cifar10_keras_model_create.py

from keras.models import Sequential
from keras.layers import Dense, MaxPooling2D, Conv2D, Flatten

def build_keras_model():
    model = Sequential()
  # CNN layer
    model.add(Conv2D(filters=32, kernel_size=3, strides=1, padding='same', activation='elu',
                     input_shape=(image_height, image_width, num_channels)))
    model.add(Conv2D(filters=32, kernel_size=3, strides=1, padding='same', activation='elu'))
    model.add(MaxPooling2D(pool_size=2))
    
    model.add(Conv2D(filters=64, kernel_size=3, strides=1, padding='same', activation='elu'))
    model.add(Conv2D(filters=64, kernel_size=3, strides=1, padding='same', activation='elu'))  
    model.add(MaxPooling2D(pool_size=2))                  

    model.add(Conv2D(filters=128, kernel_size=3, strides=1, padding='same', activation='elu'))
    model.add(Conv2D(filters=128, kernel_size=3, strides=1, padding='same', activation='elu'))              
    model.add(MaxPooling2D(pool_size=2))                   

  # Flatten
    model.add(Flatten())
  # Dense (fully connected) layers
    model.add(Dense(512, activation='relu')) 
  # output layer with softmax
    model.add(Dense(10, activation='softmax'))
  # compile with categorical_crossentropy loss function & adam optimizer
    model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
    return model
  
# create the model & show structure
kr_base_model = build_keras_model()
print(kr_base_model.summary())