Neural Network Python Project - Handwritten Digit Recognition

Today we use Tensorflow to build a neural network, which we then use to recognize images of handwritten digits that we created ourselves.

◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾◾
📚 Programming Books & Merch 📚

🌐 Social Media & Contact 🌐

[ruutjormun]

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.d]

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

[sachinkrao]

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

[anhurtjv]

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

[NEXTLevelGISRSfitsalem]

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?

[bobvance]

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.

[christopherdessources]

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.

[doktermaiskorn]

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

[aaronfroggatt]

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.

[williamikennanwosu]

Thanks for a flawless video NeuralNine!

[oingomoingo]

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 ?

[GiorgioM.]

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

[danielrocha]

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

[marktellez]

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

[LumiCrushr]

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?

[abebuenodemesquita]

mine is super innacurate. could you please help?

[btqbuoc]

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.

[AlwinmathewP]

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?

[johncheung]

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 !!

[Ayumu]

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...