import tensorflow as tf
import numpy as np

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

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

def weight_variable(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)


dim = 64
x = tf.placeholder(tf.float32, shape=[None, dim**2])
y_ = tf.placeholder(tf.float32, shape=[None, 10])

sess = tf.InteractiveSession()

w_conv1 = weight_variable([8, 2, 1, 32])
b_conv1 = bias_variable([32])

x_image = tf.reshape(x, [-1, dim, dim, 1])

h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

w_conv2 = weight_variable([4, 1, 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)

w_conv3 = weight_variable([2, 1, 64, 96])
b_conv3 = bias_variable([96])

h_conv3 = tf.nn.relu(conv2d(h_pool2, w_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3)

print(h_pool3.get_shape())

w_fc1 = weight_variable([5 * 7 * 96, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool3, [-1, 5 * 7 * 96])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)

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

w_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
train_step = tf.train.RMSPropOptimizer(0.01).minimize(cross_entropy)

exit(0)

correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())

for i in range(20000):
  # recuperer un batch
  batch_x = np.random.randn(32, 64, 64, 1)
  classes = np.array([[0, 1, 0, 0, 0, 0, 0, 0, 0, 0] for j in range(32)])
  if i % 100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x_image:batch_x, y_: classes, keep_prob: 1.0})
    print("step %d, training accuracy %g" % (i, train_accuracy))

  train_step.run(feed_dict={x_image: batch_x, y_: classes, keep_prob: 0.85})

#print("test accuracy %g"%accuracy.eval(feed_dict={
#    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))