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()

该pima-indians-diabetes.data 可下载这里.

现在我想要做的是通过以下方式将值传递给函数的NOF_COL参数create_model()

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

使用如下所示的create_model()功能:

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

但它没有给出这个错误:

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

什么是正确的方法呢？

Answer 1

您可以将一个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)

Answer 2

最后的答案不再有效。

另一种方法是从 create_model 返回一个函数，因为 KerasClassifier build_fn 需要一个函数：

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

甚至更好，根据文档

sk_params 采用模型参数和拟合参数。合法的模型参数是 build_fn 的参数。请注意，与 scikit-learn 中的所有其他估算器一样，build_fn 应为其参数提供默认值，以便您可以创建估算器而无需将任何值传递给 sk_params

所以你可以像这样定义你的函数：

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, ...)