Classify Hand-Written Digits Using Python and Convolutional Neural Networks

Classify Hand-Written Digits Using Python and Convolutional Neural Networks

In this article, I will show you how to classify hand written digits from the MNIST database using the python programming language and a machine learning technique called Convolutional Neural Networks!

Start Programming:

# Description: This program uses Convolutional Neural Networks (CNN) 
#              to classify handwritten digits as numbers 0 - 9
pip install tensorflow keras numpy matplotlib
#import the libraries
from keras.models import Sequential
from keras.layers import Dense, Conv2D, Flatten
from keras.datasets import mnist
from keras.utils import to_categorical
import matplotlib.pyplot as plt
import numpy as np
#Load the data and split it into train and test sets
(X_train,y_train), (X_test, y_test) = mnist.load_data()
#Get the image shape

The image shape of the feature data sets

Sample of the first image in the training data set as an array
#Print the image label

The label of the first image in the training data set

The image of the 1st hand written digit in the training set
#Reshape the data to fit the model
X_train = X_train.reshape(60000, 28,28,1)
X_test = X_test.reshape(10000, 28, 28, 1)
#One-Hot Encoding
y_train_one_hot = to_categorical(y_train)
y_test_one_hot = to_categorical(y_test)

#Print the new label

The label 5 one hot encoded
model = Sequential()model.add(Conv2D(64, kernel_size=3, activation='relu', input_shape=(28,28,1)))model.add(Conv2D(32, kernel_size=3, activation='relu'))model.add(Flatten())model.add(Dense(10, activation='softmax'))
#Compile the model model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
hist =, y_train_one_hot, validation_data=(X_test, y_test_one_hot), epochs=3)

Training the CNN model
#Visualize the models accuracy
plt.title('Model Accuracy')
plt.legend(['Train', 'Val'], loc='upper left')

Plot of the models training & validation/test accuracy scores
predictions = model.predict(X_test[:4])

The probabilities of each image highlighting the greatest likelihood (7,2,1,0)
#Print our predicitons as number labels for the first 4 images
print( np.argmax(predictions, axis=1))
#Print the actual labels

Top: The predicted labels, Bottom: The actual labels
#Show the first 4 images as pictures 
for i in range(0,4):   
   image = X_test[i]   
   image = np.array(image, dtype='float')   
   pixels = image.reshape((28,28))  
   plt.imshow(pixels, cmap='gray')

Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems


Source: itnext