Python layers.Subtract方法代碼示例

# 需要導入模塊: from keras import layers [as 別名]
# 或者: from keras.layers import Subtract [as 別名]
def _build_model(input_shape, hidden_layer_sizes, activation):
        """
        Build Keras Ranker NN model (Ranknet / LambdaRank NN).
        """
        # Neural network structure
        hidden_layers = []
        for i in range(len(hidden_layer_sizes)):
            hidden_layers.append(Dense(hidden_layer_sizes[i], activation=activation[i], name=str(activation[i]) + '_layer' + str(i)))
        h0 = Dense(1, activation='linear', name='Identity_layer')
        input1 = Input(shape=(input_shape,), name='Input_layer1')
        input2 = Input(shape=(input_shape,), name='Input_layer2')
        x1 = input1
        x2 = input2
        for i in range(len(hidden_layer_sizes)):
            x1 = hidden_layers[i](x1)
            x2 = hidden_layers[i](x2)
        x1 = h0(x1)
        x2 = h0(x2)
        # Subtract layer
        subtracted = Subtract(name='Subtract_layer')([x1, x2])
        # sigmoid
        out = Activation('sigmoid', name='Activation_layer')(subtracted)
        # build model
        model = Model(inputs=[input1, input2], outputs=out)
        return model 

# 需要導入模塊: from keras import layers [as 別名]
# 或者: from keras.layers import Subtract [as 別名]
def DnCNN():
    
    inpt = Input(shape=(None,None,1))
    # 1st layer, Conv+relu
    x = Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding='same')(inpt)
    x = Activation('relu')(x)
    # 15 layers, Conv+BN+relu
    for i in range(15):
        x = Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding='same')(x)
        x = BatchNormalization(axis=-1, epsilon=1e-3)(x)
        x = Activation('relu')(x)   
    # last layer, Conv
    x = Conv2D(filters=1, kernel_size=(3,3), strides=(1,1), padding='same')(x)
    x = Subtract()([inpt, x])   # input - noise
    model = Model(inputs=inpt, outputs=x)
    
    return model 

# 需要導入模塊: from keras import layers [as 別名]
# 或者: from keras.layers import Subtract [as 別名]
def test_merge_subtract():
    i1 = layers.Input(shape=(4, 5))
    i2 = layers.Input(shape=(4, 5))
    i3 = layers.Input(shape=(4, 5))
    i4 = layers.Input(shape=(3, 5))
    o = layers.subtract([i1, i2])
    assert o._keras_shape == (None, 4, 5)
    model = models.Model([i1, i2], o)

    subtract_layer = layers.Subtract()
    o2 = subtract_layer([i1, i2])
    assert subtract_layer.output_shape == (None, 4, 5)

    x1 = np.random.random((2, 4, 5))
    x2 = np.random.random((2, 4, 5))
    out = model.predict([x1, x2])
    assert out.shape == (2, 4, 5)
    assert_allclose(out, x1 - x2, atol=1e-4)

    assert subtract_layer.compute_mask([i1, i2], [None, None]) is None
    assert np.all(K.eval(subtract_layer.compute_mask(
        [i1, i2], [K.variable(x1), K.variable(x2)])))

    # Test invalid use case
    with pytest.raises(ValueError):
        subtract_layer.compute_mask([i1, i2], x1)
    with pytest.raises(ValueError):
        subtract_layer.compute_mask(i1, [None, None])
    with pytest.raises(ValueError):
        subtract_layer([i1, i2, i3])
    with pytest.raises(ValueError):
        subtract_layer([i1]) 

# 需要導入模塊: from keras import layers [as 別名]
# 或者: from keras.layers import Subtract [as 別名]
def baseline_model():
    input_1 = Input(shape=(224, 224, 3))
    input_2 = Input(shape=(224, 224, 3))

    base_model = VGGFace(model='resnet50', include_top=False)

    for x in base_model.layers[:-3]:
        x.trainable = True

    x1 = base_model(input_1)
    x2 = base_model(input_2)

    # x1_ = Reshape(target_shape=(7*7, 2048))(x1)
    # x2_ = Reshape(target_shape=(7*7, 2048))(x2)
    #
    # x_dot = Dot(axes=[2, 2], normalize=True)([x1_, x2_])
    # x_dot = Flatten()(x_dot)

    x1 = Concatenate(axis=-1)([GlobalMaxPool2D()(x1), GlobalAvgPool2D()(x1)])
    x2 = Concatenate(axis=-1)([GlobalMaxPool2D()(x2), GlobalAvgPool2D()(x2)])

    x3 = Subtract()([x1, x2])
    x3 = Multiply()([x3, x3])

    x = Multiply()([x1, x2])

    x = Concatenate(axis=-1)([x, x3])

