Comparing XOR between tensorflow and keras

xor_keras.py

import numpy as np
from keras.models import Sequential
from keras.layers.core import Activation, Dense
from keras.optimizers import SGD

X = np.array([[0,0],[0,1],[1,0],[1,1]], "float32")
y = np.array([[0],[1],[1],[0]], "float32")

model = Sequential()
model.add(Dense(2, input_dim=2, activation='sigmoid'))
model.add(Dense(1, activation='sigmoid'))

sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd)

history = model.fit(X, y, nb_epoch=10000, batch_size=4, verbose=0)

print model.predict(X)

xor_tensorflow.py

import tensorflow as tf    

input_data = [[0., 0.], [0., 1.], [1., 0.], [1., 1.]]  # XOR input
output_data = [[0.], [1.], [1.], [0.]]  # XOR output

n_input = tf.placeholder(tf.float32, shape=[None, 2], name="n_input")
n_output = tf.placeholder(tf.float32, shape=[None, 1], name="n_output")

hidden_nodes = 5

b_hidden = tf.Variable(tf.random_normal([hidden_nodes]), name="hidden_bias")
W_hidden = tf.Variable(tf.random_normal([2, hidden_nodes]), name="hidden_weights")
hidden = tf.sigmoid(tf.matmul(n_input, W_hidden) + b_hidden)

W_output = tf.Variable(tf.random_normal([hidden_nodes, 1]), name="output_weights")  # output layer's weight matrix
output = tf.sigmoid(tf.matmul(hidden, W_output))  # calc output layer's activation

cross_entropy = tf.square(n_output - output)  # simpler, but also works

loss = tf.reduce_mean(cross_entropy)  # mean the cross_entropy
optimizer = tf.train.AdamOptimizer(0.01)  # take a gradient descent for optimizing with a "stepsize" of 0.1
train = optimizer.minimize(loss)  # let the optimizer train

init = tf.initialize_all_variables()

sess = tf.Session()  # create the session and therefore the graph
sess.run(init)  # initialize all variables  

for epoch in xrange(0, 2001):
    # run the training operation
    cvalues = sess.run([train, loss, W_hidden, b_hidden, W_output],
                       feed_dict={n_input: input_data, n_output: output_data})

    if epoch % 200 == 0:
        print("")
        print("step: {:>3}".format(epoch))
        print("loss: {}".format(cvalues[1]))

print("")
print("input: {} | output: {}".format(input_data[0], sess.run(output, feed_dict={n_input: [input_data[0]]})))
print("input: {} | output: {}".format(input_data[1], sess.run(output, feed_dict={n_input: [input_data[1]]})))
print("input: {} | output: {}".format(input_data[2], sess.run(output, feed_dict={n_input: [input_data[2]]})))
print("input: {} | output: {}".format(input_data[3], sess.run(output, feed_dict={n_input: [input_data[3]]})))