Welcome to OGeek Q&A Community for programmer and developer-Open, Learning and Share
Welcome To Ask or Share your Answers For Others

Categories

0 votes
536 views
in Technique[技术] by (71.8m points)

python - How to save Scikit-Learn-Keras Model into a Persistence File (pickle/hd5/json/yaml)

I have the following code, using 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()

As stated in the code there it fails at this line:

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

With this error:

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

How can I get around it?

See Question&Answers more detail:os

与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
Welcome To Ask or Share your Answers For Others

1 Reply

0 votes
by (71.8m points)

Edit 1 : Original answer about saving model

With 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')

Edit 2 : full code example with iris dataset

# 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])

Please note that I used Keras only, not the wrapper. It only add some complexity in something simple. Also code is volontary not factored so you can have the whole picture.

Also, you said you want to output 1 or 0. It is not possible in this dataset because you have 3 output dims and classes (Iris-setosa, Iris-versicolor, Iris-virginica). If you had only 2 classes then your output dim and classes would be 0 or 1 using sigmoid output fonction.


与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
OGeek|极客中国-欢迎来到极客的世界,一个免费开放的程序员编程交流平台!开放,进步,分享!让技术改变生活,让极客改变未来! Welcome to OGeek Q&A Community for programmer and developer-Open, Learning and Share
Click Here to Ask a Question

...