def feature_extractor_network(self):
# input
in_image = Input(shape = in_shape)
# C1 Layer
nett = Conv2D(32,(5,5))(in_image)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
# M2 Layer
nett = MaxPooling2D(pool_size = (3,3))(nett)
# C3 Layer
nett = Conv2D(64,(3,3))
nett = BatchNormalization(pool_size = (3,3))(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
# L4 Layer
nett = LocallyConnected2D(128,(3,3))(nett)
# L5 Layer
nett = LocallyConnected2D(256,(3,3))(nett)
# F6 Layer
nett = Dense(512,activation='relu')(nett)
nett = Dropout(0.2)(nett)
# F7 Layer
out_features = Dense(activation='tanh')(nett)
# output
model = Model(inputs = in_image, outputs = out_features)
return model
def _create_model_2(self, input_tensor, input_shape, num_classes,
dropout_rate):
#input_tensor = Input(shape=input_shape)
model = Sequential()
model.add(
Conv2D(32,
kernel_size=(5, 5),
padding='same',
activation='relu',
input_shape=input_shape[1:]))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(
Conv2D(64, kernel_size=(3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Flatten())
model.add(Dense(1024, activation='relu'))
model.add(Dropout(dropout_rate))
if 1 == num_classes:
model.add(Dense(1, activation='sigmoid'))
#model.add(Dense(1, activation='sigmoid', activity_regularizer=keras.regularizers.activity_l2(0.0001)))
elif num_classes >= 2:
model.add(Dense(num_classes, activation='softmax'))
#model.add(Dense(num_classes, activation='softmax', activity_regularizer=keras.regularizers.activity_l2(0.0001)))
else:
assert num_classes > 0, 'Invalid number of classes.'
# Display the model summary.
#model.summary()
return model(input_tensor)
def _create_model_1(self, input_tensor, num_classes, dropout_rate):
x = Conv2D(32, kernel_size=(5, 5), padding='same',
activation='relu')(input_tensor)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(x)
x = Conv2D(64, kernel_size=(3, 3), padding='same',
activation='relu')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(x)
x = Flatten()(x)
x = Dense(1024, activation='relu')(x)
x = Dropout(dropout_rate)(x)
if 1 == num_classes:
x = Dense(1, activation='sigmoid')(x)
#x = Dense(1, activation='sigmoid', activity_regularizer=keras.regularizers.activity_l2(0.0001))(x)
elif num_classes >= 2:
x = Dense(num_classes, activation='softmax')(x)
#x = Dense(num_classes, activation='softmax', activity_regularizer=keras.regularizers.activity_l2(0.0001))(x)
else:
assert num_classes > 0, 'Invalid number of classes.'
#model = Model(inputs=input_tensor, outputs=x)
return x
def zero_padding_block(input_tensor,
filters,
stage,
block,
se_enabled=False,
se_ratio=16):
numFilters1, numFilters2 = filters
if K.image_data_format() == 'channels_last':
bn_axis = -1
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + '_' + str(block) + '_branch'
bn_name_base = 'bn' + str(stage) + '_' + str(block) + '_branch'
# downsampling directly by convolution with stride 2
x = Conv2D(numFilters1, (3, 3),
strides=(2, 2),
kernel_initializer='he_normal',
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(numFilters2, (3, 3),
kernel_initializer='he_normal',
name=conv_name_base + '2b')(x)
# squeeze and excitation block
if se_enabled:
x = squeeze_excitation_block(x, ratio=se_ratio)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
# zero padding and downsampling with 1x1 conv shortcut connection
x_shortcut = Conv2D(1, (1, 1),
strides=(2, 2),
kernel_initializer='he_normal',
name=conv_name_base + '1')(input_tensor)
x_shortcut2 = MaxPooling2D(pool_size=(1, 1),
strides=(2, 2),
border_mode='same')(input_tensor)
x_shortcut = Lambda(zeropad, output_shape=zeropad_output_shape)(x_shortcut)
x_shortcut = BatchNormalization(axis=bn_axis,
