In [1]:
'''
a standard example to build graph and run training
'''

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

import gzip
import numpy
import os
import tempfile
import math
import argparse
import sys
import time

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

from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin

In [2]:
"""mnist.py
Builds the MNIST network.
Implements the inference/loss/training pattern for model building.
1. inference() - Builds the model as far as required for running the network
forward to make predictions.
2. loss() - Adds to the inference model the layers required to generate loss.
3. training() - Adds to the loss model the Ops required to generate and
apply gradients.
This file is used by the various "fully_connected_*.py" files and not meant to
be run.
"""

# The MNIST dataset has 10 classes, representing the digits 0 through 9.
NUM_CLASSES = 10

# The MNIST images are always 28x28 pixels.
IMAGE_SIZE = 28
IMAGE_PIXELS = IMAGE_SIZE * IMAGE_SIZE


def inference(images, hidden1_units, hidden2_units):
    """Build the MNIST model up to where it may be used for inference.
    Args:
    images: Images placeholder, from inputs().
    hidden1_units: Size of the first hidden layer.
    hidden2_units: Size of the second hidden layer.
    Returns:
    softmax_linear: Output tensor with the computed logits.
    """
    # Hidden 1
    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)
    # Hidden 2
    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)
    # Linear
    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):
    """Calculates the loss from the logits and the labels.
    Args:
    logits: Logits tensor, float - [batch_size, NUM_CLASSES].
    labels: Labels tensor, int32 - [batch_size].
    Returns:
    loss: Loss tensor of type float.
    """
    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):
    """Sets up the training Ops.
    Creates a summarizer to track the loss over time in TensorBoard.
    Creates an optimizer and applies the gradients to all trainable variables.
    The Op returned by this function is what must be passed to the
    `sess.run()` call to cause the model to train.
    Args:
    loss: Loss tensor, from loss().
    learning_rate: The learning rate to use for gradient descent.
    Returns:
    train_op: The Op for training.
    """
    # Add a scalar summary for the snapshot loss.
    tf.summary.scalar('loss', loss)
    # Create the gradient descent optimizer with the given learning rate.
    optimizer = tf.train.GradientDescentOptimizer(learning_rate)
    # Create a variable to track the global step.
    global_step = tf.Variable(0, name='global_step', trainable=False)
    # Use the optimizer to apply the gradients that minimize the loss
    # (and also increment the global step counter) as a single training step.
    train_op = optimizer.minimize(loss, global_step=global_step)
    return train_op


def evaluation(logits, labels):
    """Evaluate the quality of the logits at predicting the label.
    Args:
    logits: Logits tensor, float - [batch_size, NUM_CLASSES].
    labels: Labels tensor, int32 - [batch_size], with values in the
      range [0, NUM_CLASSES).
    Returns:
    A scalar int32 tensor with the number of examples (out of batch_size)
    that were predicted correctly.
    """
    # For a classifier model, we can use the in_top_k Op.
    # It returns a bool tensor with shape [batch_size] that is true for
    # the examples where the label is in the top k (here k=1)
    # of all logits for that example.
    correct = tf.nn.in_top_k(logits, labels, 1)
    # Return the number of true entries.
    return tf.reduce_sum(tf.cast(correct, tf.int32))

In [4]:
"""Trains and Evaluates the MNIST network using a feed dictionary."""

# Basic model parameters as external flags.
FLAGS = None


def placeholder_inputs(batch_size):
    """Generate placeholder variables to represent the input tensors.
    These placeholders are used as inputs by the rest of the model building
    code and will be fed from the downloaded data in the .run() loop, below.
    Args:
    batch_size: The batch size will be baked into both placeholders.
    Returns:
    images_placeholder: Images placeholder.
    labels_placeholder: Labels placeholder.
    """
    # Note that the shapes of the placeholders match the shapes of the full
    # image and label tensors, except the first dimension is now batch_size
    # rather than the full size of the train or test data sets.
    images_placeholder = tf.placeholder(tf.float32, shape=(batch_size,
                                                         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):
    """Fills the feed_dict for training the given step.
    A feed_dict takes the form of:
    feed_dict = {
      <placeholder>: <tensor of values to be passed for placeholder>,
      ....
    }
    Args:
    data_set: The set of images and labels, from input_data.read_data_sets()
    images_pl: The images placeholder, from placeholder_inputs().
    labels_pl: The labels placeholder, from placeholder_inputs().
    Returns:
    feed_dict: The feed dictionary mapping from placeholders to values.
    """
    # Create the feed_dict for the placeholders filled with the next
    # `batch size` examples.
    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):
    """Runs one evaluation against the full epoch of data.
    Args:
    sess: The session in which the model has been trained.
    eval_correct: The Tensor that returns the number of correct predictions.
    images_placeholder: The images placeholder.
    labels_placeholder: The labels placeholder.
    data_set: The set of images and labels to evaluate, from
      input_data.read_data_sets().
    """
    # And run one epoch of eval.
    true_count = 0  # Counts the number of correct predictions.
    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():
    """Train MNIST for a number of steps."""
    # Get the sets of images and labels for training, validation, and
    # test on MNIST.
    data_sets = input_data.read_data_sets(FLAGS.input_data_dir, FLAGS.fake_data)

