CIFAR10-Conv-SELU.py

# Adapted KERAS tutorial 

import tensorflow as tf
import tensorflow.keras as keras
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, AlphaDropout, Activation, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D


import os
import pickle
import numpy as np

batch_size = 32
num_classes = 10
epochs = 2
data_augmentation = True
num_predictions = 20
save_dir = os.path.join(os.getcwd(), 'saved_models')
model_name = 'keras_cifar10_trained_model.h5'

# list devices so you can check whether your gpu is available
print(tf.config.list_physical_devices())

# 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 = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same',
                 input_shape=x_train.shape[1:],kernel_initializer='lecun_normal',bias_initializer='zeros'))
model.add(Activation('selu'))
model.add(Conv2D(32, (3, 3),kernel_initializer='lecun_normal',bias_initializer='zeros'))
model.add(Activation('selu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(AlphaDropout(0.1))

model.add(Conv2D(64, (3, 3), padding='same',kernel_initializer='lecun_normal',bias_initializer='zeros'))
model.add(Activation('selu'))
model.add(Conv2D(64, (3, 3),kernel_initializer='lecun_normal',bias_initializer='zeros'))
model.add(Activation('selu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(AlphaDropout(0.1))

model.add(Flatten())
model.add(Dense(512,kernel_initializer='lecun_normal',bias_initializer='zeros'))
model.add(Activation('selu'))
model.add(AlphaDropout(0.2))
model.add(Dense(num_classes,kernel_initializer='lecun_normal',bias_initializer='zeros'))
model.add(Activation('softmax'))

# initiate RMSprop optimizer
opt = keras.optimizers.RMSprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

if not data_augmentation:
    print('Not using data augmentation.')
    model.fit(x_train, y_train,
              batch_size=batch_size,
              epochs=epochs,
              validation_data=(x_test, y_test),
              shuffle=True)
else:
    print('Using real-time data augmentation.')
    # 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 feature-wise normalization
    # (std, mean, and principal components if ZCA whitening is applied).
    datagen.fit(x_train)

    # Fit the model on the batches generated by datagen.flow().
    model.fit(datagen.flow(x_train, y_train,
                                     batch_size=batch_size),
                        steps_per_epoch=x_train.shape[0] // batch_size,
                        epochs=epochs,
                        validation_data=(x_test, y_test))

# Save model and weights
if not os.path.isdir(save_dir):
    os.makedirs(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)

# Load label names to use in prediction results
label_list_path = 'datasets/cifar-10-batches-py/batches.meta'


keras_dir = os.path.expanduser(os.path.join('~', '.keras'))
datadir_base = os.path.expanduser(keras_dir)
if not os.access(datadir_base, os.W_OK):
    datadir_base = os.path.join('/tmp', '.keras')
label_list_path = os.path.join(datadir_base, label_list_path)

with open(label_list_path, mode='rb') as f:
    labels = pickle.load(f)

# Evaluate model with test data set and share sample prediction results
evaluation = model.evaluate(datagen.flow(x_test, y_test,
                                      batch_size=batch_size),
                                      steps=x_test.shape[0] // batch_size)

print('Model Accuracy = %.5f' % (evaluation[1]))

f = open('CIFAR10_SELU_results.txt', 'a')
f.write(' Test accuracy:' + str(evaluation[1]) +  '\n')  
f.close() 


predict_gen = model.predict(datagen.flow(x_test, y_test,
                                      batch_size=batch_size),
                                      steps=x_test.shape[0] // batch_size)

for predict_index, predicted_y in enumerate(predict_gen):
    actual_label = labels['label_names'][np.argmax(y_test[predict_index])]
    predicted_label = labels['label_names'][np.argmax(predicted_y)]
    print('Actual Label = %s vs. Predicted Label = %s' % (actual_label,
                                                          predicted_label))
    if predict_index == num_predictions:
        break