Feature Engineering with TensorFlow - Machine Learning Recipes #9
7:38
Google for Developers
Рет қаралды 179 М.
AI can't cross this line and we don't know why.
24:07
Welch Labs
Рет қаралды 1,4 МЛН
Getting Started with Weka - Machine Learning Recipes #10
9:24
Google for Developers
Рет қаралды 222 М.
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
57:45
Learn PyTorch for deep learning in a day. Literally.
25:36:58
Daniel Bourke
Рет қаралды 1,6 МЛН
But what is a neural network? | Deep learning chapter 1
18:40
3Blue1Brown
Рет қаралды 18 МЛН