def UResNet34(input_shape=(128, 128, 1), classes=1, decoder_filters=16, decoder_block_type='upsampling',
encoder_weights="imagenet", input_tensor=None, activation='sigmoid', **kwargs):
backbone = ResnetBuilder.build_resnet_34(input_shape=input_shape,input_tensor=input_tensor)
input_layer = backbone.input #input = backbone.input
output_layer = build_model(input_layer, 16,0.5) #x
model = Model(input_layer, output_layer)
c = optimizers.adam(lr = 0.01)
model.compile(loss="binary_crossentropy", optimizer=c, metrics=[my_iou_metric])
model.name = 'u-resnet34'
return model
def UXception(input_shape=(None, None, 3)):
backbone = Xception(input_shape=input_shape,
weights='imagenet',
include_top=False)
input = backbone.input
start_neurons = 16
conv4 = backbone.layers[121].output
conv4 = LeakyReLU(alpha=0.1)(conv4)
pool4 = MaxPooling2D((2, 2))(conv4)
pool4 = Dropout(0.1)(pool4)
# Middle
convm = Conv2D(start_neurons * 32, (3, 3), activation=None,
padding="same")(pool4)
convm = residual_block(convm, start_neurons * 32)
convm = residual_block(convm, start_neurons * 32)
convm = LeakyReLU(alpha=0.1)(convm)
# 10 -> 20
deconv4 = Conv2DTranspose(start_neurons * 16, (3, 3),
strides=(2, 2),
padding="same")(convm)
uconv4 = concatenate([deconv4, conv4])
uconv4 = Dropout(0.1)(uconv4)
uconv4 = Conv2D(start_neurons * 16, (3, 3),
activation=None,
padding="same")(uconv4)
uconv4 = residual_block(uconv4, start_neurons * 16)
uconv4 = residual_block(uconv4, start_neurons * 16)
uconv4 = LeakyReLU(alpha=0.1)(uconv4)
# 10 -> 20
deconv3 = Conv2DTranspose(start_neurons * 8, (3, 3),
strides=(2, 2),
padding="same")(uconv4)
conv3 = backbone.layers[31].output
uconv3 = concatenate([deconv3, conv3])
uconv3 = Dropout(0.1)(uconv3)
uconv3 = Conv2D(start_neurons * 8, (3, 3), activation=None,
padding="same")(uconv3)
uconv3 = residual_block(uconv3, start_neurons * 8)
uconv3 = residual_block(uconv3, start_neurons * 8)
uconv3 = LeakyReLU(alpha=0.1)(uconv3)
# 20 -> 40
deconv2 = Conv2DTranspose(start_neurons * 4, (3, 3),
strides=(2, 2),
padding="same")(uconv3)
conv2 = backbone.layers[21].output
conv2 = ZeroPadding2D(((1, 0), (1, 0)))(conv2)
uconv2 = concatenate([deconv2, conv2])
uconv2 = Dropout(0.1)(uconv2)
uconv2 = Conv2D(start_neurons * 4, (3, 3), activation=None,
padding="same")(uconv2)
uconv2 = residual_block(uconv2, start_neurons * 4)
uconv2 = residual_block(uconv2, start_neurons * 4)
uconv2 = LeakyReLU(alpha=0.1)(uconv2)
# 40 -> 80
deconv1 = Conv2DTranspose(start_neurons * 2, (3, 3),
strides=(2, 2),
padding="same")(uconv2)
conv1 = backbone.layers[11].output
conv1 = ZeroPadding2D(((3, 0), (3, 0)))(conv1)
uconv1 = concatenate([deconv1, conv1])
uconv1 = Dropout(0.1)(uconv1)
uconv1 = Conv2D(start_neurons * 2, (3, 3), activation=None,
padding="same")(uconv1)
uconv1 = residual_block(uconv1, start_neurons * 2)
uconv1 = residual_block(uconv1, start_neurons * 2)
uconv1 = LeakyReLU(alpha=0.1)(uconv1)
# 80 -> 160
uconv0 = Conv2DTranspose(start_neurons * 1, (3, 3),
strides=(2, 2),
padding="same")(uconv1)
uconv0 = Dropout(0.1)(uconv0)
uconv0 = Conv2D(start_neurons * 1, (3, 3), activation=None,
padding="same")(uconv0)
uconv0 = residual_block(uconv0, start_neurons * 1)
uconv0 = residual_block(uconv0, start_neurons * 1)
uconv0 = LeakyReLU(alpha=0.1)(uconv0)
uconv0 = Dropout(0.1 / 2)(uconv0)
output_layer = Conv2D(1, (1, 1), padding="same",
activation="sigmoid")(uconv0)
model = Model(input, output_layer)
model.name = 'u-xception'
return model
def UEfficientNet(input_shape=(None, None, 3), dropout_rate=0.1):
backbone = EfficientNetB4(weights='imagenet',
include_top=False,
input_shape=input_shape)
input = backbone.input
start_neurons = 16
conv4 = backbone.layers[342].output
conv4 = LeakyReLU(alpha=0.1)(conv4)
pool4 = MaxPooling2D((2, 2))(conv4)
pool4 = Dropout(dropout_rate)(pool4)
# Middle
convm = Conv2D(start_neurons * 32, (3, 3), activation=None,
padding="same")(pool4)
convm = residual_block(convm, start_neurons * 32)
convm = residual_block(convm, start_neurons * 32)
convm = LeakyReLU(alpha=0.1)(convm)
deconv4 = Conv2DTranspose(start_neurons * 16, (3, 3),
strides=(2, 2),
padding="same")(convm)
uconv4 = concatenate([deconv4, conv4])
uconv4 = Dropout(dropout_rate)(uconv4)
