Advanced MNIST with TensorFlow

Abstract

Just like programming has "Hello World", machine learning has MNIST. MNIST is a simple computer vision dataset. It consists of images of handwritten digits, as well as labels for each image telling us which digit it is. In this tutorial, we're going to train a model to look at MNIST images and predict what digits they are.

Introduction

This tutorial is taken, with slight modification and different annotations, from TensorFlow's official documentation.

This tutorial is intended for readers who are new to both machine learning and TensorFlow.

Data Retrieval

The MNIST dataset is hosted on Yann LeCun's website.

The following two lines of code will take care of downloading and reading in the data automatically.

mnist is a lightweight class which stores the training, validation, and testing sets as NumPy arrays, as well as providing a function for iterating through data minibatches.


In [1]:
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)


Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting MNIST_data/train-images-idx3-ubyte.gz
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

Data Analysis

First of all, we import the TensorFlow library.


In [2]:
import tensorflow as tf

We assign a shape of [None, 784], where 784 is the dimensionality of a single flattened 28 by 28 pixel MNIST image, and None indicates that the first dimension, corresponding to the batch size, can be of any size.

The target output classes y_ will also consist of a 2d tensor, where each row is a one-hot 10-dimensional vector (a one-hot vector is a vector which is 0 in most dimensions and 1 in a single dimension) indicating which digit class (zero to nine) the corresponding MNIST image belongs to.

Let's create some symbolic variables using TensorFlow's placeholder() operation. The result will not be a specific value; it will be a placeholder, a value that we'll input when we ask TensorFlow to run a computation.


In [3]:
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])

The input images x consists of a 2D tensor of floating point numbers. Here we assign it a shape of [None, 784], where 784 is the dimensionality of a single flattened 28 by 28 pixel MNIST image, and None indicates that the first dimension, corresponding to the batch size, can be of any size. The target output classes y_ also consists of a 2D tensor, where each row is a one-hot 10-dimensional vector indicating which digit class (zero through nine) the corresponding MNIST image belongs to.

Flattening the data throws away information about the 2D structure of the image. This is bad! We are going to use Convolutional Neural Networks (CNN), which is great in exploiting the 2D structure of an image. So, let's reshape x into a 28 x 28 matrix (the final dimension corresponding to the number of color channels).


In [4]:
x_image = tf.reshape(x, [-1,28,28,1])

To create this model, we're going to need to create a lot of weights and biases.

One should generally initialize weights with a small amount of noise for symmetry breaking, and to prevent 0 gradients.

Instead of doing this repeatedly while we build the model, let's create two handy functions to do it for us.

The resulting weights and biases will all be Variables. A Variable is a modifiable tensor that lives in TensorFlow's graph of interacting operations. It can be used and even modified by the computation. For machine learning applications, one generally has the model parameters be Variables. We create these Variables by giving tf.Variable() the initial value of the Variable


In [5]:
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)

Our convolutions uses a stride of one and are zero padded so that the output is the same size as the input.

Our pooling is plain old max pooling over 2x2 blocks.

To keep our code cleaner, let's also abstract those operations into functions.


In [6]:
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')

Build the Deep Learning architecture.


In [7]:
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

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

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)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([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)

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])

We know that every image in MNIST is of a handwritten digit between zero and nine, so we know there are only ten possible values that a given image can be.

We want to be able to look at an image and give the probabilities for it being each digit. For example, our model might look at a picture of a nine and be 80% sure it's a nine, but give a 5% chance to it being an eight (because of the top loop) and a bit of probability to all the others because it isn't 100% sure.

If you want to assign probabilities to an object being one of several different things, you want to use SoftMax: SoftMax gives us a list of values between 0 and 1 that add up to 1. A softmax regression has two steps:

  1. we add up the evidence of our input being in certain classes (with a weighted sum of the pixel intensities)
  2. we convert (normalize) that evidence into probabilities

For this reason, we use SoftMax as our last layer.


In [8]:
y_conv = tf.nn.softmax(tf.add(tf.matmul(h_fc1_drop, W_fc2), b_fc2))

Our loss function is the cross-entropy between the target and the softmax activation function applied to the model's prediction. In some rough sense, the cross-entropy is measuring how inefficient our predictions are for describing the truth, how large is the discrepancy between two probability distributions.


