NeuralNetworkSource

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense


# dimensions of our images.
img_width, img_height = 32, 32

train_data_dir = 'data/train/'
validation_data_dir = 'data/train/'
nb_train_samples = 32
nb_validation_samples = 32
nb_epoch = 500


model = Sequential()
#model.add(Convolution2D(3, 3, 32, input_shape=(3, img_width, img_height)))
#model.add(Flatten())
#model.add(Dense(3096))
#model.add(Activation('relu'))
#model.add(Dropout(0.5))
#model.add(Dense(363096))
#model.add(Activation('softmax'))

model.add(Convolution2D(32, 3, 3, input_shape=(3, 32, 32), border_mode='same', activation='relu'))
model.add(Dropout(0.2))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(363096, activation='softmax'))

model.compile(loss='sparse_categorical_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator()

train_generator = train_datagen.flow_from_directory(
        train_data_dir,
        target_size=(img_width, img_height),
        batch_size=32,
        color_mode="rgb",
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_data_dir,
        target_size=(32, 32),
        batch_size=32,
        color_mode="rgb",
        class_mode='binary')

model.fit_generator(
        train_generator,
        samples_per_epoch=nb_train_samples,
        nb_epoch=nb_epoch,
        validation_data=validation_generator,
        nb_val_samples=2)