uconv4 = Conv2D(start_neurons * 16, (3, 3),
activation=None,
padding="same")(uconv4)
uconv4 = residual_block(uconv4, start_neurons * 16)
uconv4 = residual_block(uconv4, start_neurons * 16)
uconv4 = LeakyReLU(alpha=0.1)(uconv4)
deconv3 = Conv2DTranspose(start_neurons * 8, (3, 3),
strides=(2, 2),
padding="same")(uconv4)
conv3 = backbone.layers[154].output
uconv3 = concatenate([deconv3, conv3])
uconv3 = Dropout(dropout_rate)(uconv3)
uconv3 = Conv2D(start_neurons * 8, (3, 3), activation=None,
padding="same")(uconv3)
uconv3 = residual_block(uconv3, start_neurons * 8)
uconv3 = residual_block(uconv3, start_neurons * 8)
uconv3 = LeakyReLU(alpha=0.1)(uconv3)
deconv2 = Conv2DTranspose(start_neurons * 4, (3, 3),
strides=(2, 2),
padding="same")(uconv3)
conv2 = backbone.layers[92].output
uconv2 = concatenate([deconv2, conv2])
uconv2 = Dropout(0.1)(uconv2)
uconv2 = Conv2D(start_neurons * 4, (3, 3), activation=None,
padding="same")(uconv2)
uconv2 = residual_block(uconv2, start_neurons * 4)
uconv2 = residual_block(uconv2, start_neurons * 4)
uconv2 = LeakyReLU(alpha=0.1)(uconv2)
deconv1 = Conv2DTranspose(start_neurons * 2, (3, 3),
strides=(2, 2),
padding="same")(uconv2)
conv1 = backbone.layers[30].output
uconv1 = concatenate([deconv1, conv1])
uconv1 = Dropout(0.1)(uconv1)
uconv1 = Conv2D(start_neurons * 2, (3, 3), activation=None,
padding="same")(uconv1)
uconv1 = residual_block(uconv1, start_neurons * 2)
uconv1 = residual_block(uconv1, start_neurons * 2)
uconv1 = LeakyReLU(alpha=0.1)(uconv1)
uconv0 = Conv2DTranspose(start_neurons * 1, (3, 3),
strides=(2, 2),
padding="same")(uconv1)
uconv0 = Dropout(0.1)(uconv0)
uconv0 = Conv2D(start_neurons * 1, (3, 3), activation=None,
padding="same")(uconv0)
uconv0 = residual_block(uconv0, start_neurons * 1)
uconv0 = residual_block(uconv0, start_neurons * 1)
uconv0 = LeakyReLU(alpha=0.1)(uconv0)
uconv0 = Dropout(dropout_rate / 2)(uconv0)
output_layer = Conv2D(1, (1, 1), padding="same",
activation="sigmoid")(uconv0)
model = Model(input, output_layer)
model.name = 'u-xception'
return model
def init_resnet_baseline(input_shape, num_classes):
num_hidden = 64
inp = Input(input_shape)
# block 1
conv_x = Conv1D(num_hidden, 8, padding='same')(inp)
conv_x = BatchNormalization()(conv_x)
conv_x = Activation('relu')(conv_x)
conv_y = Conv1D(num_hidden, 5, padding='same')(conv_x)
conv_y = BatchNormalization()(conv_y)
conv_y = Activation('relu')(conv_y)
conv_z = Conv1D(num_hidden, 3, padding='same')(conv_y)
conv_z = BatchNormalization()(conv_z)
## expand channels
shortcut_1 = Conv1D(num_hidden, 1, padding='same')(inp)
shortcut_1 = BatchNormalization()(shortcut_1)
outp_1 = Add()([shortcut_1, conv_z])
outp_1 = Activation('relu')(outp_1)
# block 2
conv_x = Conv1D(2 * num_hidden, 8, padding='same')(outp_1)
conv_x = BatchNormalization()(conv_x)
conv_x = Activation('relu')(conv_x)
conv_y = Conv1D(2 * num_hidden, 5, padding='same')(conv_x)
conv_y = BatchNormalization()(conv_y)
conv_y = Activation('relu')(conv_y)
conv_z = Conv1D(2 * num_hidden, 3, padding='same')(conv_y)
conv_z = BatchNormalization()(conv_z)
## expand channels
shortcut_2 = Conv1D(2 * num_hidden, 1, padding='same')(outp_1)
shortcut_2 = BatchNormalization()(shortcut_2)
outp_2 = Add()([shortcut_2, conv_z])
outp_2 = Activation('relu')(outp_2)
# block 3
conv_x = keras.layers.Conv1D(2 * num_hidden, 8, padding='same')(outp_2)
conv_x = BatchNormalization()(conv_x)
conv_x = Activation('relu')(conv_x)
conv_y = Conv1D(2 * num_hidden, 5, padding='same')(conv_x)
conv_y = BatchNormalization()(conv_y)
conv_y = Activation('relu')(conv_y)
conv_z = Conv1D(2 * num_hidden, 3, padding='same')(conv_y)
conv_z = BatchNormalization()(conv_z)
## channels are equal now
shortcut_y = BatchNormalization()(outp_2)
outp_3 = Add()([shortcut_2, conv_z])
outp_3 = Activation('relu')(outp_3)
# pooling and prediction layer
gap = GlobalAveragePooling1D()(outp_3)
outp = Dense(num_classes, activation='softmax')(gap)
model = Model(inp, outp)
model.name = 'ResNet'
return model
def DeconvNet(input_shape, num_classes):
inputs, outputs = build_deconvnet(input_shape, num_classes)
model = Model(inputs=inputs, outputs=outputs)
model.name = 'DeconvNet'
return model
