Neural Network Python Project - Handwritten Digit Recognition

แชร์
ฝัง
  • เผยแพร่เมื่อ 26 ธ.ค. 2024

ความคิดเห็น •

  • @ruutjormun2262
    @ruutjormun2262 10 หลายเดือนก่อน +8

    Had to sign in to say thank you. Breaking down each line is incredibly useful. I also love how you continually point out that there's areas for improvement and reference us to what may be classified as overkill. It gives an excellent gateway into machine learning by linking this seemingly simple explanation to actually recognised CNNs and FC layers etc.!

  • @al.d9592
    @al.d9592 3 ปีที่แล้ว +10

    This video is really, really good. Used it to resurrect my 20y old ANN skills. Will use this in my classes now!

  • @sachinkrao
    @sachinkrao 2 ปีที่แล้ว +5

    Totally underrated video, perfect for people getting started with Neural Networks!

  • @christopherdessources
    @christopherdessources 4 หลายเดือนก่อน +3

    Hi guys. Just want to help anyone following this later like I was.
    Instead of using tensorflow (if you aren't seeing tf.keras.datasets which is what had me stuck), you can get the mnist variable from : from keras.api.datasets import mnist. Also if you import keras.api as k_api (or whatever name i suck at naming), replace all the tf.keras with k_api. It should work the same.

  • @GeoffryGifari
    @GeoffryGifari 8 หลายเดือนก่อน +2

    so with tensorflow keras we don't need to code the weights and biases from scratch?

    • @kshitijnishant4968
      @kshitijnishant4968 5 หลายเดือนก่อน +1

      that's the purpose of ML frameworks like pytorch and tensorflow buddy

  • @GeoffryGifari
    @GeoffryGifari 8 หลายเดือนก่อน +1

    are there repositories out there where we can get training data?

  • @aaronfroggatt9566
    @aaronfroggatt9566 ปีที่แล้ว +6

    I followed this tutorial and it runs with similar loss and accuracy results to the video. My problem is when I make my own written numbers, the accuracy is usually less than 50%. I have tried playing around with the number of hidden layers, numbers of neurons, and number of epochs and I don't see any real change. What other likely places I could look to find a fix.

    • @HaxeHere
      @HaxeHere ปีที่แล้ว

      I have the same issue. The more I trained the data, the more inaccurate it actually got.

    • @BhanuPandey-hl9ql
      @BhanuPandey-hl9ql ปีที่แล้ว

      got the same issue here, have you fixed it any leads?
      @@HaxeHere

    • @Splendisimo
      @Splendisimo ปีที่แล้ว +3

      Try replacing all of the model.add lines with this 😉
      model.add(tf.keras.layers.Conv2D(32, (3,3), activation='sigmoid', input_shape=(28, 28, 1))) # The one in "(28, 28, 1)" is required or else it'll error out
      model.add(tf.keras.layers.MaxPool2D((2, 2)))
      model.add(tf.keras.layers.Conv2D(48, (3,3), activation='sigmoid'))
      model.add(tf.keras.layers.MaxPool2D((2, 2)))
      model.add(tf.keras.layers.Dropout(0.5))
      model.add(tf.keras.layers.Flatten())
      model.add(tf.keras.layers.Dense(500, activation='sigmoid'))
      model.add(tf.keras.layers.Dense(10, activation='sigmoid'))

    • @BasedArmenian-kh8pb
      @BasedArmenian-kh8pb 4 หลายเดือนก่อน

      @@Splendisimo
      for anyone wondering, the changes are essentially:
      - Using a convolutional neural network
      - Using a Sigmoid function instead of ReLU

  • @doktermaiskorn833
    @doktermaiskorn833 3 ปีที่แล้ว +9

    great tutorial. how can i increase the accuracy. shoudl I just screw up the epochs. I tried this, but some digits like a angeled one or a 5 that get "recognized" as a 6 or a 3(as example). sorry for my bad english :D

  • @UserError-n7n
    @UserError-n7n 6 หลายเดือนก่อน

    I have this problem at 12:12.
    It keeps giving me an error in tensorflow stating “DLL load failed while importing _pywrap_tf2

  • @williamikennanwosu
    @williamikennanwosu 2 ปีที่แล้ว +1

    Thanks for a flawless video NeuralNine!

