如何将参数传递给ScikitLearn Keras模型函数

Question

我有以下代码，使用Keras Scikit-Learn Wrapper，工作正常：

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()

可以下载pima-indians-diabetes.data。

现在我要做的是按以下方式将值NOF_COL传递到create_model()函数的参数中

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

使用类似这样的create_model()函数：

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

但是它没有给出这个错误：

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

正确的方法是什么？

Answer 1

最后一个答案不起作用了。

另一种方法是从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documentation

sk_params takes both model parameters and fitting parameters. Legal model parameters are the arguments of build_fn. Note that like all other estimators in scikit-learn, build_fn should provide default values for its arguments, so that you could create the estimator without passing any values to sk_params

所以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

然后创建一个包装器：

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

Answer 2

可以将input_dimkeyarg添加到KerasClassifier构造函数：

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