name=bn_name_base + '1')(x_shortcut)
# addition of shortcut
x = Add()([x, x_shortcut])
x = Activation('relu')(x)
return x
def projection_bottleneck_block(input_tensor,
filters,
stage,
block,
se_enabled=False,
se_ratio=16):
numFilters1, numFilters2, numFilters3 = filters
if K.image_data_format() == 'channels_last':
bn_axis = -1
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + '_' + str(block) + '_branch'
bn_name_base = 'bn' + str(stage) + '_' + str(block) + '_branch'
x = Conv2D(numFilters1, (1, 1),
strides=(2, 2),
kernel_initializer='he_normal',
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(numFilters2, (3, 3),
padding='same',
kernel_initializer='he_normal',
name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv2D(numFilters3, (1, 1),
kernel_initializer='he_normal',
name=conv_name_base + '2c')(x)
# squeeze and excitation block
if se_enabled:
x = squeeze_excitation_block(x, ratio=se_ratio)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
# projection shortcut
x_shortcut = Conv2D(numFilters3, (1, 1),
strides=(2, 2),
kernel_initializer='he_normal',
name=conv_name_base + '1')(input_tensor)
x_shortcut = BatchNormalization(axis=bn_axis,
name=bn_name_base + '1')(x_shortcut)
x = Add()([x, x_shortcut])
x = Activation('relu')(x)
return x
def resnet_layer(inputs,
num_filters=16,
kernel_size=3,
strides=1,
activation='relu',
batch_normalization=True,
conv_first=True):
conv = Conv2D(num_filters,
kernel_size=kernel_size,
strides=strides,
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=l2(1e-4))
x = inputs
if conv_first:
x = conv(x)
if batch_normalization:
x = BatchNormalization()(x)
if activation is not None:
x = Activation(activation)(x)
else:
if batch_normalization:
x = BatchNormalization()(x)
if activation is not None:
x = Activation(activation)(x)
x = conv(x)
return x
def init_model():
#K.clear_session()
tf.reset_default_graph()
model = Sequential()
model.add(Conv2D(16, (3, 3), input_shape=(28, 28, 1), padding = "SAME", activation = "relu"))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
for layer in model.layers:
print(layer.output_shape)
model.compile(loss='sparse_categorical_crossentropy',
optimizer=keras.optimizers.Adadelta(lr=0.1),
metrics=['accuracy'])
return model
def discriminator_network(self):
# input
in_image = Input(shape=self.img_shape)
# C1 layer
nett = Conv2D(64,(5,5))(in_image)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
# C2 layer
nett = Conv2D(128,(5,5))(nett)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
nett = Dropout(0.2)(nett)
# C3 layer
nett = Conv2D(256,(5,5))(nett)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
nett = Dropout(0.2)(nett)
# F4 layer
nett = Flatten()(nett)
validity = Dense(1,alpha = 0.2)(nett)
#output
model = Model(inputs = in_image, outputs = validity)
return model
import tf as tf
from tf.keras.layers import Input, Conv2D
from tf.keras import Model
input = Input((3072, 3072, 3))
x = Conv2D(filters=32, kernel_size=(11, 11), strides=(3, 3),
padding="same")(input)
x = Conv2D(filters=32, kernel_size=(11, 11), strides=(2, 2), padding="same")(x)
x = Conv2D(filters=32, kernel_size=(11, 11), strides=(2, 2), padding="same")(x)
# x = Conv2D(filters=128,kernel_size=(11,11),strides=(2,2),padding="same")(x)
# x = Conv2D(filters=64,kernel_size=(11,11),padding="same")(x)
# x = Conv2D(filters=64,kernel_size=(11,11),padding="same")(x)
# x = Conv2D(filters=64,kernel_size=(11,11),strides=(2,2),padding="same")(x)
#
# x = Conv2D(filters=128,kernel_size=(11,11),padding="same")(x)
# x = Conv2D(filters=128,kernel_size=(11,11),padding="same")(x)
# x = Conv2D(filters=128,kernel_size=(11,11),strides=(2,2),padding="same")(x)
model = Model(inputs=input, outputs=x)
model.summary()