  • @bobvance9519
    @bobvance9519 8 หลายเดือนก่อน +3

    I got this error. Changing the extension of the model to keras solved it.
    File "C:\Users\user\anaconda3\envs\main\Lib\site-packages\keras\src\saving\saving_api.py",
    line 106, in save_model
    raise ValueError(
    ValueError: Invalid filepath extension for saving. Please add either a `.keras` extension for
    the native Keras format (recommended) or a `.h5` extension. Use `model.export(filepath)` if you want to export a SavedModel for use with TFLite/TFServing/etc. Received: filepath=handwritten.model.

  • @danielrocha2521
    @danielrocha2521 9 หลายเดือนก่อน +2

    Why did we choose to use 128 neurons for our first Dense layer? I have always wondered what is the intuition that should be used for the number of neurons needed for a layer? Is it kinda just random

  • @LumiCrush3r
    @LumiCrush3r ปีที่แล้ว +2

    Why did you normalise the train and test data separately. Shouldn’t we first normalise train data and then apply the same normalisation factor to test data?

    • @purple_gemini
      @purple_gemini ปีที่แล้ว

      was thinking same, fit(Xtrain).transform(Xtrain) and fit(Xtrain).transform(Xtest)

  • @anhurtjv
    @anhurtjv 2 ปีที่แล้ว +19

    I did everything as done here, and the performance of the network is terrible, even after increasing the number of epochs!

    • @volleyball2676
      @volleyball2676 6 หลายเดือนก่อน +1

      Same problem , have you managed to fix it?

    • @FirangizRasulova
      @FirangizRasulova 5 หลายเดือนก่อน

      @@volleyball2676 same problem too, have u fixed it?

    • @larryhull2752
      @larryhull2752 3 หลายเดือนก่อน

      I’m about to try it. Let you know soon 💪 fashion mnist worked for me

    • @rnuniverseplayz
      @rnuniverseplayz 2 หลายเดือนก่อน

      For me the accuracy is pretty high but the loss is high too
      Accuracy = 0.9778
      Loss = 0.7503

  • @williamikennanwosu
    @williamikennanwosu 2 ปีที่แล้ว +1

    I'm at 14:04 and I'm getting the following error after loading the saved model 'logits and labels must have the same first dimension, got logits shape [32,10] and labels shape [25088]'. Is anyone getting the same error, I've researched it and it apparently has something to do with the loss function being sparse_categorical_crossentropy or categorical_crossentropy?

    • @williamikennanwosu
      @williamikennanwosu 2 ปีที่แล้ว +1

      I found the problem and fixed it. I wrote 'test_y = tf.keras.utils.normalize(test_X, axis=1)
      ' instead of 'test_X = tf.keras.utils.normalize(test_X, axis=1)
      '

  • @alwinshoots
    @alwinshoots 3 ปีที่แล้ว +4

    I'm very new to this and have a small doubt when training the data we normalized the pixel values to be between 0 and 1, but when we are predicting using jpgs we dont normalize it, why is that?

    • @danielrocha2521
      @danielrocha2521 9 หลายเดือนก่อน +1

      I think the reason he normalized the pixel values to be between 0 and 1 is because as he said their values range between 0 and 255. Since this is a big range of numbers normalizing the pixel data would be most ideal as it would reduce the impact of spread on our model. However, when predicting the jpgs they only take on a value between 0 - 9 so label data cannot necessarily be as spread out as the pixel data can be, rendering it kinda useless to do so.
      Again this is just my thought process. If some of my logic is incorrect, please don't hesitate to correct me internet.

