How to use the tensor flow model extracted from the keras learning model

Question

I want to build and train a neural network using the keras framework. I configured keras that it will use Tensorflow as a backend. After I trained the keram model, I tried to use only Tensorflow. I can access the session and get the tensorflow graph. But I do not know how to use the tensor flow graph, for example, to make a prediction.

I am creating a network with the following tutorial http://machinelearningmastery.com/tutorial-first-neural-network-python-keras/

in the train () method, I create and equip the model using only keras and save the keras and tensorflow model

in the eval () method

Here is my code:

from keras.models import Sequential
from keras.layers import Dense
from keras.models import model_from_json
import keras.backend.tensorflow_backend as K
import tensorflow as tf
import numpy

sess = tf.Session()
K.set_session(sess)

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

# load pima indians dataset
dataset = numpy.loadtxt("pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:, 0:8]
Y = dataset[:, 8]


def train():
    # create model
    model = Sequential()
    model.add(Dense(12, input_dim=8, init='uniform', activation='relu'))
    model.add(Dense(8, init='uniform', activation='relu'))
    model.add(Dense(1, init='uniform', activation='sigmoid'))

    # Compile model
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics['accuracy'])

    # Fit the model
    model.fit(X, Y, nb_epoch=10, batch_size=10)

    # evaluate the model
    scores = model.evaluate(X, Y)
    print("%s: %.2f%%" % (model.metrics_names[1], scores[1] * 100))

    # 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")

    # save tensorflow modell
    saver = tf.train.Saver()
    save_path = saver.save(sess, "model")

def eval():
    # load json and create model
    json_file = open('model.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.h5")

    # evaluate loaded model on test data
    loaded_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
    score = loaded_model.evaluate(X, Y, verbose=0)
    loaded_model.predict(X)
    print ("%s: %.2f%%" % (loaded_model.metrics_names[1], score[1]*100))

    # load tensorflow model
    sess = tf.Session()
    saver = tf.train.import_meta_graph('model.meta')
    saver.restore(sess, tf.train.latest_checkpoint('./'))

    # TODO try to predict with the tensorflow model only
    # without using keras functions

(sess.graph), keras, , tensorflow. , generell, keras build .

Answer 1

Keras, TensorFlow. TensorFlow. , model - loaded_model x - .

sess = K.get_session()
input_tensor = model.input
output_tensor = model.output

output_tensor.eval(feed_dict={input_tensor: x}, session=sess)