from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import os
import sys
import time

from six.moves import xrange
import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.examples.tutorials.mnist import mnist

FLAGS = None


def placeholder_inputs(batch_size):
    images_placeholder = tf.placeholder(tf.float32, shape=(batch_size,
                                                           mnist.IMAGE_PIXELS))
    labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size))
    return images_placeholder, labels_placeholder


def fill_feed_dict(data_set, images_pl, labels_pl):
    images_feed, labels_feed = data_set.next_batch(FLAGS.batch_size,
                                                   FLAGS.fake_data)
    feed_dict = {
        images_pl: images_feed,
        labels_pl: labels_feed,
    }
    return feed_dict


def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):

    true_count = 0
    steps_per_epoch = data_set.num_examples // FLAGS.batch_size
    num_examples = steps_per_epoch * FLAGS.batch_size
    for step in xrange(steps_per_epoch):
        feed_dict = fill_feed_dict(data_set,
                                   images_placeholder,
                                   labels_placeholder)
        true_count += sess.run(eval_correct, feed_dict=feed_dict)
    precision = float(true_count) / num_examples
    print('  Num examples: %d  Num correct: %d  Precision @ 1: %0.04f' %
          (num_examples, true_count, precision))


def run_training():
    data_sets = input_data.read_data_sets(FLAGS.input_data_dir, FLAGS.fake_data)

    with tf.Graph().as_default():
        images_placeholder, labels_placeholder = placeholder_inputs(
            FLAGS.batch_size)

        logits = mnist.inference(images_placeholder,
                                 FLAGS.hidden1,
                                 FLAGS.hidden2)

        loss = mnist.loss(logits, labels_placeholder)

        train_op = mnist.training(loss, FLAGS.learning_rate)

        eval_correct = mnist.evaluation(logits, labels_placeholder)

        summary = tf.summary.merge_all()

        init = tf.global_variables_initializer()

        saver = tf.train.Saver()

        sess = tf.Session()

        summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph)

        sess.run(init)

        for step in xrange(FLAGS.max_steps):
            start_time = time.time()

            feed_dict = fill_feed_dict(data_sets.train,
                                       images_placeholder,
                                       labels_placeholder)

            _, loss_value = sess.run([train_op, loss],
                                     feed_dict=feed_dict)

            duration = time.time() - start_time

            if step % 100 == 0:
                print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration))
                summary_str = sess.run(summary, feed_dict=feed_dict)
                summary_writer.add_summary(summary_str, step)
                summary_writer.flush()

            if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
                checkpoint_file = os.path.join(FLAGS.log_dir, 'model.ckpt')
                saver.save(sess, checkpoint_file, global_step=step)
                print('Training Data Eval:')
                do_eval(sess,
                        eval_correct,
                        images_placeholder,
                        labels_placeholder,
                        data_sets.train)
                print('Validation Data Eval:')
                do_eval(sess,
                        eval_correct,
                        images_placeholder,
                        labels_placeholder,
                        data_sets.validation)
                print('Test Data Eval:')
                do_eval(sess,
                        eval_correct,
                        images_placeholder,
                        labels_placeholder,
                        data_sets.test)


def main(_):
    if tf.gfile.Exists(FLAGS.log_dir):
        tf.gfile.DeleteRecursively(FLAGS.log_dir)
    tf.gfile.MakeDirs(FLAGS.log_dir)
    run_training()


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument(
        '--learning_rate',
        type=float,
        default=0.01,
        help='Initial learning rate.'
    )
    parser.add_argument(
        '--max_steps',
        type=int,
        default=2000,
        help='Number of steps to run trainer.'
    )
    parser.add_argument(
        '--hidden1',
        type=int,
        default=128,
        help='Number of units in hidden layer 1.'
    )
    parser.add_argument(
        '--hidden2',
        type=int,
        default=32,
        help='Number of units in hidden layer 2.'
    )
    parser.add_argument(
        '--batch_size',
        type=int,
        default=100,
        help='Batch size.  Must divide evenly into the dataset sizes.'
    )
    parser.add_argument(
        '--input_data_dir',
        type=str,
        default=os.path.join(os.getenv('TEST_TMPDIR', '/tmp'),
                             'tensorflow/mnist/input_data'),
        help='Directory to put the input data.'
    )
    parser.add_argument(
        '--log_dir',
        type=str,
        default=os.path.join(os.getenv('TEST_TMPDIR', '/tmp'),
                             'tensorflow/mnist/logs/fully_connected_feed'),
        help='Directory to put the log data.'
    )
    parser.add_argument(
        '--fake_data',
        default=False,
        help='If true, uses fake data for unit testing.',
        action='store_true'
    )

FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import math

import tensorflow as tf

NUM_CLASSES = 10

IMAGE_SIZE = 28
IMAGE_PIXELS = IMAGE_SIZE * IMAGE_SIZE


def inference(images, hidden1_units, hidden2_units):
    with tf.name_scope('hidden1'):
        weights = tf.Variable(
            tf.truncated_normal([IMAGE_PIXELS, hidden1_units],
                                stddev=1.0 / math.sqrt(float(IMAGE_PIXELS))),
            name='weights')
        biases = tf.Variable(tf.zeros([hidden1_units]),
                             name='biases')
        hidden1 = tf.nn.relu(tf.matmul(images, weights) + biases)

    with tf.name_scope('hidden2'):
        weights = tf.Variable(
            tf.truncated_normal([hidden1_units, hidden2_units],
                                stddev=1.0 / math.sqrt(float(hidden1_units))),
            name='weights')
        biases = tf.Variable(tf.zeros([hidden2_units]),
                         name='biases')
        hidden2 = tf.nn.relu(tf.matmul(hidden1, weights) + biases)

    with tf.name_scope('softmax_linear'):
        weights = tf.Variable(
            tf.truncated_normal([hidden2_units, NUM_CLASSES],
                                stddev=1.0 / math.sqrt(float(hidden2_units))),
            name='weights')
        biases = tf.Variable(tf.zeros([NUM_CLASSES]),
                         name='biases')
        logits = tf.matmul(hidden2, weights) + biases
    return logits


def loss(logits, labels):
    labels = tf.to_int64(labels)
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
        labels=labels, logits=logits, name='xentropy')
    return tf.reduce_mean(cross_entropy, name='xentropy_mean')


def training(loss, learning_rate):
    tf.summary.scalar('loss', loss)
    optimizer = tf.train.GradientDescentOptimizer(learning_rate)
    global_step = tf.Variable(0, name='global_step', trainable=False)
    train_op = optimizer.minimize(loss, global_step=global_step)
    return train_op


def evaluation(logits, labels):
    correct = tf.nn.in_top_k(logits, labels, 1)
    return tf.reduce_sum(tf.cast(correct, tf.int32))