  • @abebuenodemesquita8111
    @abebuenodemesquita8111 3 ปีที่แล้ว +3

    mine is super innacurate. could you please help?

  • @GiorgioM.
    @GiorgioM. 3 ปีที่แล้ว +7

    Hi F, very useful video as always! when you can, could you make a video about voice recognition/transcription in Python like youtube autosubtitle. To eliminate background noises ... what would you do? Thx

  • @Ayumu31
    @Ayumu31 6 หลายเดือนก่อน

    it seems my created model keeps giving wrong output so i increased epochs but same issue, i noticed it looks at a specific pattern and it finds it similar to another it checks to two numbers as the same number. For example, the 3 and 8 gets confused and it gets termed as 3 all the time. i wonder if it needs more training or do i need to change the code somewhere...

  • @anchorbuster3452
    @anchorbuster3452 ปีที่แล้ว +1

    really helped me a lot.
    Thank you so much😄😄

  • @akshatdodhiya
    @akshatdodhiya 3 ปีที่แล้ว +1

    Your videos are really amazing!

  • @oingomoingo7411
    @oingomoingo7411 10 หลายเดือนก่อน +3

    am i the only one whos digits are not recognized ? The mnist data set works fine and gets recognized but my own digits no chance, why ist that ?

    • @jellocrackers9107
      @jellocrackers9107 7 หลายเดือนก่อน +1

      Bro just dissed his own handwriting

    • @bthub3
      @bthub3 4 หลายเดือนก่อน

      Go onto Paint and make the canvas 28x28 pixels, then colour everything black, then write on it with white brush/pen. It works for me.

  • @abdallahlakkis449
    @abdallahlakkis449 2 หลายเดือนก่อน

    ‪How would you suggest to go from beginner to expert in ML/AI in practical terms. Assuming theoretical foundations are there‬

  • @johncheung4905
    @johncheung4905 ปีที่แล้ว +3

    I followed the video to the word, frame by frame. I got this "Mistake" before saving the model (before applying to self made numbers). The loss is 2.3, and the accuracy is 0.097. During the training though, all accuracies are over 90. Can anyone tell me what is the problem? Is there anything wrong with the test set? This is a great video. I just want to make it work !!

    • @kys8693
      @kys8693 6 หลายเดือนก่อน

      Same Problem here

    • @kys8693
      @kys8693 6 หลายเดือนก่อน

      import tensorflow as tf
      mnist = tf.keras.datasets.mnist
      (x_train, y_train), (x_test, y_test) = mnist.load_data()
      x_train = tf.keras.utils.normalize(x_train, axis=1)
      x_test = tf.keras.utils.normalize(x_test, axis=1)
      # model = tf.keras.models.Sequential([
      # tf.keras.layers.Flatten(input_shape=(28, 28)),
      # tf.keras.layers.Dense(128, activation='relu'),
      # tf.keras.layers.Dense(128, activation='relu'),
      # tf.keras.layers.Dense(10, activation='softmax')
      # ])
      # model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
      # model.fit(x_train, y_train, epochs=10)
      # model.save('project.keras')
      model = tf.keras.models.load_model('project.keras')
      loss, accuracy = model.evaluate(x_test, y_test)
      print(f'Loss: {loss}')
      print(f'Accuracy: {accuracy}')
      That fixed my problem, you can try it out if you want to

  • @godofstrangerness7096
    @godofstrangerness7096 9 วันที่ผ่านมา

    Love the vid! But I have a slight problem, my 8 and 9 are not getting recognised even with more epochs.

  • @marktellez3701
    @marktellez3701 ปีที่แล้ว +1

    lol, that intro music on a topic like this :D

  • @ranaabdulsammad2004
    @ranaabdulsammad2004 ปีที่แล้ว +1

    hey can anyone help please i am writing this code in jupyter notebook how to import images in jupyter will the process be the same???????