In [9]:
cross_entropy = - tf.reduce_sum(y_ * tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

How well does our model do? We have to figure out where we predicted the correct label. tf.argmax() is an extremely useful function which gives you the index of the highest entry in a tensor along some axis. tf.argmax(y,1) is the label our model thinks is most likely for each input, while tf.argmax(y_,1) is the correct label. We can use tf.equal to check if our prediction matches the truth.


In [10]:
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

That gives us a list of booleans. To determine what fraction are correct, we cast to floating point numbers and then take the mean. For example, [True, False, True, True] would become [1,0,1,1] which would become 0.75.


In [ ]:
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

Let's launch the graph!

Each step of the inner loop, we get a "batch" of one hundred random data points from our training set. We run train_step feeding in the batches data to replace the placeholders. Ideally, we'd like to use all our data for every step of training because that would give us a better sense of what we should be doing, but that's expensive. So, instead, we use a different subset every time. Doing this is cheap and has much of the same benefit.


In [ ]:
init = tf.initialize_all_variables()

sess = tf.Session()

with sess.as_default():
    sess.run(init)
    
    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})
            print("step %d, training accuracy %g" % (i, train_accuracy))
        train_step.run(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}))


step 0, training accuracy 0.1
step 100, training accuracy 0.8
step 200, training accuracy 0.92
step 300, training accuracy 0.8
step 400, training accuracy 0.98
step 500, training accuracy 0.92
step 600, training accuracy 1
step 700, training accuracy 0.98
step 800, training accuracy 0.86
step 900, training accuracy 1
step 1000, training accuracy 0.92
step 1100, training accuracy 0.92
step 1200, training accuracy 0.98
step 1300, training accuracy 0.96
step 1400, training accuracy 0.98
step 1500, training accuracy 0.98
step 1600, training accuracy 0.9
step 1700, training accuracy 0.96
step 1800, training accuracy 0.98
step 1900, training accuracy 0.98
step 2000, training accuracy 0.98
step 2100, training accuracy 1
step 2200, training accuracy 1
step 2300, training accuracy 0.96
step 2400, training accuracy 1
step 2500, training accuracy 0.98
step 2600, training accuracy 0.98
step 2700, training accuracy 0.98
step 2800, training accuracy 0.98
step 2900, training accuracy 0.98
step 3000, training accuracy 1
step 3100, training accuracy 0.98
step 3200, training accuracy 0.96
step 3300, training accuracy 0.98
step 3400, training accuracy 1
step 3500, training accuracy 1
step 3600, training accuracy 0.98
step 3700, training accuracy 0.98
step 3800, training accuracy 0.98
step 3900, training accuracy 0.96
step 4000, training accuracy 0.98
step 4100, training accuracy 1
step 4200, training accuracy 0.96
step 4300, training accuracy 1
step 4400, training accuracy 1
step 4500, training accuracy 0.98
step 4600, training accuracy 0.98
step 4700, training accuracy 0.96
step 4800, training accuracy 0.96
step 4900, training accuracy 0.94
step 5000, training accuracy 0.98
step 5100, training accuracy 1
step 5200, training accuracy 1
step 5300, training accuracy 1
step 5400, training accuracy 1
step 5500, training accuracy 0.98
step 5600, training accuracy 1
step 5700, training accuracy 0.98
step 5800, training accuracy 0.98
step 5900, training accuracy 1
step 6000, training accuracy 1
step 6100, training accuracy 0.98
step 6200, training accuracy 0.98
step 6300, training accuracy 0.98
step 6400, training accuracy 1
step 6500, training accuracy 1
step 6600, training accuracy 1
step 6700, training accuracy 1
step 6800, training accuracy 1
step 6900, training accuracy 1
step 7000, training accuracy 0.98
step 7100, training accuracy 1
step 7200, training accuracy 0.98
step 7300, training accuracy 1
