keras_MINST_V7.py

from __future__ import print_function
import numpy as np
np.random.seed(1671)  # for reproducibility

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

# network and training
NB_EPOCH = 20
BATCH_SIZE = 128
VERBOSE = 1
nb_classes = 10   # number of outputs = number of digits
OPTIMIZER = RMSprop(lr=0.0001) # optimizer
#OPTIMIZER = RMSprop(lr=0.01) # optimizer
N_HIDDEN = 128
DROPOUT = 0.5


# data: shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
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')

# normalize 
X_train /= 255
X_test /= 255
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

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

# M_HIDDEN hidden layers
# 10 outputs
# final stage is softmax

model = Sequential()
model.add(Dense(N_HIDDEN, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dropout(DROPOUT))
model.add(Dense(N_HIDDEN))
model.add(Activation('relu'))
model.add(Dropout(DROPOUT))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.summary()

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

history = model.fit(X_train, Y_train,
                    batch_size=BATCH_SIZE, epochs=NB_EPOCH,
                    verbose=VERBOSE)
score = model.evaluate(X_test, Y_test, verbose=VERBOSE)
print("\nTest score:", score[0])
print('Test accuracy:', score[1])