Python keras.regularizers 模块，l1l2() 实例源码

def test_W_reg():
    (X_train, Y_train), (X_test, Y_test), test_ids = get_data()
    for reg in [regularizers.l1(),
                regularizers.l2(),
                regularizers.l1l2()]:
        model = create_model(weight_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 l1l2(l1_weight=0, l2_weight=0):
    if keras_2:
        from keras.regularizers import L1L2
        return L1L2(l1_weight, l2_weight)
    else:
        from keras.regularizers import l1l2
        return l1l2(l1_weight, l2_weight)

def l1l2_penalty_reg(alpha=1.0, l1_ratio=0.5):
        '''Calculate L1 and L2 penalties for a Keras layer
        This follows the same formulation as in the R package glmnet and Sklearn
        Args:
            alpha ([float]): amount of regularization.
            l1_ratio ([float]): portion of L1 penalty. Setting to 1.0 equals 
                    Lasso.
        '''
        if l1_ratio == .0:
            return l2(alpha)
        elif l1_ratio == 1.:
            return l1(alpha)
        else:
            return l1l2(l1_ratio*alpha, 1./2*(1 - l1_ratio)*alpha)

def test_W_reg(self):
        for reg in [regularizers.identity(), regularizers.l1(), regularizers.l2(), regularizers.l1l2()]:
            model = create_model(weight_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_W_reg():
    (X_train, Y_train), (X_test, Y_test), test_ids = get_data()
    for reg in [regularizers.l1(),
                regularizers.l2(),
                regularizers.l1l2()]:
        model = create_model(weight_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 regularizer(params):
    if 'l1' in params and 'l2' in params:
        return regularizers.l1l2(params['l1'], params['l2'])
    elif 'l1' in params:
        return regularizers.l1(params['l1'])
    elif 'l2' in params:
        return regularizers.l2(params['l2'])
    else:
        return None

def test_W_reg():
    (X_train, Y_train), (X_test, Y_test), test_ids = get_data()
    for reg in [regularizers.l1(),
                regularizers.l2(),
                regularizers.l1l2()]:
        model = create_model(weight_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_W_reg(self):
        for reg in [regularizers.identity(), regularizers.l1(), regularizers.l2(), regularizers.l1l2()]:
            model = create_model(weight_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_W_reg(self):
        for reg in [regularizers.identity(), regularizers.l1(), regularizers.l2(), regularizers.l1l2()]:
            model = create_model(weight_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)