  • @yadeen6828
    @yadeen6828 ปีที่แล้ว +1

    Hi sir , if we give the image in which we give any paragraph so they can detect it
    or not ,for example in image we give A ,so the they detect it or not

    • @yadeen6828
      @yadeen6828 ปีที่แล้ว

      if any one have idea about that so tell me

  • @captainamerica768
    @captainamerica768 2 หลายเดือนก่อน +1

    what is the application u are using??

    • @poleq775
      @poleq775 หลายเดือนก่อน

      pycharm

  • @16thpolicy
    @16thpolicy 2 ปีที่แล้ว

    this might be a stupid question but it isn't obvious for me in the code. How is the output layer ordered? what I mean is how does index 0 directly map to value '0', index 1 to '1', etc. I also searched this up for letter recognition and they have 0-25 mapping in order to letters sequentially. maybe someone can explain

  • @JacobRutgersson
    @JacobRutgersson ปีที่แล้ว

    How did you comment the whole section at 12:28?

    • @ea1766
      @ea1766 ปีที่แล้ว +1

      crtl + /

  • @onuraydn7065
    @onuraydn7065 3 ปีที่แล้ว

    but what if I want to know different hxw images????? this only works for 28,28.

  • @hexyedev1336
    @hexyedev1336 3 ปีที่แล้ว

    How could I train neural networks without a dataset? Like if I would like it to idk play a video game

  • @masoon3373
    @masoon3373 3 ปีที่แล้ว

    Great!👍 More videos like this ❤️

  • @MichaZawadzki-ku1dk
    @MichaZawadzki-ku1dk ปีที่แล้ว

    Where did you download your training data and where was it loaded into your program? That is, I don't see any filename loaded...

    • @Nyo0
      @Nyo0 ปีที่แล้ว +1

      the training data is part of the tenserflow library itself u dont need to download it additionaly

  • @pranayjavvaji
    @pranayjavvaji ปีที่แล้ว

    how to downlode data set which u used ?

  • @giannhsp222
    @giannhsp222 3 ปีที่แล้ว +1

    OMG.. I was in full screen mode and on 7:45 I thought someone hacked my computer! haha! It was scary!

  • @srirammk5678
    @srirammk5678 ปีที่แล้ว

    I'm unable to evaluate the model, the error says they dont have same array size

  • @FirangizRasulova
    @FirangizRasulova 4 หลายเดือนก่อน

    The recognition sucked when i used my paint pictures. I found that it recognizes it way better when i have white on black images from paint.

    • @BasedArmenian-kh8pb
      @BasedArmenian-kh8pb 4 หลายเดือนก่อน

      The MNIST dataset are literally all black on white pictures so this is why, that is the only thing its trained on

    • @FirangizRasulova
      @FirangizRasulova 4 หลายเดือนก่อน

      @@BasedArmenian-kh8pb yes but we turned the black on white paint images to white on black. So I was expecting it to work. The owner of the channel used black on white too

  • @MICOLO253
    @MICOLO253 2 ปีที่แล้ว +1

    Hi, anyone knows which theme of PyCharm is this?

  • @aravindputtapaka5147
    @aravindputtapaka5147 ปีที่แล้ว +1

    I want a python code to convert handwritten image into plain text with accurate i have tried but i didnt got you can try it and show me..

  • @candykoko90
    @candykoko90 4 หลายเดือนก่อน

    why it's showing invalid file path use either. keras extension for saving. please add either a keras extension for the native keras format

    • @bthub3
      @bthub3 4 หลายเดือนก่อน

      There's a comment by @somith4259 where they write the whole updated code. They did 'handwritten.models.keras' to fix the problem.

    • @BasedArmenian-kh8pb
      @BasedArmenian-kh8pb 4 หลายเดือนก่อน

      Use ".keras" as the extension as it just told you

  • @Dr.Fitsum_Teshome
    @Dr.Fitsum_Teshome 2 ปีที่แล้ว

    Hi buddy, thank you for your useful videos. However, I am getting this error "NameError: name "keras" is not defined when I try to classify the datasets into training and test datasets. How can I solve this error, please?

