lunny/keras
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update 2 mnist examples

Browse Source
This commit is contained in:
fchollet 2017-02-10 18:16:11 -08:00
parent 011c1faeb4
commit ca23406974
2 changed files with 54 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
examples/mnist_cnn.py
View File

@ -9,74 +9,62 @@ from __future__ import print_function
import numpy as np import numpy as np
np.random.seed(1337) # for reproducibility np.random.seed(1337) # for reproducibility
import keras
from keras.datasets import mnist from keras.datasets import mnist
from keras.models import Sequential from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten from keras.layers import Dense, Dropout, Flatten
from keras.layers import Convolution2D, MaxPooling2D from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K from keras import backend as K
batch_size = 128 batch_size = 128
nb_classes = 10 num_classes = 10
nb_epoch = 12 num_epoch = 12
# input image dimensions # input image dimensions
img_rows, img_cols = 28, 28 img_rows, img_cols = 28, 28
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
pool_size = (2, 2)
# convolution kernel size
kernel_size = (3, 3)
# the data, shuffled and split between train and test sets # the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data() (x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first': if K.image_data_format() == 'channels_first':
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols) 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_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols) input_shape = (1, img_rows, img_cols)
else: else:
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1) x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1) x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1) input_shape = (img_rows, img_cols, 1)
X_train = X_train.astype('float32') x_train = x_train.astype('float32')
X_test = X_test.astype('float32') x_test = x_test.astype('float32')
X_train /= 255 x_train /= 255
X_test /= 255 x_test /= 255
print('X_train shape:', X_train.shape) print('x_train shape:', x_train.shape)
print(X_train.shape[0], 'train samples') print(x_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples') print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices # convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes) y_train = keras.utils.np_utils.to_categorical(y_train, num_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes) y_test = keras.utils.np_utils.to_categorical(y_test, num_classes)
model = Sequential() model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1], activation='relu',
border_mode='valid', input_shape=input_shape))
input_shape=input_shape)) model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25)) model.add(Dropout(0.25))
model.add(Flatten()) model.add(Flatten())
model.add(Dense(128)) model.add(Dense(128, activation='relu'))
model.add(Activation('relu'))
model.add(Dropout(0.5)) model.add(Dropout(0.5))
model.add(Dense(nb_classes)) model.add(Dense(num_classes, activation='softmax'))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', model.compile(loss=keras.losses.categorical_crossentropy,
optimizer='adadelta', optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy']) metrics=['accuracy'])
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, model.fit(x_train, y_train, batch_size=batch_size, num_epoch=num_epoch,
verbose=1, validation_data=(X_test, Y_test)) verbose=1, validation_data=(x_test, y_test))
score = model.evaluate(X_test, Y_test, verbose=0) score = model.evaluate(x_test, y_test, verbose=0)
print('Test score:', score[0]) print('Test loss:', score[0])
print('Test accuracy:', score[1]) print('Test accuracy:', score[1])

47
examples/mnist_mlp.py
View File

@ -11,40 +11,37 @@ np.random.seed(1337) # for reproducibility
from keras.datasets import mnist from keras.datasets import mnist
from keras.models import Sequential from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation from keras.layers import Dense, Dropout, Activation
from keras.optimizers import RMSprop from keras.optimizers import RMSprop
from keras.utils import np_utils from keras.utils import np_utils
batch_size = 128 batch_size = 128
nb_classes = 10 num_classes = 10
nb_epoch = 20 num_epoch = 20
# the data, shuffled and split between train and test sets # the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data() (x_train, y_train), (x_test, y_test) = mnist.load_data()
X_train = X_train.reshape(60000, 784) x_train = x_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784) x_test = x_test.reshape(10000, 784)
X_train = X_train.astype('float32') x_train = x_train.astype('float32')
X_test = X_test.astype('float32') x_test = x_test.astype('float32')
X_train /= 255 x_train /= 255
X_test /= 255 x_test /= 255
print(X_train.shape[0], 'train samples') print(x_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples') print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices # convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes) y_train = np_utils.to_categorical(y_train, num_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes) y_test = np_utils.to_categorical(y_test, num_classes)
model = Sequential() model = Sequential()
model.add(Dense(512, input_shape=(784,))) model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dropout(0.2)) model.add(Dropout(0.2))
model.add(Dense(512)) model.add(Dense(512, activation='relu'))
model.add(Activation('relu'))
model.add(Dropout(0.2)) model.add(Dropout(0.2))
model.add(Dense(10)) model.add(Dense(10, activation='softmax'))
model.add(Activation('softmax'))
model.summary() model.summary()
@ -52,9 +49,9 @@ model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(), optimizer=RMSprop(),
metrics=['accuracy']) metrics=['accuracy'])
history = model.fit(X_train, Y_train, history = model.fit(x_train, y_train,
batch_size=batch_size, nb_epoch=nb_epoch, batch_size=batch_size, num_epoch=num_epoch,
verbose=1, validation_data=(X_test, Y_test)) verbose=1, validation_data=(x_test, y_test))
score = model.evaluate(X_test, Y_test, verbose=0) score = model.evaluate(x_test, y_test, verbose=0)
print('Test score:', score[0]) print('Test loss:', score[0])
print('Test accuracy:', score[1]) print('Test accuracy:', score[1])