How to save the final model using keras?

Question

I use KerasClassifier to train the classifier.

Code below:

import numpy
from pandas import read_csv
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasClassifier
from keras.utils import np_utils
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load dataset
dataframe = read_csv("iris.csv", header=None)
dataset = dataframe.values
X = dataset[:,0:4].astype(float)
Y = dataset[:,4]
# encode class values as integers
encoder = LabelEncoder()
encoder.fit(Y)
encoded_Y = encoder.transform(Y)
#print("encoded_Y")
#print(encoded_Y)
# convert integers to dummy variables (i.e. one hot encoded)
dummy_y = np_utils.to_categorical(encoded_Y)
#print("dummy_y")
#print(dummy_y)
# define baseline model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Dense(4, input_dim=4, init='normal', activation='relu'))
    #model.add(Dense(4, init='normal', activation='relu'))
    model.add(Dense(3, init='normal', activation='softmax'))
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

    return model

estimator = KerasClassifier(build_fn=baseline_model, nb_epoch=200, batch_size=5, verbose=0)
#global_model = baseline_model()
kfold = KFold(n_splits=10, shuffle=True, random_state=seed)
results = cross_val_score(estimator, X, dummy_y, cv=kfold)
print("Accuracy: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))

But how to maintain the final model for future forecasting?

I usually use the code below to save the model:

# serialize model to JSON
model_json = model.to_json()
with open("model.json", "w") as json_file:
    json_file.write(model_json)
# serialize weights to HDF5
model.save_weights("model.h5")
print("Saved model to disk")

But I do not know how to insert the code of the saved model into the KerasClassifier code.

Thank.

Answer 1

The model has a method savethat saves all the details needed to restore the model. An example from keras documentation :

from keras.models import load_model

model.save('my_model.h5')  # creates a HDF5 file 'my_model.h5'
del model  # deletes the existing model

# returns a compiled model
# identical to the previous one
model = load_model('my_model.h5')

Answer 2

you can save the model in json and scales in hdf5 format .

# keras library import  for Saving and loading model and weights

from keras.models import model_from_json
from keras.models import load_model

# serialize model to JSON
#  the keras model which is trained is defined as 'model' in this example
model_json = model.to_json()


with open("model_num.json", "w") as json_file:
    json_file.write(model_json)

# serialize weights to HDF5
model.save_weights("model_num.h5")

"model_num.h5" "model_num.json",

, hdf5 . , .

# load json and create model
json_file = open('model_num.json', 'r')

loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)

# load weights into new model
loaded_model.load_weights("model_num.h5")
print("Loaded model from disk")

model.save('model_num.hdf5')
loaded_model=load_model('model_num.hdf5')

loaded_model.predict_classes("your_test_data here")

Answer 3

model.save(filepath) model.save(filepath) HDF5, :

• , .
• .
• (, )
• , , .

Python, , :

model.save("m.hdf5")

. keras.models.load_model().

, load_model() , ( ).

model.save():

• filepath: String, .
• overwrite: whether to overwrite any existing file at the target location in silent mode or provide the user with a manual hint.
• include_optimizer: if True, save the optimizer state together.