In [1]:

    

import tensorflow as tf
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

In [2]:

    

# let us parameterize our code
num_classes = 10
img_size = 28 
img_size_flat = img_size * img_size # 784
batch_size = 100
learning_rate = 0.01
training_epochs = 5000

# input data x
x_data = tf.placeholder(tf.float32, [None, img_size_flat], name="x_data") # shape = (batch_size, 784)

# input data labels 
x_labels = tf.placeholder(tf.float32, [None, num_classes], name="x_labels") # shape = (batch_size, 10)

# random weights and biases 
# we will make them Variable because we have to initialize with random values and then later train them
weights = tf.Variable(tf.ones([img_size_flat,num_classes]), name="weights") # shape = (784, 10)
biases = tf.Variable(tf.zeros([num_classes]), name="biases") # shape = (10)

# model
logits = tf.matmul(x_data, weights) + biases      # predicted labels  # shape = (batch_size, 10)

# introduce non-linearity
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=x_labels, name="cross_entropy")

# sum of all the cross_entropy is the cost of our model
cost = tf.reduce_mean(cross_entropy, name="cost")

optimizer = tf.train.AdamOptimizer(learning_rate=0.001, beta1=0.9, beta2=0.999, epsilon=1e-08, use_locking=False, name='Adam').minimize(cost)


### Now that the computation graph is ready, we need to run it using tf.Session()

# initialize the variables
init = tf.global_variables_initializer()

sess = tf.Session()

sess.run(init)

for _ in range(training_epochs):
    batch_x , batch_y = mnist.train.next_batch(batch_size)
    sess.run(fetches=optimizer, feed_dict={x_data:batch_x, x_labels:batch_y})
    

how_many_correct_pred = tf.equal(tf.argmax(x_labels, axis=1), tf.argmax(logits, 1), name="howManyCorrect")

accuracy = tf.reduce_mean(tf.cast(how_many_correct_pred, tf.float32))


# print the final accuracy on test data
print(" accuracy  ", sess.run(fetches=accuracy, feed_dict={x_data:mnist.test.images, x_labels:mnist.test.labels}))


    

    




 accuracy   0.9254