65 lines
2.0 KiB
Python
65 lines
2.0 KiB
Python
from __future__ import absolute_import
|
|
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.core import Dense, Dropout, Activation, Flatten
|
|
from keras.layers.convolutional import Convolution2D, MaxPooling2D
|
|
from keras.utils import np_utils
|
|
|
|
'''
|
|
Train a simple convnet on the MNIST dataset.
|
|
|
|
Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python mnist_cnn.py
|
|
|
|
Get to 99.25% test accuracy after 12 epochs (there is still a lot of margin for parameter tuning).
|
|
16 seconds per epoch on a GRID K520 GPU.
|
|
'''
|
|
|
|
batch_size = 128
|
|
nb_classes = 10
|
|
nb_epoch = 12
|
|
|
|
# the data, shuffled and split between tran and test sets
|
|
(X_train, y_train), (X_test, y_test) = mnist.load_data()
|
|
|
|
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28)
|
|
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28)
|
|
X_train = X_train.astype("float32")
|
|
X_test = X_test.astype("float32")
|
|
X_train /= 255
|
|
X_test /= 255
|
|
print('X_train shape:', X_train.shape)
|
|
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()
|
|
|
|
model.add(Convolution2D(32, 1, 3, 3, border_mode='full'))
|
|
model.add(Activation('relu'))
|
|
model.add(Convolution2D(32, 32, 3, 3))
|
|
model.add(Activation('relu'))
|
|
model.add(MaxPooling2D(poolsize=(2, 2)))
|
|
model.add(Dropout(0.25))
|
|
|
|
model.add(Flatten())
|
|
model.add(Dense(32*196, 128))
|
|
model.add(Activation('relu'))
|
|
model.add(Dropout(0.5))
|
|
|
|
model.add(Dense(128, nb_classes))
|
|
model.add(Activation('softmax'))
|
|
|
|
model.compile(loss='categorical_crossentropy', optimizer='adadelta')
|
|
|
|
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, show_accuracy=True, verbose=1, 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])
|