Tensorflow Quick tutorial -To be able to DeepLearning #2

DEEP MNIST FOR EXPERTS IN DL: SETUP

#interactive session makes tensorflow flexible 
import tensorflow as tf
sess = tf.InteractiveSession()

Weight Initialization
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)
Convolution and Pooling
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')

 x_image = tf.reshape(x, [-1,28,28,1]) #reshape to 4dtensor (batch,w,h,chan)

 #First layer
 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)

#Second 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)

#Dropout
keep_prob = tf.placeholder(tf.float32) #percentage of dropout
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

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

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

TRAINING

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=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, tf.float32))

sess.run(tf.global_variables_initializer())

for i in range(20000):
  batch = mnist.train.next_batch(50)
  
  if i%100 == 0: #printing accuracy
    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("Final test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

Tensorflow Quick tutorial -To be able to DeepLearning #1

What is a Tensor?

3 # a rank 0 tensor; this is a scalar with shape []
[1. ,2., 3.] # a rank 1 tensor; this is a vector with shape [3]
[[1., 2., 3.], [4., 5., 6.]] # a rank 2 tensor; a matrix with shape [2, 3]
[[[1., 2., 3.]], [[7., 8., 9.]]] # a rank 3 tensor with shape [2, 1, 3]

How to use Tensorflow?

Create graphs and run them

import tensorflow as tf
node1 = tf.constant(3.0, tf.float32)
node2 = tf.constant(4.0) # also tf.float32 implicitly

sess = tf.Session() #Create a session

node3 = tf.add(node1, node2) #Create operations
print("sess.run(node3): ",sess.run(node3))  #Run graph

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
A placeholder is a promise to provide a value later.
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
adder_node = a + b  # + provides a shortcut for tf.add(a, b)

print(sess.run(adder_node, {a: 3, b:4.5}))
print(sess.run(adder_node, {a: [1,3], b: [2, 4]}))

(We can make the computational graph more complex by adding another operation.)
add_and_triple = adder_node * 3.
print(sess.run(add_and_triple, {a: 3, b:4.5}))

Create Variables to be able to Train

Variables allow us to add trainable parameters to a graph. They are constructed with a type and initial value:

W = tf.Variable([.3], tf.float32)
b = tf.Variable([-.3], tf.float32)
x = tf.placeholder(tf.float32)
linear_model = W * x + b

# Need to explicitly initialize with default values
init = tf.global_variables_initializer()sess.run(init)

#Just runs the linear model to produce outputs with default W and b values
print(sess.run(linear_model, {x:[1,2,3,4]}))

#You can change W and B by the following code:
fixW = tf.assign(W, [-1.])
fixb = tf.assign(b, [1.])
sess.run([fixW, fixb]) #changed W and B
print(sess.run(linear_model, {x:[1,2,3,4]}))

Create Loss

y = tf.placeholder(tf.float32)
# loss
loss = tf.reduce_sum(tf.square(linear_model - y)) # sum of the squares
# optimizer
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)
# training data
x_train = [1,2,3,4]
y_train = [0,-1,-2,-3]
# training loop
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init) # reset values to wrong

for i in range(1000):
  sess.run(train, {x:x_train, y:y_train}) #This changes W and b as they are Variables

Now to check the vales of W and B we can do a sess.run

sess.run(W) #array([-0.9999904], dtype=float32)

sess.run(b) #array([ 0.99997181], dtype=float32) 

final_loss  = sess.run(loss, {x:x_train, y:y_train}) #loss: 5.69997e-11

This more complicated program can still be visualized in TensorBoard