def build_model(): """Builds and returns the network.""" # Create the inputs to the network. sky_images = Input(shape=(480, 480, 3), name='SkyImages') # sky images tsi = Input(shape=(480, 480), dtype='int64', name='TSIDecisionImages') # TSI's decision images # Main body of the network conv1 = Convolution2D(filters=32, kernel_size=3, padding='same', data_format='channels_last', activation='relu')(sky_images) maxpool1 = MaxPool2D(pool_size=(1, 100), strides=(1, 1), padding='same', data_format='channels_last')(conv1) maxpool2 = MaxPool2D(pool_size=(100, 1), strides=(1, 1), padding='same', data_format='channels_last')(conv1) concat1 = concatenate([conv1, maxpool1], axis=3) concat2 = concatenate([maxpool2, concat1], axis=3) concat3 = concatenate([concat2, sky_images], axis=3) conv2 = Convolution2D(filters=4, kernel_size=3, padding='same', data_format='channels_last', activation='relu')(concat3) decision = DecidePixelColors()(conv2) model = Model(inputs=[sky_images], outputs=[conv2, decision]) # in outputs, , decision return model
def feature_extractor(input_net):
net_1 = Conv2D(96, 1, 1)(input_net)
net_1 = ReLU()(net_1)
net_1 = Conv2D(208, 3, 1)(net_1)
net_1 = ReLU()(net_1)
net_2 = MaxPool2D(3, 1)(input_net)
net_2 = Conv2D(64, 1, 1)(net_2)
net_2 = ReLU()(net_2)
concat = concatenate(inputs=[net_1, net_2], axis=3)
pooling_out = MaxPool2D(3, 2)(concat)
return pooling_out
def generate_inceptionResnetv2_based_model():
irv2 = tf.keras.applications.inception_resnet_v2.InceptionResNetV2(
include_top=False)
irv2.trainable = False
# This returns a tensor
input1 = Input(shape=(299, 299, 3), name='input1')
input2 = Input(shape=(299, 299, 3), name='input2')
out1 = irv2(input1)
out2 = irv2(input2)
averPool = AveragePooling2D(pool_size=(8, 8))
out1 = averPool(out1)
out2 = averPool(out2)
y = concatenate([out1, out2])
dense = Dense(1)
y = dense(y)
activation = Activation('tanh')
y = activation(y)
y = Flatten()(y)
model = Model(inputs=[input1, input2], outputs=y)
return model