digits_classification.py

# Import the necessary libraries
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D , AveragePooling2D , Dense , Dropout , Flatten
from tensorflow.keras.datasets import mnist
from tensorflow.keras.optimizers import Adam
from sklearn.metrics import accuracy_score

# Defining The Structure of The Model (LeNet5 Architecture)
def LeNet5():
    model = Sequential()
    model.add(Conv2D(filters=6 , kernel_size=(5,5) , strides=(1,1) , activation="tanh" , input_shape=(32 , 32 , 1)))
    model.add(AveragePooling2D((2,2)))
    model.add(Conv2D(filters=16 , kernel_size=(5,5) , strides=(1,1) , activation="tanh" ))   
    model.add(AveragePooling2D((2,2)))
    model.add(Flatten())
    model.add(Dense(units=120 , activation="tanh"))
    model.add(Dropout(0.2))
    model.add(Dense(units=84 , activation="tanh"))
    model.add(Dropout(0.2))
    model.add(Dense(units=10 , activation="softmax"))
    adam = Adam(learning_rate=0.01)
    model.compile(optimizer=adam , loss = 'binary_crossentropy'  , metrics=['accuracy'])
    return model
# Function to prepare The Data
def prepare_dataSet(x ,y):
    #Transform The Images from 28*28 to 32*32
    x = np.pad(x , ((0,0) , (2,2) , (2,2)))
    #Reshape The Data
    x = x.reshape((x.shape[0] , 32 , 32 , 1))
    #One Hot Encodig
    y = to_categorical(y)
    #Normalize The Data
    x = x.astype('float32')
    x /= 255.0
    
    return x , y
# Function display The accuracy of our Model    
def displayAccuracy(history):
    plt.plot(history.history['accuracy'])
    plt.plot(history.history['val_accuracy'])
    plt.title('model accuracy')
    plt.ylabel('accuracy')
    plt.xlabel('epoch')
    plt.legend(['train', 'test'], loc='upper left')
    plt.show()

# Function display the loss of our Model
def displayLoss(history):
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('model loss')
    plt.ylabel('loss')
    plt.xlabel('epoch')
    plt.legend(['train', 'test'], loc='upper left')
    plt.show()

if __name__ == "__main__":

      # display The Model Architecture
      model = LeNet5()
      print("The Architecture of The Model is : ")
      print(model.summary())

      # Load The DataSet
      (x_train , y_train) , (x_test , y_test) = mnist.load_data()

      # prepare The data
      x_train , y_train = prepare_dataSet(x_train , y_train)
      x_test , y_test = prepare_dataSet(x_test , y_test)

      # Train The Model
      history = model.fit(x_train , y_train ,validation_split=0.33, epochs=10, batch_size=100)    

      #display The Model Accuracy
      displayAccuracy(history)    

      #display The Model Loss
      displayLoss(history)