Improvised in readability and organization cnn-functional-2.1.1.py

chapter2-deep-networks/cnn-functional-2.1.1.py

@@ -3,79 +3,53 @@
 ~99.3% test accuracy
 '''
 
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
+# Import required libraries
+from __future__ import absolute_import, division, print_function
 import numpy as np
-from tensorflow.keras.layers import Dense, Dropout, Input
-from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten
+from tensorflow.keras.layers import Conv2D, Dense, Dropout, Flatten, Input, MaxPooling2D
 from tensorflow.keras.models import Model
 from tensorflow.keras.datasets import mnist
 from tensorflow.keras.utils import to_categorical
 
-
-# load MNIST dataset
+# Load MNIST dataset and prepare it
 (x_train, y_train), (x_test, y_test) = mnist.load_data()
-
-# from sparse label to categorical
 num_labels = len(np.unique(y_train))
 y_train = to_categorical(y_train)
 y_test = to_categorical(y_test)
 
-# reshape and normalize input images
+# Reshape and normalize input images
 image_size = x_train.shape[1]
-x_train = np.reshape(x_train,[-1, image_size, image_size, 1])
-x_test = np.reshape(x_test,[-1, image_size, image_size, 1])
-x_train = x_train.astype('float32') / 255
-x_test = x_test.astype('float32') / 255
+x_train = np.reshape(x_train,[-1, image_size, image_size, 1]).astype('float32') / 255
+x_test = np.reshape(x_test,[-1, image_size, image_size, 1]).astype('float32') / 255
 
-# network parameters
+# Set network parameters
 input_shape = (image_size, image_size, 1)
 batch_size = 128
 kernel_size = 3
 filters = 64
 dropout = 0.3
 
-# use functional API to build cnn layers
+# Build CNN layers with functional API
 inputs = Input(shape=input_shape)
-y = Conv2D(filters=filters,
-           kernel_size=kernel_size,
-           activation='relu')(inputs)
+y = Conv2D(filters=filters, kernel_size=kernel_size, activation='relu')(inputs)
 y = MaxPooling2D()(y)
-y = Conv2D(filters=filters,
-           kernel_size=kernel_size,
-           activation='relu')(y)
+y = Conv2D(filters=filters, kernel_size=kernel_size, activation='relu')(y)
 y = MaxPooling2D()(y)
-y = Conv2D(filters=filters,
-           kernel_size=kernel_size,
-           activation='relu')(y)
-# image to vector before connecting to dense layer
+y = Conv2D(filters=filters, kernel_size=kernel_size, activation='relu')(y)
 y = Flatten()(y)
-# dropout regularization
 y = Dropout(dropout)(y)
 outputs = Dense(num_labels, activation='softmax')(y)
 
-# build the model by supplying inputs/outputs
+# Build the model and show summary
 model = Model(inputs=inputs, outputs=outputs)
-# network model in text
 model.summary()
 
-# classifier loss, Adam optimizer, classifier accuracy
-model.compile(loss='categorical_crossentropy',
-              optimizer='adam',
-              metrics=['accuracy'])
+# Compile the model
+model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
 
-# train the model with input images and labels
-model.fit(x_train,
-          y_train,
-          validation_data=(x_test, y_test),
-          epochs=20,
-          batch_size=batch_size)
+# Train the model with input images and labels
+model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=20, batch_size=batch_size)
 
-# model accuracy on test dataset
-score = model.evaluate(x_test,
-                       y_test,
-                       batch_size=batch_size,
-                       verbose=0)
-print("\nTest accuracy: %.1f%%" % (100.0 * score[1]))
+# Calculate and print model accuracy on test dataset
+score = model.evaluate(x_test, y_test, batch_size=batch_size, verbose=0)
+print("Test accuracy: %.1f%%" % (100.0 * score[1]))