如何将参数传递给Scikit-Learn Keras模型函数

Question

我有以下代码，使用Keras Scikit-Learn Wrapper，它工作良好:

from keras.models import Sequential
from keras.layers import Dense
from sklearn import datasets
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import cross_val_score
import numpy as np

def create_model():
    # create model
    model = Sequential()
    model.add(Dense(12, input_dim=4, init='uniform', activation='relu'))
    model.add(Dense(6, init='uniform', activation='relu'))
    model.add(Dense(1, init='uniform', activation='sigmoid'))
    # Compile model
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

def main():
    """
    Description of main
    """

    iris = datasets.load_iris()
    X, y = iris.data, iris.target
    NOF_ROW, NOF_COL =  X.shape
    # evaluate using 10-fold cross validation
    seed = 7
    np.random.seed(seed)
    model = KerasClassifier(build_fn=create_model, nb_epoch=150, batch_size=10, verbose=0)
    kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed)
    results = cross_val_score(model, X, y, cv=kfold)
    print(results.mean())
    # 0.666666666667

if __name__ == '__main__':
    main()

pima-indians-diabetes.data可在此处下载。

现在我要做的是通过以下方式将值NOF_COL传递给create_model()函数的参数

model = KerasClassifier(build_fn=create_model(input_dim=NOF_COL), nb_epoch=150, batch_size=10, verbose=0)

create_model()函数如下所示:

def create_model(input_dim=None):
    # create model
    model = Sequential()
    model.add(Dense(12, input_dim=input_dim, init='uniform', activation='relu'))
    model.add(Dense(6, init='uniform', activation='relu'))
    model.add(Dense(1, init='uniform', activation='sigmoid'))
    # Compile model
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

但是它失败了，给出这个错误:

TypeError: __call__() takes at least 2 arguments (1 given)

正确的做法是什么?

Answer 1

可以在KerasClassifier构造函数中添加input_dim关键字参数:

model = KerasClassifier(build_fn=create_model, input_dim=5, nb_epoch=150, batch_size=10, verbose=0)

Answer 2

最后一个答案不再有效

另一种选择是从create_model返回一个函数，因为KerasClassifier build_fn期望一个函数:

def create_model(input_dim=None):
    def model():
        # create model
        nn = Sequential()
        nn.add(Dense(12, input_dim=input_dim, init='uniform', activation='relu'))
        nn.add(Dense(6, init='uniform', activation='relu'))
        nn.add(Dense(1, init='uniform', activation='sigmoid'))
        # Compile model
        nn.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
        return nn
    return model

或者更好，根据文档

sk_params接受模型参数和拟合参数。合法的模型参数是build_fn的实参。请注意，与scikit-learn中的所有其他估计器一样，build_fn应该为其参数提供默认值，这样您就可以在不向sk_params

传递任何值的情况下创建估计器。

你可以这样定义你的函数:

def create_model(number_of_features=10): # 10 is the *default value*
    # create model
    nn = Sequential()
    nn.add(Dense(12, input_dim=number_of_features, init='uniform', activation='relu'))
    nn.add(Dense(6, init='uniform', activation='relu'))
    nn.add(Dense(1, init='uniform', activation='sigmoid'))
    # Compile model
    nn.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    return nn

并创建一个包装器:

KerasClassifier(build_fn=create_model, number_of_features=20, epochs=25, batch_size=1000, ...)

Answer 3

要传递参数给build_fn模型，可以将参数传递给__init__()，然后将其直接传递给model_build_fn。例如，调用KerasClassifier(myparam=10)将导致model_build_fn(my_param=10)

这里有一个例子:

class MyMultiOutputKerasRegressor(KerasRegressor):
    
    # initializing
    def __init__(self, **kwargs):
        KerasRegressor.__init__(self, **kwargs)
        
    # simpler fit method
    def fit(self, X, y, **kwargs):
        KerasRegressor.fit(self, X, [y]*3, **kwargs)

(…)

def get_quantile_reg_rpf_nn(layers_shape=[50,100,200,100,50], inDim= 4, outDim=1, act='relu'):
          # do model stuff...

(…)初始化Keras回归量:

base_model = MyMultiOutputKerasRegressor(build_fn=get_quantile_reg_rpf_nn,
                                         layers_shape=[50,100,200,100,50], inDim= 4, 
                                         outDim=1, act='relu', epochs=numEpochs, 
                                         batch_size=batch_size, verbose=0)