mnist_cnn_training.py

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Dropout, Flatten, MaxPooling2D
from tensorflow.keras.optimizers import Adam

import seaborn as sn
import matplotlib.pyplot as plt
import numpy as np

#Dateset preprocessing.
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

x_train = x_train.reshape(x_train.shape[0], 28, 28, 1).astype('float32')
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1).astype('float32')
input_shape = (28, 28, 1)

x_train /= 255
x_test /= 255

#CNN model.
model = Sequential()
model.add(Conv2D(32, (5, 5), input_shape=input_shape, activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.15))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(10, activation='softmax'))

model.compile(loss='sparse_categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
history=model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=10)

#Model saveing.
model.save("model\mnist_model.h5")

#acc-loss ploting.
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('Accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.savefig("plots/acc.png")

plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.savefig("plots/loss.png")

#Confusion matrix ploting.
test_pred=model.predict(x_test)

test_pred = [np.argmax(i) for i in test_pred]
cm = tf.math.confusion_matrix(labels=y_test, predictions=test_pred)

plt.figure(figsize = (10,7))
sn.heatmap(cm, annot=True, fmt='d')
plt.xlabel('predicted labels')
plt.ylabel('True labels')
plt.savefig("plots/cm.png")