TensorFlow annotated CNN

cnn.py

# Get our data
import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

import tensorflow as tf

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)

def conv2d(x, W):
    """
    x is of shape [batch, height, weight, in_channels]
    W is of shape [5, 5, in_channels, out_channels]

    1) Flattens W to a 2-D matrix with shape [height * width * in_channels, output_channels].
    2) Extracts image patches from the the input tensor to form a virtual tensor
        of shape [batch, out_height, out_width, filter_height * filter_width * in_channels].
    3) For each patch, right-multiplies the filter matrix and the image patch vector.
    """
    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'
    )

# Input, output
x = tf.placeholder("float", [None, 784])
y_ = tf.placeholder("float", [None,10])
x_image = tf.reshape(x, [-1,28,28,1]) # x=> Form of [None, 28, 28, 1]

# Initial weights
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

# First hidden state
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # [None, 28, 28, 32]
h_pool1 = max_pool_2x2(h_conv1) # [None, 14, 14, 32]

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # [None, 14, 14, 64]
h_pool2 = max_pool_2x2(h_conv2) # [None, 7, 7, 64]

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) # [None, 3136]
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) # [None, 1024]

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

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) # [None, 10]

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.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess = tf.Session()
sess.run(tf.initialize_all_variables())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0}, session=sess)
    print "step %d, training accuracy %g"%(i, train_accuracy)
  sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

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

input_data.py

"""Functions for downloading and reading MNIST data."""
from __future__ import print_function
import gzip
import os
import urllib
import numpy
SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'


def maybe_download(filename, work_directory):
    """Download the data from Yann's website, unless it's already here."""
    if not os.path.exists(work_directory):
        os.mkdir(work_directory)
    filepath = os.path.join(work_directory, filename)
    if not os.path.exists(filepath):
        filepath, _ = urllib.urlretrieve(SOURCE_URL + filename, filepath)
        statinfo = os.stat(filepath)
        print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
    return filepath


def _read32(bytestream):
    dt = numpy.dtype(numpy.uint32).newbyteorder('>')
    return numpy.frombuffer(bytestream.read(4), dtype=dt)


def extract_images(filename):
    """Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
    print('Extracting', filename)
    with gzip.open(filename) as bytestream:
        magic = _read32(bytestream)
        if magic != 2051:
            raise ValueError(
                    'Invalid magic number %d in MNIST image file: %s' %
                    (magic, filename))
        num_images = _read32(bytestream)
        rows = _read32(bytestream)
        cols = _read32(bytestream)
        buf = bytestream.read(rows * cols * num_images)
        data = numpy.frombuffer(buf, dtype=numpy.uint8)
        data = data.reshape(num_images, rows, cols, 1)
        return data


def dense_to_one_hot(labels_dense, num_classes=10):
    """Convert class labels from scalars to one-hot vectors."""
    num_labels = labels_dense.shape[0]
    index_offset = numpy.arange(num_labels) * num_classes
    labels_one_hot = numpy.zeros((num_labels, num_classes))
    labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
    return labels_one_hot


def extract_labels(filename, one_hot=False):
    """Extract the labels into a 1D uint8 numpy array [index]."""
    print('Extracting', filename)
    with gzip.open(filename) as bytestream:
        magic = _read32(bytestream)
        if magic != 2049:
            raise ValueError(
                    'Invalid magic number %d in MNIST label file: %s' %
                    (magic, filename))
        num_items = _read32(bytestream)
        buf = bytestream.read(num_items)
        labels = numpy.frombuffer(buf, dtype=numpy.uint8)
        if one_hot:
            return dense_to_one_hot(labels)
        return labels


class DataSet(object):
    def __init__(self, images, labels, fake_data=False):
        if fake_data:
            self._num_examples = 10000
        else:
            assert images.shape[0] == labels.shape[0], (
                    "images.shape: %s labels.shape: %s" % (images.shape,
                                                                                                 labels.shape))
            self._num_examples = images.shape[0]
            # Convert shape from [num examples, rows, columns, depth]
            # to [num examples, rows*columns] (assuming depth == 1)
            assert images.shape[3] == 1
            images = images.reshape(images.shape[0],
                                                            images.shape[1] * images.shape[2])
            # Convert from [0, 255] -> [0.0, 1.0].
            images = images.astype(numpy.float32)
            images = numpy.multiply(images, 1.0 / 255.0)
        self._images = images
        self._labels = labels
        self._epochs_completed = 0
        self._index_in_epoch = 0

    @property
    def images(self):
        return self._images

    @property
    def labels(self):
        return self._labels

    @property
    def num_examples(self):
        return self._num_examples

    @property
    def epochs_completed(self):
        return self._epochs_completed

    def next_batch(self, batch_size, fake_data=False):
        """Return the next `batch_size` examples from this data set."""
        if fake_data:
            fake_image = [1.0 for _ in xrange(784)]
            fake_label = 0
            return [fake_image for _ in xrange(batch_size)], [
                    fake_label for _ in xrange(batch_size)]
        start = self._index_in_epoch
        self._index_in_epoch += batch_size
        if self._index_in_epoch > self._num_examples:
            # Finished epoch
            self._epochs_completed += 1
            # Shuffle the data
            perm = numpy.arange(self._num_examples)
            numpy.random.shuffle(perm)
            self._images = self._images[perm]
            self._labels = self._labels[perm]
            # Start next epoch
            start = 0
            self._index_in_epoch = batch_size
            assert batch_size <= self._num_examples
        end = self._index_in_epoch
        return self._images[start:end], self._labels[start:end]


def read_data_sets(train_dir, fake_data=False, one_hot=False):
    class DataSets(object):
        pass
    
    data_sets = DataSets()
    if fake_data:
        data_sets.train = DataSet([], [], fake_data=True)
        data_sets.validation = DataSet([], [], fake_data=True)
        data_sets.test = DataSet([], [], fake_data=True)
        return data_sets
    TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
    TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
    TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
    TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
    VALIDATION_SIZE = 5000
    local_file = maybe_download(TRAIN_IMAGES, train_dir)
    train_images = extract_images(local_file)
    local_file = maybe_download(TRAIN_LABELS, train_dir)
    train_labels = extract_labels(local_file, one_hot=one_hot)
    local_file = maybe_download(TEST_IMAGES, train_dir)
    test_images = extract_images(local_file)
    local_file = maybe_download(TEST_LABELS, train_dir)
    test_labels = extract_labels(local_file, one_hot=one_hot)
    validation_images = train_images[:VALIDATION_SIZE]
    validation_labels = train_labels[:VALIDATION_SIZE]
    train_images = train_images[VALIDATION_SIZE:]
    train_labels = train_labels[VALIDATION_SIZE:]
    data_sets.train = DataSet(train_images, train_labels)
    data_sets.validation = DataSet(validation_images, validation_labels)
    data_sets.test = DataSet(test_images, test_labels)
    return data_sets