Last active
April 8, 2018 02:27
-
-
Save mjdietzx/3aaf9c58486f6e6ff310a0d960d8bb4e to your computer and use it in GitHub Desktop.
Standalone script based of example in keras for issue
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
'''Trains a simple convnet on the MNIST dataset. | |
Gets 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. | |
''' | |
from __future__ import print_function | |
import numpy as np | |
np.random.seed(1337) # for reproducibility | |
from keras.callbacks import ReduceLROnPlateau | |
from keras.datasets import mnist | |
from keras.models import Sequential | |
from keras.layers import Dense, Dropout, Activation, Flatten | |
from keras.layers import Convolution2D, MaxPooling2D | |
from keras.utils import np_utils | |
from keras import backend as K | |
batch_size = 128 | |
nb_classes = 10 | |
nb_epoch = 100 | |
# input image dimensions | |
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 | |
(X_train, y_train), (X_test, y_test) = mnist.load_data() | |
if K.image_dim_ordering() == 'th': | |
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) | |
input_shape = (1, img_rows, img_cols) | |
else: | |
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) | |
input_shape = (img_rows, img_cols, 1) | |
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(nb_filters, kernel_size[0], kernel_size[1], | |
border_mode='valid', | |
input_shape=input_shape)) | |
model.add(Activation('relu')) | |
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(Flatten()) | |
model.add(Dense(128)) | |
model.add(Activation('relu')) | |
model.add(Dropout(0.5)) | |
model.add(Dense(nb_classes)) | |
model.add(Activation('softmax')) | |
model.compile(loss='categorical_crossentropy', | |
optimizer='adadelta', | |
metrics=['accuracy']) | |
reduce_lr = ReduceLROnPlateau(monitor='val_loss', patience=4, cooldown=0) | |
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, | |
verbose=1, validation_data=(X_test, Y_test), callbacks=[reduce_lr]) | |
score = model.evaluate(X_test, Y_test, verbose=0) | |
print('Test score:', score[0]) | |
print('Test accuracy:', score[1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment