cifar10.py

from __future__ import print_function
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.utils import np_utils
from keras.callbacks import ReduceLROnPlateau, CSVLogger, EarlyStopping

import numpy as np
import resnet


lr_reducer = ReduceLROnPlateau(factor=np.sqrt(0.1), cooldown=0, patience=5, min_lr=0.5e-6)
early_stopper = EarlyStopping(min_delta=0.001, patience=10)
csv_logger = CSVLogger('resnet18_cifar10.csv')

batch_size = 32
nb_classes = 10
nb_epoch = 100
data_augmentation = False

img_rows, img_cols = 32, 32
img_channels = 3

(X_train, y_train), (X_test, y_test) = cifar10.load_data()

# 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)

X_train = X_train.astype('float32')
X_test = X_test.astype('float32')

mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_test -= mean_image
X_train /= 128.
X_test /= 128.

model = resnet.ResnetBuilder.build_resnet_18((img_channels, img_rows, img_cols), nb_classes)
model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

if not data_augmentation:
    print('Not using data augmentation.')
    model.fit(X_train, Y_train,
              batch_size=batch_size,
              nb_epoch=nb_epoch,
              validation_data=(X_test, Y_test),
              shuffle=True,
              callbacks=[lr_reducer, early_stopper, csv_logger])
else:
    print('Using real-time data augmentation.')
    # This will do preprocessing and realtime data augmentation:
    datagen = ImageDataGenerator(
        featurewise_center=False,  
        samplewise_center=False,  
        featurewise_std_normalization=False,  
        samplewise_std_normalization=False,  
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=0,  # randomly rotate images in the range (degrees, 0 to 180)
        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  
        vertical_flip=False)  

    datagen.fit(X_train)
    model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size),
                        steps_per_epoch=X_train.shape[0] // batch_size,
                        validation_data=(X_test, Y_test),
                        epochs=nb_epoch, verbose=1, max_q_size=100,
                        callbacks=[lr_reducer, early_stopper, csv_logger])