  • @jonathandlt1214
    @jonathandlt1214 2 ปีที่แล้ว

    Hi. Can someone help me to find my mistake. Where i can save the folder of image so that my programs will read directly to that folder. bcoz, it does not read the image number when i run the programs. really appreciate to someone help and enlighten me. tnx.

  • @kgcolor
    @kgcolor 3 ปีที่แล้ว

    Cool vid man, I want to get started, just curious as to what IDE you are using?

    • @zahraali8630
      @zahraali8630 3 ปีที่แล้ว

      Looks like pycharm, not sure though

    • @furkanbasan
      @furkanbasan 3 ปีที่แล้ว

      pycharm

  • @areebaazhar28
    @areebaazhar28 ปีที่แล้ว

    Sir imges not display when i run this code

  • @Zane_Ritchie
    @Zane_Ritchie ปีที่แล้ว

    Hey, thank you so much for this video.

  • @AliAli-wi2ys
    @AliAli-wi2ys 3 ปีที่แล้ว

    i did this 2 years ago with live opencv drawing and detection
    thx a lot

  • @Shayankhan-q8f
    @Shayankhan-q8f 7 หลายเดือนก่อน

    Is it will work for handwritten words or text?

  • @gagarinrout2034
    @gagarinrout2034 ปีที่แล้ว

    Why the dense layer with '128' units ?

    • @javali1678
      @javali1678 ปีที่แล้ว

      he just copied the value online, youtuber programmer modus operandi

  • @vantrixfn
    @vantrixfn 2 ปีที่แล้ว

    AttributeError: module 'keras.api._v2.keras.models' has no attribute 'load'

  • @muthurubant5812
    @muthurubant5812 3 ปีที่แล้ว

    You are awesome broo🔥🔥🔥🔥

  • @mohamedalisahnoun8021
    @mohamedalisahnoun8021 ปีที่แล้ว

    is there a chance i can run a code that can transform text pdf , images, voices into a model for medical stuff

  • @ushibuii8702
    @ushibuii8702 3 ปีที่แล้ว

    can u tell the digits directory thing.. u just skipped that part]

  • @itztoreveuwu3869
    @itztoreveuwu3869 10 หลายเดือนก่อน

    Amazing tutorial man, i'm a complete beginner and this is totally understandable and it's so awesome, i only have a question, what do i do if i want to use larger images, is it possible?

    • @malikmodric7161
      @malikmodric7161 9 หลายเดือนก่อน

      i think you might need image segmentation , you'll find a video about it in this chanel

  • @drip3889
    @drip3889 6 หลายเดือนก่อน

    Why did we make the hidden layers 128 neurons? This is the part no one explains in tutorials

    • @BasedArmenian-kh8pb
      @BasedArmenian-kh8pb 4 หลายเดือนก่อน

      No reason, it is default/standard and in various circumstances it could even cause minor problems changing it

  • @isururasanjana-n2v
    @isururasanjana-n2v ปีที่แล้ว

    shouldn't we normalize the input image pixel values before predicting it

    • @robbyrthomas5623
      @robbyrthomas5623 7 หลายเดือนก่อน

      I think the reason he normalized the pixel values to be between 0 and 1 is because as he said their values range between 0 and 255. Since this is a big range of numbers normalizing the pixel data would be most ideal as it would reduce the impact of spread on our model. However, when predicting the jpgs they only take on a value between 0 - 9 so label data cannot necessarily be as spread out as the pixel data can be, rendering it kinda useless to do so.

  • @NarangaravB
    @NarangaravB ปีที่แล้ว

    You really helped me a lot. Thank you so much🤩

  • @aarushkumar168
    @aarushkumar168 3 ปีที่แล้ว +1

    Please can you make a video on automating social media with python?