    # Tell TensorFlow that the model will be built into the default Graph.
    with tf.Graph().as_default():
        # Generate placeholders for the images and labels.
        images_placeholder, labels_placeholder = placeholder_inputs(
            FLAGS.batch_size)

        # Build a Graph that computes predictions from the inference model.
        logits = mnist.inference(images_placeholder,
                                 FLAGS.hidden1,
                                 FLAGS.hidden2)

        # Add to the Graph the Ops for loss calculation.
        loss = mnist.loss(logits, labels_placeholder)

        # Add to the Graph the Ops that calculate and apply gradients.
        train_op = mnist.training(loss, FLAGS.learning_rate)

        # Add the Op to compare the logits to the labels during evaluation.
        eval_correct = mnist.evaluation(logits, labels_placeholder)

        # Build the summary Tensor based on the TF collection of Summaries.
        summary = tf.summary.merge_all()

        # Add the variable initializer Op.
        init = tf.global_variables_initializer()

        # Create a saver for writing training checkpoints.
        saver = tf.train.Saver()

        # Create a session for running Ops on the Graph.
        sess = tf.Session()

        # Instantiate a SummaryWriter to output summaries and the Graph.
        summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph)

        # And then after everything is built:

        # Run the Op to initialize the variables.
        sess.run(init)

        # Start the training loop.
        for step in xrange(FLAGS.max_steps):
            start_time = time.time()

            # Fill a feed dictionary with the actual set of images and labels
            # for this particular training step.
            feed_dict = fill_feed_dict(data_sets.train,
                                     images_placeholder,
                                     labels_placeholder)

            # Run one step of the model.  The return values are the activations
            # from the `train_op` (which is discarded) and the `loss` Op.  To
            # inspect the values of your Ops or variables, you may include them
            # in the list passed to sess.run() and the value tensors will be
            # returned in the tuple from the call.
            _, loss_value = sess.run([train_op, loss],
                                   feed_dict=feed_dict)

            duration = time.time() - start_time

            # Write the summaries and print an overview fairly often.
            if step % 100 == 0:
                # Print status to stdout.
                print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration))
                # Update the events file.
                summary_str = sess.run(summary, feed_dict=feed_dict)
                summary_writer.add_summary(summary_str, step)
                summary_writer.flush()

            # Save a checkpoint and evaluate the model periodically.
            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)
                # Evaluate against the training set.
                print('Training Data Eval:')
                do_eval(sess,
                        eval_correct,
                        images_placeholder,
                        labels_placeholder,
                        data_sets.train)
                # Evaluate against the validation set.
                print('Validation Data Eval:')
                do_eval(sess,
                        eval_correct,
                        images_placeholder,
                        labels_placeholder,
                        data_sets.validation)
                # Evaluate against the test set.
                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(description='一个完整的训练MNIST模型实例')
    parser.add_argument(
        '--learning_rate',
        dest='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)   
    main(FLAGS)


Extracting /tmp/tensorflow/mnist/input_data/train-images-idx3-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/train-labels-idx1-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/t10k-images-idx3-ubyte.gz
Extracting /tmp/tensorflow/mnist/input_data/t10k-labels-idx1-ubyte.gz
Step 0: loss = 2.29 (0.048 sec)
Step 100: loss = 2.16 (0.014 sec)
Step 200: loss = 1.98 (0.003 sec)
Step 300: loss = 1.66 (0.005 sec)
Step 400: loss = 1.28 (0.006 sec)
Step 500: loss = 0.98 (0.010 sec)
Step 600: loss = 0.83 (0.010 sec)
Step 700: loss = 0.74 (0.016 sec)
Step 800: loss = 0.63 (0.013 sec)
Step 900: loss = 0.52 (0.020 sec)
Training Data Eval:
  Num examples: 55000  Num correct: 47138  Precision @ 1: 0.8571
Validation Data Eval:
  Num examples: 5000  Num correct: 4315  Precision @ 1: 0.8630
Test Data Eval:
  Num examples: 10000  Num correct: 8659  Precision @ 1: 0.8659
Step 1000: loss = 0.52 (0.003 sec)
Step 1100: loss = 0.48 (0.054 sec)
Step 1200: loss = 0.56 (0.014 sec)
Step 1300: loss = 0.45 (0.006 sec)
Step 1400: loss = 0.42 (0.016 sec)
Step 1500: loss = 0.43 (0.003 sec)
Step 1600: loss = 0.37 (0.003 sec)
Step 1700: loss = 0.30 (0.012 sec)
Step 1800: loss = 0.41 (0.003 sec)
Step 1900: loss = 0.50 (0.024 sec)
Training Data Eval:
  Num examples: 55000  Num correct: 49208  Precision @ 1: 0.8947
Validation Data Eval:
  Num examples: 5000  Num correct: 4519  Precision @ 1: 0.9038
Test Data Eval:
  Num examples: 10000  Num correct: 9008  Precision @ 1: 0.9008