train.py

#Naive-Bayes for MNIST

#import the libraries
import numpy as np
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (7,7) # Make the figures a bit bigger

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.utils import np_utils

#load the data
nb_classes = 10

# the data, shuffled and split between tran and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()
print("X_train original shape", X_train.shape)
print("y_train original shape", y_train.shape)
print("X_test original shape", X_test.shape)
print("y_test original shape", y_test.shape)

X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
Y_train = np_utils.to_categorical(y_train, 10)
Y_test = np_utils.to_categorical(y_test, 10)
X_train /= 255
X_test /= 255
print("Training matrix shape", X_train.shape)
print("Testing matrix shape", X_test.shape)

#Build the network
model = Sequential()
model.add(Dense(512, input_shape=(784,)))
model.add(Activation('relu')) # An "activation" is just a non-linear function applied to the output
                              # of the layer above. Here, with a "rectified linear unit",
                              # we clamp all values below 0 to 0.
                           
model.add(Dropout(0.2))   # Dropout helps protect the model from memorizing or "overfitting" the training data
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax')) # This special "softmax" activation among other things,
                                 # ensures the output is a valid probaility distribution, that is
                                 # that its values are all non-negative and sum to 1.
#compile the model
model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['accuracy'])

#train the model
model.fit(X_train, Y_train,
          batch_size=128, nb_epoch=12,
          verbose=1, validation_data=(X_test, Y_test))

#evaluate the model
score = model.evaluate(X_test, Y_test, verbose=0)
print('Train loss:', score[0])
print('Train accuracy:', score[1])

score = model.evaluate(X_test, Y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

#inspecting the outputs
# The predict_classes function outputs the highest probability class
# according to the trained classifier for each input example.
predicted_classes = model.predict_classes(X_test)

# Check which items we got right / wrong
correct_indices = np.nonzero(predicted_classes == y_test)[0]
incorrect_indices = np.nonzero(predicted_classes != y_test)[0]

plt.figure()
for i, correct in enumerate(correct_indices[:9]):
    plt.subplot(3,3,i+1)
    plt.imshow(X_test[correct].reshape(28,28), cmap='gray', interpolation='none')
    plt.title("Predicted {}, Class {}".format(predicted_classes[correct], y_test[correct]))
    
plt.figure()
for i, incorrect in enumerate(incorrect_indices[:9]):
    plt.subplot(3,3,i+1)
    plt.imshow(X_test[incorrect].reshape(28,28), cmap='gray', interpolation='none')
    plt.title("Predicted {}, Class {}".format(predicted_classes[incorrect], y_test[incorrect]))