2016-03-19 16:07:15 +00:00
|
|
|
'''Trains a simple deep NN on the MNIST dataset.
|
2015-12-09 02:49:14 +00:00
|
|
|
|
2016-03-19 16:07:15 +00:00
|
|
|
Gets to 98.40% test accuracy after 20 epochs
|
2015-12-09 02:49:14 +00:00
|
|
|
(there is *a lot* of margin for parameter tuning).
|
|
|
|
2 seconds per epoch on a K520 GPU.
|
|
|
|
'''
|
|
|
|
|
2015-04-30 00:17:22 +00:00
|
|
|
from __future__ import print_function
|
2015-06-27 00:41:13 +00:00
|
|
|
import numpy as np
|
2015-07-26 08:00:18 +00:00
|
|
|
np.random.seed(1337) # for reproducibility
|
2015-06-27 00:41:13 +00:00
|
|
|
|
2015-04-30 00:17:22 +00:00
|
|
|
from keras.datasets import mnist
|
|
|
|
from keras.models import Sequential
|
|
|
|
from keras.layers.core import Dense, Dropout, Activation
|
|
|
|
from keras.optimizers import SGD, Adam, RMSprop
|
2015-05-04 17:31:03 +00:00
|
|
|
from keras.utils import np_utils
|
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
|
|
|
|
|
|
|
# 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
|
|
|
|
2015-06-19 22:38:33 +00:00
|
|
|
X_train = X_train.reshape(60000, 784)
|
|
|
|
X_test = X_test.reshape(10000, 784)
|
2015-12-09 02:49:14 +00:00
|
|
|
X_train = X_train.astype('float32')
|
|
|
|
X_test = X_test.astype('float32')
|
2015-05-04 03:14:51 +00:00
|
|
|
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()
|
2015-11-20 04:13:49 +00:00
|
|
|
model.add(Dense(512, input_shape=(784,)))
|
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))
|
2015-11-20 04:13:49 +00:00
|
|
|
model.add(Dense(512))
|
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))
|
2015-10-05 01:44:49 +00:00
|
|
|
model.add(Dense(10))
|
2015-04-30 00:17:22 +00:00
|
|
|
model.add(Activation('softmax'))
|
|
|
|
|
2016-03-19 16:07:15 +00:00
|
|
|
model.summary()
|
2015-04-30 00:17:22 +00:00
|
|
|
|
2016-03-19 16:07:15 +00:00
|
|
|
model.compile(loss='categorical_crossentropy',
|
|
|
|
optimizer=Adam(),
|
|
|
|
metrics=['accuracy'])
|
|
|
|
|
|
|
|
history = 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)
|
2015-05-04 17:31:03 +00:00
|
|
|
print('Test score:', score[0])
|
|
|
|
print('Test accuracy:', score[1])
|