python - 如何将 Scikit-Learn-Keras 模型保存到持久性文件 (pickle/hd5/json/yaml)

Question

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

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

def classifier(X, y):
    """
    Description of classifier
    """
    NOF_ROW, NOF_COL =  X.shape

    def create_model():
        # create model
        model = Sequential()
        model.add(Dense(12, input_dim=NOF_COL, 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

    # 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)
    return model


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

    iris = datasets.load_iris()
    X, y = iris.data, iris.target
    X = preprocessing.scale(X)

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=0)
    model_tt = classifier(X_train, y_train)
    model_tt.fit(X_train,y_train)

    #--------------------------------------------------
    # This fail
    #-------------------------------------------------- 
    filename = 'finalized_model.sav'
    pickle.dump(model_tt, open(filename, 'wb'))
    # load the model from disk
    loaded_model = pickle.load(open(filename, 'rb'))
    result = loaded_model.score(X_test, Y_test)
    print(result)

    #--------------------------------------------------
    # This also fail
    #--------------------------------------------------
    # from keras.models import load_model       
    # model_tt.save('test_model.h5')


    #--------------------------------------------------
    # This works OK 
    #-------------------------------------------------- 
    # print model_tt.score(X_test, y_test)
    # print model_tt.predict_proba(X_test)
    # print model_tt.predict(X_test)


# Output of predict_proba
# 2nd column is the probability that the prediction is 1
# this value is used as final score, which can be used
# with other method as comparison
# [   [ 0.25311464  0.74688536]
#     [ 0.84401423  0.15598579]
#     [ 0.96047372  0.03952631]
#     ...,
#     [ 0.25518912  0.74481088]
#     [ 0.91467732  0.08532269]
#     [ 0.25473493  0.74526507]]

# Output of predict
# [[1]
# [0]
# [0]
# ...,
# [1]
# [0]
# [1]]


if __name__ == '__main__':
    main()

如代码中所述，它在这一行失败:

pickle.dump(model_tt, open(filename, 'wb'))

出现此错误:

pickle.PicklingError: Can't pickle <function create_model at 0x101c09320>: it's not found as __main__.create_model

我怎样才能绕过它？

Answer 1

编辑1:关于保存模型的原始答案

使用 HDF5:

# saving model
json_model = model_tt.model.to_json()
open('model_architecture.json', 'w').write(json_model)
# saving weights
model_tt.model.save_weights('model_weights.h5', overwrite=True)


# loading model
from keras.models import model_from_json

model = model_from_json(open('model_architecture.json').read())
model.load_weights('model_weights.h5')

# dont forget to compile your model
model.compile(loss='binary_crossentropy', optimizer='adam')

编辑 2 :带有 iris 数据集的完整代码示例

# Train model and make predictions
import numpy
import pandas
from keras.models import Sequential, model_from_json
from keras.layers import Dense
from keras.utils import np_utils
from sklearn import datasets
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder

# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)

# load dataset
iris = datasets.load_iris()
X, Y, labels = iris.data, iris.target, iris.target_names
X = preprocessing.scale(X)

# encode class values as integers
encoder = LabelEncoder()
encoder.fit(Y)
encoded_Y = encoder.transform(Y)

# convert integers to dummy variables (i.e. one hot encoded)
y = np_utils.to_categorical(encoded_Y)

def build_model():
    # create model
    model = Sequential()
    model.add(Dense(4, input_dim=4, init='normal', activation='relu'))
    model.add(Dense(3, init='normal', activation='sigmoid'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

def save_model(model):
    # saving model
    json_model = model.to_json()
    open('model_architecture.json', 'w').write(json_model)
    # saving weights
    model.save_weights('model_weights.h5', overwrite=True)

def load_model():
    # loading model
    model = model_from_json(open('model_architecture.json').read())
    model.load_weights('model_weights.h5')
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    return model


X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=0.3, random_state=seed)

# build
model = build_model()
model.fit(X_train, Y_train, nb_epoch=200, batch_size=5, verbose=0)

# save
save_model(model)

# load
model = load_model()

# predictions
predictions = model.predict_classes(X_test, verbose=0)
print(predictions)
# reverse encoding
for pred in predictions:
    print(labels[pred])

请注意，我只使用了 Keras，而不是包装器。它只会在简单的事情中增加一些复杂性。此外，代码是自愿的，不考虑因素，因此您可以了解整个情况。

另外，您说过要输出 1 或 0。在此数据集中这是不可能的，因为您有 3 个输出尺寸和类别(Iris-setosa、Iris-versicolor、Iris-virginica)。如果您只有 2 个类，那么使用 sigmoid 输出函数，您的输出昏暗和类将为 0 或 1。