step 7400, training accuracy 0.98
step 7500, training accuracy 0.98
step 7600, training accuracy 1
step 7700, training accuracy 1
step 7800, training accuracy 1
step 7900, training accuracy 1
step 8000, training accuracy 1
step 8100, training accuracy 0.98
step 8200, training accuracy 1
step 8300, training accuracy 1
step 8400, training accuracy 1
step 8500, training accuracy 1
step 8600, training accuracy 1
step 8700, training accuracy 0.98
step 8800, training accuracy 1
step 8900, training accuracy 1
step 9000, training accuracy 1
step 9100, training accuracy 1
step 9200, training accuracy 1
step 9300, training accuracy 0.98
step 9400, training accuracy 1
step 9500, training accuracy 1
step 9600, training accuracy 1
step 9700, training accuracy 1
step 9800, training accuracy 1
step 9900, training accuracy 1
step 10000, training accuracy 1
step 10100, training accuracy 1
step 10200, training accuracy 1
step 10300, training accuracy 1
step 10400, training accuracy 1
step 10500, training accuracy 1
step 10600, training accuracy 0.98
step 10700, training accuracy 1
step 10800, training accuracy 1
step 10900, training accuracy 1
step 11000, training accuracy 1
step 11100, training accuracy 1
step 11200, training accuracy 1
step 11300, training accuracy 1
step 11400, training accuracy 1
step 11500, training accuracy 1
step 11600, training accuracy 1
step 11700, training accuracy 1
step 11800, training accuracy 1
step 11900, training accuracy 1
step 12000, training accuracy 1
step 12100, training accuracy 1
step 12200, training accuracy 1
step 12300, training accuracy 1
step 12400, training accuracy 1
step 12500, training accuracy 1
step 12600, training accuracy 0.98
step 12700, training accuracy 1
step 12800, training accuracy 1
step 12900, training accuracy 0.98
step 13000, training accuracy 1
step 13100, training accuracy 1
step 13200, training accuracy 1
step 13300, training accuracy 1
step 13400, training accuracy 1
step 13500, training accuracy 1
step 13600, training accuracy 1
step 13700, training accuracy 1
step 13800, training accuracy 1
step 13900, training accuracy 1
step 14000, training accuracy 1
step 14100, training accuracy 1
step 14200, training accuracy 0.98
step 14300, training accuracy 1
step 14400, training accuracy 1
step 14500, training accuracy 1
step 14600, training accuracy 1
step 14700, training accuracy 0.98
step 14800, training accuracy 1
step 14900, training accuracy 1
step 15000, training accuracy 1
step 15100, training accuracy 1
step 15200, training accuracy 1
step 15300, training accuracy 1
step 15400, training accuracy 0.98
step 15500, training accuracy 1
step 15600, training accuracy 1
step 15700, training accuracy 1
step 15800, training accuracy 1
step 15900, training accuracy 1
step 16000, training accuracy 1
step 16100, training accuracy 1
step 16200, training accuracy 1
step 16300, training accuracy 1
step 16400, training accuracy 0.98
step 16500, training accuracy 1
step 16600, training accuracy 0.98
step 16700, training accuracy 1
step 16800, training accuracy 1
step 16900, training accuracy 1
step 17000, training accuracy 1
step 17100, training accuracy 1
step 17200, training accuracy 1
step 17300, training accuracy 1
step 17400, training accuracy 0.96
step 17500, training accuracy 1
step 17600, training accuracy 1
step 17700, training accuracy 1
step 17800, training accuracy 1
step 17900, training accuracy 1
step 18000, training accuracy 1
step 18100, training accuracy 1
step 18200, training accuracy 1
step 18300, training accuracy 1
step 18400, training accuracy 1
step 18500, training accuracy 1
step 18600, training accuracy 1
step 18700, training accuracy 1
step 18800, training accuracy 1
step 18900, training accuracy 1
step 19000, training accuracy 1
step 19100, training accuracy 1
step 19200, training accuracy 1
step 19300, training accuracy 1
step 19400, training accuracy 1
step 19500, training accuracy 1
step 19600, training accuracy 1
step 19700, training accuracy 1
step 19800, training accuracy 1
step 19900, training accuracy 0.98