    • @javali1678
      @javali1678 ปีที่แล้ว

      he just uses others tools to make stuff that he doenst really understand. so dont expect much from him

  • @rajm5349
    @rajm5349 2 ปีที่แล้ว

    kindly explain banking projects or fraud manageent or loan projects

  • @amanpiyushsharma
    @amanpiyushsharma ปีที่แล้ว

    can anyone help me the no module found name tensorflow

  • @morgoth4932
    @morgoth4932 ปีที่แล้ว

    can i do handwritten character recog using this,just by changing the dataset?

  • @theotrevalinet7560
    @theotrevalinet7560 2 ปีที่แล้ว

    HI nice video ! Do you know how to analyse images that are bigger than 28x28px ?? Thanks ;)

    • @simplyylunar
      @simplyylunar ปีที่แล้ว +1

      im not fully sure about this but you can try changing the numbers in the "model.add(tf.keras.layers.Flatten(input_shape = (28,28)))" so change it to be like "model.add(tf.keras.layers.Flatten(input_shape = (32,32)))"

  • @rudrakshchamyal1275
    @rudrakshchamyal1275 2 ปีที่แล้ว

    i am not able to load tensor flow

  • @eclipsehunter22
    @eclipsehunter22 3 ปีที่แล้ว

    Awesome bro!

  • @manzilkarmacharya1478
    @manzilkarmacharya1478 2 ปีที่แล้ว

    Can we use raspberry pie with touch screen for input

  • @HosseinOjvar
    @HosseinOjvar ปีที่แล้ว

    Helpful video , thank you ;)

  • @s.aravindh6227
    @s.aravindh6227 3 ปีที่แล้ว

    Nice video bro 👍👍👍👍👍

  • @ayshasimra8048
    @ayshasimra8048 ปีที่แล้ว

    I followed your code word by word still the result is showing error. Please help me!!

  • @tharukaridmal3117
    @tharukaridmal3117 9 หลายเดือนก่อน

    Can you asist me to identify symbols from drawing using CNN. It will be much helpful for my project

  • @a_lister242gaming7
    @a_lister242gaming7 3 ปีที่แล้ว

    Anyone know what program he's coding this in?

  • @محمدامین-س3ف
    @محمدامین-س3ف ปีที่แล้ว

    thank you very much , bro .

  • @Martin-iy8gd
    @Martin-iy8gd 2 ปีที่แล้ว +1

    Hi friend ! Nice video. Could you help me in making Handwritten Digits Recognition but using HMM?

  • @onuraydn7065
    @onuraydn7065 3 ปีที่แล้ว

    is this only works 28,28 ????

  • @AbhixSingh
    @AbhixSingh 7 หลายเดือนก่อน

    Can you make this same video with alphabet instead of number ? Pretty pls

  • @yacahumax1431
    @yacahumax1431 7 หลายเดือนก่อน

    In line #8 you are loading data, but you dont specify any files. I dont see were you are creating the actual training data and testing data. All I see is at the end , you creating data to actually use the model. where is the training data?

    • @christopherdessources
      @christopherdessources 4 หลายเดือนก่อน

      The initial training data and testing data are supplied by mnist.

  • @karthikeyan.s557
    @karthikeyan.s557 3 ปีที่แล้ว

    Awesome bro

  • @ushibuii8702
    @ushibuii8702 3 ปีที่แล้ว

    cant download tensorflow

  • @a.dennis003
    @a.dennis003 10 หลายเดือนก่อน

    To enable the following instructions: SSE SSE2 SSE3 SSE4.1 SSE4.2 AVX AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. this is the error i had

    • @robbyrthomas5623
      @robbyrthomas5623 7 หลายเดือนก่อน

      This is not an error but a statement u can ignore, but if there is no output that probably mean program was not able to get the digits directory so check your path is correct or not, for me it was to include the directory name where the digits directory was stored

  • @shaileshlprabhu1435
    @shaileshlprabhu1435 6 หลายเดือนก่อน

    For me it's not printing anything why?

  • @alexdiaz4371
    @alexdiaz4371 3 ปีที่แล้ว

    Awesome!!! Thanks

  • @Erik-fg9fk
    @Erik-fg9fk ปีที่แล้ว

    which ide is this?

