import numpy as np
import tensorflow as tf
from tensorflow.python.framework.graph_util import convert_variables_to_constants

from graphviz import Digraph

def tf_to_dot(g):
    dot = Digraph()
    for n in g.node:
        dot.node(n.name, label=n.name)

        for i in n.input:
            dot.edge(i, n.name)
    return dot

def weight_varible(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')


sess = tf.InteractiveSession()

# paras
W_conv1 = weight_varible([5, 5, 1, 32])
b_conv1 = bias_variable([32])

# conv layer-1
x = tf.placeholder(tf.float32, [None, 784], name='x')
x_image = tf.reshape(x, [-1, 28, 28, 1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# conv layer-2
W_conv2 = weight_varible([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# full connection
W_fc1 = weight_varible([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# dropout
keep_prob = tf.placeholder(tf.float32, name='keep_prob')
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# output layer: softmax
W_fc2 = weight_varible([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
y_ = tf.placeholder(tf.float32, [None, 10], name='y_')

# model training
cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.arg_max(y_conv, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

sess.run(tf.initialize_all_variables())

minimal_graph = convert_variables_to_constants(sess, sess.graph_def, [y_conv.op.name])
tf.train.write_graph(minimal_graph, '.', 'minimal_graph.txt', as_text=True)
dot = tf_to_dot(minimal_graph)
fp = open('out.dot', 'w')
print >> fp, dot
fp.close()