Python keras.regularizers 模块，activity_l1() 实例源码

def transform_model(weight_loss_pix=5e-4):
    inputs = Input(shape=( 128, 128, 3))
    x1 = Convolution2D(64, 5, 5, border_mode='same')(inputs)
    x2 = LeakyReLU(alpha=0.3, name='wkcw')(x1)
    x3 = BatchNormalization()(x2)
    x4 = Convolution2D(128, 4, 4, border_mode='same', subsample=(2,2))(x3)
    x5 = LeakyReLU(alpha=0.3)(x4)
    x6 = BatchNormalization()(x5)
    x7 = Convolution2D(256, 4, 4, border_mode='same', subsample=(2,2))(x6)
    x8 = LeakyReLU(alpha=0.3)(x7)
    x9 = BatchNormalization()(x8)
    x10 = Deconvolution2D(128, 3, 3, output_shape=(None, 64, 64, 128), border_mode='same', subsample=(2,2))(x9)
    x11 = BatchNormalization()(x10)
    x12 = Deconvolution2D(64, 3, 3, output_shape=(None, 128, 128, 64), border_mode='same', subsample=(2,2))(x11)
    x13 = BatchNormalization()(x12)
    x14 = Deconvolution2D(3, 4, 4, output_shape=(None, 128, 128, 3), border_mode='same', activity_regularizer=activity_l1(weight_loss_pix))(x13)
    output = merge([inputs, x14], mode='sum')
    model = Model(input=inputs, output=output)

    return model

def test_A_reg():
    (X_train, Y_train), (X_test, Y_test), test_ids = get_data()
    for reg in [regularizers.activity_l1(), regularizers.activity_l2()]:
        model = create_model(activity_reg=reg)
        model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
        model.fit(X_train, Y_train, batch_size=batch_size,
                  nb_epoch=nb_epoch, verbose=0)
        model.evaluate(X_test[test_ids, :], Y_test[test_ids, :], verbose=0)

def sparse_autoencoder(X, lam=1e-5):
    X = X.reshape(X.shape[0], -1)
    M, N = X.shape

    inputs = Input(shape=(N,))
    h = Dense(64, activation='sigmoid', activity_regularizer=activity_l1(lam))(inputs)
    outputs = Dense(N)(h)

    model = Model(input=inputs, output=outputs)
    model.compile(optimizer='adam', loss='mse')
    model.fit(X, X, batch_size=64, nb_epoch=3)

    return model, Model(input=inputs, output=h)

def multilayer_autoencoder(X, lam=1e-5):
    X = X.reshape(X.shape[0], -1)
    M, N = X.shape

    inputs = Input(shape=(N,))
    h = Dense(128, activation='relu')(inputs)
    encoded = Dense(64, activation='relu', activity_regularizer=activity_l1(lam))(h)
    h = Dense(128, activation='relu')(encoded)
    outputs = Dense(N)(h)

    model = Model(input=inputs, output=outputs)
    model.compile(optimizer='adam', loss='mse')
    model.fit(X, X, batch_size=64, nb_epoch=3)

    return model, Model(input=inputs, output=h)

def test_A_reg(self):
        for reg in [regularizers.activity_l1(), regularizers.activity_l2()]:
            model = create_model(activity_reg=reg)
            model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
            model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=0)
            model.evaluate(X_test[test_ids, :], Y_test[test_ids, :], verbose=0)

def test_A_reg():
    (X_train, Y_train), (X_test, Y_test), test_ids = get_data()
    for reg in [regularizers.activity_l1(), regularizers.activity_l2()]:
        model = create_model(activity_reg=reg)
        model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
        assert len(model.losses) == 1
        model.fit(X_train, Y_train, batch_size=batch_size,
                  nb_epoch=nb_epoch, verbose=0)
        model.evaluate(X_test[test_ids, :], Y_test[test_ids, :], verbose=0)

def test_A_reg():
    (X_train, Y_train), (X_test, Y_test), test_ids = get_data()
    for reg in [regularizers.activity_l1(), regularizers.activity_l2()]:
        model = create_model(activity_reg=reg)
        model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
        assert len(model.losses) == 1
        model.fit(X_train, Y_train, batch_size=batch_size,
                  nb_epoch=nb_epoch, verbose=0)
        model.evaluate(X_test[test_ids, :], Y_test[test_ids, :], verbose=0)

def test_A_reg(self):
        for reg in [regularizers.activity_l1(), regularizers.activity_l2()]:
            model = create_model(activity_reg=reg)
            model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
            model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=0)
            model.evaluate(X_test[test_ids, :], Y_test[test_ids, :], verbose=0)

def test_A_reg(self):
        for reg in [regularizers.activity_l1(), regularizers.activity_l2()]:
            model = create_model(activity_reg=reg)
            model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
            model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=0)
            model.evaluate(X_test[test_ids, :], Y_test[test_ids, :], verbose=0)