#klasifikasi sederhana menggunakan data MNIST
#model : simple CNN

from __future__ import print_function
import numpy as np
np.random.seed(1337)  # for reproducibility

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils

batch_size = 128
nb_classes = 10 #MNIST 10 kelas
nb_epoch = 100

# dimensi imagage
img_rows, img_cols = 28, 28

# banyaknya filter/kernel
nb_filters = 32

# ukuran pooling area untuk MaxPooling Layer
nb_pool = 2

# ukuran kernel/filter
kernel_size = (2, 2)

# kita gunakan data MNIST yang sudah disediakan Keras
# split train-test
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# perkecil ukuran data untuk training-testing
# hanya untuk bermain-main saja. Kalau semua, training bisa lambat
X_train = X_train[:150]
y_train = y_train[:150]
X_test = X_test[:60]
y_test = y_test[:60]

# reshape, awalnya hanya grayscale 1 channel (num_sample, row, col)
# input dari Convolution2D adalah 4 dim (num_sample, channel, row, col)
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)

X_train = X_train.astype('float32')
X_test = X_test.astype('float32')

#before: nilai berkisar antara 0 - 255
#after: nilai berkisar antara 0 - 1, normalized
X_train /= 255
X_test /= 255


# convert class vectors -> binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

# memulai membangun Arsitektur CNNs kita !
# terdiri dari Convolution2D dan MaxPooling2D
# di ujung, adalah Dense layer biasa (fully connected)
model = Sequential()

model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
                        border_mode='valid',
                        input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adadelta',
              metrics=['accuracy'])

model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
          verbose=1, validation_data=(X_test, Y_test))

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