From 7f85a6c6cbf7703083b0adb31703ec88341bbee7 Mon Sep 17 00:00:00 2001
From: Max Pumperla <max.pumperla@googlemail.com>
Date: Wed, 20 Apr 2016 08:51:02 +0200
Subject: [PATCH] generator example

---
 examples/cifar_generator_cnn.py | 114 ++++++++++++++++++++++++++++++++
 1 file changed, 114 insertions(+)
 create mode 100644 examples/cifar_generator_cnn.py

diff --git a/examples/cifar_generator_cnn.py b/examples/cifar_generator_cnn.py
new file mode 100644
index 0000000..9a1f91a
--- /dev/null
+++ b/examples/cifar_generator_cnn.py
@@ -0,0 +1,114 @@
+from __future__ import print_function
+from hyperopt import Trials, STATUS_OK, tpe
+from hyperas import optim
+from hyperas.distributions import choice, uniform
+
+
+def data():
+    from keras.preprocessing.image import ImageDataGenerator
+    from keras.datasets import cifar10
+    from keras.utils import np_utils
+
+    nb_classes = 10
+    # the data, shuffled and split between train and test sets
+    (X_train, y_train), (X_test, y_test) = cifar10.load_data()
+    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)
+
+    X_train = X_train.astype('float32')
+    X_test = X_test.astype('float32')
+    X_train /= 255
+    X_test /= 255
+
+    # this will do preprocessing and realtime data augmentation
+    datagen = ImageDataGenerator(
+        featurewise_center=False,  # set input mean to 0 over the dataset
+        samplewise_center=False,  # set each sample mean to 0
+        featurewise_std_normalization=False,  # divide inputs by std of the dataset
+        samplewise_std_normalization=False,  # divide each input by its std
+        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,  # randomly flip images
+        vertical_flip=False)  # randomly flip images
+
+    # compute quantities required for featurewise normalization
+    # (std, mean, and principal components if ZCA whitening is applied)
+    datagen.fit(X_train)
+
+    return datagen, X_train, Y_train, X_test, Y_test
+
+def model(datagen, X_train, Y_train, X_test, Y_test):
+    from keras.models import Sequential
+    from keras.layers.core import Dense, Dropout, Activation, Flatten
+    from keras.layers.convolutional import Convolution2D, MaxPooling2D
+    from keras.optimizers import SGD
+
+    batch_size = 32
+    nb_epoch = 200
+
+    # input image dimensions
+    img_rows, img_cols = 32, 32
+    # the CIFAR10 images are RGB
+    img_channels = 3
+
+    model = Sequential()
+
+    model.add(Convolution2D(32, 3, 3, border_mode='same',
+                            input_shape=(img_channels, img_rows, img_cols)))
+    model.add(Activation('relu'))
+    model.add(Convolution2D(32, 3, 3))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Dropout({{uniform(0, 1)}}))
+
+    model.add(Convolution2D(64, 3, 3, border_mode='same'))
+    model.add(Activation('relu'))
+    model.add(Convolution2D(64, 3, 3))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Dropout({{uniform(0, 1)}}))
+
+    model.add(Flatten())
+    model.add(Dense(512))
+    model.add(Activation('relu'))
+    model.add(Dropout(0.5))
+    model.add(Dense(nb_classes))
+    model.add(Activation('softmax'))
+
+    # let's train the model using SGD + momentum (how original).
+    sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
+    model.compile(loss='categorical_crossentropy',
+                  optimizer=sgd,
+                  metrics=['accuracy'])
+
+    # fit the model on the batches generated by datagen.flow()
+    model.fit_generator(datagen.flow(X_train, Y_train,
+                        batch_size=batch_size),
+                        samples_per_epoch=X_train.shape[0],
+                        nb_epoch=nb_epoch,
+                        validation_data=(X_test, Y_test))
+
+    score, acc = model.evaluate(X_test, Y_test, verbose=0)
+
+    return {'loss': -acc, 'status': STATUS_OK, 'model': model}
+
+
+if __name__ == '__main__':
+
+    datagen, X_train, Y_train, X_test, Y_test = data()
+
+    best_run, best_model = optim.minimize(model=model,
+                                          data=data,
+                                          algo=tpe.suggest,
+                                          max_evals=5,
+                                          trials=Trials())
+
+    print("Evalutation of best performing model:")
+    print(best_model.evaluate(X_test, Y_test))