Stock implementation of TensorFlow's "Deep MNIST for Experts"

cnn_stock.py

# coding: utf-8

# In[4]:


# reference: https://www.tensorflow.org/versions/r0.12/tutorials/mnist/pros/

from tensorflow.examples.tutorials.mnist import input_data


# In[5]:


import tensorflow as tf
sess = tf.InteractiveSession()


# In[6]:


mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

# Create the model
x = tf.placeholder(tf.float32, [None, 784])
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])


# In[7]:


#initialize weights
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

#initialize neurons w/ small bias
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)


# In[8]:


#convolution
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#max pooling
def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                          strides=[1, 2, 2, 1], padding='SAME')


# In[9]:


#creating first convolutional layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

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

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

#second convolutional layer
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)

#fully connected layer
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)


# In[10]:


"""
DROPOUT: this is where the magic happens

this is the stock version
"""
#holds probability that neuron's output is kept during dropout
keep_prob = tf.placeholder(tf.float32)

#TensorFlow's stock dropout function
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)


# In[11]:


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

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2


# In[ ]:


#TESTING

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_conv, labels=y_))

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, tf.float32))

sess.run(tf.global_variables_initializer())
for i in range(20000):
    #print(str(i + 1))
    batch = mnist.train.next_batch(50)
    #print accuracy every 100 iterations
    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 %.4g"%(i, train_accuracy))
        #loss = tf.Print(cross_entropy, data=[cross_entropy], message="loss: ")
        #sess.run(loss)
    train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print("test accuracy %.6g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))