2015-04-30 00:17:22 +00:00
|
|
|
from __future__ import absolute_import
|
|
|
|
from __future__ import print_function
|
|
|
|
from keras.datasets import mnist
|
|
|
|
from keras.models import Sequential
|
|
|
|
from keras.layers.core import Dense, Dropout, Activation
|
|
|
|
from keras.regularizers import l2, l1
|
|
|
|
from keras.constraints import maxnorm
|
|
|
|
from keras.optimizers import SGD, Adam, RMSprop
|
2015-05-04 17:31:03 +00:00
|
|
|
from keras.utils import np_utils
|
|
|
|
import numpy as np
|
2015-04-30 00:17:22 +00:00
|
|
|
|
|
|
|
'''
|
2015-05-04 17:31:03 +00:00
|
|
|
Train a simple deep NN on the MNIST dataset.
|
2015-04-30 00:17:22 +00:00
|
|
|
'''
|
|
|
|
|
2015-06-19 19:52:43 +00:00
|
|
|
batch_size = 128
|
2015-04-30 00:17:22 +00:00
|
|
|
nb_classes = 10
|
2015-05-04 03:14:51 +00:00
|
|
|
nb_epoch = 20
|
2015-04-30 00:17:22 +00:00
|
|
|
|
2015-05-04 17:31:03 +00:00
|
|
|
np.random.seed(1337) # for reproducibility
|
|
|
|
|
2015-04-30 00:17:22 +00:00
|
|
|
# the data, shuffled and split between tran and test sets
|
2015-05-04 03:14:51 +00:00
|
|
|
(X_train, y_train), (X_test, y_test) = mnist.load_data()
|
2015-05-04 17:31:03 +00:00
|
|
|
|
2015-05-29 23:53:37 +00:00
|
|
|
X_train = X_train.reshape(60000,784)
|
|
|
|
X_test = X_test.reshape(10000,784)
|
2015-05-04 03:14:51 +00:00
|
|
|
X_train = X_train.astype("float32")
|
|
|
|
X_test = X_test.astype("float32")
|
|
|
|
X_train /= 255
|
|
|
|
X_test /= 255
|
2015-04-30 00:17:22 +00:00
|
|
|
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)
|
|
|
|
|
|
|
|
model = Sequential()
|
2015-05-04 17:31:03 +00:00
|
|
|
model.add(Dense(784, 128))
|
2015-04-30 00:17:22 +00:00
|
|
|
model.add(Activation('relu'))
|
2015-05-04 17:31:03 +00:00
|
|
|
model.add(Dropout(0.2))
|
|
|
|
model.add(Dense(128, 128))
|
2015-04-30 00:17:22 +00:00
|
|
|
model.add(Activation('relu'))
|
2015-05-04 17:31:03 +00:00
|
|
|
model.add(Dropout(0.2))
|
|
|
|
model.add(Dense(128, 10))
|
2015-04-30 00:17:22 +00:00
|
|
|
model.add(Activation('softmax'))
|
|
|
|
|
2015-05-04 03:14:51 +00:00
|
|
|
rms = RMSprop()
|
|
|
|
model.compile(loss='categorical_crossentropy', optimizer=rms)
|
2015-04-30 00:17:22 +00:00
|
|
|
|
2015-05-04 17:31:03 +00:00
|
|
|
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, show_accuracy=True, verbose=2, validation_data=(X_test, Y_test))
|
|
|
|
score = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
|
|
|
|
print('Test score:', score[0])
|
|
|
|
print('Test accuracy:', score[1])
|