    x = Dense(100, activation="relu")(x)
    x = Dropout(0.01)(x)
    out = Dense(1, activation="sigmoid")(x)

    model = Model([input_1, input_2], out)

    model.compile(loss="binary_crossentropy", metrics=['acc'], optimizer=Adam(0.00001))

    model.summary()

    return model 

# 需要導入模塊: from keras import layers [as 別名]
# 或者: from keras.layers import Subtract [as 別名]
def baseline_model():
    input_1 = Input(shape=(224, 224, 3))
    input_2 = Input(shape=(224, 224, 3))

    base_model = ResNet50(weights='imagenet', include_top=False)

    for x in base_model.layers[:-3]:
        x.trainable = True

    x1 = base_model(input_1)
    x2 = base_model(input_2)

    # x1_ = Reshape(target_shape=(7*7, 2048))(x1)
    # x2_ = Reshape(target_shape=(7*7, 2048))(x2)
    #
    # x_dot = Dot(axes=[2, 2], normalize=True)([x1_, x2_])
    # x_dot = Flatten()(x_dot)

    x1 = Concatenate(axis=-1)([GlobalMaxPool2D()(x1), GlobalAvgPool2D()(x1)])
    x2 = Concatenate(axis=-1)([GlobalMaxPool2D()(x2), GlobalAvgPool2D()(x2)])

    x3 = Subtract()([x1, x2])
    x3 = Multiply()([x3, x3])

    x = Multiply()([x1, x2])

    x = Concatenate(axis=-1)([x, x3])

    x = Dense(100, activation="relu")(x)
    x = Dropout(0.01)(x)
    out = Dense(1, activation="sigmoid")(x)

    model = Model([input_1, input_2], out)

    model.compile(loss="binary_crossentropy", metrics=['acc'], optimizer=Adam(0.00001))

    model.summary()

    return model 

# 需要導入模塊: from keras import layers [as 別名]
# 或者: from keras.layers import Subtract [as 別名]
def get_Discriminator(input_shape_1, input_shape_2, Encoder):

    dis_inputs_1 = Input(shape=input_shape_1) # Image
    dis_inputs_2 = Input(shape=input_shape_2) # Segmentation

    mul_1 = Multiply()([dis_inputs_1, dis_inputs_2]) # Getting segmented part

    encoder_output_1 = Encoder(dis_inputs_1)

    encoder_output_2 = Encoder(mul_1)

    subtract_dis = Subtract()([encoder_output_1, encoder_output_2])

    dis_conv_block = Conv3D(128, (3, 3, 3), strides=(1, 1, 1), padding='same')(subtract_dis)
    dis_conv_block = Activation('relu')(dis_conv_block)
    dis_conv_block = Conv3D(128, (3, 3, 3), strides=(1, 1, 1), padding='same')(dis_conv_block)
    dis_conv_block = Activation('relu')(dis_conv_block)
    dis_conv_block = MaxPooling3D(pool_size=(2, 2, 2), strides=(2, 2, 2))(dis_conv_block)

    dis_conv_block = Conv3D(64, (3, 3, 3), strides=(1, 1, 1), padding='same')(dis_conv_block)
    dis_conv_block = Activation('relu')(dis_conv_block)
    dis_conv_block = Conv3D(64, (3, 3, 3), strides=(1, 1, 1), padding='same')(dis_conv_block)
    dis_conv_block = Activation('relu')(dis_conv_block)

    dis_conv_block = Conv3D(32, (3, 3, 3), strides=(1, 1, 1), padding='same')(dis_conv_block)
    dis_conv_block = Activation('relu')(dis_conv_block)
    dis_conv_block = Conv3D(32, (3, 3, 3), strides=(1, 1, 1), padding='same')(dis_conv_block)
    dis_conv_block = Activation('relu')(dis_conv_block)

    flat_1 = Flatten()(dis_conv_block)

    dis_fc_1 = Dense(256)(flat_1)
    dis_fc_1 = Activation('relu')(dis_fc_1)

    dis_drp_1 = Dropout(0.5)(dis_fc_1)

    dis_fc_2 = Dense(128)(dis_drp_1)
    dis_fc_2 = Activation('relu')(dis_fc_2)

    dis_drp_2 = Dropout(0.5)(dis_fc_2)

    dis_fc_3 = Dense(1)(dis_drp_2)
    dis_similarity_output = Activation('sigmoid')(dis_fc_3)

    Discriminator = Model(inputs=[dis_inputs_1, dis_inputs_2], outputs=dis_similarity_output)
    Discriminator.compile(optimizer=Adadelta(lr=0.01), loss='binary_crossentropy', metrics=['accuracy'])

    print('Discriminator Architecture:')
    print(Discriminator.summary())
    return Discriminator