"""

Please note, this code is only for python 3+. If you are using python 2+, please modify the code accordingly.

"""

import tensorflow as tf

from sklearn.datasets import load_digits

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import LabelBinarizer

# load data

digits = load_digits()

X = digits.data

y = digits.target

y = LabelBinarizer().fit_transform(y)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)

def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):

    # add one more layer and return the output of this layer

    Weights = tf.Variable(tf.random_normal([in_size, out_size]))

    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )

    Wx_plus_b = tf.matmul(inputs, Weights) + biases

    # here to dropout

    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)

    if activation_function is None:

        outputs = Wx_plus_b

    else:

        outputs = activation_function(Wx_plus_b, )

    return outputs

def compute_accuracy(v_xs,v_ys,v_keep_prob):

    global prediction

    y_pre = sess.run(prediction,feed_dict={xs:v_xs,keep_prob:v_keep_prob})

    correct_prediction = tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))

    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

    result = sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys,keep_prob:v_keep_prob})

    return result

# define placeholder for inputs to network

keep_prob = tf.placeholder(tf.float32)

xs = tf.placeholder(tf.float32, [None, 64])  # 8x8

ys = tf.placeholder(tf.float32, [None, 10])

# add output layer

l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)

prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)

# the loss between prediction and real data

cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),

                                              reduction_indices=[1]))  # loss

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()

sess.run(tf.initialize_all_variables())

for i in range(500):

    # here to determine the keeping probability

    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})

    if i % 50 == 0:

        print(compute_accuracy(X_train, y_train,1),compute_accuracy(X_test, y_test,1))