    • @yuvamgupta4150
      @yuvamgupta4150 5 หลายเดือนก่อน

      PyCharm by Jetbrains

  • @lunarfrosty3223
    @lunarfrosty3223 6 หลายเดือนก่อน

    keras isn't working. anyone know how to fix

    • @rishyth
      @rishyth 5 หลายเดือนก่อน

      use .h5

    • @the-notorious-khaki
      @the-notorious-khaki 5 หลายเดือนก่อน

      @@rishyth explain?

    • @BasedArmenian-kh8pb
      @BasedArmenian-kh8pb 4 หลายเดือนก่อน

      @@the-notorious-khaki
      accepted file extensions

  • @brianfitzgerald6197
    @brianfitzgerald6197 ปีที่แล้ว

    Amazing!

  • @gitasaheru2386
    @gitasaheru2386 2 ปีที่แล้ว

    Please make video Multi Layer Perceptron How To build With Manual Coding without tensorflow

  • @AJain-18
    @AJain-18 3 ปีที่แล้ว +1

    Nice video !!!

  • @Newb1eProgrammer
    @Newb1eProgrammer ปีที่แล้ว

    predict function in line 31 isnt defined according to vscode, error message is " "predict" is not a know member of "None" ". help me

  • @tomstalley3179
    @tomstalley3179 หลายเดือนก่อน

    thank you!

  • @ujjwalkashyap8055
    @ujjwalkashyap8055 3 ปีที่แล้ว

    Will u plzz provide source code for this ?

  • @akhilbisht798
    @akhilbisht798 ปีที่แล้ว

    Hey there is some problem in load_model() i cannot use predict or evaluate if i get my model from load_model() function

  • @unlimitediq1894
    @unlimitediq1894 2 ปีที่แล้ว

    errors come up for every piece of code you write. I am unsure what wizardry you're doing to get it to work on your end. it always fails on mine and it pisses me off.

    • @javali1678
      @javali1678 ปีที่แล้ว

      he doesnt really understand neural networks too, just using tensorflow, there are far better videos on the subject, just look around , these "programmer" youtubers really are the bad side of the platform, they gain massive viewers and they are junior at best.

  • @namo2943
    @namo2943 3 ปีที่แล้ว +1

    Early, and love the video!

  • @stefanlodders9521
    @stefanlodders9521 3 ปีที่แล้ว

    It is really helpful and all. Thank you. For me, there could be more illustration of what happens to our data after what command line. Often you just guess it, but you can not be sure, especially when you are not using standard python methods, as you just see the output. Like with neural networks itself. :)

    • @НикитаБаронов-с6н
      @НикитаБаронов-с6н 2 ปีที่แล้ว

      why does the neural network immediately correctly determine the numbers without any training?

    • @pattyspanker8955
      @pattyspanker8955 ปีที่แล้ว

      @@НикитаБаронов-с6н It was trained for 3 epochs with a standard dataset

  • @abhinavchoudhary6849
    @abhinavchoudhary6849 3 ปีที่แล้ว +1

    Nice video

  • @Nohope__
    @Nohope__ ปีที่แล้ว +1

    my AI thinks 3 is a 6. :(

  • @1112vinu
    @1112vinu 11 หลายเดือนก่อน

    Can anyone share the source code ?

  • @soumyadeepchatterjee1807
    @soumyadeepchatterjee1807 ปีที่แล้ว

    can you u upload the source code

  • @keshavgupta8819
    @keshavgupta8819 2 ปีที่แล้ว

    Thanku so much bro

  • @mahmoodjamshidian9525
    @mahmoodjamshidian9525 3 ปีที่แล้ว

    vary practical

  • @onuraydn7065
    @onuraydn7065 3 ปีที่แล้ว

    unbeliavable, no one before me not comment is this only works for 28,28. really unbeliavable. do you really understand what he mentioned ? I think you do not.