MNIST ML Beginner tutorial

This notebook is based on the tutorial found here

Get the MNIST dataset



In [3]:

    
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("data/MNIST",one_hot=True)









    



Extracting data/MNIST/train-images-idx3-ubyte.gz
Extracting data/MNIST/train-labels-idx1-ubyte.gz
Extracting data/MNIST/t10k-images-idx3-ubyte.gz
Extracting data/MNIST/t10k-labels-idx1-ubyte.gz

Softmax regression

There is an excellent explanation of the softmax regression here, however we are essentially building the following:

Which in matrix form looks like:

$$y = \text{softmax}(Wx + b)$$

Credit the images from the Tensorflow docs



In [4]:

    
import tensorflow as tf


# Setup our Input placeholder
x = tf.placeholder(tf.float32, [None, 784])

# Our Weights and Biases
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x,W) + b

# Define loss and optimizer
y_ = tf.placeholder(tf.float32,[None,10])

# The following is considered numerically unstable, using the line above instead
# cross_entropy = tf.reduce_mean(-(tf.reduce_sum(y_ * tf.log(y),reduction_indices=[1])))

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

Training



In [5]:

    
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

# We train our model with batches of random data
for _ in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step,feed_dict={x:batch_xs,y_:batch_ys})

Validation



In [6]:

    
# We validate our model by casting our boolean (right/wrong) into integers and taking the mean
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_:mnist.test.labels}))